CN111337939B - Method and device for estimating outer frame of rectangular object - Google Patents
Method and device for estimating outer frame of rectangular object Download PDFInfo
- Publication number
- CN111337939B CN111337939B CN201910174238.9A CN201910174238A CN111337939B CN 111337939 B CN111337939 B CN 111337939B CN 201910174238 A CN201910174238 A CN 201910174238A CN 111337939 B CN111337939 B CN 111337939B
- Authority
- CN
- China
- Prior art keywords
- straight line
- rectangular object
- points
- triangle
- point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 114
- 238000004364 calculation method Methods 0.000 claims description 31
- 238000012937 correction Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 5
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/42—Simultaneous measurement of distance and other co-ordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/497—Means for monitoring or calibrating
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
An estimation method of the outer frame of a rectangular object, comprising: based on a three-dimensional point cloud of a rectangular object, obtaining a rectangular convex hull under a bird's eye view, and obtaining a first frame by connecting points positioned at the edge of the convex hull; connecting each point in the convex hull with the origin of coordinates to obtain a plurality of line segments, wherein the first end point of each line segment is a point in the convex hull, and the second end point is the origin of the coordinate system; if the line segments in the plurality of line segments have intersection points with the first frame besides the first end points, the first end points of the line segments in the convex hull are removed, and a second frame is obtained for point connecting lines at the edges among the rest points in the convex hull; calculating the area of the second frame; connecting the two points with the farthest interval in the second frame to be used as the hypotenuse of the first right-angle triangle; calculating to obtain a first right triangle based on the area and the hypotenuse; based on the first right triangle, the outer frame of the rectangular object is obtained. Compared with the prior art, the method provided by the embodiment of the invention has stronger robustness.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle, in particular to a method and a device for estimating the outer frame of a rectangular object.
Background
The existing method for estimating the outer frame of the vehicle mainly adopts the concept of traversal, initializes a rectangle and searches the whole solution space of the rotation angle, and finds the optimal solution by calculating different evaluation criteria such as the minimum area, the maximum correlation or the minimum variance; or the minimum circumscribed rectangle is calculated, and the feature points are selected through a motion method and rotated to the correct positions. The prior art can estimate the frame of a vehicle, but has the defects of poor implementation and poor robustness, and mainly comprises the following two aspects:
(1) Because the prior art mainly adopts the concept of cyclic traversal to traverse the point cloud, the time complexity is greatly influenced by the size of the point cloud, if the number of points in the point cloud is excessive, the running speed of an algorithm can be slow, and the time for obtaining a rectangular frame of a vehicle is long, so that the prior art has the disadvantage of instantaneity.
(2) Because the prior art mainly adopts the concept of cyclic traversal, the solution space is traversed, that is, the prior art needs to calculate the rectangle with the minimum outer order or the rectangle with the minimum distance, and optimize the rectangle with the minimum cost function. If the point set is too sparse or uneven in distribution, the feature function is easy to trap into a local extremum in the optimization process, and a correct result cannot be obtained, so that the prior art has the defect of poor robustness.
Disclosure of Invention
The invention aims to provide a method and a device for estimating the outer frame of a rectangular object, wherein a laser radar is adopted to obtain three-dimensional point cloud of the rectangular object, a convex hull of the rectangular object is calculated to obtain a first frame, a point set on the convex hull is screened by a virtual scanning line method to obtain a second frame, a right triangle forming the rectangular object is calculated based on the area of the second frame, and the outer frame of the rectangular object is further obtained. On one hand, the method processes the points in the plane convex hull of the vehicle by a virtual scanning line method, and the wild points belonging to the components such as the vehicle roof, the engine cover, the trunk and the like are removed, so that the processing amount of the points can be reduced, the calculation speed is improved, and the calculation accuracy is also improved in the calculation process; on the other hand, the laser radar has universality on the fact that the point cloud scanned by the front vehicle is L-shaped, the rectangular right triangle is obtained by calculation by utilizing the characteristic of the laser radar, the rectangular frame can be obtained quickly, and compared with the point cloud processing of the L-shaped by adopting a rectangular model in the prior art, the robustness is stronger.
In a first aspect of the present invention, there is provided a method for estimating an outer frame of a rectangular object, including: based on a three-dimensional point cloud of a rectangular object, obtaining a rectangular convex hull under a bird's eye view, and obtaining a first frame by connecting points positioned at the edge of the convex hull; connecting each point in the convex hull with a coordinate origin to obtain a plurality of line segments, wherein a first endpoint of each line segment is a point positioned in the convex hull, and a second endpoint is the coordinate origin; if the line segments in the plurality of line segments have intersection points with the first frame except the first end points, the first end points of the line segments in the convex hull are removed, and a second frame is obtained for point connecting lines of the edges in the rest points in the convex hull; calculating the area of the second frame; connecting the two points with the farthest interval in the second frame to be used as the hypotenuse of the first right-angle triangle; calculating to obtain a first right triangle based on the area and the hypotenuse; based on the first right triangle, the outer frame of the rectangular object is obtained.
Further, the step of acquiring the three-dimensional point cloud of the rectangular object includes: acquiring a depth map of a laser radar; fitting the ground based on preset height information, and removing the ground in the depth map to obtain a first point set; clustering the first point set by using a region growing method to obtain a second point set; a three-dimensional point cloud of the rectangular object is obtained based on the second set of points.
Further, the step of obtaining a three-dimensional point cloud of the vehicle based on the second point set includes: screening the second point set to obtain a point set of the rectangular object on the depth map; and converting the point set of the rectangular object on the depth map into a three-dimensional point cloud of the rectangular object under the space rectangular coordinates.
Further, the step of calculating the first right triangle based on the area and the hypotenuse includes: calculating to obtain coordinates of a plurality of right triangles and right angles points thereof based on the areas and the hypotenuses; and taking the right triangle with the highest overlapping degree with the second frame in the plurality of right triangles as the first right triangle.
Further, the step of obtaining the outer frame of the rectangular object based on the first right triangle includes: and rotating the first right-angle triangle by taking the middle point of the hypotenuse as a central symmetry point to obtain the outer frame of the rectangular object.
Further, the method further comprises the step of correcting the outer frame of the rectangular object: making a vertical line from a right angle point of the first right angle triangle to a hypotenuse of the first right angle triangle, and dividing the point cloud in the second frame into two parts; respectively performing RANSAC straight line fitting on two part of point clouds based on two right-angle sides of the first right-angle triangle to respectively obtain a first straight line and a second straight line; the first straight line or the second straight line is corrected.
