CN113269060A - Vehicle illegal behavior review method and device, electronic equipment and storage medium - Google Patents

Abstract

The invention provides a vehicle illegal behavior review method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring vehicle illegal behavior information to be checked, wherein the vehicle illegal behavior information comprises illegal types; determining a corresponding illegal action review algorithm according to the illegal type; and determining a review result of the illegal action according to the illegal action review algorithm and the vehicle illegal action information. By implementing the method and the device, the corresponding review algorithm can be automatically called to realize automatic review, the review efficiency is improved, the manual review burden is reduced, the labor cost is reduced, the subjective factors during manual review can be avoided, and the review accuracy is improved.

Description

Vehicle illegal behavior review method and device, electronic equipment and storage medium

Technical Field

The invention relates to the field of computer image processing, in particular to a vehicle illegal behavior review method and device, electronic equipment and a storage medium.

Background

With the increase of urban vehicles, the front-end equipment is continuously updated, and the captured illegal behavior data is continuously increased, but in the illegal data, the camera changes along with the change of time, the complexity of the road environment is increased, and the data of non-motor vehicles, pedestrians and special vehicles are shot by mistake, so that a large amount of misjudgment data is generated. In the related art, in order to eliminate misjudged data, a large amount of manual work is required to be arranged for manual examination, the work task is heavy, a large amount of repeated work exists, and meanwhile, the phenomenon of a double-examination error is easy to occur.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for reviewing vehicle illegal activities, an electronic device, and a storage medium, so as to solve the defects that in the prior art, in order to remove misjudged data, a large amount of manual work needs to be provided for manual review, a work task is heavy, a large amount of repetitive work exists, and a review error is easily caused.

According to a first aspect, an embodiment of the present invention provides a vehicle illegal behavior review method, including the following steps: acquiring vehicle illegal behavior information to be checked, wherein the vehicle illegal behavior information comprises illegal types; determining a corresponding illegal action review algorithm according to the illegal type; and determining a review result of the illegal action according to the illegal action review algorithm and the vehicle illegal action information.

Optionally, the vehicle illegal activity information includes an image acquisition device number for acquiring vehicle illegal activities, a plurality of pieces of vehicle driving image information to be checked, and illegal vehicle license plate number information, and the determining a review result of the illegal activities according to the illegal activity review algorithm and the vehicle illegal activity information includes: extracting license plate number information in the vehicle driving image information; when the extracted license plate information is consistent with the illegal vehicle license plate information, determining lane line information of the illegal action according to the image acquisition equipment number; and carrying out illegal behavior judgment on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain a review result of illegal behaviors.

Optionally, the illegal type is that the vehicle is driven without a guide line, and the illegal behavior determination is performed on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain a review result of the illegal behavior, including: determining a vehicle driving path according to a plurality of pieces of vehicle driving image information to be checked; when the driving path of the vehicle and the regular line in the lane line information have an intersection point, the review result is that the vehicle does not effectively run according to the guide line; or

When the illegal type is that the pressing line runs, the illegal behavior judgment is carried out on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain the review result of the illegal behavior, and the method comprises the following steps: determining the relationship between the diagonal coordinates of the vehicle and the lane lines according to the information of the vehicle driving image to be audited; and when the diagonal coordinates of the vehicle are positioned at the two ends of the lane line, the rechecking result shows that the vehicle is effective in line pressing running.

Optionally, when the illegal type is reverse driving, the illegal behavior determination is performed on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain a review result of the illegal behavior, including: determining the driving direction of the vehicle according to the information of the plurality of vehicle driving images to be audited; and when the driving direction of the vehicle is opposite to the direction of the lane line in the lane information, the review result shows that the vehicle runs reversely effectively.

Optionally, the determining the review result of the illegal act according to the illegal act review algorithm and the vehicle illegal act information includes: determining lane attributes of the illegal action according to the image acquisition equipment number, wherein the lane attributes comprise a traffic control lane, a no-parking lane and a single-way lane of the target vehicle type; and when the lane attribute of the illegal action is inconsistent with the lane attribute in the vehicle illegal action information to be audited, the review result is invalid.

Optionally, the vehicle illegal activity information further includes illegal vehicle license plate number information, the lane attribute is a restricted lane of a target vehicle type, and the method further includes: when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information and vehicle type information in the vehicle driving image information are extracted; and when the license plate information is consistent with the license plate information of the illegal vehicle and the vehicle type information is consistent with the target vehicle type, the review result is that the illegal action is effective.

Optionally, the vehicle illegal activity information further includes illegal vehicle license plate number information, and the lane attribute is a prohibited parking lane, further including: when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information in the vehicle driving image information is extracted; when the license plate information is consistent with the illegal vehicle license plate information, judging whether a vehicle corresponding to the license plate information is in a forbidden area in a plurality of pieces of vehicle driving image information; and when the vehicle corresponding to the license plate number information is in the forbidden stop area in the plurality of pieces of vehicle driving image information, the review result is that the illegal action is effective.

Optionally, the vehicle illegal activity information further includes illegal vehicle license plate number information, the lane attribute is a single-lane, and the method further includes: when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information in the vehicle driving image information is extracted; when the license plate information is consistent with the license plate information of the illegal vehicle, positioning a target illegal vehicle; determining the vehicle type of the target illegal vehicle according to a target model; and when the vehicle type is not the target vehicle type, the review result is that the illegal action is effective.

Optionally, the vehicle illegal activity information includes a plurality of pieces of vehicle driving image information to be checked and illegal vehicle license plate number information, and when the illegal type is red light violation, the determining a review result of the illegal activity according to the illegal activity review algorithm and the vehicle illegal activity information includes: extracting license plate number information in the vehicle driving image information; when the extracted license plate information is consistent with the illegal vehicle license plate information, judging whether the traffic light is a red light currently or not according to the vehicle driving image information; when the red light and the green light are red lights at present, judging whether the vehicle position corresponding to the license plate number information exceeds a detection area or not; and when the vehicle position corresponding to the license plate number information exceeds the detection area, the review result is valid.

