Regional reverse vehicle searching method and device based on vehicle driving track

Abstract

The invention provides a regional reverse vehicle searching method and device based on a vehicle driving track, and the method comprises the steps: dividing a parking lot into N sub-regions according to an AI camera disposed on a vehicle driving channel, and dividing the sub-regions into M virtual regions according to a space division building; when any vehicle enters any subarea in the parking lot, the license plate of the vehicle is identified through the AI camera, and the area driving track of the vehicle in the subarea is tracked and recorded; and summarizing the area driving tracks of each license plate in all the sub-areas to obtain a vehicle driving track, judging whether the vehicle driving track is reasonable according to the area adjacent relation and the time access information of each sub-area, if so, determining a virtual area where the vehicle is parked according to the area driving track of the sub-area where the license plate appears at the latest, and if not, determining that the vehicle is parked. And obtaining the final parking position of the vehicle. The method can effectively reduce the hardware cost, improves the vehicle searching efficiency, and is suitable for reverse vehicle searching in indoor and outdoor parking environments.

Description

Technical Field

[0001] The present invention relates to the technical field of parking, and in particular to a method and device for regional reverse vehicle search based on vehicle driving tracks. Background Art

[0002] The conventional method of realizing reverse vehicle search service is to install a license plate recognition camera above each parking space to capture the parking image of the vehicle in real time or periodically, and then determine the vehicle license plate number through image recognition technology, and determine the vehicle position in combination with the parking lot positioning system to provide users with reverse vehicle search service.

[0003] However, the large-scale deployment of license plate recognition cameras has significantly increased hardware costs and the difficulty of installation and maintenance; secondly, the recognition rate of license plate recognition cameras deployed in parking spaces is easily affected by ambient light and other factors; finally, existing equipment is not suitable for outdoor installation, and it is currently inconvenient to find a car in an outdoor parking lot. Summary of the invention

[0004] In order to solve the above problems in the prior art, the present invention provides a method and device for regional reverse vehicle search based on vehicle driving trajectory, which effectively reduces hardware costs, improves vehicle search efficiency, and is suitable for reverse vehicle search in indoor and outdoor parking environments.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] In a first aspect, the present invention provides a method for regional reverse vehicle search based on vehicle driving trajectory, comprising the steps of:

[0007] The parking lot is divided into N sub-areas according to the AI ​​cameras deployed on the vehicle passage, and the sub-areas are divided into M virtual areas according to the spatial segmentation buildings, where N and M are both positive integers greater than 1;

[0008] When any vehicle enters any sub-area in the parking lot, the AI ​​camera recognizes the vehicle's license plate and tracks and records its driving trajectory in the sub-area;

[0009] The regional driving trajectories of each license plate in all sub-areas are summarized to obtain the vehicle driving trajectory. Whether the vehicle driving trajectory is reasonable is determined based on the regional adjacency relationship and the time entry and exit information of each sub-area. If reasonable, the virtual area where the vehicle is parked is determined based on the regional driving trajectory of the sub-area where the license plate appears latest, and the final parking position of the vehicle is obtained.

[0010] The beneficial effects of the present invention are: AI cameras are deployed in the vehicle passage, and sub-areas are divided according to the coverage of the AI ​​cameras, and then the sub-areas are divided into M virtual areas according to the spatial segmentation buildings. The AI ​​cameras are used to recognize and track the license plates of vehicles entering different sub-areas in the parking lot, so as to obtain the driving trajectory of the vehicle in the entire parking lot, and finally determine the final parking position of the vehicle according to the rationality of the vehicle's driving trajectory. Therefore, only a small number of cameras need to be deployed to accurately lock the vehicle position. Therefore, the present invention can effectively reduce the hardware cost, improve the efficiency of searching for vehicles, and is also suitable for reverse searching for vehicles in indoor and outdoor parking environments.

[0011] Optionally, the method further comprises the steps of:

[0012] If it is unreasonable, the license plate photos captured by the AI ​​cameras in the unreasonable multiple sub-areas will be sent to the cloud for secondary recognition, and the driving trajectories of the areas with the same license plates recognized for the second time will be attributed to the same license plate, and the driving trajectories of the areas with different license plates recognized for the second time will be attributed to different license plates. The virtual area where the vehicle is parked is determined according to the regional driving trajectory of the sub-area where each license plate appears latest, and the final parking position of the corresponding vehicle is obtained.