Further, the steps of respectively performing RANSAC straight line fitting on the two part point clouds based on the two right-angle sides of the first right-angle triangle include: respectively carrying out principal component analysis on the inner points of the first straight line and the inner points of the second straight line obtained by the RANSAC to obtain a first characteristic value and a second characteristic value, wherein the first characteristic value is the maximum characteristic value of the inner points of the first straight line, and the second characteristic value is the maximum characteristic value of the inner points of the second straight line; if the first characteristic value is larger than the second characteristic value, determining that the first straight line is a long right-angle side of the first right-angle triangle, and the second straight line is a short right-angle side of the first right-angle triangle; if the second characteristic value is larger than the first characteristic value, determining that the first straight line is a short right-angle side of the first right-angle triangle, and the second straight line is a long right-angle side of the first right-angle triangle.
Further, the step of correcting the first straight line or the second straight line includes: comparing the first straight line and the second straight line with the three-dimensional point cloud of the rectangular object respectively to obtain a first confidence value and a second confidence value; the confidence value is in direct proportion to the three-dimensional point cloud coincidence rate of the straight line and the rectangular object; the first line or the second line is modified based on the difference between the first confidence value and the second confidence value.
Further, if the first confidence value is greater than the second confidence value, correcting the second line segment; and if the first confidence value is smaller than the second confidence value, correcting the first line segment.
Further, the step of correcting the second straight line includes: calculating the slope of a second straight line based on the slope of the first straight line; performing RANSAC straight line fitting on the inner points of the second straight line based on the slope of the second straight line to obtain an equation of the second straight line; obtaining a second right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the outer frame of the corrected rectangular object based on the second right triangle.
Further, the step of correcting the first straight line includes: calculating the slope of the first straight line based on the slope of the second straight line; performing RANSAC straight line fitting on the inner points of the first straight line based on the slope of the first straight line to obtain an equation of the first straight line; determining a second right triangle corrected by the first right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the outer frame of the corrected rectangular object based on the second right triangle.
According to a second aspect of the present invention, there is provided an estimation apparatus for an outer frame of a rectangular object, comprising: the data processing module is used for obtaining a rectangular convex hull based on the three-dimensional point cloud of the rectangular object under the aerial view, and obtaining a first frame by connecting points positioned at the edge of the convex hull; the computing module is used for respectively connecting each point in the convex hull with the origin of coordinates to obtain a plurality of line segments; the first end point of each line segment is a point positioned in the convex hull, and the second end point is an origin of a coordinate system; if the line segments in the line segments have intersection points with the first frame besides the first end points, the first end points of the line segments in the convex hull are removed, and a second frame is obtained for point connecting lines of the edges in the rest points in the convex hull; calculating the area of the second frame; connecting the furthest adjacent two points in the second frame as the hypotenuse of the first right-angle triangle; calculating to obtain a first right triangle based on the area and the hypotenuse; based on the first right triangle, the outer frame of the rectangular object is obtained.
Further, the system also comprises a laser radar and a data preprocessing module; the laser radar scans the visible range to obtain a depth map; the data preprocessing unit is used for fitting the ground based on preset height information, and removing the ground in the depth map to obtain a first point set; clustering the first point set by using a region growing method to obtain a second point set; a three-dimensional point cloud of the rectangular object is obtained based on the second set of points.
Further, the data preprocessing module, the step of obtaining the three-dimensional point cloud of the rectangular object based on the second point set, includes: screening the second point set to obtain a point set of the rectangular object on the depth map; and converting the point set of the rectangular object on the depth map into a three-dimensional point cloud of the rectangular object under the space rectangular coordinates.
Further, the calculating module calculates the first right triangle based on the area and the hypotenuse, including: calculating to obtain coordinates of a plurality of right triangles and right angles points thereof based on the areas and the hypotenuses; and taking the right triangle with the highest overlapping degree with the second frame in the plurality of right triangles as the first right triangle.
Further, the calculating module, based on the first right triangle, obtains the outer frame of the rectangular object, including: and rotating the first right-angle triangle by taking the middle point of the hypotenuse as a central symmetry point to obtain the outer frame of the rectangular object.
Further, the method further comprises the following steps: the correction module is used for making a vertical line from a right angle point of the first right angle triangle to a hypotenuse of the first right angle triangle and dividing a three-dimensional point cloud of the vehicle into two parts; respectively performing RANSAC straight line fitting on two part of point clouds based on two right-angle sides of the first right-angle triangle to respectively obtain a first straight line and a second straight line; the first straight line or the second straight line is corrected.
Further, the step of performing RANSAC straight line fitting on the two part point clouds by the correction module based on the two right-angle sides of the first right-angle triangle includes: respectively carrying out principal component analysis on the inner points of the first straight line and the inner points of the second straight line obtained by the RANSAC to obtain a first characteristic value and a second characteristic value, wherein the first characteristic value is the maximum characteristic value of the inner points of the first straight line, and the second characteristic value is the maximum characteristic value of the inner points of the second straight line; if the first characteristic value is larger than the second characteristic value, determining that the first straight line is a long right-angle side of the first right-angle triangle, and the second straight line is a short right-angle side of the first right-angle triangle; if the second characteristic value is larger than the first characteristic value, determining that the first straight line is a short right-angle side of the first right-angle triangle, and the second straight line is a long right-angle side of the first right-angle triangle.
Further, the step of correcting the first straight line or the second straight line by the correction module includes: comparing the first straight line and the second straight line with the three-dimensional point cloud of the rectangular object respectively to obtain a first confidence value and a second confidence value; the confidence value is in direct proportion to the three-dimensional point cloud coincidence rate of the straight line and the rectangular object; the first line or the second line is modified based on the difference between the first confidence value and the second confidence value.
Further, the correction module determines that if the first confidence value is greater than the second confidence value, the second line segment is corrected; and if the first confidence value is smaller than the second confidence value, correcting the first line segment.
Further, the step of correcting the second straight line by the correction module includes: calculating the slope of a second straight line based on the slope of the first straight line; performing RANSAC straight line fitting on the inner points of the second straight line based on the slope of the second straight line to obtain an equation of the second straight line; obtaining a second right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the corrected outer frame of the rectangular object based on the second right triangle.
Further, the step of correcting the first straight line by the correction module includes: calculating the slope of the first straight line based on the slope of the second straight line; performing RANSAC straight line fitting on the inner points of the first straight line based on the slope of the first straight line to obtain an equation of the first straight line; determining a second right triangle corrected by the first right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the outer frame of the corrected rectangular object based on the second right triangle.
According to a third aspect of the present invention, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method for estimating the outer rim of a rectangular object.