Optionally, the vehicle illegal behavior information includes a plurality of pieces of vehicle driving image information to be checked and illegal vehicle license plate information, and the determining a review result of the illegal behavior according to the illegal behavior review algorithm and the vehicle illegal behavior information includes: extracting license plate number information in the vehicle driving image information; when the extracted license plate information is consistent with the illegal vehicle license plate information, vehicle detection is carried out according to a target vehicle positioning model to obtain a vehicle image corresponding to the illegal vehicle license plate information; according to the target person positioning model, detecting the position of a person in the vehicle image to obtain a driver image; inputting the driver image into a human behavior classification model to obtain a classification result; and determining a review result of the illegal action according to the classification result.

According to a second aspect, an embodiment of the present invention provides a vehicle illegal behavior review device, including: the information acquisition module is used for acquiring vehicle illegal behavior information to be checked, wherein the vehicle illegal behavior information comprises illegal types; the review algorithm determining module is used for determining a corresponding review algorithm of the illegal action according to the illegal type; and the review result determining module is used for determining the review result of the illegal action according to the illegal action review algorithm and the vehicle illegal action information.

According to a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for reviewing vehicle illegal activities according to the first aspect or any of the embodiments of the first aspect when executing the program.

According to a fourth aspect, an embodiment of the present invention provides a storage medium having computer instructions stored thereon, where the instructions are executed by a processor to implement the steps of the vehicle illegal behavior review method according to the first aspect or any of the embodiments of the first aspect.

The technical scheme of the invention has the following advantages:

according to the vehicle illegal behavior review method/device provided by the embodiment of the invention, the corresponding illegal behavior review algorithm is determined according to the illegal type in the vehicle illegal behavior information to be reviewed, the review result of the illegal behavior is determined according to the corresponding illegal behavior review algorithm, and aiming at a large amount of misjudgment data, the corresponding review algorithm can be automatically called to realize automatic review, so that the review efficiency is improved, the manual review burden is reduced, the labor cost is reduced, subjective factors in human review can be avoided, and the review accuracy is improved.

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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a flowchart illustrating a detailed example of a method for reviewing vehicle illegal activities according to an embodiment of the present invention;

FIG. 2 is a schematic block diagram illustrating an exemplary embodiment of a vehicle illegal activity review device according to the present invention;

fig. 3 is a schematic block diagram of a specific example of an electronic device in the embodiment of the present invention.

Detailed Description

The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. 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.

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two elements may be directly connected or indirectly connected through an intermediate medium, or may be communicated with each other inside the two elements, or may be wirelessly connected or wired connected. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

The embodiment provides a method for reviewing vehicle illegal activities, as shown in fig. 1, which includes the following steps:

s101, obtaining vehicle illegal behavior information to be checked, wherein the vehicle illegal behavior information comprises illegal types;

illustratively, the vehicle illegal action information to be checked can be obtained by the front-end camera, and the vehicle illegal action information can include the equipment number, the license plate number information, the illegal time, the illegal place, at least one piece of illegal picture information, the illegal type, the vehicle coordinate, the license plate coordinate and the like of the front-end camera, wherein the illegal type represents the initially determined illegal action type, including driving in the wrong direction, driving without a guide line, running a red light, pressing a line, running in an illegal way, driving with distraction, not fastening a safety belt, getting on the road in violation and the like, different illegal types can be distinguished by different numbers, for example, the number of going in the wrong direction is 1301, the number of driving without a guide line is 1208, the pressing line is 1345, the number of running a red light is 1625, the number of a safety belt not fastened is 6011, the number of driving with distraction is 1223, the number of the target vehicle type on the restricted lane is 1344, the number of two-way lane in one-way is 7074, forbid parking lane the vehicle parking number 13441 or 13451, etc. The embodiment does not limit the types of the vehicle illegal behavior information and the illegal types, and the skilled person can determine the information according to the needs.

The specific acquired vehicle illegal behavior information to be audited may include:

{ "Violation _ xh": 1201120001528031, # device number

＂Xh＂：＂＂，

＂VioType＂：＂Violation＂，

"Hphm": "jin FAN 788" and # license plate number

＂Hpzl＂：＂02＂，

"Wfsj": "2020-11-2611: 38: 59', and # illegal time

"Wfdd": "201050017320", # illegal site numbering

"Wfdz": ' Jinqi road and Changsheng road crossing west to east ', ' illegal address

# illegal behavior code

＂Wfxw＂：＂1208＂，

＂Clsd＂：0，

＂Clxs＂：0，

＂Sjly＂：＂1＂，

＂Sfqj＂：＂00＂，

＂Qjys＂：0，

＂Tztp1＂：＂＂，

＂Tztp2＂：＂＂，

# illegal Picture 1

＂Zjwj1＂：＂http：//172.30.2.9/weifa/2020/11/26/201050017320/baf906ae541945909febe6e6c8ccee4b.jpg＂，

# illegal Picture 2

＂Zjwj2＂：＂http：//172.30.2.9/weifa/2020/11/26/201050017320/e0a118a22c6943899e0afb6f7ba41d01.jpg＂，

# illegal Picture 3

＂Zjwj3＂：＂http：//172.30.2.9/weifa/2020/11/26/201050017320/1ccfc21b165042ba83a2d51691fb15ac.jpg＂，

# illegal Picture 4

＂Zjwj4＂：＂＂，

＂Shbj＂：＂00＂，

＂Tblhy＂：0，

＂Cjjg＂：＂121200000000＂，

＂Scbj＂：0，

＂Cdbh＂：1，

＂Zqmj＂：＂

＂，

＂Cjyh＂：＂

＂，

＂Cjsj＂：＂2020－11－26 11：38：59＂，

＂Csbl＂：0，

＂Fxbh＂：＂02＂，

＂Cscs＂：0，

＂Qjjl＂：0，

＂Zdxs＂：0，

＂Sbbh＂：＂121200000000099998＂，

＂Bdbj＂：0，

＂Sbbj＂：1，

＂Splj＂：＂http：//10.112.93.2：7777/hikvision/ch6/starttime＝20201126T113855Z/endtime＝20201126T113905Z/1.mp4＂，

