Method and device for generating traveling track of suspected vehicle

Abstract

The invention relates to the technical field of vehicle big data, and provides a suspected vehicle driving track generation method and device. Obtaining a reference driving track of the common vehicle to generate a track information file; when the common vehicle detects reference license plate information of other vehicles, recording a detection time range of the detected reference license plate information to generate a license plate scanning file; in the license plate scanning files of the common vehicles, suspected license plate information of suspected vehicles is matched with corresponding reference license plate information, so that the common vehicles which detect the suspected vehicles are searched; and obtaining the target driving track of the suspected vehicle according to the searched reference track file and reference license plate file of the common vehicle, thereby solving the problem that the driving track of the suspected vehicle cannot be determined completely due to the fact that the monitoring video cannot form effective coverage of the whole road section.

Description

Technical Field

[0001] The present invention relates to the field of vehicle big data technology, and in particular to a method and device for generating a suspected vehicle driving trajectory. Background Art

[0002] As people's living standards continue to improve, the number of cars has increased significantly. The complexity of vehicle driving trajectories in public transportation scenarios is relatively high, making it much more difficult to track suspected vehicles in public transportation scenarios.

[0003] In actual application scenarios, it is often necessary to restore the driving trajectory of a suspected vehicle based on its license plate number. However, there are still a certain number of road sections where surveillance video cannot effectively cover them, especially in tunnels and other environments; in this way, the suspected vehicle has the opportunity to escape capture by avoiding surveillance, posing a major threat to public safety.

[0004] In view of this, overcoming the defects of the prior art is an urgent problem to be solved in the field of this technology. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and device for generating a suspected vehicle's driving trajectory, the purpose of which is to generate a trajectory information file of an ordinary vehicle, and to generate a license plate scan file when an ordinary vehicle detects other vehicles; to use the suspected license plate information of the suspected vehicle to perform license plate information matching, so as to generate a target driving trajectory of the suspected vehicle based on the reference trajectory file and the reference license plate file obtained by matching, thereby greatly reducing the difficulty of tracking suspected vehicles in public transportation scenarios, and solving the problem that the suspected vehicle's driving trajectory cannot be determined at all due to the inability of surveillance video to effectively cover the entire road section.

[0006] The present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for generating a suspected vehicle driving trajectory, comprising:

[0008] Acquire a reference driving trajectory of an ordinary vehicle to generate a trajectory information file of the ordinary vehicle; wherein the reference driving trajectory includes the driving trajectory of the ordinary vehicle and the corresponding driving time;

[0009] When the ordinary vehicle detects the reference license plate information of other vehicles, the detection time range of detecting the reference license plate information is recorded to generate a license plate scanning file;

[0010] Among the license plate scan files of the common vehicles, the suspected license plate information of the suspected vehicle is matched with the corresponding reference license plate information to find the common vehicle that detected the suspected vehicle; the trajectory information file of the found common vehicle is determined as the reference trajectory file, and the corresponding license plate scan file is determined as the reference license plate file;

[0011] The target driving trajectory of the suspected vehicle is obtained according to the reference trajectory file and the reference license plate file.

[0012] Further, obtaining the target driving trajectory of the suspected vehicle according to the reference trajectory file and the reference license plate file includes:

[0013] When there are multiple ordinary vehicles with overlapping time among the multiple ordinary vehicles found, the reference trajectory file and the corresponding reference license plate file of one of the ordinary vehicles are selected according to the detection time range;

[0014] The target driving trajectory is synthesized according to the reference trajectory files and reference license plate files of the screened multiple ordinary vehicles.

[0015] Furthermore, when there are multiple ordinary vehicles with overlapping time among the multiple ordinary vehicles found, selecting a reference trajectory file and a corresponding reference license plate file of one of the ordinary vehicles according to the detection time range includes:

[0016] Obtain the detection time ranges of the multiple common vehicles found that correspond to the same reference license plate information, and obtain the candidate time range;

[0017] When the time overlap of multiple candidate time ranges is greater than the overlap threshold, retain the reference trajectory file and reference license plate file of one of the ordinary vehicles;

[0018] And / or, when there is an alternative time range within another alternative time range, retain the reference trajectory file and the reference license plate file corresponding to the other alternative time range.

[0019] Furthermore, synthesizing the target driving trajectory according to the reference trajectory files and the reference license plate files of the screened plurality of ordinary vehicles comprises:

[0020] Obtain reference trajectory files and reference license plate files of multiple filtered common vehicles;

[0021] Obtaining the detection time range corresponding to the suspected license plate information from the reference license plate file to obtain a target time range;

[0022] In the reference trajectory file, searching for a driving trajectory whose driving time matches the target time range to obtain a relevant driving trajectory;

[0023] At least one related driving trajectory is combined in chronological order to obtain the target driving trajectory.

[0024] Furthermore, the obtaining of the reference trajectory files and reference license plate files of the plurality of filtered ordinary vehicles includes:

[0025] Initiating a first inquiry request to the user of the screened ordinary vehicle; wherein the first inquiry request is used to request to use the reference driving trajectory corresponding to the user;

[0026] When the user agrees to the first inquiry request, obtaining a reference driving trajectory corresponding to the user;

[0027] Obtain the reference license plate file of the screened ordinary vehicles.

