CN113128540A

CN113128540A - Detection method and device for vehicle stealing behavior of non-motor vehicle and electronic equipment

Info

Publication number: CN113128540A
Application number: CN201911425301.8A
Authority: CN
Inventors: 蔡杭洲
Original assignee: Shenzhen Intellifusion Technologies Co Ltd
Current assignee: Shenzhen Intellifusion Technologies Co Ltd
Priority date: 2019-12-31
Filing date: 2019-12-31
Publication date: 2021-07-16
Anticipated expiration: 2039-12-31
Also published as: CN113128540B

Abstract

The embodiment of the invention provides a detection method, a device and electronic equipment for the vehicle stealing behavior of a non-motor vehicle, wherein the method comprises the following steps: acquiring non-motor vehicle driving characteristics in a tracking image, wherein the non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics; inputting the non-motor vehicle driving characteristics into a clustering engine, and clustering to obtain historical snapshot information based on the non-motor vehicle driving characteristics, wherein the historical snapshot information comprises corresponding historical non-motor vehicle characteristics and historical driver characteristics; detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information or not; and judging whether a driver has a vehicle stealing behavior or not according to the detection result. The vehicle stealing behavior can be effectively detected in real time.

Description

Detection method and device for vehicle stealing behavior of non-motor vehicle and electronic equipment

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a detection method and device for a vehicle stealing behavior of a non-motor vehicle and electronic equipment.

Background

Image recognition is one of the common technologies of community security and traffic management at present, and can greatly improve social security, for example: and detecting the traffic violation event by using a community access control system based on face recognition or a license plate image recognition. Because many non-motor vehicles do not handle the license according to the traffic management requirement for non-motor vehicle's ownership is judged comparatively singlely, and who can open this non-motor vehicle's lock promptly, and who just can drive this non-motor vehicle, is difficult to judge to the action of stealing the car, thereby leads to non-motor vehicle's easy stolen, and is difficult for discovering the personnel of stealing the car, only after the car owner reports to the police, relevant personnel carry out the analysis to a large amount of monitored data, just can find corresponding clue. Therefore, in the prior art, the vehicle stealing behavior of the non-motor vehicle cannot be effectively detected in real time.

Disclosure of Invention

The embodiment of the invention provides a method and a device for detecting the vehicle stealing behavior of a non-motor vehicle, electronic equipment and a computer readable storage medium, which can effectively detect the vehicle stealing behavior of the non-motor vehicle in real time.

In a first aspect, an embodiment of the present invention provides a method for detecting a vehicle theft behavior of a non-motor vehicle, including:

acquiring non-motor vehicle driving characteristics in a tracking image, wherein the non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics;

inputting the non-motor vehicle driving characteristics into a clustering engine, and clustering to obtain historical snapshot information based on the non-motor vehicle driving characteristics, wherein the historical snapshot information comprises corresponding historical non-motor vehicle characteristics and historical driver characteristics;

detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information or not to obtain a detection result;

and judging whether the vehicle stealing behavior exists or not according to the detection result.

In a second aspect, an embodiment of the present invention provides a device for detecting a vehicle theft behavior of a non-motor vehicle, including:

the system comprises a first acquisition module, a second acquisition module and a tracking module, wherein the first acquisition module is used for acquiring non-motor vehicle driving characteristics in a tracking image, and the non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics;

the clustering module is used for inputting the driving characteristics of the non-motor vehicles into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles, wherein the historical snapshot information comprises corresponding historical non-motor vehicle characteristics and historical driver characteristics;

the detection module is used for detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information or not;

and the judging module is used for judging whether the vehicle stealing behavior exists or not according to the detection result.

In a third aspect, an embodiment of the present invention provides an electronic device, including: the detection method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the detection method for the vehicle stealing behavior of the non-motor vehicle provided by the embodiment of the invention.

In a fourth aspect, the embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the method for detecting a vehicle theft behavior of a non-motor vehicle provided by the embodiment of the present invention are implemented.

In the embodiment of the invention, the non-motor vehicle driving characteristics in the tracking image are obtained, wherein the non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics; inputting the non-motor vehicle driving characteristics into a clustering engine, and clustering to obtain historical snapshot information based on the non-motor vehicle driving characteristics, wherein the historical snapshot information comprises corresponding historical non-motor vehicle characteristics and historical driver characteristics; detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information or not; and judging whether a driver has a vehicle stealing behavior or not according to the detection result. The method and the device have the advantages that the personnel driving the non-motor vehicles and the non-motor vehicles are identified and clustered, so that whether one person drives multiple vehicles or one vehicle drives multiple vehicles or multiple persons drives can be detected, whether vehicle stealing behaviors exist or not can be judged according to the conditions, a large amount of analysis work of relevant personnel on monitoring data can be saved, and the vehicle stealing behaviors can be effectively detected in real time.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart of a method for supervising traffic violation of a non-motor vehicle according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another detection method for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of another detection method for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 4 is a schematic flow chart of another detection method for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 5 is a schematic flow chart of another detection method for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 6 is a schematic flow chart of another detection method for vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 7 is a schematic flow chart of another detection method for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of a detection device for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 9 is a schematic structural diagram of another detection apparatus for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 10 is a schematic structural diagram of another detection apparatus for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

FIG. 11 is a schematic structural diagram of another detection apparatus for detecting vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention;

fig. 12 is a schematic structural diagram of a first obtaining module according to an embodiment of the present invention;

fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, fig. 1 is a schematic flow chart of a method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 1, including the following steps:

101. non-motor vehicle driving characteristics in the tracking image are acquired.

The non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics, the non-motor vehicle driving characteristics can be understood as characteristics that a driver drives a non-motor vehicle, and the tracking image refers to a continuous image containing the non-motor vehicle characteristics and the driver characteristics. The tracking image may be acquired by an image acquisition device, such as a community camera arranged in a community or at a community gate, or a traffic camera arranged at an intersection or on a roadside, or a camera corresponding to a community system in linkage with a traffic system. The non-motor vehicle can be a bicycle, a tricycle, an electric vehicle, a balance vehicle, a rickshaw and other non-motor vehicles, and the non-motor vehicle can be characterized by a headstock, a handle, a pedal, a tire and other non-motor vehicle. The driver features may be human face features, such as facial contours, mouth, eyes, nose, and the like. The matching of the non-motor vehicle characteristics and the driver characteristics can be performed according to the distance between the non-motor vehicle characteristics and the driver characteristics, and can also be performed according to the non-motor vehicle characteristics and the movement track of the driver. The non-motor vehicle driving characteristics can be obtained by inputting the tracking image into a target tracking engine, extracting the tracking image through the target tracking engine, extracting corresponding non-motor vehicle characteristics and driver characteristics of each image frame, and matching the non-motor vehicle characteristics and the driver characteristics to obtain the matched non-motor vehicle characteristics and driver characteristics, namely the driving characteristics of the non-motor vehicle. Specifically, in the target tracking engine, a kalman filtering algorithm may be used to track the non-motor vehicle and the driver appearing in the video, and corresponding non-motor vehicle features and driver features are extracted, so as to perform matching, thereby obtaining the driving features of the non-motor vehicle.

