CN117523472A - Passenger flow data statistics method, computer equipment and computer readable storage medium - Google Patents
Passenger flow data statistics method, computer equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN117523472A CN117523472A CN202311216586.0A CN202311216586A CN117523472A CN 117523472 A CN117523472 A CN 117523472A CN 202311216586 A CN202311216586 A CN 202311216586A CN 117523472 A CN117523472 A CN 117523472A
- Authority
- CN
- China
- Prior art keywords
- target
- passenger flow
- batch
- area
- target object
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000003993 interaction Effects 0.000 claims description 21
- 230000004044 response Effects 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 8
- 230000002123 temporal effect Effects 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 29
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000010365 information processing Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a passenger flow data statistics method, computer equipment and a computer readable storage medium. Wherein the method comprises the following steps: acquiring track information of a target object in an associated area of the target area; the target object enters or leaves the target area through the association area; acquiring time relevance of a plurality of target objects in a relevance area; and determining target passenger flow batch data of the target area by utilizing the track information and the time relevance of each target object. By the aid of the scheme, accuracy of passenger flow data statistics can be improved.
Description
Technical Field
The present disclosure relates to the field of passenger flow data statistics, and in particular, to a passenger flow data statistics method, a computer device, and a computer readable storage medium.
Background
With the rapid development of economy and the improvement of living standard of people, and the continuous expansion and prosperity of urban scale, more and more people flow in public places, such as subways, airports, train stations, museums, shops, chain stores, etc., a large amount of people flow amount is generally required to be counted or recorded for effectively managing the data of people flow.
The passenger flow data statistics can divide passenger flow personnel according to the concept of batches, and through finer division analysis of the passenger flow personnel, the passenger flow data statistics can help to know the passenger flow change trend of places, and can timely provide effective personnel management data information.
At present, passenger flow statistics is mainly achieved by using a manual mode or a camera video analysis mode, face information is collected by a camera, and passenger flow statistics is achieved through a face information comparison mode. The passenger flow statistical mode depends on the face information, so that the accuracy of the statistical passenger flow statistical data is lower.
Disclosure of Invention
The technical problem that this application mainly solves is to provide a passenger flow data statistics method, computer equipment and computer readable storage medium, can improve passenger flow data statistics's accuracy.
In order to solve the above problem, a first aspect of the present application provides a passenger flow data statistics method, which includes: acquiring track information of a target object in an associated area of the target area; the target object enters or leaves the target area through the association area; acquiring time relevance of a plurality of target objects in a relevance area; and determining target passenger flow batch data of the target area by utilizing the track information and the time relevance of each target object.
In order to solve the above problem, a second aspect of the present application provides a computer device, which includes a memory and a processor coupled to each other, where the memory stores program data, and the processor is configured to execute the program data to implement any step of the above passenger flow data statistics method.
In order to solve the above-described problems, a third aspect of the present application provides a computer-readable storage medium storing program data executable by a processor for implementing any one of the steps of the above-described passenger flow data statistical method.
According to the scheme, the track information of the target objects in the association area of the target area is obtained, wherein the association area has an association relation with the target area, the target objects enter or leave the target area through the association area, and the time association of a plurality of target objects in the association area is obtained; in addition, the method only needs to count the track information of the target object entering or leaving the associated area of the target area, so that the efficiency of passenger flow batch data statistics can be improved.
Drawings
For a clearer description of the technical solutions in the present application, the drawings required in the description of the embodiments will be briefly described below, it being obvious that the drawings described below are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a flow chart of a first embodiment of a method for statistics of passenger flow data according to the present application;
FIG. 2 is a flowchart illustrating an embodiment of step S12 in FIG. 1 of the present application;
FIG. 3 is a schematic distribution diagram of one embodiment of the association region and target region of the present application;
FIG. 4 is an exemplary diagram of one embodiment of track information for an associated region of the present application;
FIG. 5 is a flowchart illustrating an embodiment of step S13 in FIG. 1 of the present application;
FIG. 6 is a flow chart of a second embodiment of the method for statistics of passenger flow data of the present application;
FIG. 7 is an exemplary diagram of an embodiment of track information for a target area of the present application;
FIG. 8 is a flowchart illustrating an embodiment of step S22 in FIG. 6 of the present application;
FIG. 9 is a schematic structural diagram of an embodiment of a statistics device for passenger flow data according to the present application;
FIG. 10 is a schematic diagram of an embodiment of a computer device of the present application;
FIG. 11 is a schematic diagram of an embodiment of a computer-readable storage medium of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms "first," "second," and the like in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship. Further, "a plurality" herein means two or more than two. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
The present application provides the following examples, each of which is specifically described below.
Referring to fig. 1, fig. 1 is a flowchart of a first embodiment of a passenger flow data statistics method according to the present application. The method may comprise the steps of:
s11: acquiring track information of a target object in an associated area of the target area; the association area has an association relation with the target area, and the target object enters or leaves the target area through the association area.
The target area may be an area where passenger flow statistics is performed, for example, the target area may include an area of a bus, a subway, an airport, a train station, a museum, a mall, a shopping mall, a chain store, a scenic spot, etc., and the present application does not limit the target area.
The association area has an association relation with the target area, and the target object enters or leaves the target area through the association area. For example, the associated region is an entrance/exit region of the target region, e.g., the associated region has an overlapping region with the target region, etc., which is not limited in this application.
The target object may be a person, an animal, an object, etc., and may be set according to a specific application scenario, which is not limited in this application.
