Video-based vehicle tracking method, device and server

Abstract

The invention is suitable for the technical field of intelligent transportation, and provides a video-based vehicle tracking method and device, and a server. The method comprises the following steps: acquiring section vehicle fusion information and management and control road section vehicle sensing information corresponding to each vehicle in a first preset area of a management and control road section and a second preset area of the management and control road section through a plurality of sensing devices arranged on the management and control road section; fusing and updating the section vehicle fusion information and the management and control road section vehicle sensing information, determining target vehicle feature information carried by the updated management and control road section vehicle fusion information, and in combination with the management and control road section vehicle sensing information and the target vehicle feature information, updating identity feature information of vehicles sensed at different positions in real time; according to the method, the perceptual information of the vehicles at different positions in the management and control road section is effectively joined, tracking of the vehicles on the management and control road section is completed, identity feature information of each vehicle on the management and control road section is accurately determined, and efficient monitoring of each vehicle on the management and control road section is achieved.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent transportation, and particularly relates to a video-based vehicle tracking method, device and server. Background Art

[0002] With the rapid development of urban roads, the number of motor vehicles has increased sharply, making the management difficulty of urban traffic safety gradually increase.

[0003] In urban planning, there are usually some control sections with complex terrains (such as tunnels). Control sections usually have characteristics such as relatively narrow internal roadbed width, strong space tightness, small field of vision, low visibility, and usually one-way roads, making the driving environment complex. Abnormal vehicle driving behaviors such as slow vehicle speed, vehicle speeding, and vehicle stagnation may lead to serious traffic accidents and pose great potential safety hazards.

[0004] The vehicle monitoring efficiency of related control section traffic management methods is low and the monitoring accuracy is not high. Therefore, how to achieve vehicle tracking in control section traffic, improve the monitoring efficiency and monitoring accuracy has become an urgent problem to be solved. Summary of the Invention

[0005] The embodiments of this application provide a video-based vehicle tracking method, device and server, which can achieve vehicle tracking in control section traffic, improve the monitoring efficiency and monitoring accuracy.

[0006] The first aspect of the embodiments of this application provides a video-based vehicle tracking method, which is applied to a server. The server is communicatively connected to multiple sensing devices; the sensing devices are arranged in the control section, and the sensing devices include lidar and cameras; the cameras include long-focus cameras and short-focus cameras; there is an intersecting sensing connection area between the radar detection area of the lidar and the shooting area of the cameras; there is an intersecting shooting connection area between the first shooting area of the long-focus camera and the second shooting area of the short-focus camera;

[0007] The vehicle tracking method includes: obtaining, by the sensing devices, the cross-section vehicle fusion information corresponding to each vehicle in the first preset area of the control section and the control section vehicle sensing information corresponding to each vehicle in the second preset area of the control section; wherein, the cross-section vehicle fusion information includes vehicle feature information;

[0008] Performing feature matching on the cross-section vehicle fusion information and the control section vehicle sensing information corresponding to each vehicle based on the vehicle feature information to obtain the control section vehicle fusion information corresponding to each vehicle;

[0009] For each control section vehicle sensing information, determining the control section vehicle fusion information corresponding to the control section vehicle sensing information;

[0010] Update the vehicle feature information of the vehicle integration information on the control section by using the vehicle connection information of the control section corresponding to each vehicle, obtain the updated vehicle integration information on the control section corresponding to each vehicle respectively, and determine the target vehicle feature information carried by the updated vehicle integration information on the control section;

[0011] Track the vehicle trajectory according to the vehicle perception information on the control section and the target vehicle feature information.

[0012] Optionally, in a possible implementation manner of the first aspect, the above-mentioned obtaining of the cross-section vehicle integration information corresponding to each vehicle in the first preset area of the control section and the vehicle perception information on the control section corresponding to each vehicle in the second preset area of the control section by the perception device includes:

[0013] For each vehicle, when it is detected that the vehicle arrives at the first preset area of the control section, obtain the cross-section vehicle perception information of the vehicle through the perception device in the first preset area;

[0014] When it is determined according to the cross-section vehicle perception information that the vehicle arrives at the preset trigger area, obtain the vehicle feature information of the vehicle through the perception device in the second preset area;

[0015] Bind the vehicle feature information and the cross-section vehicle perception information to obtain the cross-section vehicle integration information of the vehicle;

[0016] When it is detected that the vehicle arrives at the second preset area of the control section, obtain the vehicle perception information on the control section of the vehicle through the perception device in the second preset area; wherein, the second preset area is located after the first preset area.

[0017] Optionally, in another possible implementation manner of the first aspect, the above-mentioned feature matching of the cross-section vehicle integration information and the vehicle perception information on the control section corresponding to each vehicle based on the vehicle feature information to obtain the vehicle integration information on the control section corresponding to each vehicle respectively includes:

[0018] Respectively determine the vehicle perception information on the control section that is spatio-temporally matched with each cross-section vehicle perception information, and respectively fuse the mutually matched cross-section vehicle perception information and the vehicle perception information on the control section to obtain the cross-section vehicle connection information corresponding to each vehicle;

[0019] For each cross-section vehicle connection information, determine the cross-section vehicle integration information that is feature-matched with the cross-section vehicle connection information based on the vehicle feature information, and fuse the cross-section vehicle connection information and the matched cross-section vehicle integration information to obtain the vehicle integration information on the control section of the vehicle.

[0020] Optionally, in another possible implementation manner of the first aspect, the above-mentioned method of respectively determining the vehicle perception information of the control section that is spatiotemporally matched with the vehicle perception information of each section, and respectively fusing the mutually matched vehicle perception information of the section and the vehicle perception information of the control section to obtain the vehicle connection information of the section corresponding to each vehicle includes:

[0021] For each vehicle, when it is detected that the vehicle arrives at the preset perception connection area, the vehicle perception information of the control section corresponding to the vehicle perception information of the section is obtained through the perception device; wherein, the preset perception connection area is the perception intersection area of the perception devices in the first preset area and the perception devices in the second preset area; the perception intersection area includes at least one of the perception connection area and the shooting connection area;

[0022] Perform spatiotemporal matching on the vehicle perception information of the section and the vehicle perception information of the control section corresponding to the vehicle perception information of the section, fuse the mutually matched vehicle perception information of the section and the vehicle perception information of the control section, and determine the vehicle connection information of the section corresponding to the vehicle.

[0023] Optionally, in another possible implementation manner of the first aspect, the above-mentioned vehicle perception information of the section includes the first induction moment, the first vehicle speed information, and the first vehicle spacing; the vehicle perception information of the control section includes the second induction moment, the second vehicle speed information, and the second vehicle spacing;

[0024] Correspondingly, for each vehicle, when it is detected that the vehicle arrives at the preset perception connection area, obtaining the vehicle perception information of the control section corresponding to the vehicle perception information of the section through the perception device includes:

[0025] For each vehicle, when it is detected that the vehicle arrives at the preset perception connection area, obtain the vehicle perception information of the control section through the perception device;

[0026] When it is detected that the first induction moment and the second induction moment match, and the first vehicle speed information and the second vehicle speed information match, determine the first difference between the first vehicle spacing and the second vehicle spacing;

[0027] When it is detected that the first difference is less than or equal to the preset threshold, and the first vehicle spacing and the second vehicle spacing satisfy the first preset relationship, determine the vehicle perception information of the control section corresponding to the second vehicle spacing as the vehicle perception information of the control section corresponding to the vehicle perception information of the section.