According to a fourth aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the steps of the method for estimating the external border of a rectangular object as described above.
The technical scheme of the invention has the following beneficial technical effects:
(1) The laser radar is widely applied to the automatic driving field by the characteristic of high precision and long effective detection distance. Compared with millimeter wave radar, the laser radar can accurately model surrounding environment and pedestrian vehicles. In vehicle target tracking, an accurate determination of vehicle position, size is required. According to the method, the point cloud of the vehicle is obtained through the laser radar, the geometric method is used for carrying out quick frame estimation on the vehicle model, and the accurate rectangular outer frame of the vehicle is further corrected, so that the vehicle can be tracked quickly and stably.
(2) According to the rectangular frame estimation method and device provided by the embodiment of the invention, on one hand, the points in the plane convex hull of the vehicle are processed by the virtual scanning line method, the wild points belonging to the parts such as the roof, the engine cover and the trunk are removed, the processing amount of the points can be reduced in the calculation process, the calculation speed is improved, and the calculation accuracy is also improved; on the other hand, the laser radar has universality on the fact that the point cloud scanned by the front vehicle is L-shaped, the rectangular right triangle is obtained by calculation by utilizing the characteristic of the laser radar, the rectangular frame can be obtained quickly, and compared with the point cloud processing of the L-shaped by adopting a rectangular model in the prior art, the robustness is stronger.
(3) According to the rectangular frame calculating method and device, the frame of the initially obtained rectangular object is further corrected by adopting the RANSAC, compared with the prior art, the method and device are easier to converge in iterative calculation, the number of converging steps is smaller, and further compared with the prior art, the correcting process is more stable, the calculating speed is faster, and the accuracy is higher.
Drawings
Fig. 1 is a flow chart of a method for estimating an outer frame of a rectangular object according to a first embodiment of the present invention;
FIG. 2 is a lidar depth-map of a first embodiment of the invention;
FIG. 3 is a three-dimensional point cloud of a rectangular object scanned by a lidar of a first embodiment of the invention;
FIG. 4 (a) is a first frame diagram of a first embodiment of the present invention;
FIG. 4 (b) is a schematic view of a second frame according to the first embodiment of the present invention;
FIG. 4 (c) is a schematic illustration of determining a first right triangle diagonal of a first embodiment of the invention;
Fig. 4 (d) is a schematic view of determining a first right-angle triangle point according to the first embodiment of the present invention;
Fig. 4 (e) is a schematic view of the outer rim of the rectangular object according to the first embodiment of the present invention;
FIG. 5 (a) is a schematic diagram of a modification to an estimated rectangular object outline according to a first embodiment of the present invention;
FIG. 5 (b) is a schematic diagram of two sides of an estimated rectangle according to the first embodiment of the present invention;
FIG. 5 (c) is a schematic diagram of two-sided correction of an estimated rectangular object according to a first embodiment of the present invention;
FIG. 5 (d) is a schematic view of the modified rectangular object outer frame according to the first embodiment of the present invention;
Fig. 6 is a graph showing the time-consuming operation of the estimation method according to the second embodiment of the present invention;
FIG. 7 is a graph showing the relative error results of the estimation method provided by the second embodiment of the present invention for the first embodiment;
Fig. 8 is an absolute error result diagram of the estimation method provided by the second embodiment of the present invention to the first embodiment;
Fig. 9 is a schematic structural diagram of an estimation device for the outer frame of a rectangular object according to a third embodiment of the present invention.
Detailed Description
The objects, technical solutions and advantages of the present invention will become more apparent by the following detailed description of the present invention with reference to the accompanying drawings. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
Fig. 1 is a flowchart of a method for estimating an external frame of a rectangular object according to a first embodiment of the present invention, where the method includes steps S101 to S107.
In a preferred embodiment, the laser point cloud of the rectangular object scanned by the lidar is preprocessed before step S101. The rectangular object of the present application is exemplified by a vehicle, but is not limited thereto.
Optionally, the step of preprocessing the lidar of the rectangular object scanned by the lidar includes:
First, a depth map of a visible range of the laser radar is obtained, and the depth map of the visible range of the laser radar can be seen in fig. 2.
And secondly, fitting the ground based on preset height information, and removing the ground in the depth map to obtain a first point set.
Specifically, in this step, the method of removing the ground may be: firstly, intercepting an original point set in a depth map according to a higher preset height to obtain a point set A. And then carrying out plane fitting on the point set A to obtain a ground plane equation. And secondly, respectively calculating the distance between each point in the depth map and the ground plane equation, deleting the points with the distance smaller than the threshold value (the deleted points are points belonging to the ground), and the original point set in the depth map is the points of all targets except the ground. The ground is removed, mainly to reduce the data processing amount of subsequent estimation, so that the clustering process in the third step is simpler.
And thirdly, clustering the first point set by using a region growing method to obtain a second point set.
In particular, there are many obstacles in the first set, including: front vehicles, road signs, and the like. Whereas the first set of points after the ground is removed, possibly comprising a number of stacks of point clouds, needs to be clustered to connect the point clouds belonging to one object.
The second point set refers to a point set of a rectangular object on the depth map. That is, in the third step, clustering is performed under the image coordinate system of the depth map.
And fourthly, obtaining a three-dimensional point cloud of the rectangular object based on the second point set.
Specifically, screening the second point set to find a point set belonging to a rectangular object; after finding, converting the second point set on the depth map into a three-dimensional point cloud of the rectangular object under the space rectangular coordinates. The three-dimensional point cloud of the rectangular object can be seen in fig. 3.
The method for estimating the outer frame of the rectangular object will be described in detail below.
Step S101, based on the three-dimensional point cloud of the rectangular object, obtaining a rectangular convex hull under the aerial view, and obtaining a first frame by connecting points located at the edge of the convex hull. The frame surrounded by the dotted line shown in fig. 4 (a) is the first frame.
Step S102, connecting each point in the convex hull with a coordinate origin to obtain a plurality of line segments, wherein a first end point of each line segment is a point in the convex hull, and a second end point of each line segment is the coordinate origin, and the coordinate origin is a point represented by a laser radar.
Step S103, traversing a plurality of line segments, if the line segments in the line segments have intersection points with the first frame besides the first end points, removing the first end points of the line segments in the convex hull, and obtaining a second frame for the point connecting lines at the edges among the rest points in the convex hull. In the example shown in fig. 4 (b), the border surrounded by the solid line is the second border.
In step S103, if a line between a certain point in the convex hull and the laser radar intersects with the first frame, it is explained that the point is a point that is blocked by another object, and this point is a point that is not useful for estimating the frame of the rectangular object, and thus this point may be a wild point (for example, this point may be a point belonging to the roof of the vehicle), and this point is removed.