In some embodiments, a plurality of cameras may be disposed in the target area and the associated area such that a shooting field of view of the image pickup apparatus covers the target area and the associated area. In some application scenarios, the cameras can be mounted in a top-loading or oblique-loading manner, different mounting manners are adopted according to actual scenarios, for example, the mounting manner of oblique-loading can be adopted for mounting the cameras with the height being greater than H (for example, 2.5) meters, the mounting manner of top-loading can be adopted for mounting the cameras with the height being less than H (for example, 2.5) meters, and the range of passenger flow statistical areas of large scenarios can be covered.
In some embodiments, the installed cameras may be differentiated according to acquisition area, and may be classified into target area cameras and associated area cameras. The target area camera can be used for data acquisition of the target area, and the associated area camera can be used for data acquisition of the associated area. Taking the passenger flow statistics of the chain stores as an example, the chain stores can be divided into an in-out/in-out camera and an in-store camera, and in addition, the data collected by the camera can be drawn through a webpage interface end.
In some embodiments, image data is acquired with a camera for a target object present within a target region/associated region, such that trajectory information for the target object within the associated region of the target region is acquired from the acquired image data.
In some embodiments, the object detection model may be used to perform object detection on each frame of image data of the video data collected by the camera, so as to obtain an object detection frame of each frame of image data. In addition, the multi-target tracking model is adopted to track the target object of each frame image of the video data, the multi-part association of the target object can be used for tracking, an identifier is created for each target object, thus, the target detection frame sequence of each target object is stored according to the identifier of the target object, and the track position of each target detection frame of each target object can be recorded in real time to form track information.
The target detection model may include models such as Yolo and BiFPN, and is used for detecting a face, a head and a shoulder, and an integral part of a target object, and taking the target object as an example, a human face, a head and a shoulder, a human body, and the like can be detected. The continuous multi-frame image data can be tracked by adopting a multi-target tracking model, and the tracking can be performed based on multi-part association of the target object. Wherein the multi-target tracking model may include one of SORT, deepSORT, byteTrack, boT-SORT, etc. The method can be specifically selected according to specific application scenes, and the method is not limited to the target detection model and the multi-target tracking model.
If the technical scheme of the application relates to personal information, the product applying the technical scheme of the application clearly informs the personal information processing rule before processing the personal information, and obtains independent consent of the individual. If the technical scheme of the application relates to sensitive personal information, the product applying the technical scheme of the application obtains individual consent before processing the sensitive personal information, and simultaneously meets the requirement of 'explicit consent'. For example, a clear and remarkable mark is set at a personal information acquisition device such as a camera to inform that the personal information acquisition range is entered, personal information is acquired, and if the personal voluntarily enters the acquisition range, the personal information is considered as consent to be acquired; or on the device for processing the personal information, under the condition that obvious identification/information is utilized to inform the personal information processing rule, personal authorization is obtained by popup information or a person is requested to upload personal information and the like; the personal information processing rule may include information such as a personal information processor, a personal information processing purpose, a processing mode, and a type of personal information to be processed.
In some embodiments, the target object may be a target object excluding a preset identity, where the preset identity includes at least one of a staff member, a distribution member, a passenger member, and other members. The staff may be a staff working in the target area, and the delivery staff may be, for example, a takeaway delivery staff, an express delivery staff, or the like, and in order to make the passenger flow statistics result more effective, the passenger flow statistics may not be performed on the staff, the delivery staff, or the like. Other personnel may be other personnel in the target area that do not need to perform passenger flow statistics, or personnel in a certain area, and the application is not limited to this. The passenger flow personnel can be personnel needing passenger flow statistics, and the passenger flow statistics can be carried out aiming at the passenger flow personnel in the target area when the passenger flow statistics is carried out.
S12: and acquiring the time relevance of the plurality of target objects in the relevance area.
After the track information of each target object is acquired, the track information of each target object is analyzed, so that the time relevance of the track information on the time information in the relevant area can be obtained.
The track information may include a track position of the target object in each frame of image data, or the track information may include a track position of the target object in each frame of image data spaced by a preset number of frames, and may further record time information of each track position.
In some embodiments, the correlation between the time information of each target object at each track position may be obtained as a time correlation.
In some embodiments, the correlation between the time information of each target object at the preset position of the correlation area may be obtained as the time correlation. Wherein the preset position may include at least one of: a preset sub-region in the associated region, a preset limit, at least one preset track position of the plurality of track positions, etc.
When the correlations between the time information of the plurality of or the plurality of preset positions are acquired, an average value or a sum of the plurality of correlations may be acquired as the time correlation.
In some embodiments, an image of each target object in the association region may be acquired, and time information of the image of each target object in the association region (e.g., time information of the acquired image, stay information in the association region, etc.) may be acquired by using the time information of the image of each target object in the association region, so that time correlation between each target object in the association region is acquired by using the time information.
In some embodiments, referring to fig. 2, step S12 of the above embodiments may be further extended. The method for obtaining the time relevance of the plurality of target objects in the relevance area may include the following steps:
s121: and acquiring time information of each target object passing through a preset boundary line in the associated area by utilizing the track information of each target object in the associated area.
Referring to fig. 3, the target area and the associated area have an association relationship, and the association relationship is exemplified by that the target area is adjacent to the associated area, and the target object may enter or leave the target area through the associated area. The associated region includes a first region and a second region divided by a preset boundary line, where the preset boundary line may be a straight line, a curve, a polygon, and the like, and may be selected according to a specific application scenario, which is not limited in this application. The present embodiment is described taking a preset boundary line as an example, and the traveling direction of the target object may include at least one of an in direction and an out direction. The direction of entry from the first region into the second region and the direction of exit from the second region into the first region. By utilizing the track information of the target object in the association area, the time information of the target object passing through the preset boundary line can be acquired.