It should be noted that the driving characteristics of the non-motor vehicle obtained in step 101 may include one or more characteristics of the non-motor vehicle and one or more characteristics of the driver. The tracking image may be referred to as a visual image, visual information, video image, video information, continuous video frame, continuous frame image, surveillance video, surveillance information, surveillance image, or the like.

In some possible embodiments, the above-mentioned driver characteristics may further include a posture characteristic of the person, where the posture characteristic may be a posture characteristic of a hand posture, a foot posture, an upper body posture, and the like, and by analyzing the posture characteristic of the person, it may be determined whether the person is driving the non-motor vehicle, for example, it may be determined whether a hand of the person is on a handle, and it may be determined whether a foot of the person is placed at a driving position, and the like, through the posture characteristic. The gesture features of the personnel can be used for matching drivers and passengers for the non-motor vehicles, the gesture features can be gesture features such as hand gestures, foot gestures and upper body gestures, for example, the gesture features of the personnel to which the hands on the handles belong can be judged to be matched with the drivers and passengers of the non-motor vehicles, the gesture features of the personnel to which the feet on the pedals belong can be judged to be matched with the drivers and passengers of the non-motor vehicles, and of course, when the gesture features are used for matching the drivers and passengers of the non-motor vehicles, the gesture features also need to be matched with the personnel, so that the drivers and passengers are determined. The pose characteristics and the face characteristics can be associated and matched, so that the pose characteristics are matched to corresponding people.

102. Inputting the driving characteristics of the non-motor vehicles into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles.

In this step, the non-motor vehicle driving characteristics include non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics, and the history snapshot information includes corresponding history non-motor vehicle characteristics and history driver characteristics. The above-mentioned historical snapshot information may be historical snapshot information within a preset time, such as snapshot information within 1 month, or snapshot information within 6 months. The non-motor vehicle driving characteristics may be one or more, that is, the non-motor vehicle characteristics may be one or more, the driver characteristics may be one or more, and one non-motor vehicle characteristic may match only one driver characteristic. Such as: the tracked image comprises non-motor vehicle characteristics b1, b2, b3 and b4, personnel characteristics a1, a2, a3, a4, a5 and a6, wherein the non-motor vehicle driving characteristics are 1, 2, 3 and 4, the non-motor vehicle driving characteristic 1 can be represented as matching of the non-motor vehicle characteristic b1 with the personnel characteristic a1, in this case, a person with the personnel characteristic a1 can be called a driver, and the personnel characteristic a1 is the driver characteristic a 1; non-motor driving feature 2 may be represented as a match of non-motor driving feature b2 with person feature a2, in which case the person with person feature a2 may be referred to as the driver, person feature a2 is driver feature a 2; by analogy, the personnel characteristic a3 and the personnel characteristic a4 correspond to the driver characteristics a3 and a4 respectively; a5 and a6 are not characteristic of drivers. The clustering engine can cluster the historical snapshot information of the driver according to one driver characteristic, and can also cluster the snapshot information of the non-motor vehicle according to one non-motor vehicle characteristic, and the clustering can be understood as clustering objects with the same characteristic together. The above-mentioned historical snapshot information may be the historical snapshot information that the acquisition device has snapshot to the target non-motor vehicle characteristic or the target driver characteristic in step 101, and the historical snapshot information may be fixed-length or variable-length semi-structured data stored in a historical database. In the clustering process, semi-structured data related to the target features are extracted from the historical database for clustering according to the corresponding target features. For example, the driver characteristics corresponding to the drivers a1 and a2 are a1 and a2, respectively, the non-motor vehicle characteristics corresponding to the driven non-motor vehicles B1 and B2 are B1 and B2, and the history snapshot information of the related driver a1 can be extracted from the history database according to the driver characteristic a1 for clustering; historical snapshot information of related drivers A2 can be extracted from a historical database according to the characteristics a2 of the drivers for clustering; historical snapshot information of related non-motor vehicles B1 can be extracted from a historical database according to the non-motor vehicle characteristics B1 for clustering; historical snapshot information of the relevant non-motor vehicle B2 can be extracted from the historical database according to the non-motor vehicle characteristics B2 for clustering.

It should be noted that the historical non-motor vehicle characteristics may be non-motor vehicle characteristics such as a head, a handle, a pedal, and a tire. The historical driver features may be historical human face features, such as facial contours, mouth, eyes, nose, and the like.

103. And detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information or not to obtain a detection result.

In this step, the non-motor vehicle driving characteristics include non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics, and the history snapshot information includes corresponding history non-motor vehicle characteristics and history driver characteristics. The detection may be to detect whether the corresponding driver characteristic is the same as the historical driver characteristic under the same non-motor vehicle characteristic, or to detect whether the corresponding non-motor vehicle characteristic is the same as the historical non-motor vehicle characteristic under the same driver characteristic. For example, assuming that the above-mentioned non-motor vehicle driving characteristics are (a1, B1), the above-mentioned a1 corresponds to the driver characteristic of the driver a1, the above-mentioned B1 corresponds to the non-motor vehicle characteristic of the non-motor vehicle B1, and the above-mentioned driver a1 drives the non-motor vehicle B1, and it may be determined whether the corresponding driver characteristic is the same as the historical driver characteristic under the same non-motor vehicle characteristic: if the history snapshot information corresponding to B1 is detected to be (a1, B1), (a1, B1), (a1, B1) and (a1, B1), the driver corresponding to the non-motor vehicle characteristic B1 of the non-motor vehicle B1 is always A1, that is, the corresponding driver characteristic is the same as the history driver characteristic. If the history snapshot information corresponding to b1 is detected to be (a2, b1), (A3, b1), (a4, b1) and (a4, b1), it indicates that the driver corresponding to the non-motor vehicle characteristic b1 is not always a1, that is, the corresponding driver characteristic is different from the history driver characteristic. In the above-described detection of the same driver characteristic, whether the corresponding non-motor vehicle characteristic is the historical non-motor vehicle characteristic may be: if the history snapshot information corresponding to the a1 is detected to be (a1, B1), (a1, B1), (a1, B1) and (a1, B1), the non-motor vehicle corresponding to the driver characteristic a1 of the driver A1 is always B1, namely the non-motor vehicle characteristic corresponding to the driver A1 is the same as the history non-motor vehicle characteristic. If the history snapshot information corresponding to the a1 is detected to be (a1, b2), (a1, b3), (a1, b4) and (a1, b5), the fact that the non-motor vehicle corresponding to the driver characteristic a1 of the driver A1 is changed all the time is indicated, namely that the fact that the non-motor vehicle characteristic corresponding to the driver A1 is different from the history non-motor vehicle characteristic is indicated. The detecting may be comparing the non-motor vehicle characteristics with historical non-motor vehicle characteristics one by one, and when the similarity between the historical non-motor vehicle characteristics and the non-motor vehicle characteristics is greater than or equal to a non-motor vehicle similarity threshold, the non-motor vehicle characteristics may be considered to be the same as the historical non-motor vehicle characteristics, and when the similarity between the historical non-motor vehicle characteristics and the non-motor vehicle characteristics is less than the non-motor vehicle similarity threshold, the non-motor vehicle characteristics may be considered to be different from the historical non-motor vehicle characteristics. Similarly, the detection may be to compare the similarity between the driver characteristics and the historical driver characteristics one by one, and when the similarity between the historical driver characteristics and the driver characteristics is greater than or equal to a driver similarity threshold, it may be determined that the driver characteristics are the same as the historical driver characteristics, and when the similarity between the historical driver characteristics and the driver characteristics is less than the driver similarity threshold, it may be determined that the driver characteristics are different from the historical driver characteristics.