It should be noted that, this step is to simplify the point set on the convex hull by using the virtual connection method, and is not an actual connection. The method of virtual scanning lines is used for processing points in the plane convex hull of the vehicle, and the wild points belonging to the components such as the vehicle roof, the engine cover, the trunk and the like are removed, so that the processing amount of the points can be reduced, the calculation speed is improved, and the calculation accuracy is also improved in the calculation process.
Step S104, calculating the area of the second frame.
In step S105, the two points in the second frame with the farthest intervals are connected as the hypotenuse of the first right triangle, see the oblique line in fig. 4 (c).
Step S106, calculating based on the area and the hypotenuse to obtain a first right triangle.
Specifically, calculating based on the area and the hypotenuse to obtain coordinates of a plurality of right triangles and right angles points thereof; the right triangle with the highest overlapping ratio with the second frame is taken as the first right triangle, see fig. 4 (d).
Step S107, based on the first right triangle, obtaining the outer frame of the rectangular object, see fig. 4 (e).
Optionally, taking the middle point of the bevel edge as a central symmetry point to obtain the outer frame of the rectangular object. Or parallel lines of two right-angle sides of the right-angle triangle can be respectively made along two end points of the hypotenuse, so that an outer frame of the rectangular object is obtained.
In a preferred embodiment, the method further comprises a step S108 of correcting the outer frame of the rectangular object.
The optional step S108 comprises the sub-steps of:
in step S108-1, a perpendicular line is drawn from the right angle point of the first right triangle to the hypotenuse thereof, and the point cloud in the second frame is divided into two parts, see fig. 5 (a).
In step S108-2, RANSAC (random sample consensus, consistency algorithm) straight line fitting is performed on the two part point clouds based on the two right-angle sides of the first right-angle triangle to obtain a first straight line and a second straight line respectively.
The step of respectively performing RANSAC linear simulation on two part of point clouds based on two right-angle sides of the first right-angle triangle comprises the following steps:
And respectively carrying out principal component analysis on the inner points of the first straight line and the inner points of the second straight line obtained by RANSAC to obtain a first characteristic value and a second characteristic value. The first characteristic value is the maximum characteristic value of the inner point of the first straight line, and the second characteristic value is the maximum characteristic value of the inner point of the second straight line;
If the first characteristic value is larger than the second characteristic value, determining that the first straight line is a long right-angle side of the first right-angle triangle; if the second eigenvalue is larger than the first eigenvalue, the second straight line is determined to be the long right side of the first right triangle, see fig. 5 (b).
In step S108-2, the "characteristic value" is proportional to the length.
In step S108-3, the first straight line or the second straight line is corrected.
Specifically, the first straight line and the second straight line are respectively compared with the three-dimensional point cloud of the rectangular object to respectively obtain a first confidence value and a second confidence value, see fig. 5 (c). Wherein the confidence value is proportional to the three-dimensional point cloud coincidence rate of the straight line and the rectangular object.
The first line or the second line is modified based on the difference between the first confidence value and the second confidence value.
Preferably, if the first confidence value is greater than the second confidence value, the second line segment is modified.
Specifically, the correction of the second line segment may be: calculating the slope of a second straight line based on the slope of the first straight line; performing RANSAC straight line fitting on the inner points of the second straight line based on the slope of the second straight line to obtain an equation of the second straight line; obtaining a second right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; the outer frame of the modified rectangular object is obtained based on the second right triangle, see fig. 5 (d).
Specifically, since the first straight line, the second straight line, and the hypotenuse constitute a right triangle, the slope of the second straight line and the slope of the first straight line are reciprocal. The slope of the second line is equal to 1 divided by the slope of the first line.
Preferably, if the first confidence value is smaller than the second confidence value, the first line segment is modified.
Specifically, the step of correcting the first straight line includes: calculating the slope of the first straight line based on the slope of the second straight line; performing RANSAC straight line fitting on the inner points of the first straight line based on the slope of the first straight line to obtain an equation of the first straight line; determining a second right triangle corrected by the first right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the outer frame of the corrected rectangular object based on the second right triangle.
The two partial point clouds are respectively fitted with RANSAC straight lines based on the two right-angle sides of the first right-angle triangle, which straight line is the long right-angle side can be determined, and the short right-angle side can be directly corrected. The confidence of the first straight line and the confidence of the second straight line are calculated, and in practice, in order to determine which straight line of the first straight line and the second straight line is the long right-angle side, the higher the confidence is, the higher the length of the straight line is, and the short right-angle side is corrected.
It should be noted that, the invention corrects the rectangle obtained initially by using the random sampling method of RANSAC, so as to effectively reduce interference of the wild points to the solved equation. Because only the points on the surface perpendicular to the ground on the vehicle are needed when the second frame calculation is carried out, but the points on the roof, the engine cover and the trunk cover still participate in the calculation at the moment, if the random sampling is not carried out by adopting a virtual connection method, the influence of the wild points on the solving cannot be avoided at all.
The technical scheme of the invention has the following beneficial technical effects:
(1) The laser radar is widely applied to the automatic driving field by the characteristic of high precision and long effective detection distance. Compared with millimeter wave radar, the laser radar can accurately model surrounding environment and pedestrian vehicles. In vehicle target tracking, an accurate determination of vehicle position, size is required. According to the method, the point cloud of the vehicle is obtained through the laser radar, the geometric method is used for carrying out quick frame estimation on the vehicle model, and the accurate rectangular outer frame of the vehicle is further corrected, so that the vehicle can be tracked quickly and stably.
(2) According to the rectangular frame estimation method and device provided by the embodiment of the application, on one hand, the points in the plane convex hull of the vehicle are processed by the virtual scanning line method, and the wild points belonging to the parts such as the roof, the engine cover and the trunk are removed, so that the processing amount of the points can be reduced, the calculation speed is improved, and the calculation accuracy is improved in the calculation process; on the other hand, the laser radar has universality on the fact that the point cloud scanned by the front vehicle is L-shaped, the rectangular right triangle is obtained by calculation by utilizing the characteristic of the laser radar, the rectangular frame can be obtained quickly, and compared with the point cloud processing of the L-shaped by adopting a rectangular model in the prior art, the robustness is stronger.
(3) According to the rectangular frame calculating method and device, the frame of the initially obtained rectangular object is further corrected by adopting the RANSAC, compared with the prior art, the method and device are easier to converge in iterative calculation, the number of converging steps is smaller, and further compared with the prior art, the correcting process is more stable, the calculating speed is faster, and the accuracy is higher.