[0028] Optionally, in another possible implementation manner of the first aspect, the above-mentioned second preset area of the control section includes a plurality of sequentially arranged preset sub-areas of the control section; the perception devices in each preset sub-area of the control section include at least one long-focus camera and at least one short-focus camera; correspondingly, there is at least one shooting connection area between every two adjacent preset sub-areas of the control section;

[0029] Correspondingly, the above-mentioned obtaining of vehicle connection information for the controlled section includes:

[0030] When it is detected that a vehicle arrives at a preset sub-region of the controlled section, the vehicle perception information of the controlled section within the preset sub-region of the controlled section is obtained through the perception devices within the preset sub-region of the controlled section; among them, the vehicle perception information of the controlled section within the preset sub-region of the controlled section includes the vehicle perception information of the upstream controlled section of the upstream preset sub-region of the controlled section and the vehicle perception information of the downstream controlled section of the downstream preset sub-region of the controlled section; the upstream preset sub-region of the controlled section is the upstream region among two adjacent preset sub-regions of the controlled section, and the downstream preset sub-region of the controlled section is the downstream region among two adjacent preset sub-regions of the controlled section;

[0031] For each vehicle, determine the vehicle perception information of the downstream controlled section that is spatio-temporally matched with the vehicle perception information of the upstream controlled section and bind them to obtain the vehicle connection information of the controlled section.

[0032] Optionally, in another possible implementation manner of the first aspect, the above-mentioned updating of the vehicle feature information of the vehicle fusion information of the controlled section by using the vehicle connection information of the controlled section corresponding to each vehicle to obtain the updated vehicle fusion information of the controlled section corresponding to each vehicle, and determining the target vehicle feature information carried by the updated vehicle fusion information of the controlled section includes:

[0033] For each vehicle connection information of the controlled section, determine the vehicle fusion information of the controlled section that is spatio-temporally matched with the vehicle connection information of the controlled section, and determine the corresponding vehicle feature information;

[0034] According to the vehicle feature information carried by the vehicle connection information of the controlled section, update the vehicle feature information of the vehicle fusion information of the controlled section to obtain the updated vehicle fusion information of the controlled section, and determine the target vehicle feature information carried by the updated vehicle fusion information of the controlled section.

[0035] Optionally, in yet another possible implementation manner of the first aspect, the above-mentioned vehicle connection information of the controlled section includes the first vehicle ID, the third sensing moment, the third vehicle speed information, and the third vehicle spacing; the vehicle fusion information of the controlled section includes the second vehicle ID, the fourth sensing moment, the fourth vehicle speed information, and the fourth vehicle spacing;

[0036] Correspondingly, the above-mentioned for each vehicle connection information of the controlled section, determining the vehicle fusion information of the controlled section that is spatio-temporally matched with the vehicle connection information of the controlled section, and determining the corresponding vehicle feature information includes:

[0037] For the vehicle connection information of each controlled section, when it is detected that the first vehicle ID matches the second vehicle ID, determine the second difference between the third vehicle spacing and the fourth vehicle spacing;

[0038] When it is detected that the second difference is less than or equal to a preset threshold and the second preset relationship is satisfied between the third vehicle spacing and the fourth vehicle spacing, determine the vehicle fusion information of the controlled section corresponding to the fourth vehicle spacing as the vehicle fusion information of the controlled section that matches the vehicle connection information of the controlled section;

[0039] According to the vehicle fusion information of the controlled section that matches the vehicle connection information of the controlled section, determine the vehicle feature information corresponding to the vehicle connection information of the controlled section.

[0040] The second aspect of the embodiments of the present application provides a video-based vehicle tracking device, which is applied to a server, and the server is communicatively connected to multiple sensing devices; the sensing devices are arranged in the controlled section, and the sensing devices include lidar and cameras; the cameras include long-focus cameras and short-focus cameras; there is an intersecting sensing connection area between the radar detection area of the lidar and the shooting area of the cameras; there is an intersecting shooting connection area between the first shooting area of the long-focus camera and the second shooting area of the short-focus camera;

[0041] The video-based vehicle tracking device includes:

[0042] An information acquisition module, configured to obtain the cross-section vehicle fusion information corresponding to each vehicle in the first preset area of the controlled section and the vehicle perception information of the controlled section corresponding to each vehicle in the second preset area of the controlled section through the sensing devices; wherein, the cross-section vehicle fusion information includes vehicle feature information;

[0043] An information fusion module, configured to perform feature matching on the cross-section vehicle fusion information and the vehicle perception information of the controlled section corresponding to each vehicle based on the vehicle feature information to obtain the vehicle fusion information of the controlled section corresponding to each vehicle;

[0044] An information determination module, configured to determine the vehicle fusion information of the controlled section corresponding to the vehicle perception information of the controlled section for each vehicle perception information of the controlled section;

[0045] An information update module, configured to update the vehicle feature information of the vehicle fusion information of the controlled section by using the vehicle connection information of the controlled section corresponding to each vehicle to obtain the updated vehicle fusion information of the controlled section corresponding to each vehicle, and determine the target vehicle feature information carried by the updated vehicle fusion information of the controlled section;

[0046] A vehicle tracking module, configured to perform trajectory tracking on the vehicle according to the vehicle perception information of the controlled section and the target vehicle feature information.

[0047] The third aspect of the embodiments of the present application provides a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, it implements the video-based vehicle tracking method in the first aspect above.

[0048] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program, where when the computer program is executed by a processor, it implements the video-based vehicle tracking method in the first aspect above.

[0049] The fifth aspect of the embodiments of the present application provides a computer program product, which when running on a server, causes the server to execute the video-based vehicle tracking method in the first aspect above.