[0028] Furthermore, the track information file also stores the travel speed of the ordinary vehicle and the elapsed time of the ordinary vehicle running at the travel speed;

[0029] The method for generating the suspected vehicle driving trajectory also includes:

[0030] Obtain at least one driving speed of the ordinary vehicle within a specified time range, and the elapsed time corresponding to each driving speed; wherein the specified time range is the detection time range corresponding to the target vehicle; and calculate the predicted distance according to the driving speed and the corresponding elapsed time;

[0031] At the start time when the ordinary vehicle detects the license plate information of the target vehicle, calibrating the actual distance between the ordinary vehicle and the target vehicle;

[0032] When the difference between the predicted distance and the actual distance is less than the error threshold, it is determined that the target vehicle may remain stationary within the detection time range;

[0033] Query the surveillance video to obtain at least one reference vehicle that passes by the target vehicle within the detection time range; initiate a second inquiry request to the user of the reference vehicle; wherein the second inquiry request is used to: request to obtain the driving record of the reference vehicle within the detection time range; obtain the driving record when the user agrees to the second inquiry request, so as to obtain the personnel situation corresponding to the target vehicle based on the driving record.

[0034] Further, the license plate scan file is stored as a local file of the ordinary vehicle;

[0035] Or, storing the license plate scan file in a server, and updating the license plate scan file in the server;

[0036] Or, the license plate scan file is stored as a local file of the ordinary vehicle, and when the storage time of the local file is greater than a clearing time threshold, the local file is uploaded to the server and deleted.

[0037] Further, when the ordinary vehicle detects the reference license plate information of another vehicle, recording the detection time range of the reference license plate information to generate a license plate scan file includes:

[0038] When the ordinary vehicle scans the reference license plate information of other vehicles, the start time when the ordinary vehicle scans the reference license plate information is recorded, until the ordinary vehicle cannot scan the reference license plate information, the end time is recorded, so as to obtain the detection time range according to the start time and the end time;

[0039] At least one detection time range corresponding to the ordinary vehicle is stored in the license plate scanning file.

[0040] In a second aspect, the present invention further provides a device for generating a suspected vehicle driving trajectory, comprising:

[0041] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor to execute the method for generating the driving trajectory of a suspected vehicle as described in the first aspect.

[0042] In a third aspect, the present invention further provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, which are executed by one or more processors to complete the method for generating a suspected vehicle driving trajectory as described in the first aspect.

[0043] In a fourth aspect, a computer program product comprising instructions is provided. When the instructions are executed on a computer or a processor, the computer or the processor executes a method for generating a suspected vehicle driving trajectory as described in the first to third aspects and any one of the aspects.

[0044] In a fifth aspect, the present invention further provides a system for generating a suspected vehicle driving trajectory, including a device for generating a suspected vehicle driving trajectory as in the second aspect, and using the method for generating a suspected vehicle driving trajectory as described in the first aspect to complete the interaction of the device for generating a suspected vehicle driving trajectory of the second aspect.

[0045] Different from the prior art, the present invention has at least the following beneficial effects:

[0046] The present invention records the reference driving trajectory of ordinary vehicles to generate a trajectory information file, and when the ordinary vehicle detects the reference license plate information of other vehicles, it records the detection time range of the corresponding reference license plate information to generate a license plate scan file; when it is necessary to determine the target driving trajectory of the suspected vehicle, the suspected license plate information of the suspected vehicle is used to match the license plate information in the license plate scan file to determine the ordinary vehicle that detected the suspected vehicle; because the reference driving trajectory includes the driving trajectory of the ordinary vehicle and the corresponding driving time, the license plate scan file includes the detection time range, and the target driving trajectory can be directly generated according to the reference trajectory file and the reference license plate file of the corresponding ordinary vehicle through time matching. And for the intelligent systems of most vehicles at present, the computing resources consumed by capturing the license plate information are relatively small, so the present invention greatly reduces the difficulty of tracking suspected vehicles in public transportation scenarios, and solves the problem that the driving trajectory of the suspected vehicle cannot be determined at all due to the inability of the surveillance video to effectively cover the entire road section. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 is a schematic diagram of a method for generating a suspected vehicle driving trajectory according to an embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of a specific example of a trajectory information file provided by an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of a specific example of a common vehicle detecting other vehicles provided by an embodiment of the present invention;

[0051] Figure 4 It is a schematic diagram of a specific example of a license plate scanning file provided by an embodiment of the present invention;

[0052] Figure 5 is a schematic diagram of a specific example of determining a target driving trajectory provided by an embodiment of the present invention;

[0053] Figure 6 is a flow chart of step 20 provided in an embodiment of the present invention;

[0054] Figure 7 is a flow chart of step 40 provided in an embodiment of the present invention;

[0055] Figure 8 is a flowchart of step 201 provided by an embodiment of the present invention;

[0056] Fig. 9 This is a specific example provided by an embodiment of the present invention where the time overlap between two candidate time ranges is less than the overlap threshold;

[0057] Fig.10 It is a schematic diagram of a specific example provided by an embodiment of the present invention in which the time overlap degree of two candidate time ranges is greater than the overlap threshold;

[0058] Fig.11 It is a schematic diagram of a specific example provided by an embodiment of the present invention, in which one candidate time range is within another candidate time range;

[0059] Fig.12 is a flow chart of step 202 provided in an embodiment of the present invention;

[0060] Fig.13 is a schematic diagram of a specific example of a target driving trajectory provided by an embodiment of the present invention;

[0061] Fig.14 is a schematic diagram of another specific example of a target driving trajectory provided by an embodiment of the present invention;

[0062] Fig.15 is a flowchart of step 401 provided by an embodiment of the present invention;

[0063] Fig.16 is a schematic diagram of another method for generating a suspected vehicle driving trajectory according to an embodiment of the present invention;

[0064] Fig.17 This is a schematic diagram of a specific example of a target vehicle in a stationary state provided by an embodiment of the present invention;

[0065] Fig.18 is a schematic diagram of a specific example of a common vehicle passing a target vehicle provided by an embodiment of the present invention;

[0066] Fig.19 It is a schematic diagram of the architecture of a device for generating a suspected vehicle driving trajectory provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0068] Unless the context requires otherwise, throughout the specification and claims, the term "including" is to be interpreted as open inclusion, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples" and the like are intended to indicate that specific features, structures, materials or characteristics associated with the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, the specific features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner, that is, although they may be carried in the embodiments or examples of the above terms due to reasons such as the order and position of appearance, it is not limited to that they can be carried in combination by one embodiment or example.