The accuracy of the method for estimating the outer border of the rectangular object according to the first embodiment of the present invention will be described in detail below with reference to fig. 6 to 8.
The second embodiment of the present invention adopts the estimation method (without correction) provided by the first embodiment, adopts the estimation method provided by the first embodiment and corrects, and adopts the algorithm in the "PCL" library to test and calculate the plurality of groups of data. The test data come from actual road test of the He-Sai 40 line laser radar, 28 groups of data models are randomly selected for sampling, and the actual vehicle running direction is manually marked as a true value, so that the calculation consumed time and the relative and absolute errors are statistically analyzed.
Fig. 6 is a graph showing the time-consuming operation of the estimation method according to the first embodiment of the present invention.
As shown in fig. 6 to 8, the first method represents test data (indicated by a circular broken line in the figure) using the estimation method (without correction) provided by the first embodiment, the second method represents test data (indicated by a triangular broken line in the figure) using the estimation method (with correction) provided by the first embodiment, and the third method represents test data (indicated by a square broken line in the figure) using an algorithm in the "PCL" library.
As can be seen from comparison of fig. 6, the estimation method (corrected) according to the first embodiment does not require multiple traversals, and thus the time consumed for calculation is greatly reduced compared with the estimation performed by the third method.
As can be seen from comparison of fig. 7, the relative error of each set of data of the second method is near "0", and the fluctuation under the test of different data models is small, so the second method has stronger stability and stronger robustness. The relative error of each group of data in the first method has a certain fluctuation near 0, the fluctuation of the error is obvious among different models, and compared with the first method, the stability is lower. The third method has larger fluctuation of the relative error of each group of data near 0 and larger fluctuation of the error among different models, so that the relative error estimated by the third method is larger and more instability factors exist. In summary, the second method is adopted to estimate the rectangular object as the best estimation method, and the first method is adopted, and the third method is adopted.
As can be seen from comparison of fig. 8, the absolute error of the estimation of the rectangular object by the second method is smaller, and each set of data is more stable, the estimation of the rectangular object by the first method and the third method generally has more obvious errors, but the estimation of the first method has more obvious errors, and the estimation of the second method is more prone to extreme errors.
Table 1 below gives more intuitively the values of the calculation time consumption, the relative error and the absolute error of the above three methods.
As can be seen from table 1 above, the estimation of the outer frame of the vehicle by the first method has a fairly low variance (4.887 deg) of the response time at 0.0190 ms, and is therefore hardly affected by the dot set size, and the average error of the result obtained by the second method is 0.476 degrees, and thus the average error obtained by the second method is relatively small. The mean value and variance of the consumed time are larger by adopting the third method, which proves that the method is time-consuming in calculation, and the consumed time has a larger relationship with the data quantity; moreover, the variance of the angle of the third method is large, which means that the calculation result of the third method is not very stable. Therefore, the second method gives the best results as a result of the optimal solution.
Fig. 9 is a schematic structural diagram of an estimation device for the outer frame of a rectangular object according to a third embodiment of the present invention.
As shown in fig. 9, the apparatus 100 for estimating the outer border of the rectangular object includes a data processing module 30 and a calculating module 40.
The data processing module 30 obtains a convex hull of a rectangle based on the three-dimensional point cloud of the rectangular object under the bird's eye view, and obtains a first frame by connecting points located at the edge of the convex hull.
The calculation module is used for respectively connecting each point in the convex hull with a coordinate origin to obtain a plurality of line segments, wherein a first endpoint of each line segment is a point positioned in the convex hull, and a second endpoint is the coordinate origin, and the coordinate origin is a point represented by the laser radar 20; traversing a plurality of line segments, if the line segments in the line segments have intersection points with the first frame except the first end points, removing the first end points of the line segments in the convex hull, and obtaining a second frame for the point connecting lines at the edges among the rest points in the convex hull; calculating the area of the second frame; and connecting the furthest adjacent two points in the second frame as the hypotenuse of the first right-angle triangle.
In a preferred embodiment, the apparatus further comprises a lidar 20 and a data preprocessing module 10.
The laser radar 20 scans the visible range to acquire a depth map.
The data preprocessing module 10 fits the ground based on preset height information, and removes the ground in the depth map to obtain a first point set; clustering the first point set by using a region growing method to obtain a second point set; a three-dimensional point cloud of the rectangular object is obtained based on the second set of points.
In one embodiment, the data preprocessing module 10, the step of obtaining a three-dimensional point cloud of the rectangular object based on the second point set, includes: screening the second point set to obtain a point set of the rectangular object on the depth map; and converting the point set of the rectangular object on the depth map into a three-dimensional point cloud of the rectangular object under the space rectangular coordinates.
In one embodiment, the calculating module 40 calculates a first right triangle based on the area and the hypotenuse comprising: calculating to obtain coordinates of a plurality of right triangles and right angles points thereof based on the areas and the hypotenuses; and taking the right triangle with the highest overlapping degree with the second frame in the plurality of right triangles as the first right triangle.
In one embodiment, the computing module 40 obtains the bounding box of the rectangular object based on the first right triangle includes: and rotating the first right-angle triangle by taking the middle point of the hypotenuse as a central symmetry point to obtain the outer frame of the rectangular object.
In a preferred embodiment, the apparatus further comprises: and a correction module.
The correction module makes a vertical line from a right angle point of the first right angle triangle to a hypotenuse of the first right angle triangle, and divides the three-dimensional point cloud of the vehicle into two parts; respectively performing RANSAC straight line fitting on two part point clouds based on two right-angle sides of a first right-angle triangle to respectively obtain a first characteristic value and a second characteristic value, wherein the first characteristic value is the maximum characteristic value of an inner point of the first straight line, and the second characteristic value is the maximum characteristic value of the inner point of the second straight line; if the first characteristic value is larger than the second characteristic value, determining that the first straight line is a long right-angle side of the first right-angle triangle; if the second characteristic value is larger than the first characteristic value, determining that the second straight line is a long right-angle side of the first right-angle triangle.
In one embodiment, the step of the correction module correcting the first line or the second line includes: comparing the first straight line and the second straight line with the three-dimensional point cloud of the rectangular object respectively to obtain a first confidence value and a second confidence value; the confidence value is in direct proportion to the three-dimensional point cloud coincidence rate of the straight line and the rectangular object; the first line or the second line is modified based on the difference between the first confidence value and the second confidence value.
In one embodiment, the correction module 50 determines that the second line segment is corrected if the first confidence value is greater than the second confidence value.
