A pedestrian retrieval method, device, medium and equipment based on trajectory data

Abstract

The present invention relates to the field of data processing, and in particular to a pedestrian retrieval method, device, medium and equipment based on trajectory data. By combining the location information and time information of the target pedestrian provided by a wifi device, a public mobile communication base station and a GPS device, a second actual trajectory point and a second actual time period corresponding to the target pedestrian are obtained, the actual trajectory information of the target pedestrian is clarified, and then a second initial acquisition video is obtained according to the second actual trajectory point and the second actual time period. According to the second similarity between each second initial acquisition video and a preset image of the target pedestrian, a second target acquisition video is screened out from the second initial acquisition video, thereby improving the screening accuracy of the second target acquisition video, and then improving the retrieval accuracy and tracking accuracy of the target pedestrian.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a pedestrian retrieval method, device, medium and equipment based on trajectory data. Background Art

[0002] In recent years, cameras have been widely used in the fields of home, business and public security. With the features of high-definition image quality, night vision function, intelligent recognition, etc., they can record and transmit video signals in real time, helping users to find and deal with problems in a timely manner, and they play an important role in the field of modern security. For example, video-based image retrieval is an important means of work in the field of public security. Through video analysis of the target object's movement trajectory, behavioral activities, peer contact and other behaviors within a certain period of time, it is of great significance in the work of finding the target object. Therefore, how to find relevant videos of the target object's travel in the massive camera data within the city has become an important and challenging task.

[0003] Since there are a large number of cameras in the living environment and they are widely distributed, it is impossible to complete the task of tracking the target object by simply flipping through the video manually. Therefore, the existing technology relies on the travel trajectory of the target object to reduce the search range of the video. However, the daily travel trajectory of the target object is complicated, and when the target object deliberately hides the daily travel trajectory, the search range of the video will be greatly increased, which will reduce the tracking efficiency and accuracy of the target object, and it is difficult to meet the tracking requirements of the target object.

[0004] Therefore, how to improve tracking accuracy becomes an urgent problem to be solved. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is a pedestrian retrieval method based on trajectory data, which comprises the following steps:

[0006] The preset track point collection device is obtained, wherein the track point collection device includes a wifi device, a public mobile communication base station and a GPS device.

[0007] According to the wifi device connected to the target pedestrian and the scanned wifi devices, a first connection range and a first connection time period corresponding to each connected wifi device, and a scanning range and a scanning time period corresponding to each scanned wifi device are obtained.

[0008] According to the public mobile communication base station connected to the target pedestrian, a second connection range and a second connection time period corresponding to each connected public mobile communication base station are acquired.

[0009] According to the GPS device, a GPS data set corresponding to the target pedestrian is acquired, wherein the GPS data set includes the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data.

[0010] According to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, a second actual trajectory point corresponding to the target pedestrian is obtained.

[0011] According to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times, the second actual passing time period corresponding to each second actual trajectory point is acquired.

[0012] According to all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point, the second video acquisition device corresponding to each second actual trajectory point and the second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period are obtained.

[0013] According to the preset image corresponding to the target pedestrian, a second similarity between each second initially collected video and the preset image is obtained.

[0014] According to the comparison result between the second similarity corresponding to the second initial collected video and the preset similarity threshold, the second target collected video is screened out from all the second initial collected videos.

[0015] The present invention also provides a pedestrian retrieval device based on trajectory data, the pedestrian retrieval device comprising:

[0016] The second data acquisition module is used to acquire a preset track point acquisition device, wherein the track point acquisition device includes a wifi device, a public mobile communication base station and a GPS device.

[0017] The wifi device data acquisition module is used to obtain the first connection range and the first connection time period corresponding to each connected wifi device, and the scanning range and the scanning time period corresponding to each scanned wifi device according to the wifi devices connected to the target pedestrian and the scanned wifi devices.

[0018] The base station data acquisition module is used to acquire the second connection range and the second connection time period corresponding to each public mobile communication base station connected to the target pedestrian according to the public mobile communication base station connected to the target pedestrian.

[0019] The GPS device data acquisition module is used to acquire the GPS data set corresponding to the target pedestrian according to the GPS device, wherein the GPS data set includes the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data.

[0020] The second actual track point acquisition module is used to acquire the second actual track point corresponding to the target pedestrian according to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data.

[0021] The second time period acquisition module is used to acquire the second actual passing time period corresponding to each second actual trajectory point according to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times.

[0022] The second video acquisition module is used to obtain the second video acquisition device corresponding to each second actual trajectory point and the second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period based on all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point.

[0023] The second similarity calculation module is used to obtain a second similarity between each second initial collected video and the preset image according to the preset image corresponding to the target pedestrian.

[0024] The second video screening module is used to screen out the second target acquisition video from all the second initial acquisition videos according to the comparison result between the second similarity corresponding to the second initial acquisition video and a preset similarity threshold.

[0025] The present invention also provides a non-transitory computer-readable storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned pedestrian retrieval method based on trajectory data.

[0026] The present invention also provides an electronic device, comprising a processor and the above-mentioned non-transitory computer-readable storage medium.

[0027] The present invention has at least the following beneficial effects: combining the location information of the target pedestrian provided by the wifi device, the public mobile communication base station and the GPS device, obtaining the second actual trajectory point and the second actual time period corresponding to the target pedestrian, clarifying the actual trajectory information of the target pedestrian, and then combining with the preset image of the target pedestrian, screening out the second target captured video from the second initial captured video corresponding to the actual trajectory, thereby improving the accuracy of the second target captured video, and then improving the retrieval accuracy and tracking accuracy of the target pedestrian. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 A flowchart of a pedestrian retrieval method based on trajectory data provided in Embodiment 1 of the present invention;

[0030] Figure 2 A flowchart of a pedestrian retrieval method based on video data provided in Embodiment 2 of the present invention;

[0031] Figure 3 A flowchart of a data processing method for pedestrian retrieval provided in Embodiment 3 of the present invention;

[0032] Figure 4 A schematic diagram of the structure of a pedestrian retrieval device based on trajectory data provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It is understood that, where appropriate, the above-mentioned terms used to distinguish similar objects can be interchanged so that the present invention can also implement other embodiments other than the above-mentioned illustrated embodiments or described embodiments. In addition, the terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] The first embodiment provides a pedestrian retrieval method based on trajectory data. The pedestrian retrieval method based on trajectory data includes: Figure 1 As shown:

[0037] S201, obtaining a preset track point collection device, wherein the track point collection device includes a wifi device, a public mobile communication base station and a GPS device.

[0038] Among them, the track point acquisition device can refer to a device such as a wifi device, a public mobile communication base station and a GPS device that can obtain the location area of ​​the target pedestrian. Specifically, the connection range and scanning range of the fixed wifi device are fixed, and the connection range of the public mobile communication base station is also determined, and the GPS device carried or used by the target pedestrian can report the location data of the target pedestrian. Therefore, the location area of ​​the target pedestrian can be obtained based on the wifi device connected or scanned by the target pedestrian, the public mobile communication base station connected to the target pedestrian, and the GPS device carried or used by the target pedestrian, as the basis for obtaining the second target acquisition video for retrieving the target pedestrian.

[0039] S202, according to the Wi-Fi device connected to the target pedestrian and the scanned Wi-Fi devices, obtain a first connection range and a first connection time period corresponding to each connected Wi-Fi device, and a scanning range and a scanning time period corresponding to each scanned Wi-Fi device.

[0040] Among them, the connection range and scanning range of the fixed Wi-Fi device are fixed. Therefore, according to the Wi-Fi device connected to the target pedestrian and the scanned Wi-Fi device, the first connection range and the first connection time period corresponding to each connected Wi-Fi device, as well as the scanning range and the scanning time period corresponding to each scanned Wi-Fi device can be obtained as the basis for obtaining the second actual trajectory point corresponding to the target pedestrian and the corresponding second actual passing time period.

[0041] S203: According to the public mobile communication base station to which the target pedestrian is connected, a second connection range and a second connection time period corresponding to each connected public mobile communication base station are acquired.