Referring to fig. 4, for each target object, an intersection position of a walking track of the target object and a preset boundary line may be determined by using track information of the target object in the associated region, and time information and a traveling direction of the target object at the intersection position may be acquired, where the traveling direction includes at least one of entering from the first region into the second region and entering from the second region into the first region. Taking the target objects A and B as examples, the associated area, the preset boundary line, the track information and the like can be drawn in the video picture, and the track information can be utilized to obtain the time information of the target objects A and B corresponding to the in-direction and the out-direction at the intersection position respectively.
In some embodiments, if the track information of the target object does not intersect with the preset boundary, it may be indicated that the target object may not enter the target area, and the target object may be regarded as a target object that does not need to perform passenger flow statistics, and passenger flow statistics is not performed on the target object.
Thus, the time information of the intersection position and the traveling direction are taken as the time information of the target object passing through the preset limit in the traveling direction.
In some embodiments, the target area, the associated area, the preset boundary, etc. described above may be drawn based on a video frame of the video data, so as to more clearly display the track information and time correlation of each target object.
S122: and acquiring a preset statistical value among the time information of each target object to obtain the time relevance among a plurality of target objects.
The preset statistical value may be an average value, a difference value, etc., and the preset statistical value may describe a similarity or a time interval of time information of each target object at the intersection position. Taking the difference as an example, the difference between the time information of each target object is obtained, and the time relevance between each target object is obtained.
S13: and determining target passenger flow batch data of the target area by utilizing the track information and the time relevance of each target object.
The track similarity and the time relevance of the track information of each target object can be obtained, so that whether the target objects belong to the same batch of passenger flows is determined by integrating the track similarity and the time relevance, passenger flow statistics is carried out based on the divided batches of passenger flows, and target passenger flow batch data of the target area is determined.
In some embodiments, referring to fig. 5, step S13 of the above embodiments may be further extended. The method for determining the target passenger flow batch data of the target area by utilizing the track information and the time relevance of each target object can comprise the following steps:
S131: and selecting the target objects meeting the time association condition as the objects to be counted of each batch by utilizing the time association of each target object in the association region.
Whether the time relevance of each target object in the relevance area meets the time relevance condition can be judged; wherein the time-associated condition includes: the time correlation is less than a preset time threshold. The preset time threshold may be user-defined or set based on a statistical application scenario, which is not limited in this application.
If the time correlation meets the time correlation condition, responding to the time correlation of the track information to meet the time correlation condition, and taking each target object meeting the time correlation condition as an object to be counted in the same batch. Therefore, based on each target object meeting the time association condition, each batch of objects to be counted is obtained.
If the time correlation does not meet the time correlation condition, determining that each target object which does not meet the time correlation condition belongs to target objects of different batches in response to the fact that the time correlation of the track information does not meet the time correlation condition.
In some embodiments, in order to more accurately determine whether the objects to be counted belong to the same lot, the following step S132 may be performed on the objects to be counted after the time correlation of the track information satisfies the time correlation condition.
As an example, when the target object a and the target object B enter the second area from the first area, there is an intersecting position with the preset boundary, time information t of the intersecting position of the target object a and the target object B passing the preset boundary is recorded a And t b 。
Acquiring time information t of target object A and target object B a And t b Is a time correlation of (a) to (b). If the preset time threshold is 2S (seconds), if the time correlation is less than 2S, determining that the target object a and the target object B are objects to be counted, executing the following step S132, otherwise, determining the target objects of different batches. Or, the reference time t is set, the preset time threshold is set to be 2s,if time information t a And t b If the time nodes of (2) are within the time interval of t+2, the object to be counted is determined, and the following step S132 is executed, otherwise, the target objects of different batches are determined, that is, the different batches entering the store are determined.
In some embodiments, the above manner may also be used to determine for multiple target objects, and if the time correlation between the target objects A, B, C is less than the preset time threshold for 2 seconds, the target objects A, B, C are regarded as the objects to be counted in the same batch. Or if the time correlation between the target object a and the target object B, C is less than the preset time threshold for 2 seconds, the target object A, B, C is taken as the object to be counted in the same batch.
In some embodiments, for multiple target objects, if the temporal associations between target objects A, B are all less than the preset time threshold for 2 seconds, and if the temporal associations between target objects B, C are all less than the preset time threshold for 2 seconds, then target objects A, B, C are the same batch of objects to be counted. The method and the device do not limit the distinguishing mode of the objects to be counted in the same batch.
S132: and for the objects to be counted of each batch, acquiring first track similarity among track information of the objects to be counted of the batch, selecting the objects to be counted of which the first track similarity meets a first track association condition, and determining the objects to be counted as initial objects of the same batch.
For each batch of objects to be counted, obtaining first track similarity between track information of each object to be counted, wherein a calculation method of the first track similarity comprises Euclidean distance, editing distance or Hastedorff distance and the like, and the method is not limited.
And selecting the objects to be counted, wherein the first track similarity of which meets a first track association condition, and determining the objects to be counted as the initial same batch of objects, wherein the first track association condition comprises that the first track similarity is larger than a first preset similarity threshold value.
Specifically, it may be determined whether the first trajectory similarity between the objects to be counted is greater than a first preset similarity threshold. If the first track similarity is greater than a first preset similarity threshold, determining that the objects to be counted are the same batch. Otherwise, determining the batch as different batches.
As an example, according to the track information l of the target objects a and B a And l b And judging the first track similarity of the target objects A and B. Setting a first preset similarity threshold to be a value between 0 and 1, for example, the first preset similarity threshold is 0.8, if the first track similarity is greater than the first preset similarity threshold, judging that the states of the target objects A and B when entering a target area (such as a store) are the same batch, and otherwise judging that the target objects A and B are different batches. For multiple target objects, whether the target objects belong to the same batch or not can be determined according to the first track similarity between the target objects. If the first track similarity of the target object a and the plurality of target objects is greater than a first preset similarity threshold, it may be determined that the target object a and the plurality of target objects belong to the same batch. Further, in some cases, if it is determined that the target objects a and B are the same lot and the target objects B and C are the same lot, the target objects A, B and C may be determined to be the same lot.
