CN114066739B - Background point cloud filtering method and device, computer equipment and storage medium - Google Patents
Background point cloud filtering method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114066739B CN114066739B CN202010777027.7A CN202010777027A CN114066739B CN 114066739 B CN114066739 B CN 114066739B CN 202010777027 A CN202010777027 A CN 202010777027A CN 114066739 B CN114066739 B CN 114066739B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- dimensional grid
- background
- real
- lookup table
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000013507 mapping Methods 0.000 claims abstract description 23
- 238000004590 computer program Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The application relates to a background point cloud filtering method, a background point cloud filtering device, computer equipment and a storage medium. The method comprises the following steps: obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and real-time point cloud data of the target scene is obtained, and the real-time point cloud data comprises a plurality of real-time point cloud points; mapping the plurality of real-time point cloud points into the plurality of two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid; and for each two-dimensional grid, if the minimum value of the second point cloud height corresponding to the two-dimensional grid is smaller than the minimum value of the first point cloud height corresponding to the two-dimensional grid, updating the minimum value of the first point cloud height corresponding to the two-dimensional grid according to the minimum value of the second point cloud height corresponding to the two-dimensional grid, and obtaining an updated background lookup table. By adopting the method, the accuracy of filtering the cloud points of the background points can be improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and apparatus for filtering background point cloud, a computer device, and a storage medium.
Background
In practical application, a road side radar can be arranged beside a road, the road side radar can collect traffic information on the road, and then background filtering processing is carried out on the collected traffic information, so that the identification of pedestrians or vehicles on the road is realized.
In the related art, a road side radar can collect point cloud data (i.e. traffic information described above) on a road, then uses a pre-stored background lookup table to filter out background point cloud points from the point cloud data, and after the background point cloud points are filtered out, can obtain recognition results of vehicles and pedestrians on the road based on the rest point cloud points.
However, in practical application, the road side radar often shakes or shifts due to the influence of external factors, so that it is difficult to ensure that the point cloud data collected by the road side radar each time is aimed at the same scene in the road, the scene changes correspondingly with the background change, and at present, how to adapt to the background change in the process of filtering the background point cloud points, so that the accuracy of filtering the background point cloud points is improved, and the problem to be solved is urgent.
Disclosure of Invention
Based on this, it is necessary to provide a background point cloud filtering method, a device, a computer device and a storage medium, which can improve the accuracy of filtering background point cloud points.
In a first aspect, a method for filtering background point clouds is provided, the method comprising:
obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
Mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid;
And for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
In one embodiment, the background lookup table further includes a plurality of attribute parameters corresponding to the plurality of two-dimensional grids one by one, each of the attribute parameters being used to indicate whether the corresponding two-dimensional grid corresponds to a region of interest in the target scene; the method further comprises the steps of:
And for each two-dimensional grid, determining an attribute parameter corresponding to the two-dimensional grid in the background lookup table, and if the attribute parameter corresponding to the two-dimensional grid indicates that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid.
In one embodiment, the determining a second point cloud height minimum for the real-time point cloud points of each of the two-dimensional grid mappings includes:
And for each two-dimensional grid, taking the height value of the real-time point cloud point with the lowest height in the real-time point cloud points mapped by the two-dimensional grid as the second point cloud height minimum value corresponding to the two-dimensional grid.
In one embodiment, before the obtaining the background lookup table corresponding to the target scene, the method further includes:
Acquiring an initial background lookup table, wherein each two-dimensional grid in the initial background lookup table corresponds to an initial value;
acquiring reference point cloud data of the target scene, wherein the reference point cloud data comprises a plurality of reference point cloud points;
Mapping the plurality of reference point cloud points into the plurality of two-dimensional grids, and taking the minimum point cloud height value of the reference point cloud points mapped by each two-dimensional grid as the first minimum point cloud height value corresponding to each two-dimensional grid;
and updating the initial value based on the first point cloud height minimum value corresponding to each two-dimensional grid, and generating the background lookup table.
In one embodiment, after the acquiring the real-time point cloud data of the target scene, the method further includes:
and filtering the background point cloud points in the real-time point cloud data by using the background lookup table.
In one embodiment, the filtering the background point cloud point in the real-time point cloud data using the background lookup table includes:
and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
In one embodiment, the background lookup table further includes a plurality of attribute parameters corresponding to the plurality of two-dimensional grids one by one, each of the attribute parameters being used to indicate whether the corresponding two-dimensional grid corresponds to a region of interest in the target scene; the method further comprises the steps of:
And for each real-time point cloud point, determining an attribute parameter corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the attribute parameter corresponding to the target two-dimensional grid indicates that the target two-dimensional grid does not correspond to the region of interest.