[0042] Among them, the connection range of the public mobile communication base station is determined. Then, according to the public mobile communication base station to which the target pedestrian is connected, the second connection range and second connection time period corresponding to each connected public mobile communication base station can be obtained as the basis for obtaining the second actual trajectory point and the corresponding second actual passing time period corresponding to the target pedestrian.

[0043] S204: Obtain a GPS data set corresponding to the target pedestrian according to the GPS device, wherein the GPS data set includes GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data.

[0044] Among them, the GPS device carried or used by the target pedestrian can report the location data of the target pedestrian. Then, the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data can be obtained according to the GPS device, which serves as the basis for obtaining the second actual trajectory point corresponding to the target pedestrian and the corresponding second actual passing time period.

[0045] S205: Acquire a second actual trajectory point corresponding to the target pedestrian according to all first connection ranges, all scanning ranges, all second connection ranges and all GPS positioning data.

[0046] Among them, the first connection range, scanning range, second connection range and GPS positioning data can all represent the location information of the target pedestrian. Then, by combining all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, several second actual trajectory points corresponding to the target pedestrian can be obtained as the basis for obtaining the second target acquisition video for retrieving the target pedestrian.

[0047] In the above, by combining all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, the second actual trajectory point corresponding to the target pedestrian is obtained, thereby improving the accuracy of obtaining the second actual trajectory point.

[0048] In a specific implementation, according to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, obtaining the second actual trajectory point corresponding to the target pedestrian further includes the following steps:

[0049] According to all the first connection ranges and all the scanning ranges, the n corresponding to the target pedestrian is obtained. 1 First candidate trajectory points, where n 1 Refers to an integer greater than 0.

[0050] According to all the second connection ranges, obtain the n corresponding to the target pedestrian 2 The second candidate trajectory points, where n 2 Refers to an integer greater than 0.

[0051] According to n 1 The first candidate trajectory points, n 2 The second candidate trajectory point and all GPS positioning data are used to obtain the second actual trajectory point corresponding to the target pedestrian.

[0052] Among them, the first candidate trajectory point is a location range determined based on the actual location information of the target pedestrian represented by the wifi device, the second candidate trajectory point is a location range determined based on the actual location information of the target pedestrian represented by the public mobile communication base station, and the GPS positioning data may refer to the longitude and latitude of the actual location of the target pedestrian. By combining all the first candidate trajectory points, all the second candidate trajectory points and all the GPS positioning data, the second actual trajectory point representing the actual location information of the target pedestrian is obtained.

[0053] In the above, the first candidate trajectory point is determined based on the actual location information of the target pedestrian represented by the wifi device, the second candidate trajectory point is determined based on the actual location information of the target pedestrian represented by the public mobile communication base station, and the second actual trajectory point is obtained in combination with the longitude and latitude of the actual location of the target pedestrian, thereby improving the accuracy of obtaining the second actual trajectory point.

[0054] In a specific implementation, according to all the first connection ranges and all the scanning ranges, n corresponding to the target pedestrian is obtained. 1 The first candidate trajectory point also includes the following steps:

[0055] If any first connection range has no intersection with other first connection ranges and the scanning range, any first connection range is taken as a first candidate trajectory point.

[0056] If any scanning range has no intersection with other scanning ranges and the first connection range, any scanning range is taken as a first candidate trajectory point.

[0057] If any first connection range intersects with other first connection ranges or scanning ranges, any first connection range and other first connection ranges or scanning ranges intersecting with any first connection range are taken together as a first candidate trajectory point.

[0058] If any scanning range has an intersection with other scanning ranges or the first connection range, any scanning range and other scanning ranges or the first connection range intersecting with any first scanning range are taken together as a first candidate trajectory point.

[0059] Traverse all the first connection ranges and all the scanning ranges to obtain the n corresponding to the target pedestrian 1 The first candidate trajectory point.

[0060] As described above, based on the positional relationship between all the first connection ranges and all the scanning ranges, several non-intersecting first candidate trajectory points are obtained, thereby clarifying part of the actual trajectory information of the target pedestrian, providing a data basis for predicting the complete trajectory of the target pedestrian, and improving the accuracy of the second predicted trajectory set and the retrieval accuracy of the target pedestrian.

[0061] In a specific implementation, according to all the second connection ranges, n corresponding to the target pedestrian is obtained. 2 The second candidate trajectory point also includes the following steps:

[0062] If any second connection range has no intersection with any other second connection range, any second connection range is taken as a second candidate trajectory point.

[0063] If any second connection range intersects with other second connection ranges, any second connection range and other second connection ranges intersecting with any second connection range are taken together as a second candidate trajectory point.

[0064] Traverse all the second connection ranges and obtain the n corresponding to the target pedestrian 2 The second candidate trajectory point.

[0065] As described above, based on the positional relationship between all the second connection ranges, several non-intersecting second candidate trajectory points are obtained, thereby clarifying part of the actual trajectory information of the target pedestrian, providing a data basis for predicting the complete trajectory of the target pedestrian, and improving the accuracy of the second predicted trajectory set and the retrieval accuracy of the target pedestrian.

[0066] In a specific embodiment, according to n 1 The first candidate trajectory points, n 2 The second candidate trajectory point and all GPS positioning data are used to obtain the second actual trajectory point corresponding to the target pedestrian, and the following steps are also included:

[0067] If any first candidate trajectory point has no intersection with other first candidate trajectory points and second candidate trajectory points, any first candidate trajectory point is taken as a second actual trajectory point.

[0068] If any second candidate trajectory point has no intersection with other second candidate trajectory points and the first candidate trajectory point, any second candidate trajectory point is taken as a second actual trajectory point.

[0069] If any first candidate trajectory point intersects with other first candidate trajectory points or second candidate trajectory points, any first candidate trajectory point and other first candidate trajectory points or second candidate trajectory points intersecting with any first candidate trajectory point are taken together as a second actual trajectory point.

[0070] If any second candidate trajectory point intersects with other second candidate trajectory points or first candidate trajectory points, any second candidate trajectory point and other second candidate trajectory points or first candidate trajectory points intersecting with any second candidate trajectory point are taken together as a second actual trajectory point.

[0071] If any GPS positioning data is not within the range of the first candidate trajectory point and the second candidate trajectory point, a third candidate trajectory point corresponding to any GPS positioning data is obtained according to the preset radius and the GPS positioning data.

[0072] Each third candidate trajectory point is taken as a second actual trajectory point.

[0073] Traversal n 1 The first candidate trajectory points, n 2 The second candidate trajectory point and all GPS positioning data are used to obtain the second actual trajectory point corresponding to the target pedestrian.

[0074] As described above, based on the positional relationship between all the first candidate trajectory points and all the second candidate trajectory points, combined with the GPS positioning data and the positional relationship between the first candidate trajectory points and the second candidate trajectory points, the second actual trajectory point is obtained, thereby clarifying all the actual trajectory information of the target pedestrian, providing a data basis for predicting the complete trajectory of the target pedestrian, and improving the accuracy of the second predicted trajectory set and the retrieval accuracy of the target pedestrian.

[0075] S206: Acquire a second actual passing time period corresponding to each second actual trajectory point according to all first connection time periods, all scanning time periods, all second connection time periods, and all positioning times.

[0076] In a specific implementation, according to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times, obtaining the second actual passing time period corresponding to each second actual trajectory point further includes the following steps:

[0077] According to the first connection range, scanning range, second connection range and GPS positioning data corresponding to each second actual trajectory point, the first connection time period, scanning time period, second connection time period and positioning time corresponding to each second actual trajectory point are obtained.

[0078] The union of all first connection time periods, all scanning time periods, all second connection time periods and all positioning times corresponding to each second actual trajectory point is determined as the second actual passing time period corresponding to each second actual trajectory point.

[0079] As described above, on the basis of the second actual trajectory point, combined with the first connection time period, scanning time period, second connection time period and positioning time, the second actual passing time period corresponding to each second actual trajectory point is obtained, which further supplements the actual trajectory information of the target pedestrian, provides a data basis for predicting the complete trajectory of the target pedestrian, and improves the accuracy of the second predicted trajectory set and the retrieval accuracy of the target pedestrian.