S133: and carrying out passenger flow statistics based on the initial same-batch objects to obtain target passenger flow batch data in the target area.
For the obtained initial same batch object of each batch, passenger flow statistics can be respectively carried out on each batch to obtain initial passenger flow batch data of each batch. And carrying out passenger flow statistics on the initial passenger flow batch data of each batch based on each travelling direction to obtain target passenger flow batch data in a target area.
The passenger flow statistics can be carried out on the initial same batch objects in each advancing direction respectively to obtain initial passenger flow batch data corresponding to each advancing direction of the associated area, and the initial passenger flow batch data in the advancing direction/the exiting direction can be obtained. And carrying out passenger flow statistics by integrating initial passenger flow batch data corresponding to each traveling direction, and determining target passenger flow batch data in a target area.
Specifically, the initial passenger flow batch data corresponding to each traveling direction is synthesized, and the same batch information of each target object is obtained. For example, the same lot information in each traveling direction can be obtained, for example, the same lot information in the entering direction is that the target objects A, B and C belong to the same lot, and the same lot information in the exiting direction is that the target objects B, C and F belong to the same lot.
And judging whether the same batch information of each target object accords with the first same batch condition. The first batch-identical condition includes that target objects in the same batch information of each traveling direction all belong to the same batch. For example, if the target objects B and C belong to the same lot in both the in-direction and the out-direction, it is determined that the target objects B and C meet the first lot-identical condition. For example, if the target objects a and F do not belong to the same lot in the in-direction and the out-direction, it is determined that the target objects a and F do not meet the first lot condition.
And in response to meeting the first same-batch condition, determining each target object meeting the first same-batch condition in the initial passenger flow batch data as a target same-batch object.
As an example, if the target object in-direction and out-direction are both determined to be the same lot in the initial passenger flow lot data, the same lot may be determined. The target object entering direction and the target object exiting direction are determined to be different batches in the initial passenger flow batch data, and then the different batches can be determined. Each batch may include at least one target object.
Therefore, passenger flow statistics is carried out based on the target same-batch objects, and target passenger flow batch data in the target area are obtained. The passenger flow statistics is performed on the target same batch objects of each batch, and the obtained target passenger flow batch data can comprise at least one of batch data, the number of target objects contained in each batch, and total passenger flow (i.e. the number of total target objects).
According to the method, whether the time when the target object enters and leaves the target area is the same batch or not can be judged through the time when the target object enters and leaves and the track information of the travel, so that passenger flow statistics can be carried out on the target object.
According to the scheme, the track information of the target objects in the associated area of the target area is obtained, wherein the associated area has an associated relation with the target area, the target objects enter or leave the target area through the associated area, the track information of each target object is utilized to obtain the time association of each target object in the associated area, the track information and the time association of each target object are utilized to determine the target passenger flow batch data of the target area, the track and the time association of each target object are synthesized to determine the passenger flow batch data, and the accuracy of passenger flow data statistics can be improved; in addition, the method only needs to count the track information of the target object entering or leaving the associated area of the target area, so that the efficiency of passenger flow batch data statistics can be improved.
In some embodiments, if the same lot information of the target objects does not meet the first same lot condition, that is, the lots determined by the target object in-direction and out-direction in the initial passenger flow lot data are different, for example, the target objects a and B corresponding to the in-direction belong to the same lot, and the target objects a and B corresponding to the out-direction belong to different lots, it may be determined that the target objects a and B do not meet the first same lot condition. In this case, the track information of the target object in the target area may also be acquired, and the batch situation may be determined comprehensively. Reference is made in particular to the following examples.
Referring to fig. 6, fig. 6 is a flowchart of a second embodiment of the passenger flow data statistics method of the present application. The method may comprise the steps of:
s21: and acquiring initial passenger flow batch data of the association area by utilizing the track information and time association of each target object.
The track information of the target object in the associated area of the target area can be acquired; the target object enters or leaves the target area through the association area; acquiring the time relevance of each target object in the relevant area by utilizing the track information of each target object; therefore, initial passenger flow batch data of the association area are acquired by utilizing the track information and time association of each target object.
The specific implementation process of the step S21 may refer to the specific implementation process of the above embodiment, which is not described herein.
S22: initial passenger flow batch data of the target area are obtained.
Referring to fig. 7, track information of each target object in the target area may be acquired, for example, track information of the target objects a and B may be acquired, so that whether the target objects belong to the same lot is determined by using the track similarity of the track information, so as to acquire initial passenger flow lot data of the target area. The target area and the track information of each target object can be drawn in the video picture so as to more clearly display the track information of each target object.
In some embodiments, pose information for each target object may be obtained to determine initial passenger flow volume data for each target object in the target area using the pose information.
In some embodiments, track information and gesture information of each target object in the target area can be integrated, and initial passenger flow batch data of the target area can be obtained through integration.
In some embodiments, referring to fig. 8, step S22 of the above embodiments may be further extended. The embodiment may include the steps of:
s221: and acquiring the posture information of each target object in the target area.
The sequence of target detection frames may be detected according to the identifier of the target object and the step S11, where each target detection frame in the sequence is a detection frame of the same target in different frame images, and may refer to a small image of the detection frame area. The embodiment may employ an overall detection frame of the target object, such as a body frame, as the image to be detected.
And carrying out gesture detection on the image to be detected by using the trained gesture detection model to obtain gesture information of the target object.
Alternatively, the target objects within the target area referred to in this step may be all the target objects within the target area.