[0050] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: The embodiments of the present application provide a video-based vehicle tracking method, device, and server. By using multiple sensing devices set in the control section to obtain the cross-section vehicle fusion information and the control-section vehicle sensing information corresponding to each vehicle in the first preset area and the second preset area of the control section respectively, and for each vehicle, fusing and updating the cross-section vehicle fusion information and the control-section vehicle sensing information to determine the target vehicle feature information carried in the updated control-section vehicle fusion information, and combining the control-section vehicle sensing information and the target vehicle feature information to update the identity feature information of the vehicles sensed at different positions in real time; that is, effectively connecting the sensing information of the vehicle at different positions in the control section, completing the tracking of the vehicles on the control section, accurately determining the identity feature information of each vehicle on the control section, and realizing the efficient monitoring of each vehicle on the control section. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 is a flowchart of a video-based vehicle tracking method provided by an embodiment of the present application;

[0053] Figure 2 is a structural diagram of a video-based vehicle tracking device provided by an embodiment of the present application;

[0054] Figure 3 is a structural diagram of a server provided by an embodiment of the present application. Detailed Implementation Manner

[0055] In the following description, specific details such as specific system architectures, technologies, etc. are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0056] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0057] It should also be understood that the term "and / or" used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] As used in the specification and appended claims of the present application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0059] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0060] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0061] It should be understood that the magnitudes of the sequence numbers of the steps in this embodiment do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0062] In the related art, in urban planning, there are usually some control sections with complex terrains (such as tunnels). Control sections usually have characteristics such as relatively narrow internal roadbed width, strong space tightness, small field of vision, low visibility, and usually one-way roads, making the driving environment complex. Abnormal vehicle driving behaviors such as slow vehicle speed, vehicle speeding, and vehicle stagnation may lead to serious traffic accidents, with relatively large potential safety hazards. The vehicle monitoring efficiency of the related control section traffic management method is low, and the monitoring accuracy is not high.

[0063] In view of this, the embodiments of the present application provide a video-based vehicle tracking method, device, and server. By multiple sensing devices set in the control section, the cross-section vehicle fusion information and the control section vehicle sensing information corresponding to the first preset area and the second preset area of the control section of each vehicle are obtained. For each vehicle, the cross-section vehicle fusion information and the control section vehicle sensing information are fused and updated to determine the target vehicle feature information carried by the updated control section vehicle fusion information. Combining the control section vehicle sensing information and the target vehicle feature information, the identity feature information of the vehicles sensed at different positions is updated in real time; that is, the sensing information of the vehicle at different positions in the control section is effectively connected to complete the tracking of the vehicles on the control section, accurately determine the identity feature information of each vehicle on the control section, and achieve efficient monitoring of each vehicle on the control section.

[0064] In order to illustrate the technical solutions of the present application, specific embodiments will be used to illustrate below.

[0065] A video-based vehicle tracking method provided by an embodiment of the present application is applied to a server, and the server is communicatively connected to multiple sensing devices; the sensing devices are set in the control section, and the sensing devices include lidar and cameras; the cameras include long-focus cameras and short-focus cameras; there is an intersecting sensing connection area between the radar detection area of the lidar and the shooting area of the cameras; there is an intersecting shooting connection area between the first shooting area of the long-focus camera and the second shooting area of the short-focus camera.

[0066] Among them, the control section can be a complex section with characteristics such as relatively narrow internal roadbed width, strong space tightness, small field of vision, low visibility, and usually one-way roads, such as a tunnel.

[0067] Refer to Figure 1 , which shows a schematic flow chart of a video-based vehicle tracking method provided by an embodiment of the present application. As Figure 1As shown in the figure, the video-based vehicle tracking method may include the following steps:

[0068] Step 101: Obtain the cross-section vehicle fusion information corresponding to each vehicle in the first preset area of the controlled section and the vehicle perception information of the controlled section corresponding to the second preset area of the controlled section through a sensing device.

[0069] In the embodiment of the present application, the cross-section vehicle fusion information includes, but is not limited to, the unique identification ID of the vehicle, vehicle type, size, vehicle perception map, license plate number, vehicle capture picture, etc. The vehicle perception information of the controlled section can be obtained by using a visual sensing device and includes, but is not limited to, the ID of the vehicle, vehicle type, position, perception time, size, speed information, heading angle information, perception time consumption, vehicle head-to-tail distance, vehicle left distance, vehicle right distance, front vehicle head distance, front vehicle tail distance, vehicle perception picture, etc.

[0070] In a possible implementation manner, the cross-section vehicle fusion information and the vehicle perception information of the controlled section can be obtained through the following steps: For each vehicle, when it is detected that the vehicle arrives at the first preset area of the controlled section, obtain the cross-section vehicle perception information of the vehicle through the sensing device in the first preset area; when it is determined that the vehicle arrives at the preset trigger area according to the cross-section vehicle perception information, obtain the vehicle feature information of the vehicle through the sensing device in the second preset area; bind the vehicle feature information and the cross-section vehicle perception information to obtain the cross-section vehicle fusion information of the vehicle; when it is detected that the vehicle arrives at the second preset area of the controlled section, obtain the vehicle perception information of the controlled section of the vehicle through the sensing device in the second preset area; where the second preset area is located after the first preset area.

[0071] It should be noted that the cross-section vehicle perception information can be obtained by using a variety of sensing devices to sense the vehicles in the first preset area in real time. The cross-section vehicle perception information includes, but is not limited to, the ID of the vehicle, vehicle type, position, perception time, size, speed information, heading angle information, perception time consumption, vehicle head-to-tail distance, vehicle left distance, vehicle right distance, front vehicle head distance, front vehicle tail distance, vehicle perception picture, etc.

[0072] In addition, the cross-section vehicle fusion information includes vehicle feature information. Before obtaining the vehicle feature information of the vehicle, it is first necessary to determine the dynamic prediction trigger capture information. Among them, due to a certain time delay in the sensing algorithm, the current output position is no longer the actual position of the vehicle. It is necessary to predict the current position of the vehicle according to the algorithm time delay. In extreme cases of vehicle lane change, the output position is not in the same lane as the actual position. In extreme cases of speeding vehicles, the output position is far from the actual position; therefore, by combining the distances between adjacent vehicles in the left and right and front and back, an effective trigger box can be formed, with higher fault tolerance to a certain extent and higher accuracy in locking the vehicle.

[0073] Specifically, based on the position, speed information, heading angle information, and perception time of the cross-section vehicle perception information, the position information of the current vehicle can be predicted. Then, based on the predicted position information, when the predicted position is within the preset optimal trigger area (and the preset trigger area), according to the length and width information, vehicle head-to-tail distance, vehicle left distance, and vehicle right distance in the size information of the cross-section vehicle perception information, trigger box information of the size of the preset rule threshold is formed. And based on the predicted position information, the lane where the vehicle is located is determined, and finally, the dynamic prediction trigger capture information is determined. Among them, the dynamic prediction trigger capture information includes but is not limited to the vehicle ID, vehicle type, trigger box information, lane number, trigger time, etc.

[0074] Furthermore, the vehicle feature information can specifically be vehicle identity information, including but not limited to the license plate number of the vehicle, vehicle capture pictures, and dynamic prediction trigger capture information. Specifically, according to the lane number in the trigger capture information, the corresponding license plate recognition device can be selected, and then license plate recognition for a specified vehicle type in a specified area is performed according to the trigger box information and vehicle type, so as to obtain the vehicle feature information. Thus, the license plate recognition area range is reduced through the trigger box, improving the recognition efficiency; and the vehicle recognition accuracy is improved through the vehicle type.