[0013] According to the above description, when the vehicle driving trajectory is unreasonable, the secondary license plate recognition in the cloud is used to determine the trajectory attribution in different sub-areas, thereby improving the accuracy of the vehicle parking position.

[0014] Optionally, judging whether the vehicle driving trajectory is reasonable according to the area adjacent relationship and the time entry and exit information of each sub-area includes:

[0015] According to the area adjacent relationship and the time entry and exit information of each sub-area, it is determined whether the areas sorted according to the time entry and exit information in the vehicle driving trajectory are all in an adjacent relationship.

[0016] Optionally, judging whether the vehicle driving trajectory is reasonable according to the area adjacent relationship and the time entry and exit information of each sub-area includes:

[0017] Determine whether the last driving information in the vehicle driving trajectory corresponding to the license plate is out of the first sub-area. If so, determine the second sub-area where the vehicle is finally parked based on the direction in which the vehicle exits the first sub-area. Otherwise, determine whether the vehicle driving trajectory is reasonable based on the area adjacent relationship and the time entry and exit information of each sub-area.

[0018] Optionally, after determining the second sub-area where the vehicle is finally parked according to the direction in which the vehicle exits the first sub-area, the method further comprises the following steps:

[0019] When a vehicle disappears in the second sub-area and within a time interval in which pedestrians are identified walking out of the second sub-area in other sub-areas adjacent to the second sub-area, there is only one vehicle that disappears in the second sub-area and there is only one group of pedestrians that get off the vehicle and walk out of the second sub-area, the most likely virtual area for the vehicle in the second sub-area is determined based on the driving direction and driving speed of the vehicle when leaving the first sub-area and the walking direction and walking speed of the pedestrians when entering other sub-areas.

[0020] Optionally, judging the most likely virtual area of ​​the vehicle in the second sub-area according to the driving direction and driving speed of the vehicle leaving the first sub-area and the walking direction and walking speed of the pedestrian entering other sub-areas includes:

[0021] Determine whether there is a historical parking record according to the license plate, if so, obtain the historical parking duration according to the historical parking record, otherwise obtain the average parking duration of the second sub-area;

[0022] Acquire the time length of the time interval, and determine the most likely virtual area of ​​the vehicle in the second sub-area according to the time length, the average parking time, the driving direction, the driving speed, the walking direction and the walking speed;

[0023] The driving direction is used to plan the route for the vehicle to reach each virtual area, and the walking direction is used to plan the route for the pedestrian to walk out of the second sub-area from each virtual area.

[0024] According to the above description, when a local AI camera fails, the information provided by the adjacent AI cameras can be used to more accurately estimate the virtual area where the vehicle is located in the second sub-area.

[0025] Optionally, the method further comprises the steps of:

[0026] When the vehicle disappears in the second sub-area for the first time, the latest parking situation in the second sub-area is acquired to obtain the vacant parking space situation, which is used for subsequent parking judgment.

[0027] Optionally, the most likely virtual area for the vehicle in the second sub-area is one virtual area or multiple virtual areas.

[0028] Optionally, the method further comprises the steps of:

[0029] When a vehicle search request is received from a vehicle owner, the final parking location of the vehicle bound to the vehicle owner is sent to the vehicle owner.

[0030] In a second aspect, the present invention provides a regional reverse vehicle search device based on a vehicle driving trajectory, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a regional reverse vehicle search method based on a vehicle driving trajectory of the first aspect is implemented.

[0031] Among them, the technical effect corresponding to the regional reverse vehicle search device based on the vehicle driving trajectory provided by the second aspect refers to the relevant description of the regional reverse vehicle search method based on the vehicle driving trajectory provided by the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the main process of a method for regional reverse vehicle search based on vehicle driving trajectory according to an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of a parking lot according to an embodiment of the present invention;

[0034] Figure 3 The present invention is a schematic diagram of a framework of a device for regional reverse vehicle search based on vehicle driving trajectory according to an embodiment of the present invention.

[0035] Description of reference numerals:

[0036] 1. A regional reverse vehicle search device based on vehicle driving trajectory;

[0037] 2. Processor;

[0038] 3. Memory. DETAILED DESCRIPTION

[0039] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0040] Embodiment 1

[0041] This embodiment is suitable for application scenarios where parking is required. In particular, it is used in intelligent parking management systems in public places such as large shopping malls, airports, and office buildings. The existing reverse car search costs are too high and are not suitable for outdoor parking lots. This embodiment determines the final parking position of the vehicle through the deployment of AI cameras, regional division, and license plate recognition and tracking. It is not only suitable for outdoor parking lots, but also reduces costs. See the following description for details.