Alternatively, the target object in the target area referred to in this step may be a target object whose same lot information of the target object in the associated area does not meet the first same lot condition, that is, an object belonging to a different lot in the associated area.
S222: and judging whether the gesture information of each target object meets the interaction association condition.
The trained serialized gesture recognition model can be used for judging whether the gesture information of each target object meets the interaction association condition. The cross-correlation condition may be that there is an action interaction, such as dialogue, hugging, hand-pulling, etc., which is not limited in this application.
For example, taking a target area as a store as an example, after acquiring human body posture information of a target object a and a target object B, judging whether action interaction exists between the target objects a and B, and if action interaction exists between the target objects a and B, judging that the target objects a and B are in the same batch when in the store.
If it is determined that the posture information satisfies the interaction association condition, the following step S223 is performed in response to the posture information satisfying the interaction association condition.
If it is determined that the posture information does not satisfy the interaction association condition, in response to the posture information not satisfying the interaction association condition, the following step S224 is executed.
S223: and determining the target object meeting the interaction association condition as the initial same batch object.
And taking the target objects meeting the interaction association condition as target objects belonging to the same batch in the target area so as to determine the target objects as initial target objects in the same batch.
If the interaction association condition is not satisfied, whether the target objects belong to the same batch or not can be determined through the second track similarity of the track information of the target objects. The process may include the following steps S224 to S227:
s224: and obtaining second track similarity between track information of each target object in the target area.
Alternatively, the target object in the target area referred to in this step may be the target object that does not satisfy the interaction association condition described above.
Alternatively, the target objects within the target area referred to in this step may be all the target objects within the target area.
The second track similarity between the track information of each target object in the target area can be obtained, wherein the calculation method of the second track similarity includes a euclidean distance, an editing distance, a hausdorff distance, and the like, which is not limited in the application.
S225: and judging whether the similarity of each second track meets the second track association condition.
The second track association condition includes that the second track similarity is larger than a second preset similarity threshold value. The second preset similarity threshold may be the same as the first preset similarity threshold, or the second preset similarity threshold may be different from the first preset similarity threshold.
It may be determined whether a second trajectory similarity between the target objects is greater than a second preset similarity threshold. If the second track similarity is larger than a second preset similarity threshold, determining that the target objects are in the same batch, and meeting a second track association condition. Otherwise, determining the batch as different batches.
In some embodiments, the trained interaction behavior discrimination model may be used to determine whether each second trajectory similarity satisfies the second trajectory correlation condition.
The specific implementation process of step S224 to step S225 in this embodiment may refer to the specific implementation process of step S132 in the above embodiment, and will not be described herein.
In some embodiments, the step of determining whether each second trajectory similarity satisfies the second trajectory association condition may be performed in response to the gesture information not satisfying the interaction association condition.
In response to the second track similarity satisfying the second track association condition, the following step S226 is performed.
S226: and determining the target object meeting the second track association condition as the initial same batch object.
And determining the target objects meeting the second track association condition, namely belonging to the same batch, as initial same batch objects in response to the second track similarity meeting the second track association condition.
In some implementations, in response to the second trajectory similarity not satisfying the second trajectory correlation condition, the target objects that do not satisfy the second trajectory correlation condition may be determined to belong to a different batch.
S227: and carrying out passenger flow statistics based on the initial same-batch objects to obtain initial passenger flow batch data in the target area.
Based on the initial same batch objects in the target area, passenger flow statistics can be carried out on the initial same batch objects of each batch, and initial passenger flow batch data in the representative target area is obtained. Wherein the initial passenger flow lot data may include at least one of lot data, the number of target objects contained in each lot, and the total number of target objects.
S23: and combining the initial passenger flow batch data of the associated area and the initial passenger flow batch data of the target area to determine the target passenger flow batch data of the target area.
The initial passenger flow batch data in the associated area and the initial passenger flow batch data in the target area can be synthesized to determine whether the passenger flows belong to the same batch or not, so that the accuracy of batch passenger flow data statistics is improved.
And judging whether the same batch information of each target object in the associated area meets the first same batch condition. The first batch-identical condition includes that target objects in the same batch information of each traveling direction all belong to the same batch. And in response to meeting the first same-batch condition, determining each target object meeting the first same-batch condition in the initial passenger flow batch data as a target same-batch object.
In some embodiments, in response to the same lot information of the target object in the associated area not meeting the first same lot condition, that is, belonging to different lots in the initial passenger flow lot data of each traveling direction, it is determined whether the target object in the initial passenger flow lot data of the target area meets the second same lot condition. The second same batch condition includes that same batch information of at least one traveling direction in the associated area is the same as same batch information in the target area. Or, the second same batch condition includes that the target objects in the same batch information in the target area belong to the same batch.
And responding to the second same batch condition, and determining each target object meeting the second same batch condition in the initial passenger flow batch data as a target same batch object. That is, if the target objects in the target area belong to the same lot, the target objects belonging to the same lot can be determined, and the target objects are determined to be the target objects in the same lot.
In some embodiments, the same batch information of each traveling direction in the associated region and the target object in the target region is obtained. And judging whether the same batch information meets a third same batch condition. Wherein the traveling direction includes an in direction and an out direction. The third same batch condition comprises that the target objects in at least two of the same batch information in the inlet direction, the outlet direction and the target area belong to the same batch. And in response to meeting the third same batch condition, determining each target object meeting the third same batch condition as a target same batch object.