104. And judging whether the vehicle stealing behavior exists or not according to the detection result.

The detection results include four types in step 103, the first type: under the same non-motor vehicle characteristic, the corresponding driver characteristic is the same as the historical driver characteristic; and the second method comprises the following steps: under the same non-motor vehicle characteristic, the corresponding driver characteristic is different from the historical driver characteristic; and the third is that: under the same driver characteristic, the corresponding non-motor vehicle characteristic is the same as the historical non-motor vehicle characteristic; and fourthly: the corresponding non-motor vehicle characteristic is different from the historical non-motor vehicle characteristic under the same driver characteristic. In the first detection result, since the driver characteristic is the same as the historical driver characteristic, it can be said that the vehicle corresponding to the non-vehicle characteristic is driven by the driver corresponding to the driver characteristic all the time, and it can be considered that there is no vehicle theft behavior. In the second detection result, since the driver characteristic is different from the historical driver characteristic, it can be said that the vehicle corresponding to the non-vehicle characteristic is always driven by a different driver, and the non-vehicle is always handed over, and it can be considered that vehicle theft behavior exists. In the third detection result, since the non-motor vehicle characteristics are the same as the historical non-motor vehicle characteristics, it can be said that the driver corresponding to the driver characteristics always drives the same non-motor vehicle, and it can be considered that there is no vehicle theft behavior. In the fourth detection result, since the non-motor vehicle characteristic is different from the historical non-motor vehicle characteristic, it can be said that the driver corresponding to the driver characteristic drives different non-motor vehicles all the time, and it can be considered that the vehicle stealing behavior exists.

In some possible embodiments, when the third detection result is obtained, the non-motor vehicle may be further identified, whether the non-motor vehicle is the shared non-motor vehicle is identified, if the non-motor vehicle is identified as the non-shared non-motor vehicle, the vehicle theft behavior may be considered to exist, and if the non-motor vehicle is identified as the shared non-motor vehicle, the vehicle theft behavior may be considered to not exist.

It should be noted that the detection method for the vehicle theft behavior of the non-motor vehicle provided by the embodiment of the present invention can be applied to detection equipment for the vehicle theft behavior of the non-motor vehicle, for example: the device can detect the stealing behavior of the non-motor vehicles by the community camera, the traffic camera, the computer, the server and the like.

In the embodiment of the invention, because the personnel driving the non-motor vehicles and the non-motor vehicles are identified and clustered, whether one person drives multiple vehicles or one vehicle drives multiple vehicles or multiple persons drives can be detected, so that whether the vehicle stealing behavior exists or not can be judged according to the conditions, a large amount of analysis work of related personnel on monitoring data can be saved, and the vehicle stealing behavior can be effectively detected in real time.

Optionally, referring to fig. 2, fig. 2 is a schematic flow chart of another detection method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 2, including the following steps:

201. non-motor vehicle driving characteristics in the tracking image are acquired.

Wherein the non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics.

202. Inputting the characteristics of the drivers into a clustering engine, and clustering to obtain historical snapshot information based on the characteristics of the drivers.

Wherein the historical snap-shot information includes corresponding historical non-motor vehicle characteristics and historical driver characteristics.

203. Whether the non-motor vehicle characteristics corresponding to the same driver characteristics are different from the historical non-motor vehicle characteristics is detected.

204. And if the non-motor vehicle characteristics corresponding to the same driver characteristics are different from the historical non-motor vehicle characteristics, judging that the driver has the vehicle stealing behavior.

In this embodiment, in step 202, driver features are clustered, where the driver features may be facial features, and the facial features may also be referred to as facial images, and the facial features are input into a clustering engine, and historical snapshot data with the same facial features are extracted from a historical database by the clustering engine, and when there are a plurality of drivers, different driver profiles may be established according to different facial features for storing the extracted corresponding historical snapshot data, so as to complete clustering based on the driver features. Because the clustering is completed based on the characteristics of the drivers, each category is distinguished by the characteristics of the drivers, and each category can be understood as historical snapshot information corresponding to the same driver. For example, the characteristics of the drivers are a1, a2 and A3 respectively, the characteristics correspond to drivers a1, a2 and A3 respectively, history snapshot information of the driver a1 is obtained according to a1 clustering, history snapshot information of the driver a2 is obtained according to a2 clustering, and history snapshot information of the driver A3 is obtained according to A3 clustering.

In the detection in step 203, the non-motor vehicle characteristics corresponding to the same driver may be compared with the historical non-motor vehicle characteristics in the historical snapshot information one by one, so as to determine whether the non-motor vehicle characteristics are the same as the historical non-motor vehicle characteristics. Specifically, when the similarity between the historical non-motor vehicle characteristic and the non-motor vehicle characteristic reaches a similarity threshold (e.g., 99%), the historical non-motor vehicle characteristic and the non-motor vehicle characteristic can be considered to be the same; when the similarity between the historical non-motor vehicle characteristic and the non-motor vehicle characteristic does not reach a similarity threshold (e.g., 99%), the historical non-motor vehicle characteristic and the non-motor vehicle characteristic may be considered to be different. And detecting each driver in the tracking image so as to obtain the detection result of each driver.

In step 204, since the corresponding non-motor vehicle characteristic is different from the historical non-motor vehicle characteristic under the same driver characteristic, it can be said that the driver corresponding to the driver characteristic drives different non-motor vehicles all the time, and it can be considered that the driver has a vehicle theft behavior.