[0042] Please refer to Figure 1 to Figure 2, a method for regional reverse vehicle search based on vehicle driving trajectory, comprising the steps of:

[0043] S1. Divide the parking lot into N sub-areas according to the AI ​​cameras deployed on the vehicle lanes, and divide the sub-areas into M virtual areas according to the spatial segmentation buildings.

[0044] Wherein, N and M are both positive integers greater than 1, and the virtual areas of different sub-areas are not the same.

[0045] Figure 2 Schematic diagram for explaining this embodiment. Figure 2 As shown, AI cameras include A, B, C, and D, corresponding to four lanes. The radiation range of AI camera A is the upper two rows of parking spaces, the radiation range of AI camera B is the middle two rows of parking spaces, the radiation range of AI camera C is the lower two rows of parking spaces, and the radiation range of AI camera D is the rightmost row of parking spaces, so N is 4. Among them, the space-dividing building is a support column. For AI camera A, there are nine parking spaces in the first row of parking spaces, which are divided into three-three-three arrangements by the support column. Therefore, there are three virtual areas in the first row and three virtual areas in the second row. The lanes can be divided into three virtual areas, or they can be partially divided into the upper and lower rows of parking spaces or completely belong to one of the rows of parking spaces. In this embodiment, it is the former. Therefore, in this embodiment, the number of virtual areas corresponding to sub-area a is M. A is 9. Similarly, M B is 9, M C is 9, M D is 10.

[0046] It should be noted that the road area corresponding to the leftmost traffic lane belongs to the adjacent virtual area. For example, the part just out of the entrance belongs to the leftmost virtual area of ​​the first row of parking spaces.

[0047] Among them, since it is only necessary to install the AI ​​camera at the corresponding position of the vehicle passage, the position and camera angle can be adjusted according to the light, and monitoring can be carried out in outdoor parking lots, thereby providing an applicable scenario for this embodiment.

[0048] S2. When any vehicle enters any sub-area in the parking lot, the AI ​​camera recognizes the vehicle's license plate and tracks and records its driving trajectory in the sub-area.

[0049] like Figure 2As shown in the figure, when a vehicle enters from the entrance and enters sub-area a, AI camera A will recognize the vehicle's license plate and then record its driving trajectory in sub-area a. At this time, AI camera A has recorded the virtual area and time information passed by the vehicle. When the vehicle disappears from the virtual area of ​​sub-area a and enters sub-area b, AI camera B will recognize the vehicle's license plate and track and record it.

[0050] S3. Summarize the regional driving trajectories of each license plate in all sub-areas to obtain the vehicle driving trajectory, and judge whether the vehicle driving trajectory is reasonable according to the regional adjacent relationship and the time entry and exit information of each sub-area. If reasonable, determine the virtual area where the vehicle is parked according to the regional driving trajectory of the sub-area where the license plate appears latest, and obtain the final parking position of the vehicle.

[0051] Therefore, each vehicle entering each sub-area has a corresponding license plate recognition, and vehicles with the same license plate are considered to be the same vehicle. The driving trajectories of these areas are summarized according to the same license plate to form the vehicle driving trajectory of the vehicle corresponding to this license plate in the parking lot.

[0052] Among them, judging whether the vehicle driving trajectory is reasonable based on the region adjacent relationship and the time entry and exit information of each sub-region includes:

[0053] According to the area adjacency relationship and the time entry and exit information of each sub-area, it is determined whether the areas sorted according to the time entry and exit information in the vehicle driving trajectory are all in an adjacent relationship.

[0054] It should be noted that the areas in the area adjacency relationship are virtual areas.

[0055] Specifically, the time entry and exit information between adjacent virtual areas must be adjacent. The entry and exit can be determined by the driving direction of the vehicle, so as to determine the time sequence of the two, and thus judge whether the vehicle driving trajectory is reasonable. For example, when the sub-area a is numbered a1, a2...a9 from the first row to the third row, each row from left to right, the corresponding sub-area b is b1, b2...b9, the corresponding sub-area c is c1, c2...c9, and the corresponding sub-area d is d1, d2...d10. At this time, when driving from top to bottom on the leftmost vehicle lane of the entrance to the camera B, turning left and turning right to the exit, it passes through virtual area a1, virtual area a4, virtual area a7, virtual area b1, virtual area b4, virtual area b5, virtual area b6, etc. in sequence. At this time, if it disappears in virtual area a7 and then appears in virtual area b1, the order of the areas sorted by time entry and exit information in the vehicle driving trajectory is reasonable.