[0069] In the description of the present invention, it is necessary to understand that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present disclosure.

[0070] In the description of the present invention, the terms "first" and "second" are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more. In addition, for example, the same type of nouns may be described as two independent individuals by adding "A" and "B" at the end. In this case, the corresponding features defined as "A" and "B" are only used to distinguish the same type of individuals for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features.

[0071] When describing some embodiments, the expressions "coupling", "coupling" and "connection" and their derivatives may be used. For example, when describing some embodiments, the term "connection" may be used to indicate that two or more components are in direct physical or electrical contact with each other. For another example, when describing some embodiments, the term "coupling" may be used to indicate that two or more components are in direct physical or electrical contact. However, the terms "connection" or "coupling" may also refer to two or more components that are not in direct contact with each other, but still cooperate or interact with each other, such as "optical path coupling", "wireless connection", etc. The embodiments disclosed herein are not necessarily limited to the contents of the present invention.

[0072] In the description of the present invention, the expression "A and / or B" (where A and B are used to formally represent specific characteristic contents) will be involved, and the corresponding expressions include the following three combinations: only A, only B, and a combination of A and B.

[0073] As used herein, "about," "substantially," or "approximately" includes the stated value and an average value that is within an acceptable range of deviation from the particular value as determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement system).

[0074] Embodiment 1:

[0075] In order to solve the above problems, an embodiment of the present invention provides a method for generating a suspected vehicle driving trajectory, such as Figure 1 Specifically, it includes:

[0076] Step 10: Obtain a reference driving trajectory of an ordinary vehicle to generate a trajectory information file of the ordinary vehicle; wherein the reference driving trajectory includes the driving trajectory of the ordinary vehicle and the corresponding driving time.

[0077] The following is an example of the use scenario of the method for generating a suspected vehicle driving trajectory according to an embodiment of the present invention:

[0078] At present, new energy electric vehicles are becoming more and more popular. New energy electric vehicles are often equipped with intelligent driving systems or automatic driving functions. In order to capture environmental information, cameras are often set up to collect environmental data. In addition, hybrid vehicles often collect environmental images to provide them to the vehicle's intelligent system in order to improve driving convenience. In addition, in order to avoid the situation where there is no evidence in the event of a collision dispute, most ordinary fuel vehicles are equipped with driving recorders, which is equivalent to having their own specific video monitoring system. Therefore, most vehicles have the ability to collect environmental images.

[0079] In this actual application scenario, a suspected vehicle is abandoned by a criminal. When the suspected vehicle is under control, it is necessary to restore the historical operation trajectory of the suspected vehicle to determine the criminal's historical whereabouts and analyze where the criminal picked up and who got on board using the suspected vehicle.

[0080] Since the contents recorded in the license plate scanning files of ordinary vehicles are of the same nature as those that can be recorded by surveillance cameras, all of them are information about the corresponding vehicles in public transportation scenarios, which does not involve the privacy of the whereabouts of the owners of ordinary vehicles, nor does it involve the privacy of the owners of other vehicles; when the license plate number of the suspected vehicle (i.e., the suspected license plate information) is already known, the license plate scanning files are collected from each ordinary vehicle through the vehicle intelligent platform, and the suspected license plate information is searched in the license plate scanning files, thereby obtaining the target driving trajectory of the suspected vehicle, determining the road section that the suspected vehicle was traveling on at a certain moment, and restoring the route trajectory of the suspected vehicle.

[0081] Among them, a specific example of the trajectory information file is Figure 2 As shown, an ordinary vehicle records its own position information at each moment to obtain a trajectory information file.

[0082] Step 20: When the ordinary vehicle detects the reference license plate information of other vehicles, the detection time range of detecting the reference license plate information is recorded to generate a license plate scanning file.

[0083] A specific example of an ordinary vehicle traveling on the road detecting the reference license plate information of other vehicles is as follows: Figure 3 As shown, a specific example of a license plate scanning file is Figure 4 In one embodiment, the detection time range may be: the start time when the ordinary vehicle can scan the other vehicle's license plate information when scanning the other vehicle, until the end time when the other vehicle's license plate information disappears from the environment image acquisition range of the ordinary vehicle.

[0084] Since most vehicles are able to collect environmental images, ordinary vehicles can capture the license plate information of other vehicles around them when they are driving on the road. And for most vehicle manufacturers, in order to prevent collisions with other vehicles, the vehicle intelligent system will use its own camera and radar system to scan and detect other vehicles around it, calculate the distance between other vehicles around it, and generate a model that simulates the position of other vehicles, as well as a model of the entire vehicle itself. On this basis, due to the specific position of the license plate information on the vehicle, the interception and content recognition of the license plate information will not use too many computing resources, that is, the position of the license plate information on the corresponding model of other vehicles can be directly determined, so the embodiment of the present invention captures the license plate information. In fact, it consumes less computing resources of the vehicle intelligent system and is highly practical.

[0085] Step 30: Among the license plate scan files of multiple ordinary vehicles, the suspected license plate information of the suspected vehicle is matched with the corresponding reference license plate information to find the ordinary vehicle that detected the suspected vehicle; the trajectory information file of the found ordinary vehicle is determined as the reference trajectory file, and the corresponding license plate scan file is determined as the reference license plate file.