＂AiShbj＂：＂00＂，

＂AiClbj＂：＂00＂

# vehicle coordinates 1

“Clzb1”：”＊＊，＊＊，＊＊，＊＊”

# vehicle coordinates 2

“Clzb2”：”＊＊，＊＊，＊＊，＊＊”

# vehicle coordinates 3

“Clzb3”：”＊＊，＊＊，＊＊，＊＊”

# license plate coordinate 1

“CPzb1”：”＊＊，＊＊，＊＊，＊＊”

# license plate coordinate 2

“CPzb2”：”＊＊，＊＊，＊＊，＊＊”

# license plate coordinate 3

“CPzb3”：”＊＊，＊＊，＊＊，＊＊”}

S102, determining a corresponding illegal behavior review algorithm according to the illegal category;

for example, according to the type of the law violation, the corresponding law violation review algorithm may be determined by automatically invoking a pre-stored corresponding law violation review algorithm when the type of the violation in the vehicle law violation information is detected. For example, when the number of the detected illegal category is 1301, a review algorithm corresponding to the reverse run is called. The embodiment does not limit the way of determining the corresponding illegal action review algorithm according to the type of the illegal action, and the skilled person in the art can determine the method according to the needs.

S103, determining a review result of the illegal action according to the illegal action review algorithm and the vehicle illegal action information.

Illustratively, taking the illegal category as a retrograde (the detected illegal category number is 1301) as an example, the review algorithm corresponding to the retrograde may be to extract the image acquisition device number therein, and the system database stores the configuration information of the drawn line of the monitored area corresponding to the image acquisition device number in advance. The database information can be matched through the image acquisition equipment numbers, and the line drawing configuration information corresponding to the monitoring area of the current image acquisition equipment numbers is obtained, so that the lane line direction and the lane detection area information are obtained.

Then extracting license plate coordinates in the vehicle illegal action information, intercepting a local picture of the license plate coordinates to perform license plate number recognition, and checking whether license plate characters in the picture are the same as license plate number results in the vehicle illegal action information; if the difference is not the same, returning a reverse result to be invalid; if the license plate coordinates are the same, calculating the vehicle driving direction according to the license plate coordinates corresponding to the multiple illegal events, judging whether the vehicle driving direction is opposite to the lane line direction, further judging whether the vehicle driving direction is illegal, if the vehicle driving direction is opposite to the lane line direction, the review result of the retrograde motion is valid, and if the vehicle driving direction is the same, the review result of the retrograde motion is invalid. For different illegal activities, the review algorithms are different, which is not limited in this embodiment and can be determined by those skilled in the art as needed. Tests prove that the accuracy of the review result can reach 95% or more for different illegal types.

The review result output format of the illegal activity can be expressed as:

json{

the # decision, valid (indeed an illegal event): 1, invalid: 0

‘flag’：0，

jsonType：’AI’}

According to the vehicle illegal behavior review method provided by the embodiment, the corresponding illegal behavior review algorithm is determined according to the illegal type in the vehicle illegal behavior information to be reviewed, the review result of the illegal behavior is determined according to the corresponding illegal behavior review algorithm, and aiming at a large amount of misjudged data, the corresponding review algorithm can be automatically called to realize automatic review, so that the review efficiency is improved, the manual review burden is reduced, the labor cost is reduced, subjective factors in manual review can be avoided, and the review accuracy is improved.

As an optional implementation manner of this embodiment, the vehicle illegal activity information includes an image acquisition device number for acquiring a vehicle illegal activity, a plurality of pieces of vehicle driving image information to be checked, and illegal vehicle license plate number information, and determines a review result of the illegal activity according to an illegal activity review algorithm and the vehicle illegal activity information, including:

firstly, license plate number information in vehicle driving image information is extracted;

for example, the manner of extracting the license plate number information in the vehicle driving image information may be to input the vehicle driving image information into a pre-trained license plate number recognition neural network, or to pre-process the image, and adopt license plate positioning, segmentation, character segmentation, and character recognition. By the license plate recognition mode, the accuracy rate of license plate recognition can be higher than 98%. The embodiment does not limit the manner of extracting the license plate number information in the vehicle driving image information, and a person skilled in the art can determine the license plate number information according to needs.

Secondly, when the extracted license plate information is consistent with the license plate information of the illegal vehicle, the lane line information of the illegal action is determined according to the serial number of the image acquisition equipment;

illustratively, the image acquiring device number is number information that matches each monitored road section information one-to-one, for example, the image acquiring device number is 1201120001528031, then the corresponding monitored road section information in the system is XX road and XX road information, including lane attribute, lane line direction, lane line type and other line drawing configuration information. Since the image acquisition device may not directly acquire the lane line information from the image due to the problem of the blocking object or the shooting angle, in this embodiment, according to the number of the image acquisition device, the manner of determining the lane line information where the illegal action occurs may be to match the monitored road section information corresponding to the number of the image acquisition device in the system, so as to extract the lane line information from the monitored road section information.

And thirdly, carrying out illegal behavior judgment on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to an illegal behavior review algorithm to obtain a review result of the illegal behaviors.

Exemplarily, the embodiment is described by taking an illegal type as driving without a guide line (the number of the detected illegal type is 1208), and the illegal behavior determination is performed on the lane line information and the multiple pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm, and the manner of obtaining the review result of the illegal behavior may be to determine the vehicle driving route according to the multiple pieces of vehicle driving image information to be checked, and specifically includes: compared with the mode of determining the vehicle driving path based on the video band, the embodiment can judge the illegal time through a plurality of pictures, reduces the storage space and reduces the processing amount.