In a second aspect, a background point cloud filtering device is provided, where the device includes:
The first acquisition module is used for acquiring a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
the second acquisition module is used for acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
the determining module is used for mapping the real-time point cloud points into the two-dimensional grids and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid;
And the updating module is used for updating the first point cloud height minimum value corresponding to the two-dimensional grids according to the second point cloud height minimum value corresponding to the two-dimensional grids if the second point cloud height minimum value corresponding to the two-dimensional grids is smaller than the first point cloud height minimum value corresponding to the two-dimensional grids, so as to obtain an updated background lookup table, and the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
In a third aspect, a computer device is provided, comprising a memory storing a computer program and a processor implementing the following steps when the computer program is executed:
obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
Mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid;
And for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
Mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid;
And for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
According to the background point cloud filtering method, the background point cloud filtering device, the computer equipment and the storage medium, the background lookup table corresponding to the target scene is obtained, the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene; then, acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points; mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid; and finally, for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene. Because the background point cloud filtering method provided by the application is used for filtering the background point cloud points in the real-time point cloud data of the target scene by utilizing the background lookup table, the minimum value of the first point cloud height of each two-dimensional grid in the background lookup table corresponding to the target scene is updated by utilizing the real-time point cloud points, and the updated background lookup table is continuously used for filtering the background point cloud points in the real-time point cloud data of the target scene. That is, in the present application, since the background lookup table can be updated using real-time point cloud data of the target scene, even if the current background is changed, the background lookup table can be immediately updated according to the changed background. Therefore, the application is based on the latest background lookup table when filtering the background point cloud points in the real-time point cloud data of the target scene. Therefore, the whole background point cloud filtering process can be well adapted to different background changes, and accuracy of filtering background point cloud points is improved.
Drawings
FIG. 1 is a flow chart of a background point cloud filtering method in an embodiment;
FIG. 2 is a flowchart of a background point cloud filtering method according to another embodiment;
FIG. 3 is a block diagram of a background point cloud filtering device according to an embodiment;
FIG. 4 is a block diagram of a background point cloud filtering device according to another embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In the embodiment of the present application, as shown in fig. 1, a background point cloud filtering method is provided, and the method is applied to a terminal for illustration, and it can be understood that the method can also be applied to a server, and can also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. The terminal may be, but not limited to, various roadside lidars, roadside millimeter wave radars, personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server may be implemented by an independent server or a server cluster formed by a plurality of servers, where the method includes the following steps:
step 101, a terminal acquires a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
In this step, the terminal may acquire, in real time, a background lookup table corresponding to the target scene, or may periodically acquire a background lookup table corresponding to the target scene, where the background lookup table includes a plurality of sets of correspondence between two-dimensional grids and a first point cloud height minimum value. In the subsequent process of using the background lookup table, the height value of the real-time point cloud data in the target scene and the first point cloud height minimum value corresponding to each two-dimensional grid can be utilized to judge which real-time point cloud points in the real-time point cloud data of the target scene are target points and which real-time point cloud points are background points. In general, a portion of the target scene near the ground, such as a real-time point cloud point corresponding to a road and a lawn, may be considered as a background point; while objects at a distance from the ground, such as real-time clouds corresponding to vehicles and pedestrians, may be considered target points.
Step 102, the terminal acquires real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points.
In practical application, the terminal needs to identify the background point and the target point in the target scene, so the terminal can acquire real-time point cloud data of the target scene. When the terminal is a road side laser radar, the road side laser radar can establish a three-dimensional model of the target scene by transmitting laser to objects in the target scene and receiving laser reflected by the objects in the target scene, so that real-time point cloud data in the target scene are acquired.
And 103, mapping the real-time point cloud points into the two-dimensional grids by the terminal, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid.
Based on the above steps, after the terminal obtains the real-time point cloud point of the target scene, the terminal needs to process the three-dimensional real-time point cloud point, so that the background lookup table is used for filtering the background point in the real-time point cloud point in the subsequent steps. The two-dimensional rasterization processing is a common means for processing real-time point cloud points, and the core idea of the two-dimensional rasterization processing is to map three-dimensional real-time point cloud points scanned by a road side laser radar to a two-dimensional plane, and then process the three-dimensional real-time point cloud points mapped to the two-dimensional plane by utilizing grids to obtain a plurality of two-dimensional grids, wherein each two-dimensional grid corresponds to a small area of a space and contains a part of mapped real-time point cloud points. After two-dimensional rasterization processing is performed on the real-time point cloud points in the real-time point cloud data, a second point cloud height minimum value of the real-time point cloud points corresponding to each two-dimensional grid needs to be counted. Because the height value of the real-time point cloud point can be used as a basis for judging whether the real-time point cloud point is a target point or a background point, and the second point cloud height minimum value of the real-time point cloud point corresponding to each two-dimensional grid can be used in the subsequent process of updating the background lookup table, the second point cloud height minimum value of the real-time point cloud point mapped by each two-dimensional grid needs to be counted in the step. Finally, each two-dimensional grid can be numbered according to the row and column numbers of the grids, and in the step, after the second point cloud height minimum value of the real-time point cloud point mapped by each two-dimensional grid is determined, the number of each two-dimensional grid and the second point cloud height minimum value corresponding to each two-dimensional grid can be stored.