Specifically, the step of correcting the second straight line by the correction module 50 includes: calculating the slope of a second straight line based on the slope of the first straight line; performing RANSAC straight line fitting on the inner points of the second straight line based on the slope of the second straight line to obtain an equation of the second straight line; obtaining a second right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the outer frame of the corrected rectangular object based on the second right triangle.
Specifically, since the first straight line, the second straight line, and the hypotenuse constitute a right triangle, the slope of the second straight line and the slope of the first straight line are reciprocal. The slope of the second line is equal to 1 divided by the slope of the first line.
In one embodiment, the correction module 50 determines that the first segment is corrected if the first confidence value is less than the second confidence value.
Specifically, the step of correcting the first straight line includes: calculating the slope of the first straight line based on the slope of the second straight line; performing RANSAC straight line fitting on the inner points of the first straight line based on the slope of the first straight line to obtain an equation of the first straight line; determining a second right triangle corrected by the first right triangle according to the equation of the first straight line, the equation of the second straight line and three intersection points of the hypotenuse; and obtaining the outer frame of the corrected rectangular object based on the second right triangle.
The technical scheme of the invention has the following beneficial technical effects:
(1) The laser radar is widely applied to the automatic driving field by the characteristic of high precision and long effective detection distance. Compared with millimeter wave radar, the laser radar can accurately model surrounding environment and pedestrian vehicles. In vehicle target tracking, an accurate determination of vehicle position, size is required. According to the method, the point cloud of the vehicle is obtained through the laser radar, the geometric method is used for carrying out quick frame estimation on the vehicle model, and the accurate rectangular outer frame of the vehicle is further corrected, so that the vehicle can be tracked quickly and stably.
(2) According to the rectangular frame estimation method and device provided by the embodiment of the application, on one hand, the points in the plane convex hull of the vehicle are processed by the virtual scanning line method, and the wild points belonging to the parts such as the roof, the engine cover and the trunk are removed, so that the processing amount of the points can be reduced, the calculation speed is improved, and the calculation accuracy is improved in the calculation process; on the other hand, the laser radar has universality on the fact that the point cloud scanned by the front vehicle is L-shaped, the rectangular right triangle is obtained by calculation by utilizing the characteristic of the laser radar, the rectangular frame can be obtained quickly, and compared with the point cloud processing of the L-shaped by adopting a rectangular model in the prior art, the robustness is stronger.
(3) According to the rectangular frame calculating method and device, the frame of the initially obtained rectangular object is further corrected by adopting the RANSAC, compared with the prior art, the method and device are easier to converge in iterative calculation, the number of converging steps is smaller, and further compared with the prior art, the correcting process is more stable, the calculating speed is faster, and the accuracy is higher.
A fourth embodiment of the present invention provides a computer storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the method for estimating the outer border of a rectangular object provided in the first embodiment described above.
A fifth embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the steps of the method for estimating the external border of the rectangular object in the first embodiment.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explanation of the principles of the present invention and are in no way limiting of the invention. Accordingly, any modification, equivalent replacement, improvement, etc. made without departing from the spirit and scope of the present invention should be included in the scope of the present invention. Furthermore, the appended claims are intended to cover all such changes and modifications that fall within the scope and boundary of the appended claims, or equivalents of such scope and boundary.
Claims (22)
1. The method for estimating the outer frame of the rectangular object is characterized by comprising the following steps of:
Based on the three-dimensional point cloud of the rectangular object, obtaining a convex hull of the rectangle under the aerial view, and obtaining a first frame by connecting points positioned at the edge of the convex hull;
connecting each point in the convex hull with a coordinate origin to obtain a plurality of line segments, wherein a first end point of each line segment is a point positioned in the convex hull, and a second end point is the coordinate origin;
If the line segments in the line segments have intersection points with the first frame except the first end points, the first end points of the line segments in the convex hull are removed, and a second frame is obtained for the point connecting lines at the edges among the rest points in the convex hull;
Calculating the area of the second frame;
connecting the two points with the farthest intervals in the second frame to be used as bevel edges;
calculating a first right triangle based on the area and the hypotenuse;
Obtaining an outer frame of the rectangular object based on the first right triangle; the step of calculating the first right triangle based on the area and the hypotenuse comprises:
Calculating coordinates of a plurality of right triangles and right angles points thereof based on the area and the hypotenuse;
And taking the right triangle with the highest overlapping degree with the second frame in the plurality of right triangles as the first right triangle.
2. The method of claim 1, wherein the step of obtaining a three-dimensional point cloud of the rectangular object comprises:
acquiring a depth map of a laser radar;
Fitting the ground based on preset height information, and removing the ground in the depth map to obtain a first point set;
clustering the first point set by using a region growing method to obtain a second point set;
a three-dimensional point cloud of the rectangular object is obtained based on the second set of points.
3. The method of claim 2, wherein the step of obtaining a three-dimensional point cloud of the rectangular object based on the second set of points comprises: screening the second point set to obtain a point set of the rectangular object on the depth map;
and converting the point set of the rectangular object on the depth map into a three-dimensional point cloud of the rectangular object under the space rectangular coordinates.
4. The method of claim 1, wherein the step of obtaining the outer frame of the rectangular object based on the first right triangle comprises:
And rotating the first right-angle triangle by taking the middle point of the hypotenuse as a central symmetry point to obtain the outer frame of the rectangular object.
5. The method of claim 1, further comprising the step of modifying an outer frame of the rectangular object:
making a vertical line from the right angle point of the first right angle triangle to the hypotenuse of the first right angle triangle, and dividing the point cloud in the second frame into two parts;
Respectively performing RANSAC straight line fitting on the two part point clouds based on two right-angle sides of the first right-angle triangle to respectively obtain a first straight line and a second straight line;
and correcting the first straight line or the second straight line.
6. The method of claim 5, wherein the respectively RANSAC line fitting step for the two part point clouds based on two right-angle sides of the first right-angle triangle comprises:
Respectively carrying out principal component analysis on the inner points of the first straight line and the inner points of the second straight line obtained by RANSAC to obtain a first characteristic value and a second characteristic value, wherein the characteristic values are in direct proportion to the lengths; the first characteristic value is the maximum characteristic value of the inner point of the first straight line, and the second characteristic value is the maximum characteristic value of the inner point of the second straight line;
if the first characteristic value is larger than the second characteristic value, determining that the first straight line is a long right-angle side of the first right-angle triangle, and the second straight line is a short right-angle side of the first right-angle triangle;
and if the second characteristic value is larger than the first characteristic value, determining that the first straight line is a short right-angle side of the first right-angle triangle, and the second straight line is a long right-angle side of the first right-angle triangle.