[0080] S207, according to all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point, obtain the second video acquisition device corresponding to each second actual trajectory point and the second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period.

[0081] Among them, the second video acquisition device can refer to a surveillance camera, which is used to collect behavior data of pedestrians, vehicles and other objects within a certain range.

[0082] In the above, the second initial collected video is obtained based on all the second actual trajectory points and the second actual passing time period, and is used as the video basis for retrieving the target pedestrian, thereby improving the retrieval accuracy of the target pedestrian.

[0083] S208: According to the preset image corresponding to the target pedestrian, a second similarity between each second initially collected video and the preset image is obtained.

[0084] In a specific implementation, according to the preset image corresponding to the target pedestrian, obtaining the second similarity between each second initial collected video and the preset image further includes the following steps:

[0085] A plurality of second initial pedestrian segmentation maps corresponding to each second initial collected video are obtained.

[0086] According to each second initial pedestrian segmentation map and the preset image, a second image similarity between each second initial pedestrian segmentation map and the preset image is calculated.

[0087] For any second initial collected video, an average value of the second image similarities between all second initial pedestrian segmentation images corresponding to the second initial collected video and the preset image is taken as the second similarity between any second initial collected video and the preset image.

[0088] All the second initially collected videos are traversed to obtain a second similarity between each second initially collected video and the preset image.

[0089] Among them, the second initial collected video includes not only the behavior video of pedestrians, but also the video information of other interference factors such as vehicles, buildings, animals, etc. Therefore, each frame of the second initial collected video is firstly segmented, and the second initial pedestrian segmentation map is obtained as the processing target to eliminate the influence of other interference factors on the retrieval results.

[0090] The preset image may refer to an image taken while the target pedestrian is walking, which may reflect information such as the body features and walking posture features of the target pedestrian, and serve as a reference basis for retrieving the target pedestrian from the video.

[0091] Among them, those skilled in the art know that any image similarity algorithm in the prior art falls within the protection scope of the present invention, and will not be described in detail here.

[0092] In the above, image segmentation is performed on the second initial collected video to obtain a second initial pedestrian segmentation map, and the second image similarity between each second initial pedestrian segmentation map and the preset image is calculated respectively to characterize the similarity between the pedestrian in each second initial pedestrian segmentation map and the target pedestrian, and the second similarity between each second initial collected video and the preset image is further obtained to characterize the correlation between each second initial collected video and the target pedestrian, which serves as the basis for retrieving the target pedestrian, thereby improving the retrieval accuracy of the target pedestrian.

[0093] S209: Filter out a second target collected video from all the second initial collected videos according to a comparison result between the second similarity corresponding to the second initial collected video and a preset similarity threshold.

[0094] Among them, when the second similarity corresponding to the second initial collected video is greater than the preset similarity threshold, the corresponding second initial collected video will be determined as the second target collected video, so as to analyze the movement trajectory, behavioral activities, peer contacts and other behaviors of the target pedestrian in a certain time period from the second target collected video, provide data support for finding the target object, and thus improve the accuracy of tracking personnel.

[0095] The specific value of the preset similarity threshold can be set by the implementer according to actual conditions.

[0096] In a specific implementation, the pedestrian retrieval method based on trajectory data further includes the following steps:

[0097] Get the trained trajectory prediction model.

[0098] All the second actual trajectory points and the second actual time period corresponding to each second actual trajectory point are input into the trained trajectory prediction model to obtain a second predicted trajectory set, wherein the second predicted trajectory set includes M 2 second predicted trajectory points and the second predicted elapsed time period corresponding to each second predicted trajectory point, M 2 Refers to an integer greater than 0.

[0099] According to the second predicted trajectory set, the third video acquisition device corresponding to each second predicted trajectory point and the third initial acquisition video of each third video acquisition device within the corresponding second predicted elapsed time period are acquired.

[0100] According to the preset image corresponding to the target pedestrian, a third similarity between each third initially collected video and the preset image is obtained.

[0101] According to the comparison result between the third similarity corresponding to the third initial collected video and the preset similarity threshold, the third target collected video is screened out from all the third initial collected videos.

[0102] The trained trajectory prediction model is used to extract and analyze the features of the input second actual trajectory point and the second actual time period, and output the M corresponding to the target pedestrian. 2 The second predicted trajectory points and the second predicted elapsed time period corresponding to each second predicted trajectory point are combined to obtain a second predicted trajectory set to characterize the complete trajectory of the target pedestrian and serve as a basis for obtaining a third target acquisition video to retrieve the target pedestrian.

[0103] In the above, the trajectory of the target pedestrian is predicted according to the trained trajectory prediction model, and the second predicted trajectory set is obtained to characterize the complete trajectory of the target pedestrian, which improves the completeness and richness of the trajectory information, further clarifies the video source when retrieving the target pedestrian, and provides a data basis for obtaining the third target acquisition video for retrieving the target pedestrian, thereby improving the retrieval accuracy of the target pedestrian.

[0104] In a specific implementation, the pedestrian retrieval method based on trajectory data further includes the following steps:

[0105] An initial trajectory prediction model and several real trajectory set samples are obtained, wherein each real trajectory set sample includes A real trajectory point samples of a preset pedestrian and a real passing time period sample corresponding to each real trajectory point sample.

[0106] For any real trajectory set sample, B real trajectory point samples and corresponding real time period samples in any real trajectory set sample are randomly selected to form the model input sample.

[0107] The model input sample is input into the initial trajectory prediction model to obtain the corresponding A predicted trajectory point samples and the predicted time period sample corresponding to each predicted trajectory point sample.

[0108] According to the A predicted trajectory point samples and the predicted time period sample corresponding to each predicted trajectory point sample, a predicted trajectory set sample is obtained.

[0109] According to any real trajectory set sample and the corresponding predicted trajectory set sample, the model sub-loss corresponding to any real trajectory set sample is obtained.

[0110] All true trajectory set samples are traversed, and the sum of the model sub-losses corresponding to all true trajectory set samples is determined as the total model loss of the initial trajectory prediction model.

[0111] The parameters of the initial trajectory prediction model are adjusted according to the total model loss until the model sub-loss converges to obtain the trained trajectory prediction model.

[0112] As described above, the initial trajectory prediction model is trained based on the real trajectory set samples, the accuracy of the model is characterized by the similarity between the real trajectory set samples and the corresponding predicted trajectory set samples, and the parameters of the initial trajectory prediction model are adjusted according to the gradient descent method based on the total loss of the model, thereby improving the accuracy of the trained trajectory prediction model, thereby improving the accuracy of the second predicted trajectory set and the retrieval accuracy of the target pedestrian.

[0113] In the above, combined with the location information of the target pedestrian provided by the wifi device, the public mobile communication base station and the GPS device, the second actual trajectory point and the second actual time period corresponding to the target pedestrian are obtained, the actual trajectory information of the target pedestrian is clarified, and then combined with the preset image of the target pedestrian, the second target captured video is screened out from the second initial captured video corresponding to the actual trajectory, thereby improving the accuracy of the second target captured video, and then improving the retrieval accuracy and tracking accuracy of the target pedestrian.

[0114] Embodiment 2

[0115] The second embodiment provides a pedestrian retrieval method based on video data. The pedestrian retrieval method based on video data includes the following steps: Figure 2 As shown:

[0116] S101, obtaining a first predicted trajectory set corresponding to a target pedestrian, wherein the first predicted trajectory set includes M 1 first predicted trajectory points and the first predicted elapsed time period corresponding to each first predicted trajectory point, M 1 Refers to an integer greater than 0.

[0117] Among them, the target pedestrian refers to the pedestrian whose movement trajectory, behavioral activities, peer contacts, etc. within a certain period of time need to be retrieved.

[0118] In order to retrieve the target pedestrian's movement trajectory, behavioral activities, peer contacts and other behaviors within a certain period of time, this embodiment first obtains a first predicted trajectory set corresponding to the target pedestrian within a preset period of time, which is used to predict the trajectory route of the target pedestrian, and then collects the video corresponding to the first predicted trajectory set as the basis for retrieving the target pedestrian.