[0086] Since there are sections of road where the surveillance video cannot effectively cover, in order to completely restore the historical running track of the suspected vehicle, in one embodiment, the start time and end time of the suspected vehicle's location information that cannot be determined (i.e., it disappears in the surveillance video) can be checked from the surveillance video in the public transportation scenario, and the last location information of the suspected vehicle can be determined from the previous frame of the start time in the surveillance video. Then, in the surveillance video, search for ordinary vehicles whose corresponding location information is less than a preset distance from the last location information between the start time and the end time, so as to obtain at least one ordinary vehicle that may detect the suspected vehicle during the time period when the suspected vehicle disappears in the surveillance video; wherein, the preset distance is selected by those skilled in the art according to the specific usage scenario and is not limited here. Among them, the driving direction of the ordinary vehicle whose location information is less than the preset distance from the last location information can be the same as that of the suspected vehicle, or it can be opposite to the suspected vehicle. After obtaining at least one ordinary vehicle that may detect the suspected vehicle, in the license plate scan file of the at least one ordinary vehicle, the suspected license plate information of the suspected vehicle is matched with the reference license plate information of the corresponding ordinary vehicle, and finally the ordinary vehicle whose suspected license plate information is detected is determined, and its trajectory information file is determined as the reference trajectory file, and its license plate scan file is determined as the reference license plate file; wherein, when the determined ordinary vehicle's driving direction is relative to the suspected vehicle, the position information of the trajectory information file of the ordinary vehicle is exchanged to generate a reference trajectory file; for example, when the trajectory information file records that the license plate information of the suspected vehicle can be detected from driving time m, and the license plate information of the suspected vehicle cannot be detected from driving time n, the position information corresponding to driving time m and driving time n are exchanged to obtain the reference trajectory file. In an optional embodiment, when it is determined that the driving direction of an ordinary vehicle is opposite to that of the suspected vehicle, the user of the ordinary vehicle can be asked whether the dash cam data of the ordinary vehicle can be used to analyze the changes in personnel in the suspected vehicle through the dash cam data, such as whether certain people are carried on board at a certain location and certain people get off the vehicle at a certain location.

[0087] like Figure 5 The left side shows a specific example of a reference license plate file, that is, a license plate scan file of an ordinary vehicle from which a suspected vehicle is detected; Figure 5The right side shows a specific example of a reference trajectory file, that is, a trajectory information file of an ordinary vehicle in which a suspected vehicle is detected. In the embodiment of the present invention, the suspected license plate information of the suspected vehicle (i.e., Figure 5 The "license plate information 6" in the detection result is matched with the corresponding reference license plate information to find the ordinary vehicle in which the suspected vehicle is detected; the trajectory information file of the ordinary vehicle found is determined as the reference trajectory file, and the license plate scanning file of the ordinary vehicle found is determined as the reference license plate file.

[0088] Step 40: Obtain the target driving trajectory of the suspected vehicle according to the reference trajectory file and the reference license plate file.

[0089] In one embodiment, if Figure 5 As shown, according to the "start time 6, end time 6" corresponding to the "license plate information 6" in the reference license plate file 1, the reference driving trajectory of the ordinary vehicle corresponding to the detection time range is searched in the reference trajectory file 1. Specifically, when the "start time 6, end time 6" falls within the time range formed by "driving time 2 to driving time 4" in the reference trajectory file 1, the reference driving trajectory "position information 2, position information 3 to position information 4" corresponding to "driving time 2 to driving time 4" is obtained from the reference trajectory file 1, which means that the ordinary vehicle detected the license plate information 6 during the process of driving from position information 2 to position information 4. The reference driving trajectory found is determined as a part of the target driving trajectory, so as to generate the target driving trajectory.

[0090] The present invention records the reference driving trajectory of ordinary vehicles to generate a trajectory information file, and when the ordinary vehicle detects the reference license plate information of other vehicles, it records the detection time range of the corresponding reference license plate information to generate a license plate scan file; when it is necessary to determine the target driving trajectory of the suspected vehicle, the suspected license plate information of the suspected vehicle is used to match the license plate information in the license plate scan file to determine the ordinary vehicle that detected the suspected vehicle; because the reference driving trajectory includes the driving trajectory of the ordinary vehicle and the corresponding driving time, the license plate scan file includes the detection time range, and the target driving trajectory can be directly generated according to the reference trajectory file and the reference license plate file of the corresponding ordinary vehicle through time matching. And for the intelligent systems of most vehicles at present, the computing resources consumed by capturing the license plate information are relatively small, so the present invention greatly reduces the difficulty of tracking suspected vehicles in public transportation scenarios, and solves the problem that the driving trajectory of the suspected vehicle cannot be determined at all due to the inability of the surveillance video to effectively cover the entire road section.

[0091] The following is a specific description of the embodiments of the present invention:

[0092] To illustrate the detection time range, Figure 6 As shown, the step 20 includes:

[0093] Step 101: When the ordinary vehicle scans the reference license plate information of other vehicles, the start time when the ordinary vehicle scans the reference license plate information is recorded, until the ordinary vehicle cannot scan the reference license plate information, the end time is recorded, so as to obtain the detection time range according to the start time and the end time.

[0094] Step 102: Store at least one detection time range corresponding to the ordinary vehicle in the license plate scanning file.

[0095] like Figure 4 As shown, an ordinary vehicle records the license plate information and corresponding detection time range of each other vehicle detected by it in its own license plate scanning file.