In the steps, the historical snapshot information of the same driver is obtained by clustering the characteristics of the driver, and whether the driver has a vehicle stealing behavior or not can be analyzed. In addition, when the same driver drives different non-motor vehicles, the driver can be considered to have the behavior of stealing the vehicle. Through clustering the characteristics of the drivers, whether the drivers have car stealing behaviors or not can be quickly detected, and the detection efficiency is improved.

Optionally, referring to fig. 3, fig. 3 is a schematic flow chart of another detection method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 3, including the following steps:

301. non-motor vehicle driving characteristics in the tracking image are acquired.

302. Inputting the non-motor vehicle characteristics into a clustering engine, and clustering to obtain historical snapshot information based on the non-motor vehicle characteristics.

303. Whether the condition that the characteristics of the drivers corresponding to the same non-motor vehicle are different from the historical characteristics of the drivers is detected.

304. And if the detected driver characteristics corresponding to the same non-motor vehicle are different from the historical driver characteristics, judging that the vehicle stealing behavior exists.

In this embodiment, step 302 is to cluster the non-motor vehicle characteristics, input the above non-motor vehicle characteristics into a clustering engine, extract historical snapshot data with the same non-motor vehicle characteristics from a historical database through the clustering engine, and when a plurality of non-motor vehicles exist between a driver and a corresponding driven non-motor vehicle, establish different non-motor vehicle archives according to different non-motor vehicle characteristics for storing the extracted corresponding historical snapshot data, thereby completing the clustering based on the non-motor vehicle characteristics. Because the clustering is completed based on the non-motor vehicle characteristics, each category is distinguished by the non-motor vehicle characteristics, and each category can be understood as historical snapshot information corresponding to the same non-motor vehicle. For example, the non-motor vehicles are respectively characterized by B1, B2 and B3, respectively correspond to non-motor vehicles B1, B2 and B3, historical snapshot information of the non-motor vehicle a1 is obtained according to B1 clustering, historical snapshot information of the non-motor vehicle B2 is obtained according to B2 clustering, and historical snapshot information of the non-motor vehicle B3 is obtained according to B3 clustering.

In the detection in step 303, the similarity between the driver characteristics corresponding to the same non-motor vehicle and the historical driver characteristics in the historical snapshot information of the non-motor vehicle may be compared one by one, so as to determine whether the driver characteristics are the same as the historical driver characteristics. Specifically, when the similarity between the historical driver characteristic and the driver characteristic reaches a similarity threshold (e.g., 99%), the historical driver characteristic and the driver characteristic may be considered to be the same; when the similarity between the historical driver characteristic and the driver characteristic does not reach a similarity threshold (e.g., 99%), the historical driver characteristic and the driver characteristic may be considered to be different. And detecting each non-motor vehicle in the tracking image so as to obtain the detection result of each non-motor vehicle. The driver feature may be a face feature, and the historical driver feature may be a face feature captured in history.

In step 304, since the corresponding driver characteristic is different from the historical driver characteristic under the same non-motor vehicle characteristic, it can be said that the non-motor vehicle corresponding to the non-motor vehicle characteristic is driven by different drivers all the time, it can be said that the non-motor vehicle has a stolen situation (the non-motor vehicle frequently turns hands), and meanwhile, it can be said that the driver driving the stolen non-motor vehicle has a vehicle theft behavior, and the historical driver also has a vehicle theft behavior.

In some possible embodiments, since the shared non-motor vehicle also has different driving conditions of drivers, before judging whether the vehicle stealing behavior exists, the non-motor vehicle can be identified first, whether the non-motor vehicle is the shared non-motor vehicle is judged, if the non-motor vehicle is the shared non-motor vehicle, the vehicle stealing behavior is not judged, or the vehicle stealing behavior is directly considered to be absent, so that the calculation resources are saved. In other possible embodiments, the identification judgment of the shared non-motor vehicles can be carried out in the tracking image, so that the shared non-motor vehicles can be prevented from being clustered, and the computing resources are further saved.

In the steps, the non-motor vehicle characteristics are clustered to obtain historical snapshot information of the same non-motor vehicle, and whether the non-motor vehicle is stolen or not can be analyzed. In addition, when the same non-motor vehicle is driven by different drivers, the non-motor vehicle can be considered to be stolen. By clustering the characteristics of the non-motor vehicles, whether the non-motor vehicles are stolen or not can be quickly detected, so that vehicle stealing personnel are analyzed, and the detection efficiency is improved.

Optionally, referring to fig. 4, fig. 4 is a schematic flow chart of another detection method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 4, including the following steps:

401. non-motor vehicle driving characteristics in the tracking image are acquired.

The non-motor vehicle driving characteristics comprise non-motor vehicle characteristics and driver characteristics matched with the non-motor vehicle characteristics, and the driver characteristics comprise human face characteristics.

402. Inputting the driving characteristics of the non-motor vehicles into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles.

403. And detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information.

404. And judging whether the vehicle stealing behavior exists or not according to the detection result.

405. And after judging that the vehicle stealing behavior exists, acquiring the corresponding peer information of the driver with the vehicle stealing behavior.

406. And constructing a relationship map of the driver with the vehicle stealing behavior according to the peer information.

The information of the same row in step 405 refers to the information of the person captured in the same image as the driver, and the information of the same row may be walking or driving the non-motor vehicle. The peer information may be peer information of a preset time, for example, peer information within 1 month, peer information within 6 months, and the like. The peer information includes the number of peers and the peer personnel information. The information of the same row can be obtained from a same-row database, wherein the same-row database stores a same-row file of the person to be captured, the same-row file records same-row image data of the person to be captured and the same-row person, and the same-row image data comprises a same-row place, a same-row time and the like. Specifically, the face characteristics of the driver with the vehicle stealing behavior are obtained, and the file of the same row of the driver is searched in the database of the same row through the face characteristics of the driver, so that the corresponding information of the same row is obtained.

In step 406, the relationship map includes the number of times of the same-row and the information of the persons in the same-row, and the relationship map is used for displaying the relationship between the persons in the same-row and the driver with the vehicle stealing behavior. The relation map can be a connection relation image formed by taking the face image of the driver as a central point and the face images of the persons in the same row as a connection point, each connection line represents the in-row relation between the driver and one person in the same row, and the number of times of in-row can be displayed on the connection line or on the edge of the face image corresponding to the person in the same row.

In one possible embodiment, only the fellow persons who fellow the driver more than a preset number threshold are displayed in the relationship map, for example, only the fellow persons who fellow the driver more than 5 times are displayed.

It should be noted that, the above-mentioned

steps

405 and 406 are optional, and in some possible embodiments, only the vehicle stealing behavior needs to be judged as the basis for judgment. Further, the

steps

405 and 406 may be combined with the embodiments corresponding to fig. 2 and 3.