[0119] In a specific implementation, obtaining a first predicted trajectory set corresponding to the target pedestrian further includes the following steps:

[0120] Obtain the preset trajectory point collection device and the trained trajectory prediction model.

[0121] According to the trajectory point collection device, a first trajectory set corresponding to the target pedestrian is obtained, wherein the first trajectory set includes N first actual trajectory points of the target pedestrian collected by the trajectory point collection device, and a first actual passing time period corresponding to each first actual trajectory point, where N refers to an integer greater than 0.

[0122] Input the first trajectory set into the trained trajectory prediction model to obtain the M corresponding to the target pedestrian. 1 first predicted trajectory points and a first predicted elapsed time period corresponding to each first predicted trajectory point.

[0123] According to M 1 The first predicted trajectory points and the first predicted elapsed time period corresponding to each first predicted trajectory point are used to obtain a first predicted trajectory set.

[0124] Among them, the track point acquisition device can refer to a device such as a wifi device, a public mobile communication base station and a GPS device that can obtain the location area of ​​the target pedestrian. Specifically, the connection range and scanning range of the fixed wifi device are fixed, and the connection range of the public mobile communication base station is also determined, and the GPS device carried or used by the target pedestrian can report the location data of the target pedestrian. Therefore, the location area of ​​the target pedestrian can be obtained based on the wifi device connected or scanned by the target pedestrian, the public mobile communication base station connected to the target pedestrian, and the GPS device carried or used by the target pedestrian, as the basis for obtaining the first target acquisition video for retrieving the target pedestrian.

[0125] The specific trajectory point collection device can be selected by the implementer according to the actual situation.

[0126] The trained trajectory prediction model is used to extract and analyze the features of the first actual trajectory point and the first actual time period in the input first trajectory set, and output the M corresponding to the target pedestrian. 1 The first predicted trajectory points and the first predicted elapsed time period corresponding to each first predicted trajectory point are obtained to obtain a first predicted trajectory set, which is used as a basis for obtaining a first target acquisition video of the retrieved target pedestrian.

[0127] In the above, the trajectory of the target pedestrian is predicted based on the preset trajectory point acquisition device and the trained trajectory prediction model, and the first predicted trajectory set is obtained, which clarifies the video source when retrieving the target pedestrian, provides a data basis for obtaining the first target acquisition video for retrieving the target pedestrian, and improves the retrieval accuracy of the target pedestrian.

[0128] S102: Acquire, according to the first predicted trajectory set, a first video acquisition device corresponding to each first predicted trajectory point and a first initial acquisition video of each first video acquisition device within a corresponding first predicted elapsed time period.

[0129] Among them, the first video acquisition device may refer to a surveillance camera, which is used to collect behavior data of pedestrians, vehicles and other objects within a certain range.

[0130] In the above, the first initial collected video is obtained based on the first predicted trajectory set and used as the video basis for retrieving the target pedestrian, thereby improving the retrieval accuracy of the target pedestrian.

[0131] S103, obtaining a plurality of first initial pedestrian segmentation maps corresponding to each first initial collected video, and clustering all first initial pedestrian segmentation maps corresponding to all first initial collected videos to obtain K 1 The first initial pedestrian segmentation map set, where K 1 Refers to an integer greater than 0.

[0132] Among them, the first initial collected video includes not only the behavior video of pedestrians, but also the video information of other interference factors such as vehicles, buildings, animals, etc. Therefore, each frame of the first initial collected video is firstly segmented, and the first initial pedestrian segmentation map is obtained as the processing target to eliminate the influence of other interference factors on the retrieval results.

[0133] The same pedestrian may appear in the acquisition range of multiple first video acquisition devices successively, and thus appear in multiple first initial acquisition videos successively. Therefore, all first initial pedestrian segmentation maps corresponding to all first initial acquisition videos are clustered to obtain K 1 A set of first initial pedestrian segmentation maps is used to characterize the correlation between the same pedestrian in different first initial acquisition videos and the differences between different pedestrians.

[0134] In a specific implementation, a plurality of first initial pedestrian segmentation maps corresponding to each first initial acquisition video are obtained, and all first initial pedestrian segmentation maps corresponding to all first initial acquisition videos are clustered to obtain K 1 The first initial pedestrian segmentation map set also includes the following steps:

[0135] According to the preset first frame rate, a plurality of first captured image frames corresponding to each first initial captured video are acquired.

[0136] Image segmentation is performed on each first acquired image frame according to a preset image segmentation algorithm, and a plurality of first initial pedestrian segmentation maps corresponding to each first acquired image frame are obtained.

[0137] All first initial pedestrian segmentation images corresponding to all first initial collected videos are clustered according to a preset clustering algorithm to obtain K 1 The first initial pedestrian segmentation map set.

[0138] The preset first frame rate is determined by the corresponding first video acquisition device.

[0139] Among them, those skilled in the art know that any image segmentation algorithm and any clustering algorithm in the prior art fall within the protection scope of the present invention, and will not be described in detail here.

[0140] In the above, the first initial collected video is segmented to obtain the first initial pedestrian segmentation map, and all the first initial pedestrian segmentation maps are clustered to obtain K 1 A first initial pedestrian segmentation map set is provided to characterize the correlation between the same pedestrian in different first initial collected videos and the difference between different pedestrians according to the first initial pedestrian segmentation map set, which serves as the basis for retrieving the target pedestrian, thereby improving the retrieval accuracy of the target pedestrian.

[0141] S104: Obtain a first similarity between each set of first initial pedestrian segmentation maps and the preset image according to each first initial pedestrian segmentation map and the preset image corresponding to the target pedestrian.

[0142] In a specific implementation, according to each first initial pedestrian segmentation map and the preset image corresponding to the target pedestrian, obtaining the first similarity between each first initial pedestrian segmentation map set and the preset image further includes the following steps:

[0143] The first image similarity between each first initial pedestrian segmentation image and the preset image is calculated.

[0144] For any first initial pedestrian segmentation map set, an average value of first image similarities between all first initial pedestrian segmentation maps corresponding to any first initial pedestrian segmentation map set and the preset image is used as the first similarity between any first initial pedestrian segmentation map set and the preset image.

[0145] All first initial pedestrian segmentation map sets are traversed to obtain a first similarity between each first initial pedestrian segmentation map set and a preset image.

[0146] In the above, the average value of the first image similarities between all the first initial pedestrian segmentation maps corresponding to the first initial pedestrian segmentation map set and the preset image is used as the first similarity between the corresponding first initial pedestrian segmentation map set and the preset image, which provides a basis for retrieving the first initial collected video with the highest degree of association with the target pedestrian.

[0147] S105: Obtain a first correlation degree between each first initial pedestrian segmentation map and the target pedestrian according to the first similarity and the number of first video acquisition devices corresponding to each first initial pedestrian segmentation map set.

[0148] The greater the first similarity corresponding to each first initial pedestrian segmentation map set, the higher the correlation between the first initial pedestrian segmentation map set and the target pedestrian. The greater the number of first video acquisition devices corresponding to each first initial pedestrian segmentation map set, the higher the data richness and reliability of the first initial pedestrian segmentation map set.

[0149] Therefore, the first similarity corresponding to each first initial pedestrian segmentation map set and the number of corresponding first video acquisition devices are both positively correlated with the corresponding first association degree.

[0150] In a specific implementation, according to the first similarity and the number of first video acquisition devices corresponding to each first initial pedestrian segmentation map set, obtaining the first correlation degree between each first initial pedestrian segmentation map and the target pedestrian further includes the following steps:

[0151] For the i-th first initial pedestrian segmentation map set, according to the first video acquisition device corresponding to the first initial pedestrian segmentation map corresponding to the i-th first initial pedestrian segmentation map set, the first device number of the first video acquisition device corresponding to the i-th first initial pedestrian segmentation map set is obtained, where i=1, 2..., K 1 .

[0152] According to the first similarity and the first number of devices corresponding to the i-th first initial pedestrian segmentation map set, the first correlation degree corresponding to the i-th first initial pedestrian segmentation map set is obtained:

[0153] Y 1i =(2 / (1+e^(-S i ))-1)×X 1i .