When the driving path of the vehicle and the regular line in the lane line information have an intersection point, the review result is that the vehicle does not effectively run according to the guide line; and when the driving path of the vehicle does not have an intersection point with the regular line in the lane line information, the review result is that the vehicle does not run along the guide line and is invalid. For different types of law violation, the review algorithms are different, which is not limited in this embodiment and can be determined by those skilled in the art as needed.

The method for reviewing the illegal vehicle behaviors, provided by the embodiment, comprises the steps of firstly extracting license plate number information in image information, and executing subsequent auditing when the license plate number information is consistent with the license plate number information of the illegal vehicle, so that redundant judging processes are executed when the license plate number information is not consistent with the license plate number information of the illegal vehicle, the calculated amount of review is reduced, in addition, the lane line information of the illegal vehicle is determined according to the serial number of the image acquisition equipment, the problem that the image acquisition equipment cannot directly acquire accurate lane line information from an image due to the deviation problem of shielding objects or shooting angles can be avoided, and the accuracy of reviewing the illegal vehicle behaviors is improved.

As an optional implementation manner of this embodiment, when the illegal type is running on a pressing line, the illegal behavior determination is performed on the lane line information and the multiple pieces of driving image information of the vehicle to be checked according to the illegal behavior review algorithm to obtain the review result of the illegal behavior, which includes: determining the relationship between the diagonal coordinates of the vehicle and the lane lines according to the driving image information of the vehicle to be audited; when the diagonal coordinates of the vehicle are at two ends of the lane line, the rechecking result shows that the vehicle is effective in line pressing and running.

Exemplarily, when the illegal type is line pressing driving (the detected illegal type number is 1345), the method for determining the driving path of the vehicle according to the plurality of pieces of driving image information of the vehicle to be checked may be to extract the coordinate information of the vehicle in the driving image information of the vehicle to be checked, determine whether the diagonal coordinates of the vehicle are at two ends of the lane line, and when the diagonal coordinates of the vehicle are at two ends of the lane line, the review result is that the line pressing driving of the vehicle is effective; and when the diagonal coordinates of the vehicle are not positioned at the two ends of the lane line, the rechecking result indicates that the vehicle is invalid to press the line for driving.

As an optional implementation manner of this embodiment, when the illegal type is reverse driving (the number of the detected illegal type is 1301), performing illegal behavior determination on the lane line information and the multiple pieces of driving image information of the vehicle to be checked according to an illegal behavior review algorithm to obtain a review result of the illegal behavior, including: determining the driving direction of the vehicle according to the information of the plurality of vehicle driving images to be audited; and when the driving direction of the vehicle is opposite to the direction of the lane line in the lane information, the review result shows that the vehicle runs reversely and effectively.

For example, the manner of determining the driving direction of the vehicle according to the plurality of pieces of driving image information of the vehicle to be checked may be to calculate license plate coordinates or vehicle coordinates in the plurality of pieces of driving image information of the vehicle to be checked according to the time sequence of obtaining the driving images of the vehicle, so as to obtain the driving direction of the vehicle. When the driving direction of the vehicle is opposite to the direction of the lane line in the lane information, the review result shows that the vehicle runs in the reverse direction effectively; and when the driving direction of the vehicle is the same as the direction of the lane line in the lane information, the review result is that the vehicle is invalid in reverse driving.

As an optional implementation manner of this embodiment, the vehicle illegal activity information includes an image acquisition device number for acquiring the vehicle illegal activity and a plurality of pieces of vehicle driving image information to be checked, and the determining of the review result of the illegal activity according to the illegal activity review algorithm and the vehicle illegal activity information includes: determining lane attributes of illegal behaviors according to the image acquisition equipment number, wherein the lane attributes comprise a traffic control lane of a target vehicle type, a no-parking lane and a one-way lane; and when the attribute of the lane in which the illegal act occurs is inconsistent with the attribute of the lane in the vehicle illegal act information to be audited, the review result is invalid for the illegal act.

Illustratively, the system database stores beforehand the arrangement information of the drawn lines of the monitored area corresponding to the image capturing apparatus number. The lane attribute of the illegal action can be determined by matching the image acquisition equipment number with the database information according to the image acquisition equipment number to obtain the drawn line configuration information corresponding to the monitoring area of the current image acquisition equipment number, so as to obtain the lane attribute. The lane attributes comprise a target vehicle type traffic control lane, a no-parking lane, a single lane and the like, wherein the target vehicle type traffic control lane can represent the lane or the road section prohibits the target vehicle type from driving, such as a large truck no-driving lane/road section; a prohibited parking lane may indicate that the lane or the road segment or a particular location prohibits parking; a single-lane may characterize the lane or the road segment belongs to a single-lane for a certain period of time, or the lane is a single-lane for the entire period of time.

When the lane attribute of the illegal action determined according to the image acquisition equipment number is inconsistent with the lane attribute in the vehicle illegal action information to be checked, the illegal action recorded in the vehicle illegal action information to be checked is not generated, and therefore the review result is invalid. For example, when the lane attribute in the vehicle illegal activity information to be reviewed is a prohibited-driving lane of the large truck, but the lane attribute determined according to the image acquisition device number and having the illegal activity is not the prohibited-driving lane of the large truck, it is determined that the initial illegal activity is judged to be wrong, and the review result is that the illegal activity of the large truck on the road is invalid.

As an optional implementation manner of this embodiment, the vehicle illegal activity information further includes illegal vehicle license plate information, and the lane attribute is a restricted lane of the target vehicle type, further including: when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information and vehicle type information in the vehicle driving image information are extracted; and when the license plate information is consistent with the license plate information of the illegal vehicle and the vehicle type information is consistent with the target vehicle type, the review result is that the illegal action is effective.