[0056] S4. If it is unreasonable, the license plate photos captured by the AI ​​cameras in the unreasonable multiple sub-areas are sent to the cloud for secondary recognition, and the driving trajectories of the areas with the same license plates recognized for the second time are attributed to the same license plate, and the driving trajectories of the areas with different license plates recognized for the second time are attributed to different license plates. The virtual area where the vehicle is parked is determined according to the regional driving trajectory of the sub-area where each license plate appears latest, and the final parking position of the corresponding vehicle is obtained.

[0057] Among them, if the areas in the vehicle's driving trajectory that are sorted by time entry and exit information are not adjacent, for example, the vehicle disappears in virtual area a7 and then appears in virtual area c1, and virtual area a7 of sub-area A and virtual area c1 of sub-area C are not adjacent. At this time, the cloud performs a secondary recognition of the license plate. If the license plates recognized twice are still the same, it is considered to be the same vehicle. If the license plates recognized twice are inconsistent, the corresponding regional driving trajectories are attributed to different license plates, and the final parking positions are confirmed respectively, thereby improving the accuracy of the vehicle parking position.

[0058] S5. When receiving a vehicle search request from the vehicle owner, the final parking location of the vehicle bound to the vehicle owner is sent to the vehicle owner.

[0059] In this embodiment, when the car owner needs to find the car, the final parking location of the vehicle bound to the car owner is sent to the car owner. Since the scope of the virtual area is small and will not be affected by the space-dividing buildings, the car owner only needs to reach the virtual area to quickly and accurately find his vehicle.

[0060] Therefore, the present invention can effectively reduce hardware costs, improve vehicle search efficiency, and is suitable for reverse vehicle search in indoor and outdoor parking environments.

[0061] Embodiment 2

[0062] Please refer to Figure 1 to Figure 2 , a regional reverse vehicle search method based on vehicle driving trajectory, based on the above embodiment 1, this embodiment has further limited the situation where a local AI camera fails.

[0063] In this embodiment, judging whether the vehicle driving trajectory is reasonable based on the region neighbor relationship and the time entry and exit information of each sub-region includes:

[0064] Determine whether the last driving information in the vehicle driving trajectory corresponding to the license plate is out of the first sub-area. If so, determine the second sub-area where the vehicle is finally parked based on the direction in which the vehicle exits the first sub-area. Otherwise, determine whether the vehicle driving trajectory is reasonable based on the area adjacent relationship and the time entry and exit information of each sub-area.

[0065] In this embodiment, if the last driving information in the driving track of the vehicle corresponding to the license plate is out of the first sub-area, the second sub-area it entered can be confirmed first. Since there is no driving track in the second sub-area, it is considered that the vehicle disappeared in the second sub-area. At this time, the AI ​​camera corresponding to the second sub-area may be faulty. At this time, after determining the second sub-area where the vehicle finally parked according to the direction the vehicle drove out of the first sub-area, the following steps are also included:

[0066] When a vehicle disappears in the second sub-area and within the time interval in which other sub-areas adjacent to the second sub-area identify pedestrians walking out of the second sub-area, there is only one vehicle that disappears in the second sub-area and there is only one group of pedestrians who get off the vehicle and walk out of the second sub-area, the most likely virtual area in which the vehicle is located in the second sub-area is determined based on the driving direction and driving speed of the vehicle when leaving the first sub-area and the walking direction and walking speed of the pedestrians when entering other sub-areas.