[0075] In the embodiment of the present application, after obtaining the vehicle feature information, the cross-section vehicle perception information can be uniquely locked according to the vehicle ID in the dynamic prediction trigger capture information in the vehicle feature information, completing the binding of the vehicle feature information and the cross-section vehicle perception information, and obtaining the cross-section vehicle fusion information.

[0076] Step 102: Perform feature matching on the cross-section vehicle fusion information and the control section vehicle perception information corresponding to each vehicle based on the vehicle feature information to obtain the control section vehicle fusion information corresponding to each vehicle.

[0077] In the embodiment of the present application, the control section vehicle fusion information includes but is not limited to the vehicle ID, vehicle type, size, vehicle perception map, license plate number, vehicle capture pictures, etc.

[0078] In a possible implementation manner, the control section vehicle perception information that is spatio-temporally matched with each cross-section vehicle perception information can be determined respectively, and the mutually matched cross-section vehicle perception information and control section vehicle perception information can be fused respectively to obtain the cross-section vehicle connection information corresponding to each vehicle; then for each cross-section vehicle connection information, the cross-section vehicle fusion information that is feature-matched with the cross-section vehicle connection information is determined based on the vehicle feature information, and the cross-section vehicle connection information and the matched cross-section vehicle fusion information are fused to obtain the control section vehicle fusion information of the vehicle.

[0079] It should be noted that the cross-section vehicle connection information includes, but is not limited to, the ID of the cross-section sensing vehicle and the ID of the current sensing vehicle.

[0080] As an example, the cross-section vehicle connection information can be obtained through the following steps: for each vehicle, when it is detected that the vehicle arrives at the preset sensing connection area, the vehicle sensing information of the control section corresponding to the cross-section vehicle sensing information is obtained through the sensing device; wherein, the preset sensing connection area is the sensing intersection area of the sensing devices in the first preset area and the second preset area; the sensing intersection area includes at least one of the sensing connection area and the shooting connection area; perform spatio-temporal matching on the cross-section vehicle sensing information and the vehicle sensing information of the control section corresponding to the cross-section vehicle sensing information, and fuse the mutually matching cross-section vehicle sensing information and the vehicle sensing information of the control section to determine the cross-section vehicle connection information corresponding to the vehicle.

[0081] Specifically, according to the position of the cross-section vehicle sensing information, when the vehicle enters the preset sensing connection area, spatio-temporal matching is performed according to the position, sensing time, and speed information of the vehicle sensing information of the control section, so as to match the cross-section vehicle sensing information with the vehicle sensing information of the control section and obtain the cross-section vehicle connection information.

[0082] Furthermore, the cross-section vehicle sensing information includes the first sensing time (i.e., the time when the vehicle is sensed), the first vehicle speed information, and the first vehicle distance; the vehicle sensing information of the control section includes the second sensing time, the second vehicle speed information, and the second vehicle distance. The matching of the cross-section vehicle sensing information and the vehicle sensing information of the control section can be completed only when certain conditions are met. That is, as a possible implementation manner of the embodiment of the present application, for each vehicle, when it is detected that the vehicle arrives at the preset sensing connection area, the vehicle sensing information of the control section corresponding to the cross-section vehicle sensing information is obtained through the sensing device, including: for each vehicle, when it is detected that the vehicle arrives at the preset sensing connection area, the vehicle sensing information of the control section is obtained through the sensing device; when it is detected that the first sensing time and the second sensing time match, and the first vehicle speed information and the second vehicle speed information match, determine the first difference between the first vehicle distance and the second vehicle distance; when it is detected that the first difference is less than or equal to the preset threshold, and the first vehicle distance and the second vehicle distance satisfy the first preset relationship, determine the vehicle sensing information of the control section corresponding to the second vehicle distance as the vehicle sensing information of the control section corresponding to the cross-section vehicle sensing information.

[0083] Specifically, the conditions required for the matching of the above cross-section vehicle sensing information and the vehicle sensing information of the control section can be realized through the following formula:

[0084]

[0085] where x入 x is the distance from the vehicle obtained from the cross-section vehicle perception information to the left boundary line of the leftmost lane perpendicular to the driving direction 管 L is the distance from the vehicle obtained from the vehicle perception information of the control section to the left boundary line of the leftmost lane perpendicular to the driving direction x y is the maximum allowable threshold of the matching error for the distance of the vehicle perpendicular to the driving direction 入 T is the distance from the vehicle obtained from the cross-section vehicle perception information to the cross-section of the control section along the driving direction 入 T is the vehicle time obtained from the cross-section vehicle perception information 管 y is the vehicle time obtained from the vehicle perception information of the control section 、 入 At T 管 y is the distance from the vehicle to the cross-section of the control section along the driving direction calculated according to the perception information at the moment 管 D is the distance from the vehicle obtained from the vehicle perception information of the control section to the cross-section of the control section along the driving direction 前 D is the headway distance between the front of the current vehicle and the front of the vehicle in the same lane ahead obtained from the cross-section vehicle perception information 后 D is the headway distance between the front of the current vehicle and the front of the vehicle in the same lane behind obtained from the cross-section vehicle perception information

[0086] It should be noted that the selection of the lateral distance threshold takes into account the interference in the case of vehicle parallel driving, and the selection of the longitudinal distance threshold takes into account the interference in the case of following vehicles before and after. The purpose of combining the two is to improve the connection accuracy

[0087] Furthermore, after obtaining the cross-section vehicle connection information, the ID of the vehicle can be perceived according to the cross-section of the vehicle connection information, and the cross-section vehicle fusion information can be traversed to obtain the identity information of the vehicle, so as to form the vehicle fusion information of the control section

[0088] Step 103: For each piece of vehicle perception information of the control section, determine the corresponding vehicle fusion information of the control section

[0089] In the embodiment of the present application, each piece of vehicle perception information of the control section initially corresponds to a piece of vehicle fusion information of the control section, and the subsequent steps need to update the vehicle fusion information of the control section

[0090] Step 104: Use the vehicle connection information of the control section corresponding to each vehicle to update the vehicle feature information of the vehicle fusion information of the control section, obtain the updated vehicle fusion information of the control section corresponding to each vehicle respectively, and determine the target vehicle feature information carried by the updated vehicle fusion information of the control section

[0091] In the embodiments of the present application, the target vehicle feature information includes, but is not limited to, the ID of the vehicle, the vehicle model, the location, the sensing time, the size, the speed information, the heading angle information, the sensing time consumption, the vehicle sensing picture, the license plate number, the vehicle capture picture, etc.