Exemplarily, when it is detected that the illegal type is the target vehicle type running on the restricted lane of the target vehicle type, that is, the illegal type number is 1344, license plate number information and vehicle type information in the vehicle driving image information are extracted, and the license plate number information and the vehicle type information may be obtained by capturing the vehicle driving image information according to license plate coordinates and vehicle coordinates, and inputting the captured license plate image or vehicle image into a pre-trained license plate number recognition model or vehicle type recognition model. The embodiment does not limit the manner of extracting the license plate number information and the vehicle type information in the vehicle driving image information, and a person skilled in the art can determine the information as required.

When the license plate information is inconsistent with the illegal vehicle license plate information in the illegal vehicle behavior information to be checked, the illegal vehicle license plate information to be checked is inaccurate, and the review result is invalid for illegal behaviors; when the license plate information is consistent with the license plate information of the illegal vehicle in the illegal action information of the vehicle to be checked, but the vehicle type information is inconsistent with the target vehicle type, the fact that the running of the vehicle corresponding to the license plate information on the restricted lane of the target vehicle type does not belong to illegal action is shown, and the review result is that the illegal action is invalid; when the license plate information is consistent with the license plate information of the illegal vehicle in the illegal vehicle behavior information to be checked, and the vehicle type information is consistent with the target vehicle type, it is indicated that the running of the target vehicle type vehicle corresponding to the license plate information on the restricted traffic lane of the target vehicle type really belongs to the illegal behavior, and the review result is that the illegal behavior is effective.

For example, the target vehicle type restricted lane is a section where a large truck is prohibited from driving, when the target vehicle type restricted lane is subjected to review, firstly, a plurality of license plate coordinates of a plurality of pieces of vehicle driving image information to be reviewed are extracted, the number of the plurality of pieces of vehicle driving image information to be reviewed can be three, a local picture of the license plate coordinates is captured, license plate number recognition is performed, and whether license plate characters in the picture are the same as a front-end equipment recognition result is checked; if the difference is not the same, returning to the pre-examination invalidation; if the vehicle coordinates are the same, reading the vehicle coordinates, extracting a vehicle screenshot, and judging whether the vehicle type is a large truck, if so, the prejudging is effective, and if not, the prejudging is invalid.

As an optional implementation manner of this embodiment, the vehicle illegal activity information further includes illegal vehicle license plate information, and the lane attribute is a prohibited parking lane, further including:

firstly, when it is detected that the illegal type is illegal parking lane vehicle parking, that is, the illegal type number is 13441 or 13451 (the representation forms of the forbidden regions corresponding to the two numbers are different, for example, 13441 represents that the forbidden region is a specific region of yellow cross grid, and 13451 represents that the forbidden region is the whole lane), whether the lane attribute of the illegal action is consistent with the lane attribute in the illegal action information of the vehicle to be checked is judged, and when the lane attribute is consistent with the lane attribute, license plate number information in the driving image information of a plurality of vehicles is extracted; the manner of extracting the license plate number information in the vehicle driving image information is shown in the content of extracting the license plate number information in the above embodiment, and is not described herein again.

Secondly, when the license plate information is consistent with the license plate information of the illegal vehicle, judging whether the vehicle corresponding to the license plate information is in a forbidden parking area in the driving image information of a plurality of vehicles; and when the vehicle corresponding to the license plate number information is in the forbidden stop area in the driving image information of a plurality of vehicles, the result of the review is effective.

For example, the no-parking area may represent that parking is prohibited in a specific area, or may represent that the lane is a no-parking lane, and the setting of the no-parking area is not limited in this embodiment, and may be determined by a person skilled in the art as needed. The image information of the multiple vehicle driving can be image information shot at different time, the quantity of the image information of the vehicle driving can be determined according to the time interval of the shooting and the parking time threshold value, and the parking time threshold value represents that the parking time exceeds the threshold value, so that illegal parking can be judged. For example, when the parking time threshold is 1 minute and the photographing time interval is 20S sheets, the number of pieces of vehicle driving image information may be 3 sheets. When the vehicles corresponding to the license plate information are in the forbidden parking areas in the multiple pieces of vehicle driving image information, the review result is valid; and when the vehicle corresponding to the license plate number information is not in the forbidden stop area in the driving image information of a plurality of vehicles, the review result is invalid for illegal behaviors.

As an optional implementation manner of this embodiment, the vehicle illegal activity information further includes illegal vehicle license plate information, and the lane attribute is a single-lane, further including:

firstly, when detecting that the illegal type is two-way driving of a single lane, namely the illegal type number is 7074, judging whether the lane attribute of the illegal action is consistent with the lane attribute in the illegal action information of the vehicle to be checked, if so, extracting license plate number information in the vehicle driving image information, judging whether the license plate number information is consistent with the license plate number information of the illegal vehicle, and when the license plate number information is consistent with the license plate number information of the illegal vehicle, positioning the target illegal vehicle according to the license plate number information in the illegal action information of the vehicle to be checked.

Illustratively, the one-way lane characterization includes that the lane or the road segment belongs to the one-way lane for a certain period of time, or that the lane is a one-way road throughout the period of time. When the one-way lane represents that the lane is a one-way lane in the whole time period, the mode of judging whether the lane attribute of the illegal behavior is consistent with the lane attribute in the vehicle illegal behavior information to be checked can be that whether the lane attribute information is a one-way lane is judged by matching the corresponding lane attribute information in the database according to the serial number of the image acquisition equipment. When the one-way lane represents the lane or the road section belongs to the one-way lane in a certain time period, the mode of judging the lane attribute of the illegal action further comprises the step of judging whether the time of the illegal action is within a one-way limit time range, such as (7: 00-19: 00), and if not, the review result is invalid.