Step 104, for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid by the terminal to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
After counting the second point cloud height minimum value corresponding to each two-dimensional grid, comparing the second point cloud height minimum value corresponding to each two-dimensional grid with the first point cloud height minimum value, if the second point cloud height minimum value is smaller than the first point cloud height minimum value, replacing the first point cloud height minimum value by using the second point cloud height minimum value, and if the second point cloud height minimum value is larger than the first point cloud height minimum value, not replacing. After the operation is performed on each two-dimensional grid, an updated background lookup table is obtained, and after the updated background lookup table is obtained, if the terminal continues to obtain the real-time point cloud data in the target scene, the background point cloud points in the real-time point cloud data in the target scene can be filtered by using the updated background lookup table.
According to the above process, the terminal can filter the background point cloud point in the real-time point cloud data a in the target scene according to the basic thought of filtering the background point cloud point in the real-time point cloud data B in the target scene by using the background lookup table, then update the background lookup table by using the real-time point cloud data a of the target scene to obtain the updated background lookup table, and then continue to obtain the real-time point cloud data B of the target scene, and the whole process of updating the background lookup table in real time and filtering the background point cloud point in the real-time point cloud data by using the real-time updated background lookup table is completed. The real-time point cloud data a and the real-time point cloud data B described above, wherein the real-time point cloud data a and the real-time point cloud data B are distinguished by using a and B, so as to illustrate that the real-time point cloud data B and the real-time point cloud data a are real-time point cloud data at different moments, and the real-time point cloud data B is acquired at the next moment of the real-time point cloud data a, which is not used for limiting that the real-time point cloud data used in the embodiment of the present application are only the real-time point cloud data a and the real-time point cloud data B.
In the background point cloud filtering method, a background lookup table corresponding to a target scene is obtained, the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene; then, acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points; mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid; and finally, for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene. Because the background point cloud filtering method provided by the application is used for filtering the background point cloud points in the real-time point cloud data of the target scene by utilizing the background lookup table, the minimum value of the first point cloud height of each two-dimensional grid in the background lookup table corresponding to the target scene is updated by utilizing the real-time point cloud points, and the updated background lookup table is continuously used for filtering the background point cloud points in the real-time point cloud data of the target scene. That is, in the present application, since the background lookup table can be updated using real-time point cloud data of the target scene, even if the current background is changed, the background lookup table can be immediately updated according to the changed background. Therefore, the application is based on the latest background lookup table when filtering the background point cloud points in the real-time point cloud data of the target scene. Therefore, the whole background point cloud filtering process can be well adapted to different background changes, and accuracy of filtering background point cloud points is improved.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the method further comprises the steps of:
For each two-dimensional grid, determining an attribute parameter corresponding to the two-dimensional grid in the background lookup table by the terminal, and if the attribute parameter corresponding to the two-dimensional grid indicates that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid.
In the embodiment of the application, each two-dimensional grid corresponds to an attribute parameter, and the attribute parameter comprises an effective state and an ineffective state. The active state indicates that the two-dimensional grid belongs to the region of interest and the inactive state indicates that the two-dimensional grid does not belong to the region of interest. With respect to the region of interest, after the real-time point cloud data of the target scene is acquired, the three-dimensional real-time point cloud data may be mapped to a two-dimensional image, then the region of interest is defined in the two-dimensional image, and then the two-dimensional image in which the region of interest is defined is rasterized. Whether the two-dimensional grid belongs to the region of interest can be used as a basis for judging whether the attribute parameters of the two-dimensional grid are in an invalid state or an effective state.
In the embodiment of the application, by firstly judging the attribute parameters of the two-dimensional grid, the next operation of detecting the minimum value of the second point cloud height is only performed when the attribute parameters of the two-dimensional grid indicate that the two-dimensional grid belongs to the region of interest. Therefore, invalid detection of the area outside the region of interest can be avoided, and only the region of interest is detected, so that the detection efficiency is improved.
In an embodiment of the present application, a method for determining a second point cloud height minimum value of a real-time point cloud point of each two-dimensional grid mapping in a background point cloud filtering method is provided, where the method includes:
And for each two-dimensional grid, the terminal takes the height value of the real-time point cloud point with the lowest height in the real-time point cloud points mapped by the two-dimensional grid as the second point cloud height minimum value corresponding to the two-dimensional grid.