7. The method of claim 5, wherein the step of modifying the first line or the second line comprises:
Comparing the first straight line and the second straight line with the three-dimensional point cloud of the rectangular object respectively to obtain a first confidence value and a second confidence value; wherein the confidence value is in direct proportion to the three-dimensional point cloud coincidence rate of the straight line and the rectangular object;
and correcting the first straight line or the second straight line based on the difference value of the first confidence value and the second confidence value.
8. The method of claim 7, wherein the second straight line is modified if the first confidence value is greater than the second confidence value;
and if the first confidence coefficient value is smaller than the second confidence coefficient value, correcting the first straight line.
9. The method according to claim 7 or 8, wherein the step of modifying the second straight line comprises:
Calculating the slope of the second straight line based on the slope of the first straight line;
Performing RANSAC straight line fitting on the inner points of the second straight line based on the slope of the second straight line to obtain an equation of the second straight line;
obtaining a second right triangle according to the equation of the first straight line, the equation of the second straight line and the three intersection points of the hypotenuse;
And obtaining the corrected outer frame of the rectangular object based on the second right triangle.
10. The method according to claim 7 or 8, wherein the step of modifying the first straight line comprises:
calculating the slope of the first straight line based on the slope of the second straight line;
performing RANSAC straight line fitting on the inner points of the first straight line based on the slope of the first straight line to obtain an equation of the first straight line;
Determining a second right triangle corrected for the first right triangle according to the equation of the first straight line, the equation of the second straight line and the three intersection points of the hypotenuse;
And obtaining the corrected outer frame of the rectangular object based on the second right triangle.
11. An estimation device for an outer frame of a rectangular object, comprising:
The data processing module (30) is used for obtaining a convex hull of the rectangle under the aerial view based on the three-dimensional point cloud of the rectangular object, and obtaining a first frame by connecting points positioned at the edge of the convex hull;
The computing module (40) is used for respectively connecting each point in the convex hull with the origin of coordinates to obtain a plurality of line segments; the first end point of each line segment is a point positioned in the convex hull, and the second end point is an origin of a coordinate system; if the line segments in the line segments have intersection points with the first frame besides the first end points, the first end points of the line segments in the convex hull are removed, and a second frame is obtained for the point connecting lines at the edges among the rest points in the convex hull;
Calculating the area of the second frame;
Connecting the adjacent two points with farthest intervals in the second frame to be used as a bevel edge;
calculating a first right triangle based on the area and the hypotenuse;
Obtaining an outer frame of the rectangular object based on the first right triangle;
-a calculation module (40), the step of calculating the first right triangle based on the area and the hypotenuse comprising:
Calculating coordinates of a plurality of right triangles and right angles points thereof based on the area and the hypotenuse;
And taking the right triangle with the highest overlapping degree with the second frame in the plurality of right triangles as the first right triangle.
12. The apparatus of claim 11, further comprising a lidar (20) and a data preprocessing module (10);
a laser radar (20) for scanning the visible range and acquiring a depth map;
The data preprocessing module (10) is used for fitting the ground based on preset height information, and removing the ground in the depth map to obtain a first point set;
clustering the first point set by using a region growing method to obtain a second point set;
a three-dimensional point cloud of the rectangular object is obtained based on the second set of points.
13. The apparatus of claim 12, wherein the data preprocessing module (10) obtains the three-dimensional point cloud of the rectangular object based on the second set of points comprises:
screening the second point set to obtain a point set of the rectangular object on the depth map;
and converting the point set of the rectangular object on the depth map into a three-dimensional point cloud of the rectangular object under the space rectangular coordinates.
14. The apparatus of claim 11, wherein the computing module (40) obtains the outer frame of the rectangular object based on the first right triangle comprises:
And rotating the first right-angle triangle by taking the middle point of the hypotenuse as a central symmetry point to obtain the outer frame of the rectangular object.
15. The apparatus as recited in claim 11, further comprising:
The correction module is used for making a vertical line from the right angle point of the first right angle triangle to the hypotenuse of the first right angle triangle and dividing the three-dimensional point cloud of the second frame into two parts;
Respectively performing RANSAC straight line fitting on the two part point clouds based on two right-angle sides of the first right-angle triangle to respectively obtain a first straight line and a second straight line;
and correcting the first straight line or the second straight line.
16. The apparatus of claim 15, wherein the correction module performs RANSAC line fitting on the two part point clouds based on two right-angle sides of the first right-angle triangle, respectively, comprising:
Respectively carrying out principal component analysis on the inner points of the first straight line and the inner points of the second straight line obtained by RANSAC to obtain a first characteristic value and a second characteristic value, wherein the characteristic value is in direct proportion to the length, the first characteristic value is the maximum characteristic value of the inner points of the first straight line, and the second characteristic value is the maximum characteristic value of the inner points of the second straight line;
if the first characteristic value is larger than the second characteristic value, determining a first straight line as a long right-angle side of the first right-angle triangle, and determining a second straight line as a short right-angle side of the first right-angle triangle;
and if the second characteristic value is larger than the first characteristic value, determining that a first straight line is a short right-angle side of the first right-angle triangle, and determining that a second straight line is a long right-angle side of the first right-angle triangle.
17. The apparatus of claim 15, wherein the step of the correction module correcting the first line or the second line comprises:
Comparing the first straight line and the second straight line with the three-dimensional point cloud of the rectangular object respectively to obtain a first confidence value and a second confidence value; wherein the confidence value is in direct proportion to the three-dimensional point cloud coincidence rate of the straight line and the rectangular object;
and correcting the first straight line or the second straight line based on the difference value of the first confidence value and the second confidence value.
18. The apparatus of claim 17, wherein the correction module determines: if the first confidence coefficient value is larger than the second confidence coefficient value, correcting the second straight line;
and if the first confidence coefficient value is smaller than the second confidence coefficient value, correcting the first straight line.
19. The apparatus of claim 17 or 18, wherein the step of the correction module correcting the second line comprises:
Calculating the slope of the second straight line based on the slope of the first straight line;
Performing RANSAC straight line fitting on the inner points of the second straight line based on the slope of the second straight line to obtain an equation of the second straight line;
obtaining a second right triangle according to the equation of the first straight line, the equation of the second straight line and the three intersection points of the hypotenuse;
And obtaining the corrected outer frame of the rectangular object based on the second right triangle.