When the attribute of the lane where the illegal action occurs is consistent with the attribute of the lane in the illegal action information of the vehicle to be checked, namely the attribute of the lane where the illegal action occurs at present really belongs to a single lane, license plate number information in the vehicle driving image information is extracted, whether the license plate number information is consistent with the license plate number information of the illegal vehicle in the illegal action information of the vehicle to be checked is judged, and when the detected license plate number information is inconsistent with the license plate number information of the illegal vehicle in the illegal action information of the vehicle to be checked, a review result is invalid for the illegal action; when the detected vehicle license plate number information is consistent with the illegal vehicle license plate number information in the vehicle illegal action information to be checked, a target illegal vehicle is positioned in the vehicle driving image information further according to the license plate number information in the vehicle illegal action information to be checked, and the mode of positioning the target illegal vehicle can be that the position of each vehicle in the picture is identified through a vehicle structural algorithm. The vehicle driving image may be composed of a plurality of images, for example, 3 images, the vehicle driving image with the largest/closest target is preferentially selected, if the first image does not identify the target illegal vehicle, the 2 nd image is taken, and the like is repeated until the target illegal vehicle is identified.

Secondly, determining the vehicle type of the target illegal vehicle according to the target model;

illustratively, the target model may be a ResNet50 motor vehicle attribute model, and the accuracy of vehicle type identification of target illegal vehicles may reach 98% and above. From the target model, a vehicle type of the target illicit vehicle may be determined. The target model is not limited in this embodiment, and those skilled in the art can determine the target model as needed.

And thirdly, when the vehicle type is not the target vehicle type, the review result is that the illegal action is effective.

Illustratively, the target vehicle type may refer to a vehicle that is not subject to the one-way lane rule, such as a bus. When the type of the vehicle is not the bus, the review result is valid, so that misjudgment on the vehicle which is not limited by the rule of the single-way lane is avoided when the review is carried out on the illegal running of the single-way lane, and the accuracy of the review is improved.

As an optional implementation manner of this embodiment, the vehicle illegal activity information includes a plurality of pieces of vehicle driving image information to be checked and illegal vehicle license plate number information, and when the illegal type is red light violation (the illegal type number is detected to be 1625), the review result of the illegal activity is determined according to the illegal activity review algorithm and the vehicle illegal activity information, including:

firstly, license plate number information in vehicle driving image information is extracted; for details, refer to the corresponding parts of the above embodiments, and are not described herein again.

Secondly, when the extracted license plate information is consistent with the license plate information of the illegal vehicle, judging whether the traffic light is the red light currently or not according to the driving image information of the vehicle; when the red light and the green light are red lights at present, whether the vehicle position corresponding to the license plate number information exceeds the detection area or not is judged. And when the vehicle position corresponding to the license plate number information exceeds the detection area, the review result is valid for illegal behaviors.

Exemplarily, when the extracted license plate number information is consistent with the illegal vehicle license plate number information, judging whether the traffic light is the red light currently according to the vehicle driving image information; and when the extracted license plate information is inconsistent with the illegal vehicle license plate information, the review result is invalid for illegal behaviors. When the red light and the green light are red lights at present, judging whether the vehicle position corresponding to the license plate number information exceeds the detection area, and when the vehicle position corresponding to the license plate number information exceeds the detection area, judging that the review result is valid illegal behaviors; and when the red light and the green light are not the red light currently, the review result is invalid for illegal behaviors.

As an optional implementation manner of this embodiment, the vehicle illegal activity information includes a plurality of pieces of vehicle driving image information to be checked and illegal vehicle license plate number information, and when the illegal type is distracted driving or unbelted driving (it is detected that the illegal type number is 1223 or it is detected that the illegal type number is 6011), determining a review result of the illegal activity according to the illegal activity review algorithm and the vehicle illegal activity information includes:

firstly, license plate number information in vehicle driving image information is extracted; when the extracted license plate information is consistent with the license plate information of the illegal vehicle, vehicle detection is carried out according to the target vehicle positioning model to obtain a vehicle image corresponding to the license plate information of the illegal vehicle;

for an exemplary manner of extracting the license plate number information in the vehicle driving image information, reference is made to the corresponding parts of the above embodiments, and details are not repeated herein. Generally speaking, a driving image of a vehicle to be checked is formed by splicing two consecutive frames of pictures, so that half of the driving image needs to be cut out for license plate recognition, and when the license plate recognition result is inconsistent with the license plate information of an illegal vehicle, the review result of illegal behaviors is invalid. And when the extracted license plate information is consistent with the illegal vehicle license plate information, carrying out vehicle detection according to the target vehicle positioning model to obtain a vehicle image corresponding to the illegal vehicle license plate information. Wherein the target vehicle positioning model may be YOLO V4.

Secondly, detecting the position of a person in the vehicle image according to the target person positioning model to obtain a driver image;

illustratively, when obtaining the vehicle image, the vehicle image may be input to a target person localization model, which may be a YOLO V3 window model, the exact window position is detected using a YOLOV3 window model, and the right half area is cropped to obtain the driver image.

Then, inputting the images of the drivers into a human behavior classification model to obtain a classification result; and determining the review result of the illegal action according to the classification result.

For example, when the illegal category is distracted driving, the personnel behavior classification model may be a distracted driving classification model, and when it is detected that the driver makes a call, the obtained classification result is that the driver is distracted driving, then the review result of the illegal behavior is valid, otherwise, the review result is invalid.

When the illegal type is that the driver does not wear the safety belt, the personnel behavior classification model can be a safety belt unfastening classification model, when the situation that the driver does not wear the safety belt is detected, the obtained classification result is that the driver drives without wearing the safety belt, and then the review result of the illegal behavior is valid, otherwise, the result is invalid.