In the embodiment of the application, after two-dimensional rasterization processing is performed on the real-time point cloud data of the target scene, the minimum height value of the real-time point cloud point corresponding to each two-dimensional grid needs to be counted, and then the minimum height value of the real-time point cloud point corresponding to each two-dimensional grid is used as the minimum height value of the second point cloud. However, when mapping, there is no corresponding real-time point cloud point in some two-dimensional grids, then no processing is performed on the two-dimensional grids, that is, when the first point cloud height minimum value is updated by using the second point cloud height minimum value, the corresponding two-dimensional grids still have the first point cloud height minimum value after being updated.
In the embodiment of the application, the second point cloud height minimum value can be simply obtained by calculating the real-time point cloud point height minimum value corresponding to each two-dimensional grid, and when the two-dimensional grids do not have the corresponding real-time point cloud points, the two-dimensional grids are not updated, so that the real reliability of data in the implementation process of the whole technical scheme is ensured.
In an embodiment of the present application, please refer to fig. 2, another method for filtering a background point cloud is provided, which includes:
in step 201, the terminal obtains an initial background lookup table, where each two-dimensional grid in the initial background lookup table corresponds to an initial value.
When filtering the cloud point of the background point of the target scene, an initial background lookup table is stored first, wherein the initial background lookup table is a lookup table which is not updated by the real-time point cloud data of the target scene, and all two-dimensional grids contained in the initial background lookup table correspond to initial values, and the initial values can be 0.
Step 202, a terminal acquires reference point cloud data of the target scene, where the reference point cloud data includes a plurality of reference point cloud points.
Regarding reference point cloud data of the target scene, when the terminal is a road side laser radar, the road side laser radar needs to be initialized when the road side laser radar is initially set at the road side, the road side laser radar needs to collect the reference point cloud data of the target scene first, the reference point cloud data refers to the point cloud data collected when no target object exists in the target scene, that is, all the point cloud points in the reference point cloud data can be regarded as background point cloud points, the reference point cloud data is used for updating an initial background lookup table, and the steps of filtering background point cloud points and updating the background lookup table can be completed only after the initial background lookup table is used.
And 203, mapping the plurality of reference point cloud points into the plurality of two-dimensional grids by the terminal, and taking the minimum point cloud height value of the reference point cloud points mapped by each two-dimensional grid as the first minimum point cloud height value corresponding to each two-dimensional grid.
The mapping to a plurality of two-dimensional grids mentioned in this step is the two-dimensional rasterization processing described in the foregoing. After the two-dimensional rasterization processing, the minimum value of the point cloud height of the reference point cloud point corresponding to each two-dimensional grid needs to be counted, and then the minimum value of the point cloud height of the reference point cloud point corresponding to each two-dimensional grid is stored. And if the certain two-dimensional grid does not have the corresponding reference point cloud point, storing the initial value as the minimum point cloud height value corresponding to the two-dimensional grid. This ensures that each two-dimensional grid can correspond to a first point cloud height minimum.
And 204, updating the initial value by the terminal based on the first point cloud height minimum value corresponding to each two-dimensional grid, and generating the background lookup table.
After the point cloud height minimum value of the reference point cloud point corresponding to each two-dimensional grid is counted, the method is equivalent to obtaining the first point cloud height minimum value corresponding to each two-dimensional grid, then storing each two-dimensional grid and the first point cloud height minimum value corresponding to each two-dimensional grid, and the background lookup table is provided with a plurality of groups of corresponding relations between the two-dimensional grids and the first point cloud height minimum values. The terminal can filter the background point cloud points in the real-time point cloud data in the target scene by using the background lookup table. The method comprises the steps of determining a reference point cloud data, wherein the reference point cloud data is a two-dimensional grid, and determining a background lookup table according to the reference point cloud data, wherein the region of interest can be defined in the two-dimensional rasterization process of the reference point cloud data, so that the finally obtained background lookup table not only comprises the corresponding relation between the two-dimensional grids and the minimum value of the first point cloud height, but also can comprise attribute parameters of each two-dimensional grid.
In the embodiment of the application, the initial background lookup table can be obtained rapidly by performing two-dimensional rasterization processing on the reference point cloud data in the target scene.