As an example, take the target area as a store and the associated area as an entrance and exit of the store as an example. And (5) integrating the initial passenger flow batch data of the store and the import and export to judge the batch judgment results when personnel enter, in-store and leave, and judging the final batch result. If the person enters and leaves, the person is judged to be in the same batch, and the final judging result is the same batch no matter whether the person is judged to be in the same batch in the store. If the person enters and leaves, the person is judged to be different batches, and whether the person is judged to be the same batch in a store or not, the final judging result is different batches. If the person enters and leaves and is judged to be different results, the judgment result of the person in the store needs to be referred at the moment. If the in-store discrimination result is the same batch, the final result is the same batch. If the in-store discrimination result is different batches, the final result is different batches. Thus, persons belonging to the same lot can be determined as the target same lot object.
Then, passenger flow statistics can be performed based on the target same-batch objects to obtain target passenger flow batch data in the target area.
In this embodiment, when the same batch of the target area is determined, the determination result of the same batch can be comprehensively determined by using the gesture information and the track information of the target object, so as to improve the accuracy of passenger flow batch data statistics in the target area. In addition, the discrimination results of the same batch of the target objects in the association area and the target area can be synthesized, the target same batch of the target objects can be finally determined, and the accuracy of passenger flow batch data statistics can be further improved.
In some embodiments, the above-described object detection model, multi-object tracking model, gesture detection model, interaction behavior discrimination model, and the like may be trained in advance. The following is illustrated as an example, and the present application is not limited thereto.
The training pictures can be collected to label rectangular frames of faces, head shoulders and human bodies, the target detection models (such as YOLO or other target detection models) are used for detecting the head shoulders and the human bodies, the head shoulder detection frames and the human body detection frames are obtained, and the target detection models are trained to obtain trained target detection models. The training method of the multi-target tracking model may refer to the training process of the target detection model, which is not described in detail in this application.
Human body interaction behavior gesture marking can be performed on the collected human body detection frames, gesture detection is performed on the human body detection frames by using a gesture detection model (Openpost or other gesture detection deep learning model), and training is performed to obtain a trained gesture detection model. In addition, the marked gesture sequence can be modeled, semantic behavior descriptions (such as dialogue, hugging, hand pulling and the like) are generated between every two people, and the data are trained through the interactive behavior discrimination model to obtain the trained interactive behavior discrimination model. The interactive behavior discrimination model may be, for example, a serialization model such as an LSTM (Long short-term memory network).
For the above embodiment, the present application further provides a passenger flow data statistics device, where the passenger flow data statistics device is used to implement the steps of any embodiment of the passenger flow data statistics method.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an embodiment of a statistics device for passenger flow data in the present application. The statistics device 30 of the passenger flow data comprises an acquisition trajectory module 31, a time correlation module 32 and a passenger flow statistics module 33. The acquisition trajectory module 31, the time correlation module 32, and the passenger flow statistics module 33 are connected to each other.
The track acquisition module 31 is used for acquiring track information of the target object in the associated area of the target area; the association area has an association relation with the target area, and the target object enters or leaves the target area through the association area.
The time correlation module 32 is configured to obtain time correlations of a plurality of target objects in a correlation area.
The passenger flow statistics module 33 is configured to determine target passenger flow batch data of the target area by using the track information and the time correlation of each target object.
For the implementation of this embodiment, reference may be made to the implementation process of the foregoing embodiment, which is not described herein.
For the foregoing embodiments, the present application provides a computer device, please refer to fig. 10, fig. 10 is a schematic structural diagram of an embodiment of the computer device of the present application. The computer device 40 comprises a memory 41 and a processor 42, wherein the memory 41 and the processor 42 are coupled to each other, and the memory 41 stores program data, and the processor 42 is configured to execute the program data to implement the steps in any embodiment of the above passenger flow data statistics method.
In the present embodiment, the processor 42 may also be referred to as a CPU (Central Processing Unit ). The processor 42 may be an integrated circuit chip having signal processing capabilities. Processor 42 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The general purpose processor may be a microprocessor or the processor 42 may be any conventional processor or the like.
For the method of the above embodiment, which may be implemented in the form of a computer program, the present application proposes a computer readable storage medium, please refer to fig. 11, fig. 11 is a schematic structural diagram of an embodiment of the computer readable storage medium of the present application. The computer readable storage medium 50 stores therein program data 51 executable by a processor, the program data 51 being executable by the processor to implement the steps of any of the embodiments of the passenger flow data statistics method described above.
The computer readable storage medium 50 of the present embodiment may be a medium such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, which may store the program data 51, or may be a server storing the program data 51, which may send the stored program data 51 to another device for operation, or may also run the stored program data 51 by itself.
In the several embodiments provided in the present application, it should be understood that the disclosed methods and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical, or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-readable storage medium, which is a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all or part of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, including several instructions to cause an electronic device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application.
It will be apparent to those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed over a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored in a computer readable storage medium for execution by computing devices, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
The foregoing description is only exemplary embodiments of the present application and is not intended to limit the scope of the present application, and all equivalent structures or equivalent processes using the descriptions and the drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the present application.
Claims (13)
1. A method of passenger flow data statistics, the method comprising:
acquiring track information of a target object in an associated area of the target area; the association area has an association relation with the target area, and the target object enters or leaves the target area through the association area; and
Acquiring time relevance of a plurality of target objects in the relevance area;
and determining target passenger flow batch data of the target area by utilizing the track information and the time relevance of each target object.
2. The method of claim 1, wherein the obtaining the temporal relevance of the plurality of target objects in the relevance area comprises:
acquiring time information of each target object passing through a preset boundary line in the association area by utilizing the track information of each target object in the association area;
and acquiring preset statistical values among the time information of the plurality of target objects to obtain the time relevance among the plurality of target objects.
3. The method of claim 2, wherein the associated region comprises a first region and a second region divided by the predetermined boundary line; the obtaining time information of each target object passing through a preset boundary line in the association area by using the track information of each target object in the association area comprises the following steps:
for each target object, determining the intersection position of the walking track of the target object and the preset boundary line by utilizing track information of the target object in the association area, and acquiring time information and the advancing direction of the target object at the intersection position; the direction of travel includes at least one of entering the second region from the first region, entering the first region from the second region;
And taking the time information of the intersection position and the traveling direction as the time information of the target object passing through the preset boundary line in the traveling direction.