The present embodiment provides a vehicle illegal action review device, as shown in fig. 2, including:

the information acquisition module 201 is configured to acquire vehicle illegal behavior information to be checked, where the vehicle illegal behavior information includes an illegal category; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

A review algorithm determining module 202, configured to determine a corresponding review algorithm for the illegal action according to the type of the illegal action; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the review result determining module 203 is configured to determine a review result of the illegal activity according to the illegal activity review algorithm and the vehicle illegal activity information. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the review result determining module 203 includes:

the first license plate number extraction module is used for extracting license plate number information in the vehicle driving image information; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The lane line determining module is used for determining the lane line information of the illegal action according to the serial number of the image acquisition equipment when the extracted license plate information is consistent with the license plate information of the illegal vehicle; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the first review result determining submodule is used for judging illegal behaviors according to the illegal behavior review algorithm on the lane line information and the plurality of pieces of vehicle driving image information to be reviewed to obtain a review result of the illegal behaviors. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the review result determining module 203 includes:

the route determining module is used for determining a vehicle driving route according to the information of a plurality of vehicle driving images to be checked; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The non-guide-line running review module is used for determining whether the vehicle runs effectively according to the guide line or not when the driving path of the vehicle and the rule line in the lane line information have an intersection point; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again. Or

A review result determination module 203, comprising:

the vehicle diagonal coordinate relation determining module is used for determining the relation between the vehicle diagonal coordinates and the lane lines according to the vehicle driving image information to be audited; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the vehicle line pressing review module is used for judging that the vehicle line pressing running is effective as a result of review when the diagonal coordinates of the vehicle are at the two ends of the lane line. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the review result determining module 203 includes:

the driving direction determining module is used for determining the driving direction of the vehicle according to the information of the plurality of driving images of the vehicle to be checked; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the reverse running review module is used for judging that the vehicle runs reversely and effectively according to the review result when the driving direction of the vehicle is opposite to the direction of the lane line in the lane information. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the review result determining module 203 includes:

the lane attribute determining module is used for determining lane attributes of the illegal behaviors according to the image acquisition equipment numbers, wherein the lane attributes comprise a traffic control lane of a target vehicle type, a no-parking lane and a single-line lane; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the second review result determining submodule is used for determining that the review result is invalid when the lane attribute of the illegal action is inconsistent with the lane attribute in the vehicle illegal action information to be reviewed. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the apparatus for reviewing vehicle illegal activities further includes:

the license plate and vehicle type extraction module is used for extracting license plate information and vehicle type information in the vehicle driving image information when the lane attribute of the illegal behavior is consistent with the lane attribute in the vehicle illegal behavior information to be checked; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the target vehicle on-road review module is used for determining that the review result is valid for illegal behaviors when the license plate information is consistent with the license plate information of the illegal vehicle and the vehicle type information is consistent with the target vehicle type. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the apparatus for reviewing vehicle illegal activities further includes:

the second license plate number extraction module is used for extracting license plate number information in the vehicle driving image information when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The vehicle position judging module is used for judging whether a vehicle corresponding to the license plate number information is in a forbidden parking area in a plurality of pieces of vehicle driving image information when the license plate number information is consistent with the illegal vehicle license plate number information; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the forbidden re-examination module is used for determining that the re-examination result is valid for illegal behaviors when the vehicle corresponding to the license plate number information is in the forbidden region in the plurality of pieces of vehicle driving image information. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the apparatus for reviewing vehicle illegal activities further includes:

the third license plate number extraction module is used for extracting license plate number information in the vehicle driving image information when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The target illegal vehicle positioning module is used for positioning a target illegal vehicle when the license plate information is consistent with the license plate information of the illegal vehicle; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The vehicle type determining module is used for determining the vehicle type of the target illegal vehicle according to the target model; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the target vehicle review module is used for determining that the review result is valid for illegal behaviors when the vehicle type is not the target vehicle type. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the review result determining module 203 includes:

the fourth license plate number extraction module is used for extracting license plate number information in the vehicle driving image information; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The red light judgment module is used for judging whether the traffic light is the red light currently or not according to the vehicle driving image information when the extracted license plate information is consistent with the illegal vehicle license plate information; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The area detection module is used for judging whether the vehicle position corresponding to the license plate number information exceeds a detection area or not when the red light and the green light are red light at present; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the red light running review module is used for determining that the review result is valid for illegal behaviors when the vehicle position corresponding to the license plate number information exceeds the detection area. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

As an optional implementation manner of this embodiment, the review result determining module 203 includes:

the fifth license plate number extraction module is used for extracting license plate number information in the vehicle driving image information; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The vehicle image positioning module is used for detecting the vehicle according to a target vehicle positioning model when the extracted license plate information is consistent with the illegal vehicle license plate information to obtain a vehicle image corresponding to the illegal vehicle license plate information; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The target person positioning module is used for detecting the position of a person in the vehicle image according to a target person positioning model to obtain a driver image; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The classification module is used for inputting the driver image into a human behavior classification model to obtain a classification result; for details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

And the classification result review module is used for determining the review result of the illegal action according to the classification result. For details, reference is made to the corresponding parts of the above method embodiments, which are not described herein again.

The embodiment of the present application also provides an electronic device, as shown in fig. 3, including a processor 310 and a memory 320, where the processor 310 and the memory 320 may be connected by a bus or in other manners.

Processor 310 may be a Central Processing Unit (CPU). The Processor 310 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or any combination thereof.

The memory 320, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the vehicle law violation review method in the embodiments of the present invention. The processor executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions, and modules stored in the memory.

The memory 320 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 320 may optionally include memory located remotely from the processor, which may be connected to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The one or more modules are stored in the memory 320 and, when executed by the processor 310, perform a vehicle law violation review method as in the embodiment of FIG. 1.

The details of the electronic device may be understood with reference to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.

The present embodiment also provides a computer storage medium, where the computer storage medium stores computer executable instructions, where the computer executable instructions can execute any of the method embodiments 1 described above in the review method of illegal vehicle behaviors. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.

It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.

Claims (13)

1. A vehicle illegal behavior review method is characterized by comprising the following steps:

acquiring vehicle illegal behavior information to be checked, wherein the vehicle illegal behavior information comprises illegal types;

determining a corresponding illegal action review algorithm according to the illegal type;

and determining a review result of the illegal action according to the illegal action review algorithm and the vehicle illegal action information.