In the steps, the relationship map of the vehicle stealing personnel is formed by acquiring the peer information of the vehicle stealing personnel (the driver with the vehicle stealing behavior), so that the social relationship of the vehicle stealing personnel can be visually displayed, and the analysis and mining of the vehicle stealing personnel group by the related police personnel are facilitated.

Optionally, referring to fig. 5, fig. 5 is a schematic flow chart of another detection method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 5, including the following steps:

501. non-motor vehicle driving characteristics in the tracking image are acquired.

502. Inputting the driving characteristics of the non-motor vehicles into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles.

503. And detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information.

504. And judging whether the vehicle stealing behavior exists or not according to the detection result.

505. And after judging that the vehicle stealing behavior exists, acquiring the corresponding peer information of the driver with the vehicle stealing behavior.

506. And constructing a relationship map of the driver with the vehicle stealing behavior according to the peer information.

507. And comparing the information of the persons in the same row with the information of the persons in the prior department.

508. And adjusting the relation map according to the comparison result to obtain the relation map of the suspect with the vehicle stealing behavior.

In step 507, the predecessor information library may include predecessor information of vehicle stealing personnel, further, the predecessor information of vehicle stealing personnel refers to predecessor information of vehicle stealing personnel who steals the non-motor vehicle, the predecessor information includes information of vehicle stealing personnel and information of vehicle stealing behavior, the information of vehicle stealing behavior includes information of vehicle stealing time, vehicle stealing place, vehicle type to be stolen, and the like, and the information of vehicle stealing personnel includes information of human face characteristics, identity information, and the like. The identity information may be name, identification number, age, date of birth, etc. The peer information includes face features, identity information and the like. The comparison can be the comparison of human face characteristics and also can be the comparison of identity information. Specifically, the face features of the fellow passenger can be compared with the face features of the car stealing passenger in the front department passenger library, or the identity information of the fellow passenger can be compared with the identity information of the car stealing passenger in the front department passenger library.

In step 507, after comparing the peer information in the predecessor library, if the peer corresponding to the peer information is a predecessor in the predecessor library, the relationship map is adjusted, where the adjustment may be to highlight a connection line between the peer and the driver, for example, a connection line whose common peer is gray is a red connection line, or to directly mark a face image of the peer, and mark the face image as a predecessor, so as to obtain a relationship map of the suspect. The suspect relationship map is used for displaying fellow persons with large vehicle theft suspicion, such as predecessors, for example, fellow persons who have fellow persons more than 50 times.

It should be noted that, the above-mentioned

steps

505 and 506 are optional, and in some possible embodiments, only the vehicle stealing behavior needs to be judged as the basis for judging. Step 505 and step 506 described above may be combined with the embodiments corresponding to fig. 2 and fig. 3.

In the steps, the relationship map of the vehicle stealing personnel is formed by acquiring the peer information of the vehicle stealing personnel (the driver with the vehicle stealing behavior), so that the social relationship of the vehicle stealing personnel can be visually displayed, and the analysis and mining of the vehicle stealing personnel group by the related police personnel are facilitated. In addition, whether the fellow staff is the predecessor is inquired, the relationship map of the suspect is obtained, the social relationship of the vehicle stealing personnel is further visually displayed, and therefore the related police personnel can conveniently conduct further analysis and mining on the vehicle stealing personnel group.

Optionally, referring to fig. 6, fig. 6 is a schematic flow chart of another detection method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 6, including the following steps:

601. non-motor vehicle driving characteristics in the tracking image are acquired.

602. Inputting the driving characteristics of the non-motor vehicles into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles.

603. And detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information.

604. And judging whether the vehicle stealing behavior exists or not according to the detection result.

605. And after the vehicle stealing behavior is judged to exist, continuously taking a snapshot of the driver with the vehicle stealing behavior, and acquiring corresponding snapshot information.

606. And forming a track aiming at the driver with the vehicle stealing behavior according to the snapshot information.

In step 605, continuously capturing the driver with the vehicle theft behavior may be understood as tracking the driver, that is, tracking and capturing the driver through cameras disposed in multiple places. The snapshot information includes the face characteristics of the driver, the snapshot time and the snapshot place, and the snapshot place can be the same as the installation place of the camera.

In step 606, a trajectory of the driver may be obtained according to the snapshot time and the snapshot location, where the trajectory is used to analyze the location where the driver has appeared, and the trajectory may be understood as how the driver moves from which location to which location within what time period and what movement route the driver has. For example, the snapshot time is 12 points and 11 points, and the snapshot place is a backdoor of a certain cell; the snapshot time is 12 points and 30 minutes, and the snapshot place is an intersection A; the snapshot time is 12 points and 50 minutes, and the snapshot place is the intersection B; the snapshot time is 13 points and 15 points, and the snapshot place is a certain second-hand vehicle. The resulting traces are: the rear door of a certain cell → the road junction A → the intersection B → a certain second-hand vehicle. The analysis of the vehicle stealing personnel can be carried out through the tracks, such as the analysis of where dirty points are located, the analysis of where the gathering points of the group personnel are located, and the like. For example, at the time of the intersection a, the driver also drives the stolen non-motor vehicle, and at the time of the intersection B, the driver does not drive the stolen non-motor vehicle, so that the driver can obtain that the dirty point is between the intersection a and the intersection B, and a more accurate position of the dirty point is calculated by calculating the speed of the driver at the intersection a and the speed of the driver at the intersection B, and combining the time of the driver from the intersection a to the intersection B and the distance from the intersection a to the intersection B. The driver can drive the stolen non-motor vehicle to travel with other people, and the non-motor vehicle disappears after traveling to a certain place, so that the position of the gathering point of the group member is judged to be near the certain place.

It should be noted that, the

above steps

605 and 606 are optional, and in some possible embodiments, only the vehicle stealing behavior needs to be determined as a basis for judgment. Further, the

steps

605 and 606 may be combined with the embodiments corresponding to fig. 2 and 3.

In the steps, the trajectory of the vehicle stealing personnel (the driver with the vehicle stealing behavior) is obtained by continuously capturing the vehicle stealing personnel, and the moving trajectory of the vehicle stealing personnel can be visually displayed, so that the analysis and excavation of the group gathering points or the dirty selling points of the vehicle stealing personnel by the related police personnel are facilitated.

Optionally, referring to fig. 7, fig. 7 is a schematic flow chart of another detection method for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, as shown in fig. 7, including the following steps:

701. and acquiring the non-motor vehicle motion information and the personnel motion information in the tracking image.

702. And matching the characteristics of the non-motor vehicles with the characteristics of corresponding drivers according to the movement information of the non-motor vehicles and the personnel movement information to form the driving characteristics of the non-motor vehicles.