In an embodiment of the present application, a method for filtering background point cloud points in real-time point cloud data by using the background lookup table in a background point cloud filtering method is provided, where the method includes:
and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids by the terminal, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
In the embodiment of the application, after the terminal acquires the real-time point cloud points, the real-time point cloud points are mapped into a plurality of two-dimensional grids according to the two-dimensional rasterization method provided by the content, and the number and the size of the two-dimensional grids are consistent with those of the two-dimensional grids corresponding to the background lookup table, so that the two-dimensional grids are conveniently subjected to one-to-one corresponding comparison processing. For each real-time point cloud point, when judging whether the real-time point cloud point belongs to a target point or a background point, determining a target two-dimensional grid corresponding to the real-time point cloud point, then determining a first point cloud height minimum value corresponding to the target two-dimensional grid in a background lookup table, and filtering the real-time point cloud point as the background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point. When the height value of the real-time point cloud point is larger than the minimum value of the first point cloud height corresponding to the target two-dimensional grid by a certain threshold value, the real-time point cloud point is judged to belong to the target point, otherwise, the real-time point cloud point belongs to the background point.
In the embodiment of the application, the real-time point cloud point is a target point or a background point can be rapidly and conveniently identified by firstly determining the target two-dimensional grid corresponding to the real-time point cloud point and then comparing the difference value between the height value of the real-time point cloud point and the first point cloud height value corresponding to the target two-dimensional grid, and the efficiency of filtering the background point cloud point is improved.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the background point cloud filtering method further comprises the following steps:
And for each real-time point cloud point, determining an attribute parameter corresponding to the target two-dimensional grid in the background lookup table by the terminal, and filtering the real-time point cloud point as a background point cloud point if the attribute parameter corresponding to the target two-dimensional grid indicates that the target two-dimensional grid does not correspond to the region of interest.
In the embodiment of the application, besides the height value of the real-time point cloud point is used for judging whether the real-time point cloud point is the target point or the background point, the attribute parameters of the two-dimensional grid recorded in the content can be used for judging. Because the attribute parameters of the two-dimensional grid can represent whether the two-dimensional grid belongs to the region of interest, when the attribute parameters of the target two-dimensional grid indicate that the target two-dimensional grid does not correspond to the region of interest, the real-time point cloud points corresponding to the target two-dimensional grid can be directly filtered as background point cloud points.
The region of interest is generally a manually delimited region, for example, the region of interest can be manually delimited on the mapped two-dimensional image, and in general, vehicles and pedestrians often appear on roads in the target scene, and the vehicles and pedestrians are targets that need to be detected in a focused manner, and plants and buildings outside the roads in the target scene generally exist as a background, and do not need to be detected specifically. The road area in the two-dimensional image is typically divided into regions of interest, and then the portions outside the regions of interest can be considered to belong to background spots. Therefore, in the embodiment of the application, whether the real-time point cloud points are used as background point cloud points to be filtered can be judged by judging whether the attribute parameters corresponding to the target two-dimensional grid indicate the region of interest.
In the embodiment of the application, whether the real-time point cloud points belong to the background point cloud points can be directly judged through the attribute parameters corresponding to the target two-dimensional grid, so that the efficiency of filtering the background point cloud points is improved.
It should be understood that, although the steps in the flowcharts of fig. 1 to 2 are sequentially shown as indicated by arrows, the steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in fig. 1-2 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In an embodiment of the present application, as shown in fig. 3, a background point cloud filtering apparatus 300 is provided, including: the first acquiring module 301, the second acquiring module 302, the determining module 303 and the updating module 304, wherein:
The first obtaining module 301 is configured to obtain a background lookup table corresponding to a target scene, where the background lookup table includes a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one to one, and the background lookup table is configured to filter background point cloud points in point cloud data of the target scene;
A second obtaining module 302, configured to obtain real-time point cloud data of the target scene, where the real-time point cloud data includes a plurality of real-time point cloud points;
A determining module 303, configured to map the plurality of real-time point cloud points into the plurality of two-dimensional grids, and determine a second point cloud height minimum value of the real-time point cloud points mapped by each of the two-dimensional grids;
And the updating module 304 is configured to update, for each two-dimensional grid, the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, to obtain an updated background lookup table, where the updated background lookup table is used to filter the background point cloud points in the point cloud data of the target scene.
In an embodiment of the present application, please refer to fig. 4, another background point cloud filtering apparatus 400 is provided, where the background point cloud filtering apparatus 400 includes, in addition to the modules included in the background point cloud filtering apparatus 300, optionally, the background point cloud filtering apparatus 400 further includes: a detection module 305, a generation module 306 and a filtering module 307.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the detection module 305 is configured to: and for each two-dimensional grid, determining an attribute parameter corresponding to the two-dimensional grid in the background lookup table, and if the attribute parameter corresponding to the two-dimensional grid indicates that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid.
In the embodiment of the present application, the determining module 303 is specifically configured to: and for each two-dimensional grid, taking the height value of the real-time point cloud point with the lowest height in the real-time point cloud points mapped by the two-dimensional grid as the second point cloud height minimum value corresponding to the two-dimensional grid.