[0154] Where Y 1i It refers to the first correlation degree corresponding to the i-th first initial pedestrian segmentation map set, S i refers to the number of first devices corresponding to the i-th first initial pedestrian segmentation map set, X 1i It refers to the first similarity corresponding to the i-th first initial pedestrian segmentation map set, and e is an exponential function.

[0155] In the above, combined with the first similarity corresponding to each first initial pedestrian segmentation map set and the corresponding number of first video acquisition devices, the first degree of association between each first initial pedestrian segmentation map and the target pedestrian is calculated, which improves the calculation accuracy of the first degree of association and thereby improves the retrieval accuracy of the target pedestrian.

[0156] S106, according to the first correlation degree, from K 1 A first target pedestrian segmentation map set is selected from the first initial pedestrian segmentation map sets.

[0157] In a specific implementation, according to the first correlation degree, from K 1 Screening out a first target pedestrian segmentation map set from a first initial pedestrian segmentation map set also includes the following steps:

[0158] Comparison K 1 The first correlation degrees corresponding to the first initial pedestrian segmentation map sets are calculated, and the first initial pedestrian segmentation map set corresponding to the largest first correlation degree is determined as the first target pedestrian segmentation map set.

[0159] S107: Determine the first initial collected video corresponding to the first target pedestrian segmentation map set as the first target collected video for retrieving the target pedestrian.

[0160] Among them, the first initial collected video corresponding to the first target pedestrian segmentation map set is determined as the first target collected video for retrieving the target pedestrian. The movement trajectory, behavioral activities, peer contact and other behaviors of the target pedestrian can be analyzed through the first target collected video to provide data support for finding the target object, thereby improving the accuracy of tracking the person.

[0161] In the above, the first initial collected video is obtained based on the first predicted trajectory set, and the influence of interference factors on the retrieval results is eliminated through image segmentation. The correlation between the same pedestrian in different first initial collected videos and the difference between different pedestrians are characterized according to the first initial pedestrian segmentation map set. Therefore, the first similarity corresponding to each first initial pedestrian segmentation map set and the corresponding number of first video acquisition devices are combined to calculate the first correlation degree between each first initial pedestrian segmentation map and the target pedestrian, thereby improving the calculation accuracy of the first correlation degree, thereby improving the retrieval accuracy and tracking accuracy of the target pedestrian.

[0162] Embodiment 3

[0163] The third embodiment provides a data processing method for pedestrian retrieval. The data processing method for pedestrian retrieval includes: Figure 3 As shown:

[0164] S301, obtaining a second initial captured video corresponding to a target pedestrian, and a predicted trajectory point and a second video capturing device corresponding to each second initial captured video.

[0165] In a specific implementation, obtaining the second initial collected video corresponding to the target pedestrian further includes the following steps:

[0166] The second predicted trajectory set corresponding to the target pedestrian is obtained, wherein the second predicted trajectory set includes M 2 second predicted trajectory points and the second predicted elapsed time period corresponding to each second predicted trajectory point, M 2 Refers to an integer greater than 0.

[0167] According to the second predicted trajectory set, T second video acquisition devices corresponding to each second predicted trajectory point and the second initial acquisition video of each second video acquisition device within the corresponding second predicted elapsed time period are obtained, where T refers to the total number of second video acquisition devices.

[0168] In the above, the complete predicted trajectory of the target pedestrian is characterized based on the second predicted trajectory set, and the corresponding second initial collected video is obtained according to the second predicted trajectory set as the video basis for retrieving the target pedestrian, thereby improving the retrieval accuracy of the target pedestrian.

[0169] In a specific implementation, obtaining the second predicted trajectory set corresponding to the target pedestrian further includes the following steps:

[0170] The preset trajectory point collection device and the trained trajectory prediction model are obtained, wherein the trajectory point collection device includes a wifi device, a public mobile communication base station and a GPS device.

[0171] According to the wifi device connected to the target pedestrian and the scanned wifi devices, a first connection range and a first connection time period corresponding to each connected wifi device, and a scanning range and a scanning time period corresponding to each scanned wifi device are obtained.

[0172] According to the public mobile communication base station connected to the target pedestrian, a second connection range and a second connection time period corresponding to each connected public mobile communication base station are acquired.

[0173] According to the GPS device, a GPS data set corresponding to the target pedestrian is acquired, wherein the GPS data set includes the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data.

[0174] According to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, a second actual trajectory point corresponding to the target pedestrian is obtained.

[0175] According to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times, the second actual passing time period corresponding to each second actual trajectory point is acquired.

[0176] All the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point are input into the trained trajectory prediction model to obtain a second predicted trajectory set.

[0177] In the above, the location information of the target pedestrian is characterized according to the first connection range, the scanning range, the second connection range and the GPS positioning data, and a number of second actual trajectory points corresponding to the target pedestrian are obtained in combination with all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data. The second actual passing time period corresponding to each second actual trajectory point is obtained in combination with the first connection time period, the scanning time period, the second connection time period and the positioning time, and the actual trajectory information of the target pedestrian is clarified. The complete predicted trajectory of the target pedestrian is obtained in combination with the trained trajectory prediction model, thereby improving the accuracy of the second predicted trajectory set and the retrieval accuracy of the target pedestrian.

[0178] S302: Perform image segmentation on each second initial collected video to obtain a plurality of second initial pedestrian segmentation maps corresponding to each second initial collected video and a collection time corresponding to each second initial pedestrian segmentation map.

[0179] Among them, the second initial collected video includes not only the behavior video of pedestrians, but also the video information of other interference factors such as vehicles, buildings, animals, etc. Therefore, each frame of the second initial collected video is firstly segmented, and the second initial pedestrian segmentation map is obtained as the processing target to eliminate the influence of other interference factors on the retrieval results.

[0180] In a specific implementation, performing image segmentation on each second initial collected video, and obtaining a plurality of second initial pedestrian segmentation maps corresponding to each second initial collected video and a collection time corresponding to each second initial pedestrian segmentation map further includes the following steps:

[0181] According to the preset second frame rate, a plurality of second acquired image frames corresponding to each second initial acquired video and the acquisition time corresponding to each second acquired image frame are acquired.

[0182] Image segmentation is performed on each second acquired image frame according to a preset image segmentation algorithm, and a plurality of second initial pedestrian segmentation maps corresponding to each second acquired image frame are obtained.

[0183] For any second initial pedestrian segmentation map, the acquisition time corresponding to the second acquisition image frame corresponding to any second initial pedestrian segmentation map is determined as the acquisition time corresponding to the any second initial pedestrian segmentation map.

[0184] The preset second frame rate is determined by the corresponding second video acquisition device.

[0185] In the above, image segmentation is performed on each frame of the second initial captured video, and the second initial pedestrian segmentation map is obtained as the processing target, thereby eliminating the influence of other interference factors on the retrieval results, thereby improving the retrieval accuracy of the target pedestrian.

[0186] S303, clustering all the second initial pedestrian segmentation images corresponding to all the second initial collected videos to obtain K 2 A second initial pedestrian segmentation map set, wherein the second initial pedestrian segmentation maps in each second initial pedestrian segmentation map set are sorted according to the corresponding acquisition time, K 2 Refers to an integer greater than 0.

[0187] Among them, all the second initial pedestrian segmentation maps are clustered to obtain K 2 A second initial pedestrian segmentation map set is provided to characterize the correlation between the same pedestrian in different second initial collected videos and the difference between different pedestrians according to the second initial pedestrian segmentation map set.

[0188] S304, for any second initial pedestrian segmentation map set, calculate the third image similarity between any two second initial pedestrian segmentation maps in the current second initial pedestrian segmentation map set, and determine the average value of all third image similarities corresponding to the current second initial pedestrian segmentation map set as the first clustering reliability corresponding to the current second initial pedestrian segmentation map set.

[0189] Among them, in the same second initial pedestrian segmentation map set, the higher the similarity between the second initial pedestrian segmentation maps, the higher the clustering effect of the corresponding second initial pedestrian segmentation map set, that is, the higher the reliability of the first clustering.