2. The method according to claim 1, wherein the vehicle illegal activity information includes an image acquisition device number for acquiring vehicle illegal activities, a plurality of pieces of vehicle driving image information to be checked, and illegal vehicle license plate number information, and the determining a review result of the illegal activities according to the illegal activity review algorithm and the vehicle illegal activity information includes:

extracting license plate number information in the vehicle driving image information;

when the extracted license plate information is consistent with the illegal vehicle license plate information, determining lane line information of the illegal action according to the image acquisition equipment number;

and carrying out illegal behavior judgment on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain a review result of illegal behaviors.

3. The method according to claim 2, wherein the illegal category is driving without a guide line, and the illegal action determination of the lane line information and the plurality of pieces of vehicle driving image information to be reviewed according to the illegal action review algorithm to obtain the review result of the illegal action comprises:

determining a vehicle driving path according to a plurality of pieces of vehicle driving image information to be checked;

when the driving path of the vehicle and the regular line in the lane line information have an intersection point, the review result is that the vehicle does not effectively run according to the guide line; or

When the illegal type is that the pressing line runs, the illegal behavior judgment is carried out on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain the review result of the illegal behavior, and the method comprises the following steps:

determining the relationship between the diagonal coordinates of the vehicle and the lane lines according to the information of the vehicle driving image to be audited;

and when the diagonal coordinates of the vehicle are positioned at the two ends of the lane line, the rechecking result shows that the vehicle is effective in line pressing running.

4. The method according to claim 2, wherein when the illegal type is reverse driving, the illegal behavior determination is performed on the lane line information and the plurality of pieces of vehicle driving image information to be checked according to the illegal behavior review algorithm to obtain a review result of the illegal behavior, and the method comprises:

determining the driving direction of the vehicle according to the information of the plurality of vehicle driving images to be audited;

and when the driving direction of the vehicle is opposite to the direction of the lane line in the lane information, the review result shows that the vehicle runs reversely effectively.

5. The method according to claim 1, wherein the vehicle illegal activity information includes an image acquisition device number for acquiring vehicle illegal activities and a plurality of pieces of vehicle driving image information to be checked, and the determining a review result of the illegal activities according to the illegal activity review algorithm and the vehicle illegal activity information includes:

determining lane attributes of the illegal action according to the image acquisition equipment number, wherein the lane attributes comprise a traffic control lane, a no-parking lane and a single-way lane of the target vehicle type;

and when the lane attribute of the illegal action is inconsistent with the lane attribute in the vehicle illegal action information to be audited, the review result is invalid.

6. The method of claim 5, wherein the vehicle unlawful behavior information further comprises unlawful vehicle license plate information, the lane attribute is a target vehicle type restricted lane, further comprising:

when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information and vehicle type information in the vehicle driving image information are extracted;

and when the license plate information is consistent with the license plate information of the illegal vehicle and the vehicle type information is consistent with the target vehicle type, the review result is that the illegal action is effective.

7. The method of claim 5, wherein the vehicle unlawful behavior information further comprises unlawful vehicle license plate information, the lane attribute is a prohibited parking lane, further comprising:

when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information in the vehicle driving image information is extracted;

when the license plate information is consistent with the illegal vehicle license plate information, judging whether a vehicle corresponding to the license plate information is in a forbidden area in a plurality of pieces of vehicle driving image information;

and when the vehicle corresponding to the license plate number information is in the forbidden stop area in the plurality of pieces of vehicle driving image information, the review result is that the illegal action is effective.

8. The method of claim 5, wherein the vehicle unlawful behavior information further comprises unlawful vehicle license plate information, the lane attribute is a single-lane, further comprising:

when the lane attribute of the illegal action is consistent with the lane attribute in the vehicle illegal action information to be checked, license plate number information in the vehicle driving image information is extracted;

when the license plate information is consistent with the license plate information of the illegal vehicle, positioning a target illegal vehicle;

determining the vehicle type of the target illegal vehicle according to a target model;

and when the vehicle type is not the target vehicle type, the review result is that the illegal action is effective.

9. The method according to claim 1, wherein the vehicle illegal activity information includes a plurality of pieces of vehicle driving image information to be checked and illegal vehicle license plate information, and when the illegal type is red light violation, the determining a review result of the illegal activity according to the illegal activity review algorithm and the vehicle illegal activity information includes:

extracting license plate number information in the vehicle driving image information;

when the extracted license plate information is consistent with the illegal vehicle license plate information, judging whether the traffic light is a red light currently or not according to the vehicle driving image information;

when the red light and the green light are red lights at present, judging whether the vehicle position corresponding to the license plate number information exceeds a detection area or not;

and when the vehicle position corresponding to the license plate number information exceeds the detection area, the review result is valid.

10. The method according to claim 1, wherein the vehicle illegal activity information includes a plurality of pieces of vehicle driving image information to be reviewed and illegal vehicle license plate information, and the determining a review result of the illegal activity according to the illegal activity review algorithm and the vehicle illegal activity information includes:

extracting license plate number information in the vehicle driving image information;

when the extracted license plate information is consistent with the illegal vehicle license plate information, vehicle detection is carried out according to a target vehicle positioning model to obtain a vehicle image corresponding to the illegal vehicle license plate information;

according to the target person positioning model, detecting the position of a person in the vehicle image to obtain a driver image;

inputting the driver image into a human behavior classification model to obtain a classification result;

and determining a review result of the illegal action according to the classification result.

11. A vehicle illegal activity review device is characterized by comprising:

the information acquisition module is used for acquiring vehicle illegal behavior information to be checked, wherein the vehicle illegal behavior information comprises illegal types;

the review algorithm determining module is used for determining a corresponding review algorithm of the illegal action according to the illegal type;

and the review result determining module is used for determining the review result of the illegal action according to the illegal action review algorithm and the vehicle illegal action information.

12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of reviewing vehicle law violations of any one of claims 1-10 are implemented when the program is executed by the processor.

13. A storage medium having stored thereon computer instructions, which when executed by a processor, carry out the steps of the method for reviewing vehicle unlawful acts of any one of claims 1 to 10.

Images