703. Inputting the driving characteristics of the non-motor vehicles into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles.

704. And detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information.

705. And judging whether the vehicle stealing behavior exists or not according to the detection result.

The motion information of the non-motor vehicle features may be speed or trajectory of the non-motor vehicle features, and the motion information of the face features may be speed or trajectory of the face features. In the image recognition technology, the feature to be recognized is made into a feature frame, for example, the non-motor vehicle feature and the human face feature are respectively made into a non-motor vehicle feature frame and a human face feature frame, the motion information of the non-motor vehicle feature can be embodied as the motion information of the non-motor vehicle feature frame, the motion information of the human face feature can be embodied as the motion information of the human face feature frame, the human face features in the preset range of the non-motor vehicle features can be obtained by obtaining the human face feature frame in the preset range of the non-motor vehicle features, this predetermined range may be a pixel radius of a non-motor vehicle feature box on the image, or may be a dimensional radius, such as, the face features within the radius of 100 pixels of the non-motor vehicle feature can be obtained, and for example, the face feature frame with the distance from the center of the face feature frame to the center of the non-motor vehicle feature frame being less than 200 pixels can be obtained. The face features with the motion information closest to or the same as the motion information of the non-motor vehicle features can be extracted through the motion information of the non-motor vehicle features and the motion information of the face features within the preset range of the non-motor vehicle features, and the face features are used as the face features owned by the driver, so that the driver can be matched. For example, assuming that the non-motor vehicle feature is B, the motion information of B is C, the motion information of face features a1, a2 and A3 exist in a preset range of B, and the motion information of a1, a2 and A3 is D1, D2 and D3 respectively, one closest to C is selected from D1, D2 and D3, if D1 is closest to C, the face feature corresponding to D1 is a1, a person having the face feature a1 is matched as a driver, and in the example, D C, D1, D2 and D3 may be a speed, a trajectory or a distance.

Optionally, the matching of the non-locomotive to the driver according to the motion information of the non-locomotive features and the motion information of the human face features in the preset range includes: forming a face set according to the motion information of the non-motor vehicle characteristics and the motion information of the face characteristics in a preset range; and matching drivers for the non-locomotive according to the face set.

Specifically, the motion information of the non-motor vehicle features may be a speed or a trajectory of the non-motor vehicle features, the motion information of the face features may be a speed or a trajectory of the face features, the face set is a face feature set within a preset range of the non-motor vehicle features, the face set may be identified by a specific number or letter label, such as the face set E, the face set 1, or the like, or may be identified by a feature value of the non-motor vehicle features, such as the non-motor vehicle features are B, the face set is identified as the face set B, or may be identified by a color of a feature frame on an image, such as a feature frame of one non-motor vehicle feature on the image is green, a feature frame of the face features within the preset range of the image is also identified as a green frame, and the face set may be identified by a green representative identifier G. In step 202, the non-motor vehicle features and the human face features are visually tracked, and a plurality of frames of images can be acquired. Through multi-frame images, motion information of non-motor vehicle characteristics and motion information of human face characteristics can be obtained through calculation, and human face characteristics with motion information similar to that of the non-motor vehicle characteristics are extracted within a preset range of the non-motor vehicle characteristics to form a human face set. The preset range may be a pixel radius or a size radius on the image, the motion information of the face feature is similar to the motion information of the non-motor vehicle feature, or may be a motion information threshold of the non-motor vehicle feature, for example, a speed threshold interval of the non-motor vehicle feature, and when the speed of the face feature falls into the speed threshold interval of the non-motor vehicle feature, the motion information of the face feature may be considered to be similar to the motion information of the non-motor vehicle feature. For example: the speed threshold interval of the non-motor vehicle features is 30 codes to 35 codes, when the speed of the human face features is 33 codes, the speed of the human face features can be considered to be similar to the speed of the non-motor vehicle features, and therefore the motion information of the human face features is considered to be similar to the motion information of the non-motor vehicle features. The speed threshold interval for the non-motor vehicle feature may be set by the speed of the non-motor vehicle feature. The motion information of the face features is similar to the motion information of the non-motor vehicle features, or the non-motor vehicle features and the track similarity threshold of the face features, and when the track similarity of the face features and the track similarity of the non-motor vehicle features reaches the track similarity threshold, the motion information of the face features can be considered to be similar to the motion information of the non-motor vehicle features. For example: the track similarity threshold of the non-motor vehicle features and the human face features can be set to be 80%, and when the track similarity of the human face features and the track similarity of the non-motor vehicle features exceeds 80%, the motion information of the human face features and the motion information of the non-motor vehicle features can be considered to be similar.

In some possible embodiments, a face set may be formed in each frame of image, multiple face sets may be obtained from multiple frames of images, and an intersection is obtained from the multiple face sets to obtain a final face set. The face features in the final face set obtained by intersection calculation are face features which always exist in a preset range of non-motor vehicle features in the process of visual tracking, and also can be said to be face features which keep a certain distance from the non-motor vehicle in the process of driving the non-motor vehicle. For example: assuming that 400 frames of images are acquired in the visual tracking, 4 frames of images including the 100 th frame, the 200 th frame, the 300 th frame and the 400 th frame are extracted to form 4 face sets E1, E2, E3 and E4 respectively, the E1 includes face features a1, a2, A3 and A4, the E2 includes face features a1, a2, A4 and A5, the E3 includes face features a1, a2, A5 and A6, the E4 includes face features a1, a2, A4 and A6, the final face set E including the face features a1 and a2 is obtained by intersecting the face features a1, E2, E3 and E4, and the driver can be matched in the final face set E, and at this time, the driver who has the most closely matched face features by comparing the motion information of the face features a1 and a2 with the motion information of the non-motor vehicle features.

Optionally, the motion information of the non-motor vehicle features includes speeds of the non-motor vehicle features, and the motion information of the human face features includes speeds of the human face features; according to the motion information of the non-motor vehicle characteristics and the motion information of the human face characteristics within a preset range, a human face set is formed, and the method comprises the following steps: comparing the speed of the non-motor vehicle characteristic with the speed of the human face characteristic to obtain a speed comparison result; and forming the face set according to the speed comparison result.