[0096] The license plate scan file is stored as a local file of the ordinary vehicle; or, the license plate scan file is stored in a server and the license plate scan file in the server is updated; or, the license plate scan file is stored as a local file of the ordinary vehicle, and when the storage time of the local file is greater than the clearing time threshold, the local file is uploaded to the server and the local file is deleted. The clearing time is selected by a person skilled in the art according to a specific usage scenario; in an optional embodiment, the clearing time may be one week. For each ordinary vehicle, although a large number of license plate information can be detected during driving, since only the start time and the end time need to be recorded and there is no need to record the driving path of other vehicles, the data volume of the license plate scan file is very small.

[0097] After determining the reference license plate file recording the suspected license plate information, since it is very likely that multiple ordinary vehicles are detected on the overlapping road sections, the embodiment of the present invention screens out some ordinary vehicles to reduce the reference trajectory files and reference license plate files to be processed subsequently, thereby reducing the workload of subsequent operation steps; specifically, Figure 7 As shown, the step 40 includes:

[0098] Step 201: When there are multiple ordinary vehicles with overlapping time among the multiple ordinary vehicles found, a reference trajectory file and a corresponding reference license plate file of one of the ordinary vehicles are selected according to the detection time range.

[0099] The multiple ordinary vehicles found refer to ordinary vehicles with suspected license plate information detected, that is, ordinary vehicles with suspected license plate information included in the corresponding license plate scan file.

[0100] Step 202: synthesizing the target driving trajectory according to the reference trajectory files and reference license plate files of the selected plurality of ordinary vehicles.

[0101] The selected multiple ordinary vehicles refer to: one of the ordinary vehicles among the multiple ordinary vehicles that overlap in time.

[0102] In order to illustrate the process of selecting reference trajectory files and reference license plate files, Figure 8 As shown, in step 201, when there are multiple ordinary vehicles with overlapping time among the multiple ordinary vehicles found, the reference trajectory file and the corresponding reference license plate file of one of the ordinary vehicles are screened out according to the detection time range, including:

[0103] Step 301: Obtain the detection time ranges of multiple ordinary vehicles corresponding to the same reference license plate information to obtain an alternative time range.

[0104] In order to save computing resources, the embodiment of the present invention firstly filters out ordinary vehicles with overlapping time.

[0105] Step 302: When the time overlap of the multiple candidate time ranges is greater than the overlap threshold, retain the reference trajectory file and reference license plate file of one of the ordinary vehicles.

[0106] The overlap threshold is selected by those skilled in the art according to the specific usage scenario, and in principle the overlap threshold value needs to be as large as possible. In one embodiment, the reference trajectory file and the reference license plate file of ordinary vehicles with a larger detection time range may be retained.

[0107] like Fig. 9 As shown, a specific example of a time overlap between two candidate time ranges being less than an overlap threshold; Fig.10 As shown in FIG. 1 , a specific example of a time overlap between two candidate time ranges being greater than the overlap threshold. Since different ordinary vehicles are likely to scan the suspect vehicle from different angles, such as Fig. 9 As shown in , if the time overlap does not exceed the overlap threshold, it means that the overlap of the driving trajectories is not high. Not using any of the two reference driving trajectories to generate the target driving trajectory will result in missing data in the target driving trajectory. Fig.10 As shown, if the time overlap exceeds the overlap threshold, it means that the driving trajectory overlap is high. If the reference trajectory file and reference license plate file of an ordinary vehicle with a larger detection time range are used to generate the target driving trajectory, the data required for the target driving trajectory can be filled as much as possible.

[0108] Step 303: and / or, when there is an alternative time range within another alternative time range, retain the reference trajectory file and the reference license plate file corresponding to the other alternative time range.

[0109] like Fig.10 and 11 Shown is a specific example where there is an alternative time range within another alternative time range, such as Fig.10 As shown, the alternative time range a is within the alternative time range b, and the reference trajectory file and reference license plate file corresponding to the alternative time range b are retained; Fig.11 It is shown that the alternative time range c is within the alternative time range d, and the reference trajectory file and the reference license plate file corresponding to the alternative time range d are retained.

[0110] In order to illustrate the process of synthesizing the target driving trajectory, Fig.12 As shown, in step 202, synthesizing the target driving trajectory according to the reference trajectory files and reference license plate files of the selected plurality of ordinary vehicles includes:

[0111] Step 401: Obtain reference trajectory files and reference license plate files of a plurality of filtered ordinary vehicles.

[0112] Step 402: Obtain the detection time range corresponding to the suspected license plate information from the reference license plate file to obtain a target time range.

[0113] Step 403: In the reference trajectory file, find the driving trajectory whose driving time matches the target time range to obtain the relevant driving trajectory.

[0114] Step 404: Combine at least one related driving trajectory in chronological order to obtain the target driving trajectory.

[0115] like Fig.13 The figure shows a specific example of a target driving trajectory provided by an embodiment of the present invention; in one embodiment, all the related driving trajectories found can be: the related driving trajectory 1 corresponds to Fig.13 From trajectory node 1 to trajectory node 3, the relevant driving trajectory 2 corresponds to Fig.13 From trajectory node 2 to trajectory node 4, the relevant driving trajectory 3 corresponds to Fig.13 In another embodiment, the relevant driving trajectory 1 corresponds to the trajectory node 4 to the trajectory node 6, and the relevant driving trajectory 1, the relevant driving trajectory 2 and the relevant driving trajectory 3 are combined to obtain the target driving trajectory; wherein the relevant driving trajectory 1 and the relevant driving trajectory 2 overlap, and the overlapping road section is the trajectory node 2 to the trajectory node 3. Fig.13 From trajectory node 1 to trajectory node 2, the relevant driving trajectory 2 corresponds to Fig.13 From trajectory node 2 to trajectory node 3, the relevant driving trajectory 3 corresponds to Fig.13The trajectory node 3 and the trajectory node 6 in the figure are combined to obtain the target driving trajectory by combining the related driving trajectory 1, the related driving trajectory 2 and the related driving trajectory 3.