[0190] S305: According to the predicted trajectory points and the second video acquisition devices corresponding to each second initial acquired video, the number of trajectory points and the number of devices corresponding to the current second initial pedestrian segmentation map set are acquired.

[0191] Among them, according to the predicted trajectory points and second video acquisition devices corresponding to each second initial pedestrian segmentation map in the current second initial pedestrian segmentation map set, the number of trajectory points and the number of devices corresponding to the current second initial pedestrian segmentation map set are obtained as the basis for characterizing the richness of the data source of the current second initial pedestrian segmentation map.

[0192] S306: Obtain a third correlation degree between the current second initial pedestrian segmentation map and the target pedestrian according to the first cluster reliability, the number of trajectory points and the number of devices corresponding to the current second initial pedestrian segmentation map set.

[0193] Among them, the larger the number of trajectory points and the number of devices corresponding to each second initial pedestrian segmentation map set are, the higher the data richness and reliability of the second initial pedestrian segmentation map set is.

[0194] Therefore, the first clustering reliability, the number of trajectory points and the number of devices corresponding to each second initial pedestrian segmentation map set are positively correlated with the corresponding third association degree.

[0195] In a specific embodiment, according to

[0196] The first cluster reliability, the number of trajectory points and the number of devices corresponding to the current second initial pedestrian segmentation map set, and obtaining the third correlation degree between the current second initial pedestrian segmentation map and the target pedestrian also include the following steps:

[0197] For the j-th second initial pedestrian segmentation map set, according to the first clustering reliability Z corresponding to the j-th second initial pedestrian segmentation map set j , the number of trajectory points GJ j and the number of devices P j , get the third correlation degree between the jth second initial pedestrian segmentation map set and the target pedestrian:

[0198] Y 3j =(2 / (1+e^(-(α 1 ×P j +α 2 ×GJ j )))-1)×Z j .

[0199] Where Y 3j It refers to the third correlation degree corresponding to the jth second initial pedestrian segmentation map set, P j GJ refers to the number of devices corresponding to the jth second initial pedestrian segmentation map set. j refers to the number of trajectory points corresponding to the jth second initial pedestrian segmentation map set, Z j It refers to the reliability of the first cluster corresponding to the jth second initial pedestrian segmentation map set, α 1 refers to the first preset weight, α 2 It refers to the second preset weight, and e is an exponential function.

[0200] As described above, combined with the first clustering reliability, the number of trajectory points and the number of devices corresponding to each second initial pedestrian segmentation map set, the third degree of association between each second initial pedestrian segmentation map and the target pedestrian is calculated, which improves the calculation accuracy of the third degree of association and thereby improves the retrieval accuracy of the target pedestrian.

[0201] S307, according to the third association degree corresponding to all the second initial pedestrian segmentation graph sets, from K2 A third target pedestrian segmentation map set is selected from the second initial pedestrian segmentation map sets.

[0202] In a specific implementation, according to the third association degree corresponding to all second initial pedestrian segmentation map sets, from K 2 Screening out a third target pedestrian segmentation map set from the second initial pedestrian segmentation map set also includes the following steps:

[0203] Comparison K 2 The third correlation degrees corresponding to the second initial pedestrian segmentation map sets are calculated, and the second initial pedestrian segmentation map set corresponding to the largest third correlation degree is determined as the third target pedestrian segmentation map set.

[0204] S308: Determine the second initial collected video corresponding to the third target pedestrian segmentation map set as the third target collected video for retrieving the target pedestrian.

[0205] Among them, the second initial collected video corresponding to the third target pedestrian segmentation map set is determined as the third target collected video for retrieving the target pedestrian. The movement trajectory, behavioral activities, peer contact and other behaviors of the target pedestrian can be analyzed through the third target collected video to provide data support for finding the target object, thereby improving the accuracy of tracking the person.

[0206] In the above, the third image similarity between the second initial pedestrian segmentation maps in the second initial pedestrian segmentation map set is combined to characterize the first clustering reliability corresponding to the second initial pedestrian segmentation map set, and then combined with the first clustering reliability corresponding to the second initial pedestrian segmentation map set, according to the first clustering reliability corresponding to the current second initial pedestrian segmentation map set, the number of trajectory points and the number of devices, the third correlation degree between the current second initial pedestrian segmentation map and the target pedestrian is characterized, thereby improving the accuracy of the third correlation degree, and then improving the accuracy of the third target acquisition video, thereby improving the retrieval accuracy and tracking accuracy of the target pedestrian.

[0207] Embodiment 4

[0208] The fourth embodiment provides a pedestrian retrieval device based on trajectory data. The pedestrian retrieval device based on trajectory data includes: Figure 4 As shown:

[0209] The second data acquisition module 41 is used to acquire a preset track point acquisition device, wherein the track point acquisition device includes a wifi device, a public mobile communication base station and a GPS device.

[0210] The Wi-Fi device data acquisition module 42 is used to obtain the first connection range and the first connection time period corresponding to each connected Wi-Fi device, and the scanning range and the scanning time period corresponding to each scanned Wi-Fi device according to the Wi-Fi devices connected to the target pedestrian and the scanned Wi-Fi devices.

[0211] The base station data acquisition module 43 is used to acquire the second connection range and the second connection time period corresponding to each public mobile communication base station connected to the target pedestrian according to the public mobile communication base station connected to the target pedestrian.

[0212] The GPS device data acquisition module 44 is used to acquire the GPS data set corresponding to the target pedestrian according to the GPS device, wherein the GPS data set includes the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data.

[0213] The second actual track point acquisition module 45 is used to acquire the second actual track point corresponding to the target pedestrian according to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data.

[0214] The second time period acquisition module 46 is used to acquire the second actual passing time period corresponding to each second actual trajectory point according to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times.

[0215] The second video acquisition module 47 is used to obtain the second video acquisition device corresponding to each second actual trajectory point and the second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period based on all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point.

[0216] The second similarity calculation module 48 is used to obtain a second similarity between each second initial collected video and the preset image according to the preset image corresponding to the target pedestrian.

[0217] The second video screening module 49 is used to screen out the second target collected video from all the second initial collected videos according to the comparison result between the second similarity corresponding to the second initial collected video and a preset similarity threshold.

[0218] In a specific implementation, the second actual trajectory point acquisition module 45 includes:

[0219] The first candidate trajectory point acquisition submodule is used to obtain n corresponding to the target pedestrian according to all the first connection ranges and all the scanning ranges. 1 First candidate trajectory points, where n 1Refers to an integer greater than 0.

[0220] The second candidate trajectory point acquisition submodule is used to obtain n corresponding to the target pedestrian according to all the second connection ranges. 2 The second candidate trajectory points, where n 2 Refers to an integer greater than 0.

[0221] The second actual trajectory point acquisition submodule is used to obtain the actual trajectory point according to the n 1 first candidate trajectory points, the n 2 The second candidate trajectory points and all GPS positioning data are used to obtain the second actual trajectory point corresponding to the target pedestrian.

[0222] In a specific implementation, the first candidate trajectory point acquisition submodule includes:

[0223] The first candidate trajectory point acquisition unit is configured to take any first connection range as a first candidate trajectory point if there is no intersection between any first connection range and other first connection ranges and the scanning range.

[0224] The second candidate trajectory point acquisition unit is used to take any scanning range as a first candidate trajectory point if there is no intersection between any scanning range, the other scanning range and the first connection range.

[0225] The third candidate trajectory point acquisition unit is used to take any first connection range and other first connection ranges or scanning ranges intersecting with any first connection range as a first candidate trajectory point if there is an intersection between any first connection range and other first connection ranges or scanning ranges.

[0226] The fourth candidate trajectory point acquisition unit is used to take any scanning range and other scanning ranges or first connection ranges intersecting with any first scanning range as a first candidate trajectory point if there is an intersection between any scanning range and other scanning ranges or first connection ranges.

[0227] The first range traversal unit is used to traverse all first connection ranges and all scanning ranges to obtain n corresponding to the target pedestrian 1 The first candidate trajectory point.