4. The method of claim 1, wherein said determining target passenger flow lot data for said target area using said trajectory information and said time correlation for each of said target objects comprises:
selecting target objects meeting time association conditions as objects to be counted of each batch by utilizing the time association of each target object in the association region;
for each batch of objects to be counted, acquiring first track similarity among track information of the objects to be counted of the batch, selecting the objects to be counted of which the first track similarity meets a first track association condition, and determining the objects to be counted as initial objects in the same batch;
and carrying out passenger flow statistics based on the initial same-batch object to obtain target passenger flow batch data in the target area.
5. The method according to claim 4, wherein the selecting, as the objects to be counted for each lot, the target objects satisfying the time association condition by using the time association of each target object in the association area includes:
Judging whether the time relevance of each target object in the relevance area meets a time relevance condition or not; wherein the time-related conditions include: the time relevance is smaller than a preset time threshold;
and responding to the time relevance of the track information to meet the time relevance condition, and obtaining the objects to be counted of each batch based on each target object meeting the time relevance condition.
6. The method of claim 4, wherein the performing passenger flow statistics based on the initial same lot object to obtain target passenger flow lot data in the target area comprises:
respectively carrying out passenger flow statistics on initial same batch objects in each traveling direction to obtain initial passenger flow batch data corresponding to each traveling direction in the associated area;
and carrying out passenger flow statistics by integrating initial passenger flow batch data corresponding to each traveling direction, and determining target passenger flow batch data in the target area.
7. The method of claim 6, wherein the integrating the initial passenger flow lot data corresponding to each travel direction for passenger flow statistics, determining the target passenger flow lot data in the target area, comprises:
Synthesizing initial passenger flow batch data corresponding to each traveling direction, and acquiring the same batch information of each target object;
judging whether the same batch information of each target object accords with a first same batch condition;
in response to meeting the first same-batch condition, determining each target object meeting the first same-batch condition in the initial passenger flow batch data as a target same-batch object;
and carrying out passenger flow statistics based on the target same-batch objects to obtain target passenger flow batch data in the target area.
8. The method of claim 1, wherein said determining target passenger flow lot data for said target area using said trajectory information and said time correlation for each of said target objects comprises:
acquiring initial passenger flow batch data of the association area by utilizing the track information and the time association of each target object;
acquiring initial passenger flow batch data of the target area;
and integrating the initial passenger flow batch data of the associated area and the initial passenger flow batch data of the target area to determine the target passenger flow batch data of the target area.
9. The method of claim 8, wherein the integrating the initial passenger flow lot data for the associated zone and the initial passenger flow lot data for the target zone to determine target passenger flow lot data for the target zone comprises:
If the same batch information of the target object in the associated area does not meet the first same batch condition, judging whether the target object in the initial passenger flow batch data of the target area meets the second same batch condition;
in response to meeting the second same batch condition, determining each target object meeting the second same batch condition in the initial passenger flow batch data as a target same batch object;
and carrying out passenger flow statistics based on the target same-batch objects to obtain target passenger flow batch data in the target area.
10. The method of claim 8, wherein the acquiring initial passenger flow lot data for the target area comprises:
acquiring second track similarity between track information of each target object in the target area;
judging whether the similarity of each second track meets a second track association condition or not;
in response to the second track similarity meeting a second track association condition, determining a target object meeting the second track association condition as an initial same batch object;
and carrying out passenger flow statistics based on the initial same-batch objects to obtain initial passenger flow batch data in the target area.
11. The method of claim 10, wherein before determining whether each of the second track similarities satisfies a second track association condition, the method comprises:
acquiring the attitude information of each target object in the target area;
judging whether the gesture information of each target object meets the interaction association condition or not:
responding to the gesture information meeting the interaction association condition, and determining a target object meeting the interaction association condition as the initial same batch object; or,
and responding to the gesture information not meeting the interaction association condition, and executing the step of judging whether the similarity of each second track meets the second track association condition.
12. A computer device comprising a memory and a processor coupled to each other, the memory having stored therein program data, the processor being adapted to execute the program data to implement the steps of the method of any of claims 1 to 11.