Specifically, the non-motor vehicle characteristics and the human face characteristics are visually tracked, and a multi-frame image can be obtained. Through the multi-frame images, the speed of the non-motor vehicle features and the speed of the human face features can be calculated, and the human face features with the speed similar to that of the non-motor vehicle features are extracted within the preset range of the non-motor vehicle features to form a human face set. The speed of the non-motor vehicle feature and the speed of the human face feature can be obtained by calculating position change and time of a central point of a middle feature frame of an image recognition technology in an image, a preset range can be a pixel radius or a size radius on the image, the speed of the human face feature is similar to the speed of the non-motor vehicle feature, and can be a speed threshold of the non-motor vehicle feature, for example, a speed threshold interval of the non-motor vehicle feature, the speed of the human face feature is compared with the speed threshold interval of the non-motor vehicle feature, and when the speed of the human face feature falls into the speed threshold interval of the non-motor vehicle feature, the speed of the human face feature is considered to be similar to the speed of: the speed threshold interval of the non-motor vehicle features is 30 codes to 35 codes, the speed of the human face feature A1 is assumed to be 33 codes, the speed of the human face feature A2 is 34 codes, the speed of the human face feature A3 is 29 codes, the speeds of the human face features A1 and A2 and the speeds of the non-motor vehicle features can be considered to be similar, so that the human face features A1 and A2 are recorded into a human face set, therefore, people obviously not driving the motor vehicle, such as people with the human face feature A3, only the human face features A1 and A2 in the human face set can be removed, the human face feature elements in the human face set are reduced, only the human face features A1 and A2 in the human face set need to be calculated during matching, and the calculated amount of the driver matched through the human face set is reduced. When the formed face set is an empty set, the face can be integrated into a non-empty face set by increasing the preset range of the non-motor vehicle features and/or expanding the speed threshold interval of the non-motor vehicle features.

Optionally, the motion information of the non-motor vehicle features includes tracks of the non-motor vehicle features, and the motion information of the human face features includes tracks of the human face features; forming a face set according to the motion information of the non-motor vehicle features and the motion information of the face features in a preset range, and the face set comprises the following steps: comparing the track of the non-motor vehicle characteristic with the track of the human face characteristic to obtain a track comparison result; and forming the face set according to the track comparison result.

Specifically, the track comparison result may be a track coincidence degree of the track of the human face feature and the track of the non-motor vehicle feature, for example, the track of the center of the feature frame of the human face feature in the continuous image and the track of the center of the feature frame of the non-motor vehicle feature in the continuous image are compared with each other at the same end point, and a ratio of a track coincidence length of the track of the human face feature and the track of the non-motor vehicle feature to a total track length of the track of the human face feature and the non-motor vehicle feature is calculated to obtain the coincidence degree, for example: assuming that the track length of the face feature is 49, the track length of the non-motor vehicle feature is 51, the overlap length is 45, and the overlap ratio is 45 × 2/(49+51) × 100% — 90%. If the contact ratio of 90% is greater than the track contact ratio threshold value of the track of the human face features and the track of the non-motor vehicle features, the human face features can be recorded into a human face set.

In addition, the trajectory comparison result may also be a comparison result of the trajectory of the human face feature and the trajectory equation of the trajectory of the non-motor vehicle feature, for example, a ratio or a difference of constants in the two trajectory equations may be used, and the closer the ratio is to 1, the more similar the two trajectory equations are, the closer the difference is to 0, the more similar the two trajectory equations are.

Optionally, matching the driver for the non-locomotive according to the face set includes: detecting the number of the human face features of the human face set, and judging whether a plurality of human face features exist in the human face set; and if a plurality of face features exist, selecting the face feature closest to the non-motor vehicle feature pixel from the plurality of face features, and determining the face feature as the face feature of the driver to obtain the driver of the non-motor vehicle.

Specifically, the pixel may be the smallest pixel interval between the center of the feature frame of the human face feature and the center of the feature frame of the non-motor vehicle feature in the image, or the smallest pixel interval between the border of the feature frame of the human face feature and the center of the feature frame of the non-motor vehicle feature.

In addition, if a plurality of face features do not exist in the face set, that is, the face features in the face set are unique, the unique face features in the face set can be directly considered to belong to the driver, and therefore the driver can be determined.

In some possible embodiments, if a plurality of face features exist in the face set, the face feature closest to the non-motor vehicle feature size may be selected from the plurality of face features and determined as the face feature of the driver, so as to obtain the non-motor vehicle driver. In addition, the face features with the highest image quality can be selected to be determined as the face features of the driver.

In the steps, the non-motor vehicle and the driver are matched, so that the only driver is matched for the non-motor vehicle, and the false detection caused by the participation of other people can be avoided.

Referring to fig. 8, fig. 8 is a schematic structural diagram of a detection apparatus for detecting a vehicle theft behavior of a non-motor vehicle according to an embodiment of the present invention, and as shown in fig. 8, the apparatus includes:

a first obtaining module 801, configured to obtain non-motor vehicle driving characteristics in a tracking image, where the non-motor vehicle driving characteristics include non-motor vehicle characteristics and driver characteristics matching the non-motor vehicle characteristics;

a clustering module 802, configured to input the driving characteristics of the non-motor vehicles into a clustering engine, and perform clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicles, where the historical snapshot information includes corresponding historical non-motor vehicle characteristics and historical driver characteristics;

a detection module 803, configured to detect whether there is a situation where the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information;

and the judging module 804 is used for judging whether the vehicle stealing behavior exists or not according to the detection result.

Optionally, as shown in fig. 8, the clustering module 802 is further configured to input the characteristics of the drivers into a clustering engine, and perform clustering to obtain historical snapshot information based on the characteristics of the drivers;

the detection module 803 is further configured to detect whether there is a situation where the non-motor vehicle characteristic corresponding to the same driver characteristic is different from the historical non-motor vehicle characteristic;

the determining module 804 is further configured to determine that the driver has a vehicle theft behavior if it is detected that the non-motor vehicle characteristics corresponding to the same driver characteristics are different from the historical non-motor vehicle characteristics.

Optionally, as shown in fig. 8, the clustering module 802 is further configured to input the non-motor vehicle characteristics into a clustering engine, and perform clustering to obtain historical snapshot information based on the non-motor vehicle characteristics;

the detection module 803 is further configured to detect whether there is a situation where the driver characteristics corresponding to the same non-motor vehicle are different from the historical driver characteristics;

the determining module 804 is further configured to determine that a vehicle theft behavior exists if it is detected that the driver characteristics corresponding to the same non-motor vehicle are different from the historical driver characteristics.

Optionally, as shown in fig. 9, the apparatus further includes:

a second obtaining module 807, configured to obtain peer information corresponding to a driver with a vehicle theft behavior after determining that the vehicle theft behavior exists, where the peer information includes peer times and peer information;

and the map construction module 808 is configured to construct a relationship map of the driver with the vehicle theft behavior according to the peer information, where the relationship map includes the number of peers and peer information, and the relationship map is used to show the peer relationship between the peer and the driver with the vehicle theft behavior.

Optionally, as shown in fig. 10, the apparatus further includes:

a comparison module 809, configured to compare the peer information with a predecessor information base, where the predecessor information base includes predecessor information of car stealing personnel;

and the adjusting module 810 is configured to adjust the relationship map according to the comparison result to obtain a suspect relationship map with a car stealing behavior, where the suspect relationship map includes the number of times of the same trip and corresponding information of the previous department of the car stealing personnel.