[0067] In this embodiment, it is only for the case where there is only one vehicle disappearing in the second sub-area and there is only one group of pedestrians getting off and walking out of the second sub-area. The former is to monitor whether there are multiple vehicles entering the second sub-area in the time interval. When multiple vehicles enter the second sub-area in overlapping time, the information of pedestrians cannot be distinguished more accurately at this time, so the virtual area prediction in this case is not considered. The latter judgment on pedestrians excludes pedestrians passing through the second sub-area from other sub-areas. Therefore, it should be understood that the adjacent sub-areas will know the situation of pedestrians entering the second sub-area, and then compare them with the pedestrians leaving the second sub-area to obtain the pedestrians who get off and walk out of the second sub-area. At this time, according to the driving direction and driving speed of the vehicle leaving the first sub-area and the walking direction and walking speed of the pedestrians entering other sub-areas, the most likely virtual area for the vehicle in the second sub-area includes:

[0068] S31, judging whether there is a historical parking record according to the license plate, if so,

[0069] Among them, the entire process from the vehicle entering the second sub-area to the owner walking out of the second sub-area includes the vehicle's driving process to the parking space, the vehicle parking process and the owner's walking process. The vehicle parking process is estimated based on historical parking records or the average parking time. The vehicle's driving process to the parking space is estimated based on the vehicle's driving direction and driving speed when it leaves the first sub-area. During the owner's walking process, the walking direction and walking speed of pedestrians entering other sub-areas are estimated.

[0070] S32, obtaining the time length of the time interval, and determining the most likely virtual area in which the vehicle is in the second sub-area according to the time length, average parking time, driving direction, driving speed, walking direction and walking speed;

[0071] The driving direction is used to plan the route for vehicles to reach each virtual area, and the walking direction is used to plan the route for pedestrians to walk out of the second sub-area from each virtual area.

[0072] Thus, the time length of the entire process is known, and the distance can be obtained according to the route. Thus, the distance of the vehicle in the process of driving to the parking space can be solved by the two equations of time and distance, so as to determine the most likely virtual area of ​​the vehicle in the second sub-area. Figure 2 For example, when the vehicle disappears in virtual area a7 and enters sub-area b, there is no information about the vehicle entering sub-area b in the vehicle's driving trajectory, that is, the last driving information is exiting sub-area a and entering sub-area b. After time T, AI camera D recognizes that a pedestrian has entered virtual area d5. If time T is long, it is predicted according to the formula that the pedestrian is in virtual areas b1 and b7. If time T is short, it is predicted that the pedestrian is in virtual areas b3 and b9. Therefore, the most likely virtual area for the vehicle in the second sub-area in this embodiment is one virtual area or multiple virtual areas.

[0073] In this embodiment, the steps are also included:

[0074] When the vehicle disappears in the second sub-area for the first time, the most recent parking situation in the second sub-area is obtained to obtain the vacant parking space situation, which is used for subsequent parking judgment.

[0075] That is, if the AI ​​camera just fails, a more accurate judgment can be made based on the availability of parking spaces.

[0076] In this embodiment, the virtual area where the parking lot is predicted is not only for finding the car, but also involves the recommendation of parking navigation routes. In real life scenarios, the parking area is larger and the routes are more complicated. By accurately predicting the parking area even when the AI ​​camera fails, the parking experience of the car owner can be effectively improved.

[0077] Embodiment 3

[0078] Please refer to Figure 3 A regional reverse vehicle search device 1 based on vehicle driving trajectory includes a memory 3, a processor 2, and a computer program stored in the memory 3 and executable on the processor 2. When the processor 2 executes the computer program, the steps in the above-mentioned embodiment 1 or 2 are implemented.

[0079] Since the system / device described in the above embodiments of the present invention is a system / device used to implement the method of the above embodiments of the present invention, a person skilled in the art can understand the specific structure and deformation of the system / device based on the method described in the above embodiments of the present invention, and thus will not be described in detail here. All systems / devices used in the method of the above embodiments of the present invention belong to the scope of protection of the present invention.

[0080] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0082] It should be noted that in the claims, any reference numerals placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by the same hardware. The use of the words first, second, third, etc., is for convenience of expression only and does not indicate any order. These words may be understood as part of the component name.

[0083] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0084] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0085] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A method for regional reverse vehicle search based on vehicle driving trajectory, characterized in that: Includes steps: The parking lot is divided into N sub-areas according to the AI ​​cameras deployed on the vehicle passage, and the sub-areas are divided into M virtual areas according to the spatial segmentation buildings, where N and M are both positive integers greater than 1; When any vehicle enters any sub-area in the parking lot, the AI ​​camera recognizes the vehicle's license plate and tracks and records its driving trajectory in the sub-area; The regional driving trajectories of each license plate in all sub-areas are summarized to obtain the vehicle driving trajectory. Whether the vehicle driving trajectory is reasonable is determined based on the regional adjacency relationship and the time entry and exit information of each sub-area. If reasonable, the virtual area where the vehicle is parked is determined based on the regional driving trajectory of the sub-area where the license plate appears latest, and the final parking position of the vehicle is obtained.