[0116] In addition, when the collected data of ordinary vehicles is limited, there may be a small number of driving trajectories of the suspected vehicle that cannot be generated, such as Fig.14 As shown, in one embodiment, the relevant driving trajectory 1 corresponds to Fig.14 From trajectory node 1 to trajectory node 2, the relevant driving trajectory 2 corresponds to Fig.14 From trajectory node 3 to trajectory node 4, the relevant driving trajectory 3 corresponds to Fig.14 From trajectory node 4 to trajectory node 5, the relevant driving trajectory 4 corresponds to Fig.14 The target driving trajectory is obtained by combining the trajectory node 5 and the trajectory node 6 in the target vehicle, and combining the related driving trajectory 1, the related driving trajectory 2, the related driving trajectory 3 and the related driving trajectory 4; wherein, the driving trajectory of the suspect vehicle between the trajectory node 2 and the trajectory node 3 cannot be generated. In an optional embodiment, in view of this situation, the road information between the trajectory node 2 and the trajectory node 3 can be obtained according to the map. When there are three roads between the trajectory node 2 and the trajectory node 3, the three roads are all used as the key inspection sections for the suspect vehicle and the corresponding criminals, and the first moment of the suspect vehicle at the trajectory node 2 and the second moment at the trajectory node 3 are obtained. The search personnel conduct information survey on the vehicles traveling on the key inspection section between the first moment and the second moment to restore the driving trajectory of the suspect vehicle.

[0117] In order to ensure that the privacy of ordinary vehicle owners is not violated, such as Fig.15 As shown, in step 401, the obtaining of reference trajectory files and reference license plate files of a plurality of filtered ordinary vehicles includes:

[0118] Step 501: Initiate a first inquiry request to users of screened ordinary vehicles; wherein the first inquiry request is used to request to use a reference driving trajectory corresponding to the user.

[0119] Step 502: When the user agrees to the first inquiry request, a reference driving trajectory corresponding to the user is obtained.

[0120] Step 503: Obtain the reference license plate file of the screened ordinary vehicles.

[0121] Since the data in the reference driving file involves the privacy of the owner's personal real-time location information, it is necessary to initiate a first inquiry request to the ordinary vehicle owner and obtain their consent before obtaining the reference driving file. Since the reference license plate file does not involve privacy, it can be obtained directly.

[0122] Embodiment 2:

[0123] Based on the method for generating the driving trajectory of the suspected vehicle in Example 1, this embodiment further provides a method for using ordinary vehicles to check the personnel of the target vehicle, which is described in detail below:

[0124] The track information file also stores the travel speed of the ordinary vehicle and the elapsed time of the ordinary vehicle running at the travel speed. Fig.16 As shown, the method for generating the driving trajectory of the suspected vehicle also includes:

[0125] Step 601: Obtain at least one driving speed of the ordinary vehicle within a specified time range, and the elapsed time corresponding to each driving speed; wherein the specified time range is the detection time range corresponding to the target vehicle; calculate the predicted distance based on the driving speed and the corresponding elapsed time.

[0126] The method of this embodiment can be used to determine whether other vehicles are likely to be stationary within a certain time period and road section, such as parked on the side of the road.

[0127] A specific example of the relative position relationship between the target vehicle and the ordinary vehicle is Fig.17 As shown, the target vehicle is: one of the designated other vehicles that can be detected by the ordinary vehicle, and the corresponding target vehicle is designated from the other vehicles through the detection time range.

[0128] like Fig.18 As shown, when the driving speed of an ordinary vehicle changes within a specified time range (for example, the driving speed from the first moment to the second moment is different from the driving speed from the second moment to the third moment), the time taken for the vehicle to run at the driving speed from the first moment to the second moment is taken as the corresponding elapsed time, and the time taken for the vehicle to run at the driving speed from the second moment to the third moment is taken as the corresponding elapsed time.

[0129] Then, each distance is equal to the product of the driving speed and the corresponding elapsed time, and the distance of each part is accumulated to get the predicted distance.

[0130] Step 602: At the start time when the ordinary vehicle detects the license plate information of the target vehicle, calibrate the actual distance between the ordinary vehicle and the target vehicle.

[0131] Most cars are equipped with cameras and radar systems, which are calibrated with each other to achieve distance detection; once an ordinary vehicle detects the license plate information of the target vehicle (such as Fig.17As shown, when the license plate information of the target vehicle appears within the scanning range of an ordinary vehicle), the actual distance between the ordinary vehicle and the target vehicle is immediately calibrated and obtained, wherein the actual distance is the straight-line distance between the ordinary vehicle and the target vehicle along the direction of travel of the ordinary vehicle; in one embodiment, the actual distance can be calibrated by the radar system of the ordinary vehicle, and the radar system will provide a distance reading to the target vehicle; the specific method of calibrating the actual distance by the radar system is selected by those skilled in the art according to the specific usage scenario and is not limited here. In an optional embodiment, when an ordinary vehicle detects the license plate information of the target vehicle and the target vehicle is within the effective scanning area of ​​the radar system, the actual distance is calibrated and obtained; the effective scanning area of ​​the radar system can be a fixed value, such as 10 meters; if the distance between the target vehicle and the ordinary vehicle exceeds the fixed value, the ordinary vehicle does not need to analyze the license plate information of the target vehicle, because the license plate information analysis when the distance is too far consumes excessive computing resources of the ordinary vehicle intelligent system.