13. A computer readable storage medium, characterized in that program data executable by a processor are stored, said program data being for implementing the steps of the method according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311216586.0A CN117523472B (en) | 2023-09-19 | 2023-09-19 | Passenger flow data statistics method, computer equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311216586.0A CN117523472B (en) | 2023-09-19 | 2023-09-19 | Passenger flow data statistics method, computer equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117523472A true CN117523472A (en) | 2024-02-06 |
| CN117523472B CN117523472B (en) | 2024-10-15 |
Family
ID=89740704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311216586.0A Active CN117523472B (en) | 2023-09-19 | 2023-09-19 | Passenger flow data statistics method, computer equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117523472B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120092492A1 (en) * | 2010-10-19 | 2012-04-19 | International Business Machines Corporation | Monitoring traffic flow within a customer service area to improve customer experience |
| CN111652160A (en) * | 2020-06-05 | 2020-09-11 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and storage medium |
| CN112052838A (en) * | 2020-10-10 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Object flow data monitoring method and device and readable storage medium |
| CN112597880A (en) * | 2020-12-21 | 2021-04-02 | 杭州海康威视系统技术有限公司 | Passenger flow batch identification method and device, computer equipment and readable storage medium |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN112818173A (en) * | 2021-01-21 | 2021-05-18 | 浙江大华技术股份有限公司 | Method and device for identifying associated object and computer readable storage medium |
| US20210166040A1 (en) * | 2019-11-15 | 2021-06-03 | Beijing Sensetime Technology Development Co., Ltd. | Method and system for detecting companions, electronic device and storage medium |
| CN113220750A (en) * | 2021-05-28 | 2021-08-06 | 重庆中科云从科技有限公司 | Method and device for identifying fellow persons and computer readable storage medium |
| CN113705470A (en) * | 2021-08-30 | 2021-11-26 | 北京市商汤科技开发有限公司 | Method and device for acquiring passenger flow information, computer equipment and storage medium |
| CN114155488A (en) * | 2021-11-30 | 2022-03-08 | 北京市商汤科技开发有限公司 | Method and device for acquiring passenger flow data, electronic equipment and storage medium |
| CN114185964A (en) * | 2021-12-03 | 2022-03-15 | 深圳市商汤科技有限公司 | Data processing method, device, equipment, storage medium and program product |
| GB202213132D0 (en) * | 2022-02-10 | 2022-10-26 | Toshiba Kk | Information processing device, information processing method, information processing system, and computer program |
| WO2023071185A1 (en) * | 2021-10-28 | 2023-05-04 | 上海商汤智能科技有限公司 | Method and apparatus for compiling statistics on customer flow, and computer device and storage medium |
-
2023
- 2023-09-19 CN CN202311216586.0A patent/CN117523472B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120092492A1 (en) * | 2010-10-19 | 2012-04-19 | International Business Machines Corporation | Monitoring traffic flow within a customer service area to improve customer experience |
| US20210166040A1 (en) * | 2019-11-15 | 2021-06-03 | Beijing Sensetime Technology Development Co., Ltd. | Method and system for detecting companions, electronic device and storage medium |
| CN111652160A (en) * | 2020-06-05 | 2020-09-11 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and storage medium |
| CN112052838A (en) * | 2020-10-10 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Object flow data monitoring method and device and readable storage medium |
| CN112597880A (en) * | 2020-12-21 | 2021-04-02 | 杭州海康威视系统技术有限公司 | Passenger flow batch identification method and device, computer equipment and readable storage medium |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN112818173A (en) * | 2021-01-21 | 2021-05-18 | 浙江大华技术股份有限公司 | Method and device for identifying associated object and computer readable storage medium |
| CN113220750A (en) * | 2021-05-28 | 2021-08-06 | 重庆中科云从科技有限公司 | Method and device for identifying fellow persons and computer readable storage medium |
| CN113705470A (en) * | 2021-08-30 | 2021-11-26 | 北京市商汤科技开发有限公司 | Method and device for acquiring passenger flow information, computer equipment and storage medium |
| WO2023071185A1 (en) * | 2021-10-28 | 2023-05-04 | 上海商汤智能科技有限公司 | Method and apparatus for compiling statistics on customer flow, and computer device and storage medium |
| CN114155488A (en) * | 2021-11-30 | 2022-03-08 | 北京市商汤科技开发有限公司 | Method and device for acquiring passenger flow data, electronic equipment and storage medium |
| CN114185964A (en) * | 2021-12-03 | 2022-03-15 | 深圳市商汤科技有限公司 | Data processing method, device, equipment, storage medium and program product |
| GB202213132D0 (en) * | 2022-02-10 | 2022-10-26 | Toshiba Kk | Information processing device, information processing method, information processing system, and computer program |
Non-Patent Citations (1)
| Title |
|---|
| 徐凯航: "基于小群体关联的行人重识别关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 4, 15 April 2017 (2017-04-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117523472B (en) | 2024-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407946B (en) | Cross-line counting method, deep neural network training method, device and electronic equipment | |
| Blunsden et al. | The BEHAVE video dataset: ground truthed video for multi-person behavior classification | |
| Cai et al. | Deep learning-based video system for accurate and real-time parking measurement | |
| US10248860B2 (en) | System and method for object re-identification | |
| Cheriyadat et al. | Detecting dominant motions in dense crowds | |
| Feris et al. | Large-scale vehicle detection, indexing, and search in urban surveillance videos | |
| US9659238B2 (en) | Video object classification | |
| US8131010B2 (en) | High density queue estimation and line management | |
| US8249301B2 (en) | Video object classification | |
| US8351647B2 (en) | Automatic detection and aggregation of demographics and behavior of people | |
| US20170169297A1 (en) | Computer-vision-based group identification | |
| CN103310444B (en) | A kind of method of the monitoring people counting based on overhead camera head | |
| CN105809178A (en) | Population analyzing method based on human face attribute and device | |
| CN109615864A (en) | Vehicle congestion analysis method, system, terminal and storage medium based on video structural | |
| CN110717358B (en) | Visitor number counting method and device, electronic equipment and storage medium | |
| WO2022078134A1 (en) | People traffic analysis method and system, electronic device, and readable storage medium | |
| CN109829382A (en) | The abnormal object early warning tracing system and method for Behavior-based control feature intelligent analysis | |
| Xiang et al. | Autonomous Visual Events Detection and Classification without Explicit Object-Centred Segmentation and Tracking. | |
| Sun et al. | A generic framework for monitoring local freight traffic movements using computer vision-based techniques | |
| Haq et al. | A fast hybrid computer vision technique for real-time embedded bus passenger flow calculation through camera | |
| Jiao et al. | Traffic behavior recognition from traffic videos under occlusion condition: a Kalman filter approach | |
| Balali et al. | Video-based highway asset recognition and 3D localization | |
| CN117523472B (en) | Passenger flow data statistics method, computer equipment and computer readable storage medium | |
| CN112562315A (en) | Method, terminal and storage medium for acquiring traffic flow information | |
| Yu et al. | Length-based vehicle classification in multi-lane traffic flow |
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 |