2. A method for regional reverse vehicle search based on vehicle driving trajectory according to claim 1, characterized in that: Also includes the steps: If it is unreasonable, the license plate photos captured by the AI ​​cameras in the unreasonable multiple sub-areas will be sent to the cloud for secondary recognition, and the driving trajectories of the areas with the same license plates recognized for the second time will be attributed to the same license plate, and the driving trajectories of the areas with different license plates recognized for the second time will be attributed to different license plates. The virtual area where the vehicle is parked is determined according to the regional driving trajectory of the sub-area where each license plate appears latest, and the final parking position of the corresponding vehicle is obtained.

3. The method for regional reverse vehicle search based on vehicle driving trajectory according to claim 1, characterized in that: The determining whether the vehicle driving trajectory is reasonable based on the area adjacent relationship and the time entry and exit information of each sub-area includes: According to the area adjacent relationship and the time entry and exit information of each sub-area, it is determined whether the areas sorted according to the time entry and exit information in the vehicle driving trajectory are all in an adjacent relationship.

4. The method for regional reverse vehicle search based on vehicle driving trajectory according to claim 1, characterized in that: The determining whether the vehicle driving trajectory is reasonable based on the area adjacent relationship and the time entry and exit information of each sub-area includes: Determine whether the last driving information in the vehicle driving trajectory corresponding to the license plate is out of the first sub-area. If so, determine the second sub-area where the vehicle is finally parked based on the direction in which the vehicle exits the first sub-area. Otherwise, determine whether the vehicle driving trajectory is reasonable based on the area adjacent relationship and the time entry and exit information of each sub-area.

5. The method for regional reverse vehicle search based on vehicle driving trajectory according to claim 4 is characterized in that: After determining the second sub-area where the vehicle is finally parked according to the direction in which the vehicle leaves the first sub-area, the following steps are further included: When a vehicle disappears in the second sub-area and within a time interval in which pedestrians are identified walking out of the second sub-area in other sub-areas adjacent to the second sub-area, there is only one vehicle that disappears in the second sub-area and there is only one group of pedestrians that get off the vehicle and walk out of the second sub-area, the most likely virtual area for the vehicle in the second sub-area is determined based on the driving direction and driving speed of the vehicle when leaving the first sub-area and the walking direction and walking speed of the pedestrians when entering other sub-areas.

6. A method for regional reverse vehicle search based on vehicle driving trajectory according to claim 5, characterized in that: The determining of the most likely virtual area for the vehicle to be in the second sub-area according to the driving direction and driving speed of the vehicle leaving the first sub-area and the walking direction and walking speed of the pedestrian entering other sub-areas comprises: Determine whether there is a historical parking record according to the license plate, if so, obtain the historical parking duration according to the historical parking record, otherwise obtain the average parking duration of the second sub-area; Acquire the time length of the time interval, and determine the most likely virtual area of ​​the vehicle in the second sub-area according to the time length, the average parking time, the driving direction, the driving speed, the walking direction and the walking speed; The driving direction is used to plan the route for the vehicle to reach each virtual area, and the walking direction is used to plan the route for the pedestrian to walk out of the second sub-area from each virtual area.

7. The method for regional reverse vehicle search based on vehicle driving trajectory according to claim 5, characterized in that: Also includes the steps: When the vehicle disappears in the second sub-area for the first time, the latest parking situation in the second sub-area is acquired to obtain the vacant parking space situation, which is used for subsequent parking judgment.

8. The method for regional reverse vehicle search based on vehicle driving trajectory according to claim 5, characterized in that: The most likely virtual area for the vehicle to be in the second sub-area is one virtual area or multiple virtual areas.

9. The method for regional reverse vehicle search based on vehicle driving trajectory according to claim 3, characterized in that: Also includes the steps: When a vehicle search request is received from a vehicle owner, the final parking location of the vehicle bound to the vehicle owner is sent to the vehicle owner.

10. A device for regional reverse vehicle search based on vehicle driving trajectory, 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 for regional reverse vehicle search based on vehicle driving trajectory described in any one of claims 1 to 9 is implemented.

Images