[0228] In a specific implementation, the second candidate trajectory point acquisition submodule includes:

[0229] The fifth candidate trajectory point obtaining unit is configured to take any second connection range as a second candidate trajectory point if there is no intersection between any second connection range and any other second connection range.

[0230] The sixth candidate trajectory point acquiring unit is configured to take any second connection range and other second connection ranges intersecting with any second connection range as a second candidate trajectory point if there is an intersection between any second connection range and other second connection ranges.

[0231] The second range traversal unit is used to traverse all second connection ranges to obtain n corresponding to the target pedestrian 2 The second candidate trajectory point.

[0232] In a specific implementation, the second actual trajectory point acquisition submodule includes:

[0233] The first actual trajectory point acquiring unit is configured to take any first candidate trajectory point as a second actual trajectory point if there is no intersection between any first candidate trajectory point and other first candidate trajectory points and second candidate trajectory points.

[0234] The second actual trajectory point acquiring unit is configured to take any second candidate trajectory point as a second actual trajectory point if there is no intersection between any second candidate trajectory point and other second candidate trajectory points and the first candidate trajectory point.

[0235] The third actual trajectory point acquisition unit is used to take any first candidate trajectory point and other first candidate trajectory points or second candidate trajectory points intersecting with any first candidate trajectory point as a second actual trajectory point if there is an intersection between any first candidate trajectory point and other first candidate trajectory points or second candidate trajectory points.

[0236] The fourth actual trajectory point acquisition unit is used to take any second candidate trajectory point and other second candidate trajectory points or first candidate trajectory points intersecting with any second candidate trajectory point as a second actual trajectory point if there is an intersection between any second candidate trajectory point and other second candidate trajectory points or first candidate trajectory points.

[0237] The fifth candidate trajectory point acquisition unit is used to acquire a third candidate trajectory point corresponding to any GPS positioning data according to a preset radius and the GPS positioning data if any GPS positioning data is not within the range of the first candidate trajectory point and the second candidate trajectory point.

[0238] The fifth actual trajectory point acquisition unit is configured to take each third candidate trajectory point as a second actual trajectory point.

[0239] The third data traversal unit is used to traverse the n 1 first candidate trajectory points, the n 2 The second candidate trajectory points and all GPS positioning data are used to obtain the second actual trajectory point corresponding to the target pedestrian.

[0240] In a specific implementation, the second time period acquisition module 46 includes:

[0241] The first time period acquisition submodule is used to obtain the first connection time period, scanning time period, second connection time period and positioning time corresponding to each second actual trajectory point according to the first connection range, scanning range, second connection range and GPS positioning data corresponding to each second actual trajectory point.

[0242] The second time period acquisition submodule is used to determine the union of all first connection time periods, all scanning time periods, all second connection time periods and all positioning times corresponding to each second actual trajectory point as the second actual passing time period corresponding to each second actual trajectory point.

[0243] In a specific implementation, the second similarity calculation module 48 includes:

[0244] The second image segmentation submodule is used to obtain a plurality of second initial pedestrian segmentation images corresponding to each second initial collected video.

[0245] The second image similarity calculation submodule is used to calculate the second image similarity between each second initial pedestrian segmentation map and the preset image according to each second initial pedestrian segmentation map and the preset image.

[0246] The second similarity calculation submodule is used to calculate, for any second initial collected video, an average value of the second image similarities between all second initial pedestrian segmentation maps corresponding to the second initial collected video and the preset image as the second similarity between any second initial collected video and the preset image.

[0247] The second video traversal submodule is used to traverse all the second initial collected videos and obtain the second similarity between each second initial collected video and the preset image.

[0248] In a specific implementation, the pedestrian retrieval device based on trajectory data further includes:

[0249] Model acquisition module, used to obtain the trained trajectory prediction model;

[0250] The second trajectory prediction module is used to input all the second actual trajectory points and the second actual time period corresponding to each second actual trajectory point into the trained trajectory prediction model to obtain a second predicted trajectory set, wherein the second predicted trajectory set includes M 2 second predicted trajectory points and the second predicted elapsed time period corresponding to each second predicted trajectory point, M 2 Refers to an integer greater than 0;

[0251] A third initial acquisition video acquisition module is used to acquire, according to the second predicted trajectory set, a third video acquisition device corresponding to each second predicted trajectory point, and a third initial acquisition video of each third video acquisition device within the corresponding second predicted elapsed time period;

[0252] A third similarity acquisition module, configured to acquire a third similarity between each third initially collected video and the preset image according to the preset image corresponding to the target pedestrian;

[0253] The third target acquisition video acquisition module is used to select the third target acquisition video from all the third initial acquisition videos according to the comparison result between the third similarity corresponding to the third initial acquisition video and a preset similarity threshold.

[0254] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0255] Embodiment 5

[0256] Embodiment 5 of the present invention provides a non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to implement the steps:

[0257] A preset track point collection device is obtained, wherein the track point collection device includes a wifi device, a public mobile communication base station and a GPS device.

[0258] According to the wifi device connected to the target pedestrian and the scanned wifi devices, a first connection range and a first connection time period corresponding to each connected wifi device, and a scanning range and a scanning time period corresponding to each scanned wifi device are obtained.

[0259] According to the public mobile communication base station to which the target pedestrian is connected, a second connection range and a second connection time period corresponding to each connected public mobile communication base station are acquired.

[0260] According to the GPS device, a GPS data set corresponding to the target pedestrian is acquired, wherein the GPS data set includes the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data.

[0261] According to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, a second actual trajectory point corresponding to the target pedestrian is obtained.

[0262] According to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times, the second actual passing time period corresponding to each second actual trajectory point is acquired.

[0263] According to all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point, the second video acquisition device corresponding to each second actual trajectory point and the second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period are obtained.

[0264] According to the preset image corresponding to the target pedestrian, a second similarity between each second initially collected video and the preset image is obtained.

[0265] According to the comparison result between the second similarity corresponding to the second initial collected video and the preset similarity threshold, the second target collected video is screened out from all the second initial collected videos.

[0266] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchronization Link) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0267] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0268] Embodiment 6

[0269] A sixth embodiment of the present invention provides an electronic device, which includes a processor and the non-transitory computer-readable storage medium in the fifth embodiment of the present invention.

[0270] The above are only preferred embodiments of the present invention, and are not intended to limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A pedestrian retrieval method based on trajectory data, characterized in that: The pedestrian retrieval method comprises the following steps: Obtaining a preset track point collection device, wherein the track point collection device includes a wifi device, a public mobile communication base station and a GPS device; According to the wifi device connected to the target pedestrian and the scanned wifi devices, a first connection range and a first connection time period corresponding to each connected wifi device, and a scanning range and a scanning time period corresponding to each scanned wifi device are obtained; According to the public mobile communication base station connected to the target pedestrian, acquiring a second connection range and a second connection time period corresponding to each connected public mobile communication base station; According to the GPS device, a GPS data set corresponding to the target pedestrian is obtained, wherein the GPS data set includes GPS positioning data of the target pedestrian and a positioning time corresponding to each GPS positioning data; According to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, a second actual track point corresponding to the target pedestrian is obtained, wherein the obtaining of the second actual track point corresponding to the target pedestrian according to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data further comprises the following steps: According to all the first connection ranges and all the scanning ranges, n1 first candidate trajectory points corresponding to the target pedestrian are obtained, where n1 is an integer greater than 0; According to all the second connection ranges, n2 second candidate trajectory points corresponding to the target pedestrian are obtained, where n2 is an integer greater than 0; According to the n1 first candidate trajectory points, the n2 second candidate trajectory points and all GPS positioning data, a second actual trajectory point corresponding to the target pedestrian is obtained; The method of acquiring n1 first candidate trajectory points corresponding to the target pedestrian according to all the first connection ranges and all the scanning ranges further includes the following steps: If any first connection range has no intersection with other first connection ranges and the scanning range, taking any first connection range as a first candidate trajectory point; If any scanning range has no intersection with other scanning ranges and the first connection range, taking any scanning range as a first candidate trajectory point; If any first connection range intersects with other first connection ranges or scanning ranges, the first connection range and other first connection ranges or scanning ranges intersecting with the first connection range are taken together as a first candidate trajectory point; If any scanning range intersects with other scanning ranges or the first connection range, the scanning range and the other scanning ranges or the first connection range intersecting with the scanning range are taken together as a first candidate trajectory point; Traversing all first connection ranges and all scanning ranges to obtain n1 first candidate trajectory points corresponding to the target pedestrian; According to all the first connection time periods, all the scanning time periods, all the second connection time periods and all the positioning times, a second actual passing time period corresponding to each second actual trajectory point is obtained; According to all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point, a second video acquisition device corresponding to each second actual trajectory point and a second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period are acquired; According to the preset image corresponding to the target pedestrian, a second similarity between each second initially collected video and the preset image is obtained; According to the comparison result between the second similarity corresponding to the second initial collected video and the preset similarity threshold, the second target collected video is screened out from all the second initial collected videos.