Optionally, as shown in fig. 11, the apparatus further includes:

the third obtaining module 811 is configured to continuously take a snapshot of a driver with a vehicle theft behavior after determining that the vehicle theft behavior exists, and obtain corresponding snapshot information;

and a track module 812, configured to form a track for the driver with the vehicle theft behavior according to the snapshot information, where the track is used to analyze a place where the driver with the vehicle theft behavior appears.

Optionally, as shown in fig. 12, the first obtaining module 801 includes:

an acquiring unit 8011, configured to acquire non-motor vehicle motion information and person motion information in the tracking image, where the non-motor vehicle motion information includes a non-motor vehicle feature, and the person motion information includes a driver feature;

a matching unit 8012, configured to match corresponding driver characteristics for the non-motor vehicle characteristics according to the non-motor vehicle motion information and the person motion information, so as to form non-motor vehicle driving characteristics.

It should be noted that the detection apparatus for a vehicle theft behavior of a non-motor vehicle provided in the embodiment of the present invention may be applied to a detection device for a vehicle theft behavior of a non-motor vehicle, for example: the device can detect the stealing behavior of the non-motor vehicles by the community camera, the traffic camera, the computer, the server and the like.

The traffic violation supervision device for the non-motor vehicle provided by the embodiment of the invention can realize each implementation mode in the method embodiments of fig. 1 to 8 and corresponding beneficial effects, and is not repeated herein for avoiding repetition.

Referring to fig. 13, fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 13, including: a memory 1302, a processor 1301 and a computer program stored on the memory and executable on the processor, wherein:

the processor 1301 is used to call the computer program stored in the memory 1302, and performs the following steps:

detecting whether the driving characteristics of the non-motor vehicle are different from the corresponding historical snapshot information or not;

Optionally, the inputting, performed by the processor 1301, the driving characteristics of the non-motor vehicle into a clustering engine, and clustering to obtain historical snapshot information based on the driving characteristics of the non-motor vehicle, includes:

inputting the characteristics of drivers into a clustering engine, and clustering to obtain historical snapshot information based on the characteristics of the drivers;

the detection performed by processor 1301 whether there is a situation where the driving characteristics of the non-motor vehicle are not the same as the corresponding historical snap-shot information includes:

detecting whether the non-motor vehicle characteristics corresponding to the same driver characteristics are different from the historical non-motor vehicle characteristics or not;

the determining, performed by the processor 1301, whether a vehicle theft behavior exists according to the detection result includes:

and if the non-motor vehicle characteristics corresponding to the same driver characteristics are different from the historical non-motor vehicle characteristics, judging that the driver has the vehicle stealing behavior.

inputting the non-motor vehicle characteristics into a clustering engine, and clustering to obtain historical snapshot information based on the non-motor vehicle characteristics;

detecting whether the condition that the characteristics of drivers corresponding to the same non-motor vehicle are different from the historical characteristics of the drivers exists or not;

and if the detected driver characteristics corresponding to the same non-motor vehicle are different from the historical driver characteristics, judging that the vehicle stealing behavior exists.

Optionally, the processor 1301 further performs the following steps:

after judging that the vehicle stealing behavior exists, acquiring peer information corresponding to a driver with the vehicle stealing behavior, wherein the peer information comprises peer times and peer information;

and constructing a relation map of the driver with the vehicle stealing behavior according to the peer information, wherein the relation map comprises the number of the peers and the information of the peers, and the relation map is used for displaying the peer relation between the peers and the driver with the vehicle stealing behavior.

Optionally, the processor 1301 further performs the following steps:

comparing the information of the fellow passengers with a presidential passenger library, wherein the presidential passenger library comprises the information of the presidential passengers who steal the vehicle;

and adjusting the relation map according to the comparison result to obtain a suspect relation map with the vehicle stealing behavior, wherein the suspect relation map comprises the number of times of the same trip and corresponding foreadministrative information of the vehicle stealing personnel.

Optionally, the processor 1301 further performs the following steps:

after the vehicle stealing behavior is judged to exist, continuously taking a snapshot of the driver with the vehicle stealing behavior, and acquiring corresponding snapshot information;

and forming a track aiming at the driver with the vehicle stealing behavior according to the snapshot information, wherein the track is used for analyzing the place where the driver with the vehicle stealing behavior appears.

Optionally, the acquiring of the non-motor vehicle driving feature in the tracking image performed by the processor 1301 includes:

acquiring non-motor vehicle motion information and personnel motion information in a tracking image, wherein the non-motor vehicle motion information comprises non-motor vehicle characteristics, and the personnel motion information comprises driver characteristics;

and matching the characteristics of the non-motor vehicles with the characteristics of corresponding drivers according to the non-motor vehicle movement information and the personnel movement information to form the driving characteristics of the non-motor vehicles.

It should be noted that the electronic device provided in the embodiment of the present invention may be applied to a detection device for a vehicle theft behavior of a non-motor vehicle, for example: the device can detect the stealing behavior of the non-motor vehicles by the community camera, the traffic camera, the computer, the server and the like.

The electronic device provided by the embodiment of the present invention can implement each implementation manner in the method embodiments of fig. 1 to 7, and corresponding beneficial effects, and are not described herein again to avoid repetition.

The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program realizes each process of the embodiment of the method for supervising the traffic violation of the non-motor vehicle, which is provided by the embodiment of the invention, and can achieve the same technical effect, and is not repeated here in order to avoid repetition.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims

1. A detection method for the vehicle stealing behavior of a non-motor vehicle is characterized by comprising the following steps:

2. The method of claim 1, wherein the inputting the non-motor driving characteristics into a clustering engine, clustering results in historical snap-shots based on the non-motor driving characteristics, comprises:

the detecting whether the non-motor vehicle driving characteristics are different from the corresponding historical snapshot information includes:

the judging whether the vehicle stealing behavior exists or not according to the detection result comprises the following steps:

3. The method of claim 1, wherein the inputting the non-motor driving characteristics into a clustering engine, clustering results in historical snap-shots based on the non-motor driving characteristics, comprises:

4. The method of claim 1, wherein the method further comprises:

5. The method of claim 4, wherein the method further comprises:

6. The method of claim 1, wherein the method further comprises:

7. The method of any one of claims 1 to 6, wherein the acquiring non-motor vehicle driving features in the tracking image comprises:

8. A detection device for detecting the vehicle stealing behavior of a non-motor vehicle is characterized by comprising:

9. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for detecting the theft behavior of a non-motor vehicle according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, having a computer program stored thereon, which, when being executed by a processor, implements the steps of the method for detecting a theft behavior of a non-motor vehicle according to any one of claims 1 to 7.