In an embodiment of the present application, the generating module 306 is configured to: acquiring an initial background lookup table, wherein each two-dimensional grid in the initial background lookup table corresponds to an initial value; acquiring reference point cloud data of the target scene, wherein the reference point cloud data comprises a plurality of reference point cloud points; mapping the plurality of reference point cloud points into the plurality of two-dimensional grids, and taking the minimum point cloud height value of the reference point cloud points mapped by each two-dimensional grid as the first minimum point cloud height value corresponding to each two-dimensional grid; and updating the initial value based on the first point cloud height minimum value corresponding to each two-dimensional grid, and generating the background lookup table.
In the embodiment of the present application, the filtering module 307 is configured to: and filtering the background point cloud points in the real-time point cloud data by using the background lookup table.
In the embodiment of the present application, the filtering module 307 is specifically configured to: and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the filtering module 307 is specifically configured to: and for each real-time point cloud point, determining an attribute parameter corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the attribute parameter corresponding to the target two-dimensional grid indicates that the target two-dimensional grid does not correspond to the region of interest.
For specific limitation of the background point cloud filtering device, reference may be made to the limitation of the background point cloud filtering method hereinabove, and the description thereof will not be repeated here. All or part of the modules in the background point cloud filtering device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In an embodiment of the present application, a computer device is provided, which may be a terminal, and an internal structure diagram thereof may be shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a background point cloud filtering method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment of the present application, there is provided a computer device including a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
Mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid;
And for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the processor when executing the computer program also implements the steps of: and for each two-dimensional grid, determining an attribute parameter corresponding to the two-dimensional grid in the background lookup table, and if the attribute parameter corresponding to the two-dimensional grid indicates that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid.
In an embodiment of the present application, the processor when executing the computer program further implements the following steps:
And for each two-dimensional grid, taking the height value of the real-time point cloud point with the lowest height in the real-time point cloud points mapped by the two-dimensional grid as the second point cloud height minimum value corresponding to the two-dimensional grid.
In an embodiment of the present application, the processor when executing the computer program further implements the following steps:
Acquiring an initial background lookup table, wherein each two-dimensional grid in the initial background lookup table corresponds to an initial value; acquiring reference point cloud data of the target scene, wherein the reference point cloud data comprises a plurality of reference point cloud points; mapping the plurality of reference point cloud points into the plurality of two-dimensional grids, and taking the minimum point cloud height value of the reference point cloud points mapped by each two-dimensional grid as the first minimum point cloud height value corresponding to each two-dimensional grid; and updating the initial value based on the first point cloud height minimum value corresponding to each two-dimensional grid, and generating the background lookup table.
In an embodiment of the present application, the processor when executing the computer program further implements the following steps:
and filtering the background point cloud points in the real-time point cloud data by using the background lookup table.
In an embodiment of the present application, the processor when executing the computer program further implements the following steps:
and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the processor when executing the computer program also implements the steps of:
And for each real-time point cloud point, determining an attribute parameter corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the attribute parameter corresponding to the target two-dimensional grid indicates that the target two-dimensional grid does not correspond to the region of interest.
In an embodiment of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
Mapping the real-time point cloud points into the two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid;
And for each two-dimensional grid, if the second point cloud height minimum value corresponding to the two-dimensional grid is smaller than the first point cloud height minimum value corresponding to the two-dimensional grid, updating the first point cloud height minimum value corresponding to the two-dimensional grid according to the second point cloud height minimum value corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the computer program when executed by the processor also performs the steps of: and for each two-dimensional grid, determining an attribute parameter corresponding to the two-dimensional grid in the background lookup table, and if the attribute parameter corresponding to the two-dimensional grid indicates that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid.
In an embodiment of the present application, the computer program when executed by the processor further implements the steps of:
And for each two-dimensional grid, taking the height value of the real-time point cloud point with the lowest height in the real-time point cloud points mapped by the two-dimensional grid as the second point cloud height minimum value corresponding to the two-dimensional grid.
In an embodiment of the present application, the computer program when executed by the processor further implements the steps of:
Acquiring an initial background lookup table, wherein each two-dimensional grid in the initial background lookup table corresponds to an initial value; acquiring reference point cloud data of the target scene, wherein the reference point cloud data comprises a plurality of reference point cloud points; mapping the plurality of reference point cloud points into the plurality of two-dimensional grids, and taking the minimum point cloud height value of the reference point cloud points mapped by each two-dimensional grid as the first minimum point cloud height value corresponding to each two-dimensional grid; and updating the initial value based on the first point cloud height minimum value corresponding to each two-dimensional grid, and generating the background lookup table.
In an embodiment of the present application, the computer program when executed by the processor further implements the steps of:
and filtering the background point cloud points in the real-time point cloud data by using the background lookup table.