[0132] Step 603: When the difference between the predicted distance and the actual distance is less than the error threshold, it is determined that the target vehicle may remain stationary within the detection time range.

[0133] There are two situations in which the ordinary vehicle cannot detect the target vehicle: (1) the ordinary vehicle exceeds the target vehicle; or (2) the target vehicle speeds up, increasing the distance between the target vehicle and the ordinary vehicle and disappearing from the monitoring field of the ordinary vehicle. When the difference between the predicted distance and the actual distance is less than the error threshold in both situations (1) and (2), it is determined that the target vehicle remains stationary within the detection time range.

[0134] In order to avoid the misjudgment caused by situation (2), in one embodiment, within a specified time range, the radar system will measure the distance between itself and the target vehicle in real time. If the distance detected by the radar system is gradually decreasing and the difference between the predicted distance and the actual distance is less than the error threshold, it is determined that the target vehicle may remain stationary within the detection time range.

[0135] The error threshold is selected by technicians in this field according to specific usage scenarios and experience, and the error threshold is an acceptable error range between the predicted distance and the actual distance.

[0136] When the following expression is met, it is determined that the target vehicle remains stationary within the detection time range:

[0137] d 预测 +th=v1t1+v2t2+...+v n t n

[0138] Among them, d 预测represents the predicted distance, th represents the error threshold, and v1 represents the first driving speed of the ordinary vehicle within the specified time range (for example, Fig.18 t1 represents the time that the ordinary vehicle runs at the first speed, and v2 represents the second speed of the ordinary vehicle within the specified time range (for example, Fig.18 t2 represents the time it takes for the ordinary vehicle to run at the first speed, v n represents the nth driving speed of the ordinary vehicle within a specified time range (for example, Fig.18 The driving speed at the third moment in time), t n Indicates the elapsed time of the ordinary vehicle running at the first driving speed.

[0139] like Fig.18 As shown, if the actual distance is equal to the predicted distance, it means that for the target vehicle, the ordinary vehicle simply relies on its own driving speed to pass the target vehicle in space. It can be deduced that the target vehicle is likely to have not moved within the specified time range, that is, it is likely to be in a stationary state.

[0140] Step 604: query the surveillance video to obtain at least one reference vehicle that passes the target vehicle within the detection time range; initiate a second inquiry request to the user of the reference vehicle; wherein the second inquiry request is used to: request to obtain the driving record of the reference vehicle within the detection time range; obtain the driving record when the user agrees to the second inquiry request, so as to obtain the personnel situation corresponding to the target vehicle based on the driving record.

[0141] After determining that the target vehicle may be stationary within the detection time range, in order to confirm the personnel situation of the target vehicle, the search personnel can retrieve the surveillance video in the public transportation scene, and search for the reference vehicle that passes the target vehicle within the detection time range in the surveillance video. After finding the reference vehicle, this embodiment uses the driving record and other audio and video data recorded by the driving recorder of the reference vehicle to restore the situation near the target vehicle within the detection time range. Since the driving record and other audio and video data involve the personal privacy of the owner, this embodiment initiates a second inquiry request to the owner of the reference vehicle, and only after obtaining his consent can the driving record be obtained from the driving recorder of the reference vehicle. In order to facilitate the search personnel to analyze whether there are people who get off the target vehicle and the corresponding time and place information within the detection time range, and whether there are new people in the target vehicle and the corresponding time and place information, etc., based on the driving record, to achieve tracking of the personnel situation of the target vehicle within the detection time range based on ordinary vehicles.

[0142] Embodiment 3:

[0143] like Fig.19 FIG. 1 is a schematic diagram of the structure of a device for generating a suspected vehicle driving trajectory according to an embodiment of the present invention. The device for generating a suspected vehicle driving trajectory according to this embodiment includes one or more processors 21 and a memory 22. Fig.19 A processor 21 is taken as an example.

[0144] The processor 21 and the memory 22 may be connected via a bus or other means. Fig.19 The example of connecting through bus is taken in the following.

[0145] The memory 22 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs and non-volatile computer executable programs, such as the method for generating the driving trajectory of a suspected vehicle in this embodiment. The processor 21 executes the method for generating the driving trajectory of a suspected vehicle by running the non-volatile software programs and instructions stored in the memory 22.

[0146] The memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 22 may optionally include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the processor 21 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0147] The program instructions / modules are stored in the memory 22, and when executed by the one or more processors 21, the method for generating the suspected vehicle driving trajectory in the above-mentioned embodiment is executed, for example, each step of the method for generating the suspected vehicle driving trajectory of the embodiment of the present invention described above is executed.

[0148] An embodiment of the present invention further provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors, such as Fig.19 A processor 21 can enable the above one or more processors to execute the method for generating the driving trajectory of a suspected vehicle in a specific embodiment of the present invention, for example, to execute each step of the method for generating the driving trajectory of a suspected vehicle in the embodiment of the present invention described above; it can also realize Fig.19 The various modules and units described above; or executing the method for generating the driving trajectory of a suspected vehicle in a specific embodiment of the present invention, for example, executing the various steps of the method for generating the driving trajectory of a suspected vehicle in the embodiment of the present invention described above; it can also be realized Fig.19 The various modules and units described.

[0149] It is worth noting that the information interaction, execution process, etc. between the modules and units within the above-mentioned devices and systems are based on the same concept as the processing method embodiment of the present invention. The specific contents can be found in the description of the method embodiment of the present invention and will not be repeated here.