2. The pedestrian retrieval method based on trajectory data according to claim 1, characterized in that: The step of obtaining n2 second candidate trajectory points corresponding to the target pedestrian according to all the second connection ranges further comprises the following steps: If there is no intersection between any second connection range and any other second connection range, taking any second connection range as a second candidate trajectory point; If any second connection range intersects with other second connection ranges, the second connection range and other second connection ranges intersecting with the second connection range are taken together as a second candidate trajectory point; Traverse all second connection ranges to obtain n2 second candidate trajectory points corresponding to the target pedestrian.

3. The pedestrian retrieval method based on trajectory data according to claim 1, characterized in that: The step of obtaining the second actual trajectory point corresponding to the target pedestrian according to the n1 first candidate trajectory points, the n2 second candidate trajectory points and all GPS positioning data further comprises the following steps: If there is no intersection between any first candidate trajectory point and other first candidate trajectory points and second candidate trajectory points, taking any first candidate trajectory point as a second actual trajectory point; If any second candidate trajectory point has no intersection with other second candidate trajectory points and the first candidate trajectory point, taking any second candidate trajectory point as a second actual trajectory point; If any first candidate trajectory point intersects with other first candidate trajectory points or second candidate trajectory points, the first candidate trajectory point and other first candidate trajectory points or second candidate trajectory points intersecting with the first candidate trajectory point are collectively regarded as a second actual trajectory point; If any second candidate trajectory point intersects with other second candidate trajectory points or first candidate trajectory points, the second candidate trajectory point and other second candidate trajectory points or first candidate trajectory points intersecting with the second candidate trajectory point are collectively regarded as a second actual trajectory point; If any GPS positioning data is not within the range of the first candidate trajectory point and the second candidate trajectory point, a third candidate trajectory point corresponding to any GPS positioning data is obtained according to the preset radius and the GPS positioning data; Taking each third candidate trajectory point as a second actual trajectory point; The n1 first candidate trajectory points, the n2 second candidate trajectory points and all GPS positioning data are traversed to obtain a second actual trajectory point corresponding to the target pedestrian.

4. The pedestrian retrieval method based on trajectory data according to claim 1, characterized in that: The step of obtaining the second similarity between each second initially collected video and the preset image corresponding to the target pedestrian further comprises the following steps: Obtaining a plurality of second initial pedestrian segmentation images corresponding to each second initial collected video; Calculating a second image similarity between each second initial pedestrian segmentation map and the preset image according to each second initial pedestrian segmentation map and the preset image; For any second initial collected video, taking an average of second image similarities between all second initial pedestrian segmentation images corresponding to the second initial collected video and the preset image as the second similarity between the any second initial collected video and the preset image; All the second initially collected videos are traversed to obtain a second similarity between each second initially collected video and the preset image.

5. The pedestrian retrieval method based on trajectory data according to claim 1, characterized in that: The pedestrian retrieval method further comprises the following steps: Get the trained trajectory prediction model; Input all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point into the trained trajectory prediction model to obtain a second predicted trajectory set, wherein the second predicted trajectory set includes M2 second predicted trajectory points and the second predicted elapsed time period corresponding to each second predicted trajectory point, where M2 refers to an integer greater than 0; According to the second predicted trajectory set, a third video acquisition device corresponding to each second predicted trajectory point and a third initial acquisition video of each third video acquisition device within the corresponding second predicted elapsed time period are acquired; According to the preset image corresponding to the target pedestrian, a third similarity between each third initially collected video and the preset image is obtained; According to the comparison result between the third similarity corresponding to the third initial collected video and the preset similarity threshold, the third target collected video is screened out from all the third initial collected videos.

6. A pedestrian retrieval device based on trajectory data, characterized in that: The pedestrian retrieval device comprises: A second data acquisition module is used to acquire a preset track point acquisition device, wherein the track point acquisition device includes a wifi device, a public mobile communication base station and a GPS device; The wifi device data acquisition module is used to acquire the first connection range and the first connection time period corresponding to each connected wifi device, and the scanning range and the scanning time period corresponding to each scanned wifi device according to the wifi device connected to the target pedestrian and the scanned wifi devices; A base station data acquisition module, configured to acquire, according to the public mobile communication base station to which the target pedestrian is connected, a second connection range and a second connection time period corresponding to each public mobile communication base station connected; A GPS device data acquisition module, used to acquire a GPS data set corresponding to the target pedestrian according to the GPS device, wherein the GPS data set includes the GPS positioning data of the target pedestrian and the positioning time corresponding to each GPS positioning data; The second actual track point acquisition module is used to acquire the second actual track point corresponding to the target pedestrian according to all the first connection ranges, all the scanning ranges, all the second connection ranges and all the GPS positioning data, wherein the second actual track point acquisition module further includes: A first candidate trajectory point acquisition submodule, configured to acquire n1 first candidate trajectory points corresponding to the target pedestrian according to all first connection ranges and all scanning ranges, wherein n1 is an integer greater than 0; A second candidate trajectory point acquisition submodule, used to acquire n2 second candidate trajectory points corresponding to the target pedestrian according to all second connection ranges, wherein n2 is an integer greater than 0; A second actual trajectory point acquisition submodule, configured to acquire a second actual trajectory point corresponding to the target pedestrian according to the n1 first candidate trajectory points, the n2 second candidate trajectory points and all GPS positioning data; Wherein, the first candidate trajectory point acquisition submodule further includes: A first candidate trajectory point acquisition unit, configured to take any first connection range as a first candidate trajectory point if there is no intersection between any first connection range and other first connection ranges and the scanning range; A second candidate trajectory point acquisition unit, configured to take any scanning range as a first candidate trajectory point if there is no intersection between any scanning range and the other scanning ranges and the first connection range; a third candidate trajectory point acquisition unit, configured to take any first connection range and other first connection ranges or scanning ranges intersecting with any first connection range as a first candidate trajectory point if there is an intersection between any first connection range and other first connection ranges or scanning ranges; a fourth candidate trajectory point acquisition unit, configured to take any scanning range and the other scanning range or the first connection range intersecting with any scanning range as a first candidate trajectory point if there is an intersection between any scanning range and other scanning ranges or the first connection range; A first range traversal unit, used to traverse all first connection ranges and all scanning ranges to obtain n1 first candidate trajectory points corresponding to the target pedestrian; A second time period acquisition module, used to acquire a second actual passing time period corresponding to each second actual trajectory point according to all first connection time periods, all scanning time periods, all second connection time periods and all positioning times; A second video acquisition module is used to acquire, according to all the second actual trajectory points and the second actual elapsed time period corresponding to each second actual trajectory point, a second video acquisition device corresponding to each second actual trajectory point, and a second initial acquisition video of each second video acquisition device in the corresponding second actual elapsed time period; A second similarity calculation module, used to obtain a second similarity between each second initial collected video and the preset image according to the preset image corresponding to the target pedestrian; The second video screening module is used to screen out the second target acquisition video from all the second initial acquisition videos according to the comparison result between the second similarity corresponding to the second initial acquisition video and a preset similarity threshold.

7. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the pedestrian retrieval method based on trajectory data as described in any one of claims 1 to 5.

8. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 7.

Images