[0092] In a possible implementation manner, the second preset area of the controlled section includes a plurality of sequentially arranged preset sub-areas of the controlled section; the sensing devices in each preset sub-area of the controlled section include at least one long-focus camera and at least one short-focus camera; correspondingly, there is at least one shooting connection area between every two adjacent preset sub-areas of the controlled section. Before performing step 104, it is necessary to first obtain the vehicle connection information of the controlled section, and the specific steps are as follows: when it is detected that a vehicle arrives at a preset sub-area of the controlled section, obtain the vehicle sensing information of the controlled section in the preset sub-area of the controlled section through the sensing devices in the preset sub-area of the controlled section; wherein, the vehicle sensing information of the controlled section in the preset sub-area of the controlled section includes the vehicle sensing information of the upstream controlled section in the upstream preset sub-area of the controlled section and the vehicle sensing information of the downstream controlled section in the downstream preset sub-area of the controlled section; the upstream preset sub-area of the controlled section is the upstream area among two adjacent preset sub-areas of the controlled section, and the downstream preset sub-area of the controlled section is the downstream area among two adjacent preset sub-areas of the controlled section; for each vehicle, determine the vehicle sensing information of the downstream controlled section that is spatio-temporally matched with the vehicle sensing information of the upstream controlled section and bind them to obtain the vehicle connection information of the controlled section.

[0093] Specifically, according to the position of the vehicle sensing information of the upstream controlled section (that is, the vehicle sensing information of the upstream controlled section of the preset sub-area of the controlled section), when the vehicle enters the preset sub-area of the controlled section, perform spatio-temporal matching according to the position, sensing time, and speed information of the vehicle sensing information of the downstream controlled section (that is, the vehicle sensing information of the downstream controlled section of the preset sub-area of the controlled section), so as to complete the matching of the vehicle sensing information of the upstream controlled section and the vehicle sensing information of the downstream controlled section, and form the vehicle connection information of the controlled section. Among them, the vehicle connection information of the controlled section includes, but is not limited to, the ID of the upstream sensing vehicle and the ID of the current sensing vehicle.

[0094] In a possible implementation manner, after obtaining the vehicle connection information of the controlled section, the above step 104 may include: for each vehicle connection information of the controlled section, determine the vehicle fusion information of the controlled section that is spatio-temporally matched with the vehicle connection information of the controlled section, and determine the corresponding vehicle feature information; according to the vehicle feature information carried by the vehicle connection information of the controlled section, update the vehicle feature information of the vehicle fusion information of the controlled section to obtain the updated vehicle fusion information of the controlled section, and determine the target vehicle feature information carried by the updated vehicle fusion information of the controlled section.

[0095] Further, the matching of the controlled road section vehicle connection information and the controlled road section vehicle fusion information can be completed only when certain conditions are met. Therefore, the controlled road section vehicle connection information includes the first vehicle ID, the third sensing moment, the third vehicle speed information and the third vehicle distance; the controlled road section vehicle fusion information includes the second vehicle ID, the fourth sensing moment, the fourth vehicle speed information and the fourth vehicle distance. As a possible implementation method of the present application embodiment, for each controlled road section vehicle connection information, the controlled road section vehicle fusion information that matches the controlled road section vehicle connection information in time and space is determined, and the corresponding vehicle characteristic information is determined, including: for each controlled road section vehicle connection information, when the first vehicle ID is detected to match the second vehicle ID, the second difference between the third vehicle distance and the fourth vehicle distance is determined; when the second difference is detected to be less than or equal to the preset threshold, and the third vehicle distance and the fourth vehicle distance meet the second preset relationship, the controlled road section vehicle fusion information corresponding to the fourth vehicle distance is determined as the controlled road section vehicle fusion information that matches the controlled road section vehicle connection information; according to the controlled road section vehicle fusion information that matches the controlled road section vehicle connection information, the vehicle characteristic information corresponding to the controlled road section vehicle connection information is determined.

[0096] Specifically, the conditions that need to be met for matching the above-mentioned controlled road section vehicle connection information with the controlled road section vehicle fusion information can be achieved through the following formula:

[0097]

[0098] Among them, x 上 is the distance from the vehicle to the left boundary line of the leftmost lane along the direction perpendicular to the driving direction obtained through the vehicle perception information of the upstream controlled section, x 下 L is the distance from the vehicle to the left boundary line of the leftmost lane perpendicular to the driving direction obtained through the vehicle perception information of the downstream controlled road section, x The maximum threshold allowed for the distance matching error between the vehicle and the driving direction, y 上 is the distance from the vehicle along the driving direction to the cross section of the controlled section obtained through the vehicle perception information of the upstream controlled section, T 上 is the vehicle time obtained through the vehicle perception information of the upstream controlled section, T 下 is the vehicle time obtained through the vehicle perception information of the downstream controlled section, y 、 上 For T 下 The distance from the vehicle along the driving direction to the controlled section calculated based on the perception information at any time, y 下 is the distance from the vehicle along the driving direction to the cross section of the controlled section obtained through the vehicle perception information of the downstream controlled section, D 前D is the headway between the current vehicle's head and the vehicle ahead in the same lane obtained from the vehicle perception information of the upstream control section. 后 is the headway between the current vehicle's head and the vehicle behind in the same lane obtained from the vehicle perception information of the upstream control section.

[0099] It should be noted that the selection of the lateral distance threshold takes into account the interference in the case of vehicle parallel driving, and the selection of the longitudinal distance threshold takes into account the interference in the case of following vehicles. The purpose of combining the two is to improve the connection accuracy.

[0100] In the embodiment of the present application, according to the vehicle ID in the vehicle perception information of the control section, the updated vehicle fusion information of the control section is traversed to obtain the target vehicle feature information carried by the updated vehicle fusion information of the control section.

[0101] Step 105, perform trajectory tracking on the vehicle according to the vehicle perception information of the control section and the target vehicle feature information.

[0102] In the embodiment of the present application, after obtaining the target vehicle feature information, the vehicle perception information of the control section can be combined to generate vehicle trajectory information carrying the identity, so as to realize the trajectory tracking of the vehicle.

[0103] The video-based vehicle tracking method disclosed in the above embodiments of the present application obtains the cross-section vehicle fusion information and the vehicle perception information of the control section corresponding to the first preset area and the second preset area of the control section of each vehicle through a plurality of sensing devices set in the control section, and for each vehicle, the cross-section vehicle fusion information and the vehicle perception information of the control section are fused and updated to determine the target vehicle feature information carried by the updated vehicle fusion information of the control section, and combine the vehicle perception information of the control section and the target vehicle feature information to update the identity feature information of the vehicles sensed at different positions in real time; that is, effectively connect the perception information of the vehicles at different positions in the control section, complete the tracking of the vehicles on the control section, accurately determine the identity feature information of each vehicle on the control section, and realize the efficient monitoring of each vehicle on the control section.

[0104] See Figure 2 , which shows a schematic structural diagram of a video-based vehicle tracking device provided by an embodiment of the present application. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown.

[0105] The video-based vehicle tracking device is applied to a server, and the server is communicatively connected to multiple sensing devices; the sensing devices are arranged on a controlled section, and the sensing devices include lidar and cameras; the cameras include a long-focus camera and a short-focus camera; there is an intersecting sensing connection area between the radar detection area of the lidar and the shooting area of the cameras; there is an intersecting shooting connection area between the first shooting area of the long-focus camera and the second shooting area of the short-focus camera.