[0150] A person skilled in the art may understand that all or part of the steps in the various methods of the embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0151] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a suspected vehicle driving trajectory, characterized in that: include: Acquire a reference driving trajectory of an ordinary vehicle to generate a trajectory information file of the ordinary vehicle; wherein the reference driving trajectory includes the driving trajectory of the ordinary vehicle and the corresponding driving time; When the ordinary vehicle detects the reference license plate information of other vehicles, the detection time range of detecting the reference license plate information is recorded to generate a license plate scanning file; Among the license plate scan files of the common vehicles, the suspected license plate information of the suspected vehicle is matched with the corresponding reference license plate information to find the common vehicle that detected the suspected vehicle; the trajectory information file of the found common vehicle is determined as the reference trajectory file, and the corresponding license plate scan file is determined as the reference license plate file; The target driving trajectory of the suspected vehicle is obtained according to the reference trajectory file and the reference license plate file.

2. The method for generating a suspected vehicle driving trajectory according to claim 1, characterized in that: The step of obtaining the target driving trajectory of the suspect vehicle according to the reference trajectory file and the reference license plate file includes: When there are multiple ordinary vehicles with overlapping time among the multiple ordinary vehicles found, the reference trajectory file and the corresponding reference license plate file of one of the ordinary vehicles are selected according to the detection time range; The target driving trajectory is synthesized according to the reference trajectory files and reference license plate files of the screened multiple ordinary vehicles.

3. The method for generating a suspected vehicle driving trajectory according to claim 2, characterized in that: When there are multiple ordinary vehicles with overlapping time among the multiple ordinary vehicles found, the reference trajectory file and the corresponding reference license plate file of one of the ordinary vehicles are selected according to the detection time range, including: Obtain the detection time ranges of the multiple common vehicles found that correspond to the same reference license plate information, and obtain the candidate time range; When the time overlap of multiple candidate time ranges is greater than the overlap threshold, retain the reference trajectory file and reference license plate file of one of the ordinary vehicles; And / or, when there is an alternative time range within another alternative time range, retain the reference trajectory file and the reference license plate file corresponding to the other alternative time range.

4. The method for generating a suspected vehicle driving trajectory according to claim 2, characterized in that: The synthesizing the target driving trajectory according to the reference trajectory files and the reference license plate files of the selected plurality of ordinary vehicles comprises: Obtain reference trajectory files and reference license plate files of multiple filtered common vehicles; Obtaining the detection time range corresponding to the suspected license plate information from the reference license plate file to obtain a target time range; In the reference trajectory file, searching for a driving trajectory whose driving time matches the target time range to obtain a relevant driving trajectory; At least one related driving trajectory is combined in chronological order to obtain the target driving trajectory.

5. The method for generating a suspected vehicle driving trajectory according to claim 4, characterized in that: The obtaining of the reference trajectory files and reference license plate files of the plurality of ordinary vehicles selected includes: Initiating a first inquiry request to the user of the screened ordinary vehicle; wherein the first inquiry request is used to request to use the reference driving trajectory corresponding to the user; When the user agrees to the first inquiry request, obtaining a reference driving trajectory corresponding to the user; Obtain the reference license plate file of the screened ordinary vehicles.

6. The method for generating a suspected vehicle driving trajectory according to claim 1, characterized in that: The track information file also stores the travel speed of the common vehicle and the elapsed time of the common vehicle running at the travel speed; The method for generating the suspected vehicle driving trajectory also includes: Obtain at least one driving speed of the ordinary vehicle within a specified time range, and the elapsed time corresponding to each driving speed; wherein the specified time range is the detection time range corresponding to the target vehicle; and calculate the predicted distance according to the driving speed and the corresponding elapsed time; At the start time when the ordinary vehicle detects the license plate information of the target vehicle, calibrating the actual distance between the ordinary vehicle and the target vehicle; When the difference between the predicted distance and the actual distance is less than the error threshold, it is determined that the target vehicle may remain stationary within the detection time range; Query the surveillance video to obtain at least one reference vehicle that passes by the target vehicle within the detection time range; initiate a second inquiry request to the user of the reference vehicle; wherein the second inquiry request is used to: request to obtain the driving record of the reference vehicle within the detection time range; obtain the driving record when the user agrees to the second inquiry request, so as to obtain the personnel situation corresponding to the target vehicle based on the driving record.

7. The method for generating a suspected vehicle driving trajectory according to any one of claims 1 to 6, characterized in that: Storing the license plate scan file as a local file of the ordinary vehicle; Or, storing the license plate scan file in a server, and updating the license plate scan file in the server; Or, the license plate scan file is stored as a local file of the ordinary vehicle, and when the storage time of the local file is greater than a clearing time threshold, the local file is uploaded to the server and deleted.

8. The method for generating a suspected vehicle driving trajectory according to any one of claims 1 to 6, characterized in that: When the ordinary vehicle detects the reference license plate information of another vehicle, recording the detection time range of the reference license plate information to generate a license plate scanning file includes: When the ordinary vehicle scans the reference license plate information of other vehicles, the start time when the ordinary vehicle scans the reference license plate information is recorded, until the ordinary vehicle cannot scan the reference license plate information, the end time is recorded, so as to obtain the detection time range according to the start time and the end time; At least one detection time range corresponding to the ordinary vehicle is stored in the license plate scanning file.

9. A device for generating a suspected vehicle driving trajectory, characterized in that: The device for generating the suspected vehicle's driving trajectory includes at least one processor and a memory, and the at least one processor and the memory are connected via a data bus. The memory stores instructions that can be executed by the at least one processor. After the instructions are executed by the processor, they are used to implement the method for generating the suspected vehicle's driving trajectory described in any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors to complete the method for generating the driving trajectory of a suspected vehicle as described in any one of claims 1-8.

Images