20. The apparatus of claim 17 or 18, wherein the step of the correction module correcting the first straight line comprises:
calculating the slope of the first straight line based on the slope of the second straight line;
performing RANSAC straight line fitting on the inner points of the first straight line based on the slope of the first straight line to obtain an equation of the first straight line;
Determining a second right triangle corrected for the first right triangle according to the equation of the first straight line, the equation of the second straight line and the three intersection points of the hypotenuse;
And obtaining the corrected outer frame of the rectangular object based on the second right triangle.
21. A computer storage medium, wherein the storage medium has stored thereon a computer program, which when executed by a processor, performs the steps of the method of estimating the outer border of a rectangular object as claimed in any of claims 1 to 10.
22. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of estimating the outline of a rectangular object as claimed in any one of claims 1 to 10 when the program is executed by the processor.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2018115664766 | 2018-12-19 | ||
| CN201811566476 | 2018-12-19 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111337939A CN111337939A (en) | 2020-06-26 |
| CN111337939B true CN111337939B (en) | 2024-07-19 |
Family
ID=71185771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910174238.9A Active CN111337939B (en) | 2018-12-19 | 2019-03-08 | Method and device for estimating outer frame of rectangular object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111337939B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117681197B (en) * | 2023-12-18 | 2024-07-23 | 安徽工布智造工业科技有限公司 | 6-Axis robot material taking visual material distribution algorithm based on steel structure 3D model |
| CN118071994B (en) * | 2024-02-27 | 2024-08-27 | 数据堂（北京）科技股份有限公司 | Incomplete point cloud data labeling method, device and terminal in automatic driving scene |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334811A (en) * | 2007-06-27 | 2008-12-31 | 中国科学院微电子研究所 | Method for cutting CIF format polygon into PG3600 format rectangle |
| CN101661741A (en) * | 2008-08-29 | 2010-03-03 | 富士通株式会社 | Method and device for traversing triangle in graphical raster scanning |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6212132B1 (en) * | 1998-08-04 | 2001-04-03 | Japan Radio Co., Ltd. | Three-dimensional radar apparatus and method for displaying three-dimensional radar image |
| JP3944034B2 (en) * | 2002-09-05 | 2007-07-11 | 日立ソフトウエアエンジニアリング株式会社 | Partition data creation method and apparatus |
| GB2400288B (en) * | 2003-04-02 | 2005-12-28 | Canon Europa Nv | Generating texture maps for use in 3D computer graphics |
| US9129211B2 (en) * | 2012-03-15 | 2015-09-08 | GM Global Technology Operations LLC | Bayesian network to track objects using scan points using multiple LiDAR sensors |
| CN102915560B (en) * | 2012-09-21 | 2014-12-10 | 中国石油大学(华东) | Threshold-irrelative point cloud filtering method and device for airborne laser radar |
| JP6591257B2 (en) * | 2015-10-21 | 2019-10-16 | 株式会社パスコ | Image processing apparatus, image processing method, and program |
| CN105572687B (en) * | 2015-12-11 | 2017-09-01 | 中国测绘科学研究院 | A kind of method that building digital adventure appearance is made based on mobile lidar point cloud |
| CN105388465B (en) * | 2015-12-17 | 2017-10-24 | 西安电子科技大学 | Sea clutter simulation method based on wave spectrum model |
| CN106291506A (en) * | 2016-08-16 | 2017-01-04 | 长春理工大学 | Vehicle target recognition methods based on single line cloud data machine learning and device |
| CN107656287B (en) * | 2017-10-30 | 2019-08-16 | 中国科学院合肥物质科学研究院 | A kind of Boundary Extraction device and method of the crudefiber crop row based on laser radar |
| CN108828621A (en) * | 2018-04-20 | 2018-11-16 | 武汉理工大学 | Obstacle detection and road surface partitioning algorithm based on three-dimensional laser radar |
| CN108873943B (en) * | 2018-07-20 | 2021-06-29 | 南京奇蛙智能科技有限公司 | Image processing method for centimeter-level accurate landing of unmanned aerial vehicle |
-
2019
- 2019-03-08 CN CN201910174238.9A patent/CN111337939B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334811A (en) * | 2007-06-27 | 2008-12-31 | 中国科学院微电子研究所 | Method for cutting CIF format polygon into PG3600 format rectangle |
| CN101661741A (en) * | 2008-08-29 | 2010-03-03 | 富士通株式会社 | Method and device for traversing triangle in graphical raster scanning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111337939A (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110031824B (en) | Laser radar combined calibration method and device | |
| Kang et al. | Automatic targetless camera–lidar calibration by aligning edge with gaussian mixture model | |
| WO2018205119A1 (en) | Roadside detection method and system based on laser radar scanning | |
| CN111046776B (en) | Method for detecting obstacle of path of mobile robot based on depth camera | |
| CN109146948B (en) | Crop growth phenotype parameter quantification and yield correlation analysis method based on vision | |
| CN109752701A (en) | A kind of road edge detection method based on laser point cloud | |
| CN109635816B (en) | Lane line generation method, apparatus, device, and storage medium | |
| CN110728753B (en) | Target point cloud 3D bounding box fitting method based on linear fitting | |
| WO2020168685A1 (en) | Three-dimensional scanning viewpoint planning method, device, and computer readable storage medium | |
| CN114119998B (en) | Vehicle-mounted point cloud ground point extraction method and storage medium | |
| CN112882059A (en) | Unmanned ship inland river obstacle sensing method based on laser radar | |
| CN110673107A (en) | Road edge detection method and device based on multi-line laser radar | |
| Cheng et al. | Building boundary extraction from high resolution imagery and lidar data | |
| CN109523579B (en) | Method and device for matching video image of unmanned aerial vehicle with three-dimensional map | |
| WO2022179094A1 (en) | Vehicle-mounted lidar external parameter joint calibration method and system, medium and device | |
| CN111522019B (en) | Error correction method and device for underwater photon position | |
| CN111337939B (en) | Method and device for estimating outer frame of rectangular object | |
| KR101092250B1 (en) | Apparatus and method for object segmentation from range image | |
| CN112017249A (en) | Vehicle-mounted camera roll angle obtaining and mounting angle correcting method and device | |
| CN113205563B (en) | Automatic driving sensor combined calibration target and calibration method | |
| CN115718305A (en) | Laser point cloud highway section processing method, device, equipment and storage medium | |
| CN112711027B (en) | Tunnel inner transverse positioning method based on laser radar point cloud data | |
| CN113569958A (en) | Laser point cloud data clustering method, device, equipment and medium | |
| CN112446907B (en) | Method and device for registering single-line point cloud and multi-line point cloud | |
| CN113238205A (en) | Unmanned aerial vehicle surveying and mapping point cloud data offset correction method and system based on artificial intelligence |
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 | ||
| GR01 | Patent grant |