[0106] The video-based vehicle tracking device may specifically include the following modules:

[0107] An information acquisition module 201, configured to obtain, through the sensing devices, the cross-section vehicle fusion information corresponding to each vehicle in the first preset area of the controlled section and the controlled-section vehicle sensing information corresponding to each vehicle in the second preset area of the controlled section; wherein, the cross-section vehicle fusion information includes vehicle feature information.

[0108] An information fusion module 202, configured to perform feature matching on the cross-section vehicle fusion information and the controlled-section vehicle sensing information corresponding to each vehicle based on the vehicle feature information to obtain the controlled-section vehicle fusion information corresponding to each vehicle.

[0109] An information determination module 203, configured to determine, for each controlled-section vehicle sensing information, the controlled-section vehicle fusion information corresponding to the controlled-section vehicle sensing information.

[0110] An information update module 204, configured to update the vehicle feature information of the controlled-section vehicle fusion information by using the controlled-section vehicle connection information corresponding to each vehicle to obtain the updated controlled-section vehicle fusion information corresponding to each vehicle, and determine the target vehicle feature information carried by the updated controlled-section vehicle fusion information.

[0111] A vehicle tracking module 205, configured to perform trajectory tracking on the vehicle according to the controlled-section vehicle sensing information and the target vehicle feature information.

[0112] The vehicle tracking device based on video disclosed in the above embodiments of the present application obtains the cross-section vehicle fusion information and the vehicle perception information of the control section corresponding to each vehicle in the first preset area and the second preset area of the control section through a plurality of sensing devices arranged in the control section. For each vehicle, the cross-section vehicle fusion information and the vehicle perception information of the control section are fused and updated to determine the target vehicle feature information carried by the updated vehicle fusion information of the control section. Combining the vehicle perception information of the control section and the target vehicle feature information, the identity feature information of the vehicles sensed at different positions is updated in real time; that is, the perception information of the vehicle at different positions in the control section is effectively connected to complete the tracking of the vehicles on the control section, accurately determine the identity feature information of each vehicle on the control section, and realize the efficient monitoring of each vehicle on the control section.

[0113] Further, in a possible implementation manner of the embodiment of the present application, the above information acquisition module 201 may specifically include the following sub-modules:

[0114] The first acquisition sub-module is used to, for each vehicle, when it is detected that the vehicle arrives at the first preset area of the control section, obtain the cross-section vehicle perception information of the vehicle through the sensing devices in the first preset area.

[0115] The second acquisition sub-module is used to, when it is determined according to the cross-section vehicle perception information that the vehicle arrives at the preset trigger area, obtain the vehicle feature information of the vehicle through the sensing devices in the second preset area.

[0116] The first processing sub-module is used to bind the vehicle feature information and the cross-section vehicle perception information to obtain the cross-section vehicle fusion information of the vehicle.

[0117] The third acquisition sub-module is used to, when it is detected that the vehicle arrives at the second preset area of the control section, obtain the vehicle perception information of the control section of the vehicle through the sensing devices in the second preset area; wherein, the second preset area is located after the first preset area.

[0118] Further, in another possible implementation manner of the embodiment of the present application, the above information fusion module 202 may specifically include the following sub-modules:

[0119] The second processing sub-module is used to respectively determine the vehicle perception information of the control section that is spatio-temporally matched with each cross-section vehicle perception information, and respectively fuse the mutually matched cross-section vehicle perception information and the vehicle perception information of the control section to obtain the cross-section vehicle connection information corresponding to each vehicle.

[0120] A third processing sub-module, configured to, for each cross-section vehicle connection information, determine cross-section vehicle fusion information that matches the characteristics of the cross-section vehicle connection information based on the vehicle characteristic information, and fuse the cross-section vehicle connection information and the matched cross-section vehicle fusion information to obtain the vehicle fusion information of the vehicle's controlled section.

[0121] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned second processing sub-module may specifically include the following units:

[0122] An acquisition unit, configured to, for each vehicle, when it is detected that the vehicle arrives at a preset sensing connection area, obtain the controlled-section vehicle sensing information corresponding to the cross-section vehicle sensing information through a sensing device; wherein, the preset sensing connection area is the sensing intersection area of the sensing devices in the first preset area and the second preset area; the sensing intersection area includes at least one of a sensing connection area and a shooting connection area.

[0123] A first processing unit, configured to perform spatio-temporal matching on the cross-section vehicle sensing information and the controlled-section vehicle sensing information corresponding to the cross-section vehicle sensing information, fuse the mutually matching cross-section vehicle sensing information and the controlled-section vehicle sensing information, and determine the cross-section vehicle connection information corresponding to the vehicle.

[0124] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned cross-section vehicle sensing information includes a first sensing moment, a first vehicle speed information, and a first vehicle distance; the controlled-section vehicle sensing information includes a second sensing moment, a second vehicle speed information, and a second vehicle distance; correspondingly, the above-mentioned acquisition unit is specifically configured to, for each vehicle, when it is detected that the vehicle arrives at a preset sensing connection area, obtain the controlled-section vehicle sensing information through a sensing device; when it is detected that the first sensing moment and the second sensing moment match, and the first vehicle speed information and the second vehicle speed information match, determine a first difference between the first vehicle distance and the second vehicle distance; when it is detected that the first difference is less than or equal to a preset threshold, and the first vehicle distance and the second vehicle distance satisfy a first preset relationship, determine the controlled-section vehicle sensing information corresponding to the second vehicle distance as the controlled-section vehicle sensing information corresponding to the cross-section vehicle sensing information.

[0125] Further, in another possible implementation manner of the embodiment of the present application, the above-mentioned second preset area of the controlled section includes a plurality of sequentially arranged controlled-section preset sub-areas; each controlled-section preset sub-area includes at least one long-focus camera and at least one short-focus camera; correspondingly, there is at least one shooting connection area between every two adjacent controlled-section preset sub-areas; correspondingly, the above-mentioned video-based vehicle tracking device may specifically include the following modules:

[0126] The first processing module is configured to, when detecting that a vehicle arrives at a preset sub-region of a controlled section, obtain the vehicle sensing information of the controlled section within the preset sub-region of the controlled section through the sensing devices within the preset sub-region of the controlled section; wherein, the vehicle sensing information of the controlled section within the preset sub-region of the controlled section includes the vehicle sensing information of the upstream controlled section of the upstream preset sub-region of the controlled section and the vehicle sensing information of the downstream controlled section of the downstream preset sub-region of the controlled section; the upstream preset sub-region of the controlled section is the upstream region of two adjacent preset sub-regions of the controlled section, and the downstream preset sub-region of the controlled section is the downstream region of two adjacent preset sub-regions of the controlled section.

[0127] The second processing module is configured to, for each vehicle, determine the vehicle sensing information of the downstream controlled section that is spatio-temporally matched with the vehicle sensing information of the upstream controlled section and bind them to obtain the vehicle connection information of the controlled section.

[0128] Further, in another possible implementation manner of the embodiment of the present application, the above information update module 204 may specifically include the following sub-modules:

[0129] The fourth processing sub-module is configured to, for each vehicle connection information of the controlled section, determine the vehicle fusion information of the controlled section that is spatio-temporally matched with the vehicle connection information of the controlled section and determine the corresponding vehicle feature information.

[0130] The fifth processing sub-module is configured to update the vehicle feature information of the vehicle fusion information of the controlled section according to the vehicle feature information carried by the vehicle connection information of the controlled section to obtain the updated vehicle fusion information of the controlled section, and determine the target vehicle feature information carried by the updated vehicle fusion information of the controlled section.

[0131] Further, in another possible implementation manner of the embodiment of the present application, the above vehicle connection information of the controlled section includes the first vehicle ID, the third sensing moment, the third vehicle speed information, and the third vehicle spacing; the vehicle fusion information of the controlled section includes the second vehicle ID, the fourth sensing moment, the fourth vehicle speed information, and the fourth vehicle spacing. The above fourth processing sub-module may specifically include the following units:

[0132] The second processing unit is configured to, for each vehicle connection information of the controlled section, when detecting that the first vehicle ID matches the second vehicle ID, determine the second difference between the third vehicle spacing and the fourth vehicle spacing.

[0133] The third processing unit is configured to, when detecting that the second difference is less than or equal to a preset threshold and the third vehicle spacing and the fourth vehicle spacing satisfy a second preset relationship, determine the vehicle fusion information of the controlled section corresponding to the fourth vehicle spacing as the vehicle fusion information of the controlled section that is matched with the vehicle connection information of the controlled section.

[0134] A fourth processing unit is configured to determine vehicle feature information corresponding to the vehicle connection information of the controlled section according to the vehicle fusion information of the controlled section that matches the vehicle connection information of the controlled section.

[0135] The vehicle tracking device based on video provided by the embodiments of the present application can be applied to the foregoing method embodiments. For details, refer to the description of the foregoing method embodiments and will not be elaborated herein.

[0136] Figure 3 is a schematic structural diagram of a server provided by an embodiment of the present application. As Figure 3 shown, the server 300 of this embodiment includes: at least one processor 310 ( Figure 3 only one processor is shown), a memory 320, and a computer program 321 stored in the memory 320 and executable on the at least one processor 310. When the processor 310 executes the computer program 321, the steps in the foregoing method embodiment of the vehicle tracking method based on video are implemented.

[0137] The server 300 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The server may include, but is not limited to, a processor 310 and a memory 320. Those skilled in the art can understand that Figure 3 merely examples of the server 300, which do not constitute a limitation to the server 300, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0138] The so-called processor 310 may be a central processing unit (CPU), and the processor 310 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0139] In some embodiments, the memory 320 may be an internal storage unit of the server 300, such as the hard disk or memory of the server 300. In some other embodiments, the memory 320 may also be an external storage device of the server 300, such as a plug-in hard disk equipped on the server 300, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 320 may also include both the internal storage unit of the server 300 and external storage devices. The memory 320 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as the program code of the computer program, etc. The memory 320 may also be used to temporarily store data that has been output or will be output.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0141] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0143] In the embodiments provided in the present application, it should be understood that the disclosed device / server and method can be implemented in other ways. For example, the device / server embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0144] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0146] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of the present application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0147] The implementation of all or part of the processes in the method of the above embodiments in this application can also be completed by a computer program product. When the computer program product runs on a server, it enables the server to execute the steps in the above-mentioned method embodiments.

[0148] The above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A video-based vehicle tracking method, characterized in that, Applied to a server, the server is communicatively connected to a plurality of sensing devices; the sensing devices are arranged in a controlled section, and the sensing devices include lidar and cameras; the cameras include long-focus cameras and short-focus cameras; there is an intersecting sensing connection area between the radar detection area of the lidar and the shooting area of the cameras; There is an intersecting shooting connection area between the first shooting area of the long-focus camera and the second shooting area of the short-focus camera; The vehicle tracking method based on video includes: Obtaining, by the sensing devices, the cross-section vehicle fusion information corresponding to each vehicle in the first preset area of the controlled section and the controlled-section vehicle sensing information corresponding to each vehicle in the second preset area of the controlled section; wherein, the cross-section vehicle fusion information includes vehicle feature information; Performing feature matching on the cross-section vehicle fusion information and the controlled-section vehicle sensing information corresponding to each vehicle based on the vehicle feature information to obtain the controlled-section vehicle fusion information corresponding to each vehicle; For each of the controlled-section vehicle sensing information, determining the controlled-section vehicle fusion information corresponding to the controlled-section vehicle sensing information; Updating the vehicle feature information of the controlled-section vehicle fusion information by using the controlled-section vehicle connection information corresponding to each vehicle to obtain the updated controlled-section vehicle fusion information corresponding to each vehicle, and determining the target vehicle feature information carried by the updated controlled-section vehicle fusion information; Performing trajectory tracking on the vehicle according to the controlled-section vehicle sensing information and the target vehicle feature information.

2. The video-based vehicle tracking method according to claim 1, characterized in that, The obtaining, by the sensing devices, the cross-section vehicle fusion information corresponding to each vehicle in the first preset area of the controlled section and the controlled-section vehicle sensing information corresponding to each vehicle in the second preset area of the controlled section includes: For each vehicle, when it is detected that the vehicle arrives at the first preset area of the controlled section, obtaining the cross-section vehicle sensing information of the vehicle by the sensing devices in the first preset area; When it is determined according to the cross-section vehicle sensing information that the vehicle arrives at the preset trigger area, obtaining the vehicle feature information of the vehicle by the sensing devices in the second preset area; Binding the vehicle feature information and the cross-section vehicle sensing information to obtain the cross-section vehicle fusion information of the vehicle; When it is detected that the vehicle arrives at the second preset area of the controlled section, obtaining the controlled-section vehicle sensing information of the vehicle by the sensing devices in the second preset area; wherein, the second preset area is located after the first preset area.

3. The video-based vehicle tracking method according to claim 2, characterized in that, The performing feature matching on the cross-section vehicle fusion information and the controlled-section vehicle sensing information corresponding to each vehicle based on the vehicle feature information to obtain the controlled-section vehicle fusion information corresponding to each vehicle includes: Respectively determining the controlled-section vehicle sensing information that is spatio-temporally matched with each cross-section vehicle sensing information, and respectively fusing the mutually matched cross-section vehicle sensing information and the controlled-section vehicle sensing information to obtain the cross-section vehicle connection information corresponding to each vehicle; For each of the cross-section vehicle connection information, based on the vehicle feature information, determine the cross-section vehicle fusion information that matches the characteristics of the cross-section vehicle connection information, and fuse the cross-section vehicle connection information and the matching cross-section vehicle fusion information to obtain the vehicle fusion information for the controlled section of the vehicle.

4. The video-based vehicle tracking method according to claim 3, wherein The method of separately determining the vehicle perception information for the controlled section that is spatiotemporally matched with each of the cross-section vehicle perception information, and separately fusing the mutually matched cross-section vehicle perception information and the vehicle perception information for the controlled section to obtain the cross-section vehicle connection information corresponding to each vehicle includes: For each vehicle, when it is detected that the vehicle arrives at the preset perception connection area, obtain the vehicle perception information for the controlled section corresponding to the cross-section vehicle perception information through the perception device; wherein, the preset perception connection area is the perception intersection area of the perception devices in the first preset area and the perception devices in the second preset area; the perception intersection area includes at least one of the perception connection area and the shooting connection area; Perform spatiotemporal matching on the cross-section vehicle perception information and the vehicle perception information for the controlled section corresponding to the cross-section vehicle perception information, and fuse the mutually matched cross-section vehicle perception information and the vehicle perception information for the controlled section to determine the cross-section vehicle connection information corresponding to the vehicle.

5. The video-based vehicle tracking method according to claim 4, wherein The cross-section vehicle perception information includes a first sensing moment, a first vehicle speed information, and a first vehicle spacing; the vehicle perception information for the controlled section includes a second sensing moment, a second vehicle speed information, and a second vehicle spacing; Correspondingly, the step of, for each vehicle, when it is detected that the vehicle arrives at the preset perception connection area, obtaining the vehicle perception information for the controlled section corresponding to the cross-section vehicle perception information through the perception device includes: For each vehicle, when it is detected that the vehicle arrives at the preset perception connection area, obtain the vehicle perception information for the controlled section through the perception device; When it is detected that the first sensing moment and the second sensing moment match, and the first vehicle speed information and the second vehicle speed information match, determine a first difference between the first vehicle spacing and the second vehicle spacing; When it is detected that the first difference is less than or equal to a preset threshold, and the first vehicle spacing and the second vehicle spacing satisfy a first preset relationship, determine the vehicle perception information for the controlled section corresponding to the second vehicle spacing as the vehicle perception information for the controlled section corresponding to the cross-section vehicle perception information.

6. The video-based vehicle tracking method according to claim 1, wherein, The second preset area of the controlled section includes a plurality of sequentially arranged preset sub-areas of the controlled section; each preset sub-area of the controlled section includes at least one long-focus camera and at least one short-focus camera; correspondingly, there is at least one shooting connection area between every two adjacent preset sub-areas of the controlled section; Correspondingly, the step of obtaining the vehicle connection information for the controlled section includes: When it is detected that the vehicle arrives at a preset sub-region of the controlled section, the vehicle perception information of the controlled section within the preset sub-region of the controlled section is obtained through the perception devices within the preset sub-region of the controlled section; wherein, the vehicle perception information of the controlled section within the preset sub-region of the controlled section includes the vehicle perception information of the upstream controlled section of the upstream preset sub-region of the controlled section, and the vehicle perception information of the downstream controlled section of the downstream preset sub-region of the controlled section; the upstream preset sub-region of the controlled section is the upstream region among the two adjacent preset sub-regions of the controlled section, and the downstream preset sub-region of the controlled section is the downstream region among the two adjacent preset sub-regions of the controlled section; For each vehicle, determine and bind the vehicle perception information of the downstream controlled section that is spatio-temporally matched with the vehicle perception information of the upstream controlled section to obtain the vehicle connection information of the controlled section.

7. The video-based vehicle tracking method according to claim 1, wherein Updating the vehicle feature information of the vehicle fusion information of the controlled section by using the vehicle connection information of the controlled section corresponding to each vehicle to obtain the updated vehicle fusion information of the controlled section corresponding to each vehicle respectively, and determining the target vehicle feature information carried by the updated vehicle fusion information of the controlled section includes: For each vehicle connection information of the controlled section, determine the vehicle fusion information of the controlled section that is spatio-temporally matched with the vehicle connection information of the controlled section, and determine the corresponding vehicle feature information; According to the vehicle feature information carried by the vehicle connection information of the controlled section, update the vehicle feature information of the vehicle fusion information of the controlled section to obtain the updated vehicle fusion information of the controlled section, and determine the target vehicle feature information carried by the updated vehicle fusion information of the controlled section.

8. The video-based vehicle tracking method according to claim 7, wherein The vehicle connection information of the controlled section includes the first vehicle ID, the third sensing moment, the third vehicle speed information, and the third vehicle spacing; the vehicle fusion information of the controlled section includes the second vehicle ID, the fourth sensing moment, the fourth vehicle speed information, and the fourth vehicle spacing; Correspondingly, for each vehicle connection information of the controlled section, determining the vehicle fusion information of the controlled section that is spatio-temporally matched with the vehicle connection information of the controlled section, and determining the corresponding vehicle feature information includes: For each vehicle connection information of the controlled section, when it is detected that the first vehicle ID matches the second vehicle ID, determine the second difference between the third vehicle spacing and the fourth vehicle spacing; When it is detected that the second difference is less than or equal to a preset threshold and the third vehicle spacing and the fourth vehicle spacing satisfy a second preset relationship, determine the vehicle fusion information of the controlled section corresponding to the fourth vehicle spacing as the vehicle fusion information of the controlled section that is matched with the vehicle connection information of the controlled section; According to the vehicle fusion information of the controlled section that is matched with the vehicle connection information of the controlled section, determine the vehicle feature information corresponding to the vehicle connection information of the controlled section.

9. A video-based vehicle tracking device, characterized in that, Applied to a server, the server is communicatively connected to a plurality of sensing devices; the sensing devices are arranged in a controlled section, and the sensing devices include lidars and cameras; the cameras include long-focus cameras and short-focus cameras; there is an intersecting sensing connection area between the radar detection area of the lidar and the shooting area of the camera; There is an intersecting shooting connection area between the first shooting area of the long-focus camera and the second shooting area of the short-focus camera; The video-based vehicle tracking device includes: An information acquisition module, configured to obtain cross-section vehicle fusion information corresponding to each vehicle in a first preset area of the controlled section and vehicle perception information of the controlled section corresponding to each vehicle in a second preset area of the controlled section through the sensing devices; wherein, the cross-section vehicle fusion information includes vehicle feature information; An information fusion module, configured to perform feature matching on the cross-section vehicle fusion information and the vehicle perception information of the controlled section corresponding to each vehicle based on the vehicle feature information to obtain the vehicle fusion information of the controlled section corresponding to each vehicle; An information determination module, configured to determine, for each vehicle perception information of the controlled section, the vehicle fusion information of the controlled section corresponding to the vehicle perception information of the controlled section; An information update module, configured to update the vehicle feature information of the vehicle fusion information of the controlled section by using the vehicle connection information of the controlled section corresponding to each vehicle to obtain the updated vehicle fusion information of the controlled section corresponding to each vehicle, and determine the target vehicle feature information carried by the updated vehicle fusion information of the controlled section; A vehicle tracking module, configured to perform trajectory tracking on the vehicle according to the vehicle perception information of the controlled section and the target vehicle feature information.

10. A server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1 to 8 is implemented.

Images