In an embodiment of the present application, the computer program when executed by the processor further implements the steps of:
and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
In the embodiment of the application, the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, wherein each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to the region of interest in the target scene; the computer program when executed by the processor also performs the steps of:
And for each real-time point cloud point, determining an attribute parameter corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the attribute parameter corresponding to the target two-dimensional grid indicates that the target two-dimensional grid does not correspond to the region of interest.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (7)
1. A method for filtering background point clouds, the method comprising:
obtaining a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene; acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points; the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, and each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to a region of interest in the target scene;
Mapping the plurality of real-time point cloud points into the plurality of two-dimensional grids, and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid; for each two-dimensional grid, determining attribute parameters corresponding to the two-dimensional grid in the background lookup table, and if the attribute parameters corresponding to the two-dimensional grid indicate that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid;
For each two-dimensional grid, if the minimum value of the second point cloud height corresponding to the two-dimensional grid is smaller than the minimum value of the first point cloud height corresponding to the two-dimensional grid, updating the minimum value of the first point cloud height corresponding to the two-dimensional grid according to the minimum value of the second point cloud height corresponding to the two-dimensional grid to obtain an updated background lookup table, wherein the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
After the real-time point cloud data of the target scene are obtained, filtering background point cloud points in the real-time point cloud data by utilizing the background lookup table; and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
2. The method of claim 1, wherein said determining a second point cloud height minimum for real-time point cloud points for each of said two-dimensional grid mappings comprises:
And for each two-dimensional grid, taking the height value of the real-time point cloud point with the lowest height in the real-time point cloud points mapped by the two-dimensional grid as the second point cloud height minimum value corresponding to the two-dimensional grid.
3. The method of claim 1, wherein prior to the obtaining the context look-up table for the target scene, the method further comprises:
Acquiring an initial background lookup table, wherein each two-dimensional grid in the initial background lookup table corresponds to an initial value;
acquiring reference point cloud data of the target scene, wherein the reference point cloud data comprises a plurality of reference point cloud points;
Mapping the plurality of reference point cloud points into the plurality of two-dimensional grids, and taking the minimum point cloud height value of the reference point cloud points mapped by each two-dimensional grid as the first minimum point cloud height value corresponding to each two-dimensional grid;
And updating the initial value based on the first point cloud height minimum value corresponding to each two-dimensional grid, and generating the background lookup table.
4. The method of claim 1, wherein the background look-up table further comprises a plurality of attribute parameters in one-to-one correspondence with the plurality of two-dimensional grids, each of the attribute parameters being for indicating whether the corresponding two-dimensional grid corresponds to a region of interest in the target scene; the method further comprises the steps of:
And for each real-time point cloud point, determining an attribute parameter corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the attribute parameter corresponding to the target two-dimensional grid indicates that the target two-dimensional grid does not correspond to the region of interest.
5. A background point cloud filtering device, the device comprising:
the first acquisition module is used for acquiring a background lookup table corresponding to a target scene, wherein the background lookup table comprises a plurality of first point cloud height minimum values corresponding to a plurality of two-dimensional grids one by one, and the background lookup table is used for filtering background point cloud points in point cloud data of the target scene; the background lookup table further comprises a plurality of attribute parameters corresponding to the two-dimensional grids one by one, and each attribute parameter is used for indicating whether the corresponding two-dimensional grid corresponds to a region of interest in the target scene;
The second acquisition module is used for acquiring real-time point cloud data of the target scene, wherein the real-time point cloud data comprises a plurality of real-time point cloud points;
The determining module is used for mapping the real-time point cloud points into the two-dimensional grids and determining a second point cloud height minimum value of the real-time point cloud points mapped by each two-dimensional grid; for each two-dimensional grid, determining attribute parameters corresponding to the two-dimensional grid in the background lookup table, and if the attribute parameters corresponding to the two-dimensional grid indicate that the two-dimensional grid corresponds to the region of interest, detecting whether a second point cloud height minimum value corresponding to the two-dimensional grid is smaller than a first point cloud height minimum value corresponding to the two-dimensional grid;
The updating module is used for updating the first point cloud height minimum value corresponding to the two-dimensional grids according to the second point cloud height minimum value corresponding to the two-dimensional grids if the second point cloud height minimum value corresponding to the two-dimensional grids is smaller than the first point cloud height minimum value corresponding to the two-dimensional grids, so as to obtain an updated background lookup table, and the updated background lookup table is used for filtering background point cloud points in point cloud data of the target scene;
The filtering module is used for filtering background point cloud points in the real-time point cloud data by utilizing the background lookup table after acquiring the real-time point cloud data of the target scene; and for each real-time point cloud point, determining a target two-dimensional grid corresponding to the real-time point cloud point in the plurality of two-dimensional grids, determining a first point cloud height minimum value corresponding to the target two-dimensional grid in the background lookup table, and filtering the real-time point cloud point as a background point cloud point if the sum of the first point cloud height minimum value and a preset threshold value is not smaller than the height value of the real-time point cloud point.
6. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010777027.7A CN114066739B (en) | 2020-08-05 | 2020-08-05 | Background point cloud filtering method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010777027.7A CN114066739B (en) | 2020-08-05 | 2020-08-05 | Background point cloud filtering method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114066739A CN114066739A (en) | 2022-02-18 |
| CN114066739B true CN114066739B (en) | 2024-10-29 |
Family
ID=80231986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010777027.7A Active CN114066739B (en) | 2020-08-05 | 2020-08-05 | Background point cloud filtering method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114066739B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117974748A (en) * | 2022-10-24 | 2024-05-03 | 顺丰科技有限公司 | Method, device, computer equipment and storage medium for measuring package size |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019609A (en) * | 2017-11-20 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Map updating method, device and computer readable storage medium |
| CN110349192A (en) * | 2019-06-10 | 2019-10-18 | 西安交通大学 | A kind of tracking of the online Target Tracking System based on three-dimensional laser point cloud |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019179495A (en) * | 2018-03-30 | 2019-10-17 | パナソニックＩｐマネジメント株式会社 | Sensor processing system, distance measuring system, mobile object, sensor processing method, and program |
| CN110067274B (en) * | 2019-04-29 | 2021-08-13 | 北京拓疆者智能科技有限公司 | Equipment control method and excavator |
| CN110658531B (en) * | 2019-08-23 | 2022-03-29 | 畅加风行(苏州)智能科技有限公司 | Dynamic target tracking method for port automatic driving vehicle |
| CN110705458B (en) * | 2019-09-29 | 2022-06-28 | 北京智行者科技有限公司 | Boundary detection method and device |
| CN110988909B (en) * | 2019-12-31 | 2023-06-27 | 南京林业大学 | TLS-based vegetation coverage measuring method for sand vegetation in severe cold fragile area |
-
2020
- 2020-08-05 CN CN202010777027.7A patent/CN114066739B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019609A (en) * | 2017-11-20 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Map updating method, device and computer readable storage medium |
| CN110349192A (en) * | 2019-06-10 | 2019-10-18 | 西安交通大学 | A kind of tracking of the online Target Tracking System based on three-dimensional laser point cloud |
Non-Patent Citations (1)
| Title |
|---|
| 城市交通场景下基于三维激光雷达的交通信息检测方法研究;杨思远;中国优秀硕士学位论文全文数据库工程科技II辑;20200415(第4期);16-25 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114066739A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11422261B2 (en) | Robot relocalization method and apparatus and robot using the same | |
| US11709058B2 (en) | Path planning method and device and mobile device | |
| CN109190573B (en) | Ground detection method applied to unmanned vehicle, electronic equipment and vehicle | |
| CN110443786B (en) | Laser radar point cloud filtering method and device, computer equipment and storage medium | |
| CN111862292B (en) | Data rendering method and device for transmission line corridor and computer equipment | |
| CN110990516B (en) | Map data processing method, device and server | |
| CN107239794B (en) | Point cloud data segmentation method and terminal | |
| CN111144228B (en) | Obstacle identification method based on 3D point cloud data and computer equipment | |
| CN112329789B (en) | Point cloud extraction method and device, computer equipment and storage medium | |
| CN114693875A (en) | Point cloud visualization optimization method and system, electronic device and storage medium | |
| CN114063098A (en) | Multi-target tracking method, device, computer equipment and storage medium | |
| CN114066739B (en) | Background point cloud filtering method and device, computer equipment and storage medium | |
| CN112418038A (en) | Human body detection method, human body detection device, electronic equipment and medium | |
| US8483478B1 (en) | Grammar-based, cueing method of object recognition, and a system for performing same | |
| CN114859938A (en) | Robot, dynamic obstacle state estimation method and device and computer equipment | |
| CN112583900B (en) | Data processing method for cloud computing and related product | |
| CN116824128A (en) | Target detection method, target detection device, electronic equipment and storage medium | |
| CN114253639B (en) | Data caching method, device, computer equipment and storage medium | |
| CN111626288B (en) | Data processing method, device, computer equipment and storage medium | |
| CN109612467B (en) | Track simplifying method and system and track visualization system | |
| CN114630102A (en) | Method and device for detecting angle change of data acquisition equipment and computer equipment | |
| CN117985053B (en) | Sensing capability detection method and device | |
| CN112923916B (en) | Map simplifying method and device, electronic equipment and machine-readable storage medium | |
| CN116047537B (en) | Road information generation method and system based on laser radar | |
| CN117475247A (en) | Target bump set acquisition method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |