CN109300313B

CN109300313B - Illegal behavior detection method, camera and server

Info

Publication number: CN109300313B
Application number: CN201710612707.1A
Authority: CN
Inventors: 张勇; 徐忠杰; 潘振
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2017-07-25
Filing date: 2017-07-25
Publication date: 2021-06-08
Anticipated expiration: 2037-07-25
Also published as: CN109300313A

Abstract

The invention provides a method for detecting illegal behaviors, a camera and a server, and belongs to the technical field of monitoring. The method comprises the following steps: when detecting that a vehicle runs on the first lane, the ith camera acquires a first picture shot by the vehicle when the vehicle runs to each position of a group of corresponding positions arranged on the first lane and license plate information of the vehicle, wherein i is an integer from 1 to N; and when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, the ith camera sends the first picture and the license plate information of the vehicle to a server so that the server judges whether the vehicle is illegal. The invention can improve the efficiency of detecting the illegal action.

Description

Illegal behavior detection method, camera and server

Technical Field

The invention relates to the technical field of monitoring, in particular to a method for detecting illegal behaviors, a camera and a server.

Background

The highway includes a freeway and a traffic lane. The traffic law stipulates that a vehicle runs on a traffic lane of a highway, and when the vehicle needs to overtake a front vehicle, the vehicle can enter a freeway, quickly overtake the front vehicle on the freeway and then run on the traffic lane.

Some drivers occupy the fast lane for a long distance under the condition that the traffic lane on the expressway allows normal driving, and the rules of traffic laws are violated. At present, illegal behaviors that vehicles occupy express lanes for a long distance are mainly discovered through law enforcement on the traffic police site.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:

when the traffic police performs law on site, the illegal behavior that the vehicle occupies the express way for a long distance can be found only by driving the traffic police car to follow the vehicle for a period of time, and the efficiency is low.

Disclosure of Invention

In view of this, the present invention provides a method, a camera and a server for detecting an illegal activity, which can improve the efficiency of detecting the illegal activity.

Specifically, the method comprises the following technical scheme:

in a first aspect, the present invention provides a method for detecting an illegal activity, the method being applied to a camera system, the camera system including N cameras, N being an integer greater than or equal to 2, the N cameras being arranged on a road and adjacent cameras being spaced apart by a preset distance, the road including a first lane and a second lane which are adjacent in position, the method including:

when detecting that a vehicle runs on the first lane, the ith camera acquires a first picture shot by the vehicle when the vehicle runs to each position of a group of corresponding positions arranged on the first lane and license plate information of the vehicle, wherein i is an integer from 1 to N;

and when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, the ith camera sends the first picture and the license plate information of the vehicle to a server so that the server judges whether the vehicle is illegal.

Optionally, the method further comprises:

when the ith camera is not the last camera of the N cameras, the ith camera sends an instruction including the license plate information of the vehicle to the next adjacent camera when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, and the instruction is used for triggering the next camera to take pictures.

Optionally, the method further comprises:

when the ith camera is not the first camera of the N cameras, the ith camera receives an instruction sent by the last camera adjacent to the ith camera, wherein the instruction comprises the license plate information acquired by the last camera;

and the ith camera shoots a second picture according to the instruction and sends the second picture and the license plate information included by the instruction to the server.

Optionally, before the ith camera sends the first picture acquired by the ith camera and the license plate information of the vehicle to the server, the method includes:

and the ith camera sends the first picture and the license plate information of the vehicle to a server when the license plate type of the vehicle is the license plate type corresponding to the large vehicle.

In a second aspect, the present invention provides a method for detecting an illegal activity, the method comprising:

the method comprises the steps that a server receives pictures and license plate information sent by at least two adjacent cameras in a camera system, wherein the camera system comprises N cameras, N is an integer larger than or equal to 2, the N cameras are arranged on a road, and the adjacent cameras are spaced by a preset distance;

and the server judges that the license plate information sent by the at least two cameras are the same, determines vehicle violation corresponding to the license plate information, and synthesizes pictures sent by the at least two cameras into a violation process picture.

In a third aspect, the present invention provides a camera, the camera being any one of a camera system including N cameras, N being an integer greater than or equal to 2, the N cameras being arranged on a road and adjacent two cameras being spaced apart by a preset distance, the road including a first lane and a second lane which are located adjacent to each other, the camera including:

the acquisition module is used for acquiring a first picture shot by the vehicle when the vehicle runs to each position in a group of positions set on the first lane corresponding to the camera and license plate information of the vehicle when the vehicle runs to the first lane;

and the sending module is used for sending the first picture and the license plate information of the vehicle to a server when no vehicle runs on the second lane in the process of determining that the vehicle passes through each position in a group of positions corresponding to the camera, so that the server judges whether the vehicle is illegal.

Optionally, when the camera is not the last camera of the N cameras that the vehicle passes by,

the sending module is further configured to send an instruction including license plate information of the vehicle to a next camera adjacent to the camera when it is determined that no vehicle is running on the second lane in a process that the vehicle passes through each position in the group of positions, where the instruction is used to trigger the next camera to take a picture.

Optionally, the camera further comprises:

the receiving module is used for receiving an instruction sent by the previous camera adjacent to the camera when the camera is not the first camera of the N cameras through which the vehicle passes, wherein the instruction comprises license plate information acquired by the previous adjacent camera;

the shooting module is used for shooting a second picture according to the instruction;

the sending module is further configured to send the second picture and the license plate information included in the instruction to the server.

Optionally, the sending module is configured to send the first picture and the license plate information of the vehicle to a server when the license plate type of the vehicle is a license plate type corresponding to a large vehicle.

In a fourth aspect, the present invention provides a server, comprising:

the system comprises a receiving module, a processing module and a display module, wherein the receiving module is used for receiving pictures and license plate information sent by at least two adjacent cameras in a camera system, the camera system comprises N cameras, N is an integer greater than or equal to 2, the N cameras are arranged on a road, and the adjacent cameras are spaced by a preset distance;

the determining module is used for determining vehicle violation corresponding to the license plate information when the license plate information sent by the at least two cameras is judged to be the same, and synthesizing pictures sent by the at least two adjacent cameras into a violation process picture.

The technical scheme provided by the embodiment of the invention has the beneficial effects that:

according to the illegal behavior detection method, the camera and the server, the illegal behavior of the vehicle is detected through the picture shot by the camera, and the efficiency is high. Each camera acquires a first picture shot when the vehicle passes through each position in a group of positions on a corresponding first lane and license plate information of the vehicle, and when the camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the group of positions, the acquired license plate information of the vehicle is sent to a server; and the server judges that the license plate information sent by at least two adjacent cameras is the same, and determines the vehicle violation corresponding to the license plate information. The illegal action detection through at least two adjacent cameras can increase the detection distance, so that the fact that the vehicle occupies the express way for a long distance is effectively proved, and the accuracy for judging whether the vehicle is illegal is higher.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of an exemplary implementation environment in accordance with an embodiment of the invention;

FIG. 2 is a schematic diagram of an exemplary implementation environment in accordance with an embodiment of the invention;

FIG. 3 is a schematic diagram of an exemplary implementation environment in accordance with an embodiment of the invention;

FIG. 4 is a flow chart of a method for detecting an illegal activity according to an embodiment of the present invention;

FIG. 5 is a flow chart of a method for detecting an illegal activity according to an embodiment of the present invention;

FIG. 6 is a flow chart of a method for detecting an illegal activity according to an embodiment of the present invention;

FIG. 7 is a flow chart of a method for detecting an illegal activity according to an embodiment of the present invention;

FIG. 8 is a flow chart of a method for detecting an illegal activity according to an embodiment of the present invention;

FIG. 9 is a flow chart of a method for detecting an illegal activity according to an embodiment of the present invention;

FIG. 10 is a block diagram of a camera in an embodiment of the invention;

FIG. 11 is a block diagram of a server in an embodiment of the invention.

Detailed Description

In order to make the technical solutions and advantages of the present invention clearer, the following will describe embodiments of the present invention in further detail with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of an exemplary implementation environment in which the present invention may be implemented. Referring to fig. 1, the implementation environment includes a camera system and a server 102. The camera system includes N cameras 101, N being an integer greater than or equal to 2. The N cameras 101 are arranged on the road with a preset distance between two adjacent cameras 101. The connection between two adjacent cameras 101 and between the N cameras 101 and the server 102 may be through a wireless or wired network.

For example, referring to fig. 2, the camera system may include two cameras 101, i.e., N equals 2, camera 1011 and camera 1012, respectively. As another example, referring to fig. 3, the camera system may include three cameras 101, i.e., N equals 3, camera 1011, camera 1012 and camera 1013, respectively. The preset distance can be 200 meters, 300 meters or 400 meters, and the preset distances between different cameras can be the same or different.

The road comprises a first lane and a second lane, the first lane and the second lane are adjacent, and the driving direction corresponding to the first lane is the same as the driving direction corresponding to the second lane. In the present invention, a vehicle violation is defined when the vehicle is traveling a long distance on a first lane and no vehicle is traveling in a second lane.

For example, assuming that the road is an expressway, the first lane may be a freeway of the expressway, and the second lane may be a traffic lane of the expressway, with the two lanes adjacent. China's law stipulates that vehicles should run on a traffic lane of an expressway, and the behavior that the vehicles occupy a highway for a long distance and no vehicle runs on the traffic lane is illegal.

Each camera 101 in the N cameras 101 corresponds to a group of positions, the group of positions corresponding to the camera 101 includes M positions, the M positions are all disposed on the first lane and are all located in front of a lens of the camera 101, and M is an integer greater than or equal to 1. When the camera 101 is not the first camera of the N cameras 101, the M positions corresponding to the camera 101 are located between the camera 101 and its adjacent previous camera 101.

The first of the N cameras 101 is the camera through which the vehicle first passes. For example, referring to fig. 3, a camera system includes a camera 1011, a camera 1012 and a camera 1013, the three cameras are disposed on a road, and two adjacent cameras are spaced apart by a preset distance; the driving direction of the road is the direction pointed by the arrow, the first camera passed by the vehicle driving on the road is the camera 1011, namely the first camera of the three cameras is the camera 1011, the second camera is the camera 1012, and the third camera is the camera 1013; among them, position 1, position 2, and position 3 are provided on the first lane in front of the lens of the camera 1011, position 4, position 5, and position 6 are provided on the first lane between the camera 1011 and the camera 1012, and position 7, position 8, and position 9 are provided on the first lane between the camera 1012 and the camera 1013.

Referring to fig. 4, an embodiment of the present invention provides a method for detecting an illegal activity, which can be applied to the implementation environment shown in fig. 1, and includes the following steps.

Step 101: when detecting that a vehicle runs on the first lane, the ith camera acquires a first picture shot by the vehicle when the vehicle runs to each position of a group of corresponding positions arranged on the first lane and license plate information of the vehicle, wherein i is an integer from 1 to N.

Step 102: and when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, the ith camera sends the first picture and the license plate information of the vehicle to the server so as to enable the server to judge whether the vehicle is illegal.

In the embodiment of the invention, the illegal behaviors of the vehicle are detected through the pictures shot by the camera, so that the efficiency is higher. Each camera acquires a first picture shot when the vehicle passes through each position in a group of positions on a corresponding first lane and license plate information of the vehicle, and when the camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the group of positions, the acquired license plate information of the vehicle is sent to a server; and the server judges that the license plate information sent by at least two adjacent cameras is the same, and determines the vehicle violation corresponding to the license plate information. The illegal action detection through at least two adjacent cameras can increase the detection distance, so that the fact that the vehicle occupies the first lane in a long distance is effectively proved, and the accuracy for judging whether the vehicle is illegal is higher.

Referring to fig. 5, the method for detecting an illegal activity according to the present invention can be applied to the implementation environment shown in fig. 1, and includes the following steps.

Step 201: when detecting that a vehicle runs on the first lane, the ith camera acquires a first picture shot by the vehicle when the vehicle runs to each position of a group of corresponding positions arranged on the first lane and license plate information of the vehicle in the first picture, wherein i is an integer from 1 to N.

Optionally, when the ith camera is not the first camera of the N cameras through which the vehicle passes, before executing this step, the ith camera may further receive an instruction sent by the last camera adjacent to the ith camera, where the instruction includes the license plate information acquired by the last camera; and the ith camera shoots a second picture according to the instruction, sends the second picture and the license plate information included by the instruction to the server, and then executes the step.

Step 202: and when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, the ith camera sends the first picture and the license plate information of the vehicle in the first picture to the server so that the server judges whether the vehicle is illegal.

In this step, there are various implementations of determining that no vehicle is running on the second lane by the ith camera, and this embodiment only lists two implementations, and the other implementations are not listed.

In a first implementation manner, the ith camera determines whether a vehicle runs on the second lane according to the first picture acquired by the ith camera.

Specifically, when the ith camera determines that no vehicle runs on the second lane in each first picture acquired by the ith camera, it is determined that no vehicle runs on the second lane in the process that the vehicle passes through each position in a group of positions corresponding to the ith camera.

Because the distance between any two adjacent positions in the group of positions corresponding to each camera is short, the time for the vehicle to pass through any two adjacent positions is short, when the vehicle runs on a highway or the like, the running speed of the vehicle is high, the vehicle cannot turn from the first lane to the second lane and return from the second lane to the first lane during the time for passing through the two adjacent positions, and therefore whether the vehicle runs on the second lane in the process of passing through each position in the group of positions can be determined through the first picture corresponding to each position.

The ith camera determines that no vehicle runs on the second lane through the acquired first picture, the number of processed pictures is small, the efficiency can be improved, the processing difficulty is reduced, the configuration requirement on the camera is low, and the use cost is reduced.

In a second implementation, the ith camera determines whether a vehicle is traveling in the second lane based on a picture taken in real time during a time between the first time and the second time.

The first time is when the ith camera detects that the vehicle passes a first position in the corresponding set of positions, and the second time is when the ith camera detects that the vehicle passes a last position in the corresponding set of positions.

Specifically, when the ith camera determines that no vehicle is running on the second lane in each picture shot in real time within the time between the first time and the second time, it is determined that no vehicle is running on the second lane in the process that the vehicle passes through each position in the group of positions corresponding to the ith camera.

The realization mode can be used for speed-limiting or traffic-jam road sections on the expressway, and the detection precision is higher.

Step 203: when the ith camera is not the last camera of the N cameras, sending an instruction including the license plate information of the vehicle to the next camera adjacent to the ith camera, wherein the instruction is used for triggering the next camera to take a picture.

The ith camera may transmit the instruction to the next camera adjacent to the ith camera by wire or wirelessly.

The (i + 1) th camera receives the instruction sent by the ith camera, takes a second picture according to the instruction, and sends the second picture and the license plate information included in the instruction to the server. Thereafter, the operation of the i-th camera in steps 201 to 203 is performed.

According to the illegal action detection method provided by the embodiment, the illegal action of the vehicle is detected through the picture shot by the camera, and the efficiency is high. Each camera acquires a first picture shot when the vehicle passes through each position in a group of positions on a corresponding first lane, and when the camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the corresponding group of positions, the acquired first picture and the license plate information of the vehicle in the first picture are sent to a server; and when the camera is not the last camera and no other vehicle is judged to be on the adjacent second lane in the process that the vehicle passes through the group of positions, sending an instruction to the adjacent next camera to enable the adjacent next camera to acquire a second picture. The second picture can prove that the camera and the next adjacent camera are two adjacent cameras, the detection distance is increased, and the persuasion of illegal evidence is improved.

Referring to fig. 6, an embodiment of the present invention provides a method for detecting an illegal activity, which can be applied to the implementation environment shown in fig. 1, and includes the following steps.

Step 301: when detecting that a vehicle runs on the first lane, the ith camera acquires a first picture shot by the vehicle when the vehicle runs to each position of a group of corresponding positions arranged on the first lane and license plate information of the vehicle in the first picture, wherein i is an integer from 1 to N.

Step 302: and when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions and the license plate type of the vehicle is the license plate type corresponding to the large vehicle, sending the first picture and the license plate information of the vehicle to the server so that the server judges whether the vehicle is illegal.

The process of determining that the license plate type of the vehicle is the license plate type corresponding to the large vehicle by the ith camera can be as follows:

and when the ith camera judges that the license plate of the vehicle is a yellow license plate and is not the license plate of the learner-driven vehicle, determining that the license plate type of the vehicle is the license plate type corresponding to the large vehicle.

In the embodiment of the invention, the illegal behaviors of the vehicle are detected through the pictures shot by the camera, so that the efficiency is higher. Each camera acquires a first picture shot when a vehicle passes through each position in a group of positions on a corresponding first lane and license plate information of the vehicle in the first picture, and when the camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the group of positions and the license plate type of the vehicle is the license plate type corresponding to a large vehicle, the acquired license plate information of the vehicle is sent to a server; and the server judges that the license plate information sent by at least two adjacent cameras is the same, and determines that the large-scale vehicle corresponding to the license plate information is illegal. The illegal action detection through at least two adjacent cameras can increase the detection distance, so that the fact that the large-sized vehicle occupies the first lane in a long distance is effectively proved, and the accuracy for judging whether the large-sized vehicle is illegal is higher.

Referring to fig. 7, an embodiment of the present invention provides a method for detecting an illegal activity, which can be applied to the implementation environment shown in fig. 1, and includes the following steps.

Step 401: when the first camera detects that a vehicle runs on the first lane, the first camera acquires a first picture shot by the vehicle when the vehicle runs to each position in a group of positions set on the first lane and corresponding to the first camera, and license plate information of the vehicle in the first picture.

A vehicle traveling on a first lane may be because the vehicle occupies the first lane over a vehicle traveling on a second lane, or may be because the vehicle occupies the first lane for a long distance and travels on the first lane. When the vehicle is traveling on the first lane, the vehicle may pass each of a set of positions set on the first lane corresponding to the first camera in turn.

The first camera shoots a road in front of the lens in real time, detects whether a vehicle runs on the first lane according to a picture when the first camera shoots the road, and detects the current position of the vehicle if the vehicle runs on the first lane. The first camera can detect the vehicle before the vehicle drives to the first position or the first position in the corresponding position group, and then the first camera acquires a first picture taken at the first position; then, continuously shooting pictures by the first camera, and acquiring a first picture shot at a second position when the vehicle is detected to pass through the second position in the position group according to the pictures; the first camera then continues to take pictures until the first picture taken at the mth position in the set of positions is acquired.

The operation of the first camera to detect the vehicle and the position of the vehicle from the taken picture may be:

the first camera detects the vehicle through some characteristics of the vehicle such as vehicle lamps, vehicle windows and the like, and the position of the vehicle is obtained through the steps of background modeling, target segmentation, target tracking, triggering judgment and the like by adopting a video algorithm.

The first camera can acquire the license plate information of the vehicle according to any one of the acquired M first pictures, and the acquired license plate information is used as the license plate information of the vehicle in each first picture of the M first pictures. The license plate information may include a license plate number, a license plate color, and the like.

Since the mth position is closest to the first camera, and the first picture taken at the mth position is clearest, the accuracy of obtaining the license plate information of the vehicle according to the first picture taken at the mth position is highest, and the detailed obtaining process may be as follows:

the first camera can adopt a video algorithm to position and segment the license plate position in the first picture shot at the Mth position, and adopts a deep neural network technology to identify the license plate to obtain the license plate information.

Referring to fig. 2, the camera system includes a first camera, a second camera, and a third camera, and the first camera 1011 and the second camera 1012 are disposed on the fast-driving lane. The first camera 1011 has a lens with a position 1, a position 2 and a position 3 in front of the freeway, and the first camera 1011 and the second camera 1012 have a lens with a position 4, a position 5 and a position 6 in the freeway. When the first camera 1011 detects that the vehicle passes through the position 1, the position 2 and the position 3, a first picture is obtained, and when the first camera 1011 obtains the license plate information of the vehicle according to the first picture taken when the vehicle passes through the position 3.

Step 402: when the first camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, an instruction including the license plate information is sent to the next adjacent camera, and the first picture and the license plate information of the vehicle in the first picture are sent to the server.

The determination of whether no vehicle is traveling in the second lane during the vehicle's passing each of the set of positions by the first camera may be performed in the two manners described above in step 202, but is not limited to the two manners described above.

The first picture sent by the first camera to the server may be M first pictures acquired by the first camera, or may be one picture obtained by synthesizing the M first pictures acquired by the first camera. The first camera sends an instruction to the next adjacent camera, i.e. to the second camera, for triggering the next camera to take a picture.

Step 403: the server receives and stores a first picture sent by a first camera and license plate information of a vehicle in the first picture.

The server correspondingly stores the received first picture and the license plate information of the vehicle in the first picture in a corresponding relation between the picture and the license plate information, and the corresponding relation can be located in a hard disk and a database, so that the first picture and the license plate information of the vehicle in the first picture can be directly called from the database and the hard disk in the subsequent illegal detection process.

Step 404: the ith camera receives an instruction sent by the (i-1) th camera to acquire a second picture, the instruction sent by the (i-1) th camera comprises the license plate information of the vehicle in the acquired first picture, and the ith camera sends the second picture and the license plate information included in the received instruction to the server.

In this step, the ith camera may set the acquired license plate information of the vehicle in the second picture as the license plate information included in the instruction it receives.

In the present embodiment, i is an integer of 2 to N. When the ith camera is the second camera, the (i-1) th camera is the first camera; when the ith camera is a third camera, the (i-1) th camera is a second camera; and so on.

The ith-1 camera acquires a first picture shot at the last position in a group of positions corresponding to the ith camera and then sends an instruction to the ith camera, and the ith camera acquires a second picture according to the instruction after receiving the instruction. The vehicle is between the last position in the set of positions corresponding to the i-1 th camera and the first position in the set of positions corresponding to the i-th camera when the i-th camera acquires the second picture. Referring to fig. 2, when the second camera 1012 receives the instruction from the first camera 1011, the second camera 1012 immediately acquires a second picture. The second camera 1012 takes a second picture with the vehicle between position 3 and position 4.

The second picture acquired by the ith camera can link the first picture acquired by the ith-1 camera with the first picture acquired by the ith camera, so as to increase the detection distance. Because the time taken by the ith-1 camera to acquire the first picture shot at the Mth position and recognize the license plate information according to the picture is shorter, the distance between the position of the vehicle when the ith camera shoots the second picture and the Mth position corresponding to the ith-1 camera is shorter, and therefore the vehicle in the second picture shot by the ith camera and the vehicle in the first picture shot by the ith-1 camera at the Mth position are considered to be the same vehicle.

The ith camera does not need to detect the vehicle in the second picture, the distance shot by the ith camera is greater than or equal to the distance between the ith camera and the (i-1) th camera, so that the image of the (i-1) th camera is ensured to be included in the second picture, and when the picture shot by the (i-1) th camera and the picture shot by the ith camera are presented to a driver as illegal evidence, the (i) th camera and the (i-1) th camera are two cameras adjacent in position through the second picture, namely, the (i) th camera and the (i-1) th camera are proved to be two cameras arranged on the same road section, and the illegal evidence persuasion is increased.

Step 405: when the ith camera detects that the vehicle runs on the first lane, the ith camera acquires a first picture shot by the vehicle when the vehicle runs to each position in a group of corresponding positions arranged on the first lane and license plate information of the vehicle in the first picture.

The vehicle travels on the first lane, possibly continuing to pass in turn through each of a set of positions provided on the first lane corresponding to the ith camera.

The ith camera shoots a road in front of the lens in real time, detects whether a vehicle runs on the first lane according to one picture when the picture is shot, and detects the current position of the vehicle if the vehicle runs. The ith camera can detect the vehicle before the vehicle runs to the first position or the first position in the corresponding position group, and acquire a first picture taken at the first position; then, the ith camera continues to shoot pictures and obtains a first picture shot at a second position when the vehicle is detected to pass through the second position in the position group according to the pictures; the ith camera then continues to take pictures until the first picture taken at the mth position in the set of positions is acquired.

Referring to fig. 2, when the second camera 1012 detects that the vehicle passes through the position 4, the position 5, and the position 6 on the first lane from the photographed pictures, first pictures are respectively acquired; when the second camera 1012 drives the vehicle to the position 6, the license plate information of the vehicle is identified according to the acquired first picture.

The operation of the ith camera to detect the vehicle and the position of the vehicle from the photographed picture may be:

the ith camera detects the vehicle through some characteristics of the vehicle such as vehicle lamps, vehicle windows and the like, and the position of the vehicle is obtained through the steps of background modeling, target segmentation, target tracking, triggering judgment and the like by adopting a video algorithm.

The ith camera can acquire the license plate information of the vehicle according to any one of the acquired M first pictures, and the acquired license plate information is used as the license plate information of the vehicle in each of the M first pictures. The license plate information may include a license plate number, a license plate color, and the like.

the ith camera can adopt a video algorithm to position and segment the license plate position in the first picture shot at the Mth position, and adopts a deep neural network technology to identify the license plate to obtain the license plate information.

Step 406: and when the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, sending the first picture and the license plate information of the vehicle in the first picture to the server.

When the ith camera is not the nth camera, sending an instruction to the (i + 1) th camera, where the instruction is used to trigger the (i + 1) th camera to take the second picture, and the (i + 1) th camera may perform the operations of the (i) th camera in the above-mentioned steps 404 to 406, which will not be described in detail herein. When the ith camera is the nth camera, no instruction is sent.

In this step, the ith camera determines that the vehicle is not traveling in the second lane while passing through its corresponding set of positions, which may be performed in the two manners described above in step 202, but is not limited to the two manners described above.

The first picture sent by the ith camera to the server may be M first pictures acquired by the ith camera, or a picture obtained by synthesizing the M first pictures acquired by the ith camera.

Step 407: and the server receives and stores the first picture, the second picture and the license plate information of the vehicle in the first picture and the license plate information included by the instruction sent by the ith camera.

The server correspondingly stores the received first picture, the received second picture, the license plate information of the vehicle in the first picture and the license plate information included by the command in a corresponding relation between the pictures and the license plate information, and the corresponding relation can be located in a hard disk and a database, so that the subsequent illegal detection process can be directly called from the database and the hard disk.

Step 408: after the server receives the first picture, the second picture and the license plate information of the vehicle in the first picture sent by the Nth camera and the license plate information included by the instruction, when the license plate information of the vehicle in the first pictures sent by at least two adjacent cameras is judged to be the same, the vehicle violation corresponding to the license plate information is determined, and the pictures sent by at least two adjacent cameras are combined into the picture of the violation process.

In this embodiment, the N cameras in the camera system take pictures with labels, and the server can determine which camera the picture was taken according to the labels of the pictures.

After the server receives the license plate information of the vehicle in the first picture sent by the Nth camera and the license plate information included in the instruction, whether the license plate information of the vehicle in the first pictures sent by at least two adjacent cameras is the same is judged. When the server detects that the license plate information of the vehicles in the first pictures sent by the at least two adjacent cameras is the same, determining that the vehicles corresponding to the license plate information are illegal. Specifically, the server may determine whether the license plate information sent by the ith camera is the same as the license plate information sent by the i-1 th camera according to the license plate information included in the instruction sent by the ith camera and the license plate information of the vehicle in the first picture, and since the license plate information included in the instruction received by the ith camera is the license plate information of the vehicle in the first picture acquired by the i-1 th camera, when the license plate information included in the instruction received by the ith camera is the same as the license plate information of the vehicle in the first picture acquired by the ith camera, it may be determined that the license plate information acquired by the ith camera is the same as the license plate information acquired by the i-1 th camera, and then it may be determined that the vehicle corresponding to the license plate information is illegal. When the license plate information of the vehicle in the first picture sent by the ith camera is the same as the license plate information included in the instruction, the server finds out the first picture sent by the ith camera according to the license plate information of the vehicle in the first picture, finds out the second picture sent by the ith camera and the first picture sent by the ith-1 camera according to the license plate information included in the instruction, and synthesizes the first picture sent by the ith-1 camera, the second picture sent by the ith camera and the first picture sent by the ith camera into illegal process pictures according to the shooting time sequence.

In this embodiment, when the first camera determines that the vehicle is a large vehicle according to the acquired license plate information of the vehicle in the first picture, the first camera sends the acquired first picture and the license plate information of the vehicle in the first picture to the server. And when the ith camera judges that the vehicle is a large vehicle according to the acquired license plate information, the ith camera sends the acquired first picture, the acquired second picture, the license plate information of the vehicle in the first picture and the license plate information included in the instruction to the server. Specifically, when the first camera or/and the ith camera determines that the license plate is a yellow license plate according to the license plate information of the vehicle in the acquired first picture or the algorithm detects that the vehicle is a large vehicle according to the type of the vehicle, the vehicle in the acquired first picture is determined to be the large vehicle. The license plate of the learner-driven vehicle is a yellow license plate and contains the words for learning, and when the acquired license plate is the yellow license plate but does not contain the words for learning, the vehicle in the first picture can be determined to be a large vehicle. Therefore, the server can judge whether the illegal behaviors of the large-scale vehicles exist according to the received pictures and the license plate information sent by the N cameras.

In this embodiment, the road may be an expressway, the first lane may be a fast lane of the expressway, and the second lane may be a traffic lane of the expressway. However, the invention is not limited to this, the road may also be an urban road, the first lane may be a bus lane, the second lane may be a common vehicle lane, and the common vehicle may temporarily occupy the bus lane to overtake.

In summary, the illegal activity detection method provided by the embodiment detects the illegal activity of the vehicle through the picture taken by the camera, and the efficiency is high. Each camera acquires a first picture shot when the vehicle passes through each position in a group of positions on a corresponding first lane, and when a certain camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the corresponding group of positions according to the acquired first picture, the acquired license plate information of the vehicle is sent to a server; the server judges that the license plate information sent by at least two adjacent cameras is the same, determines vehicle violation corresponding to the license plate information, detects violation behaviors through the at least two adjacent cameras to increase the detection distance, effectively proves that the vehicle occupies a express way for a long distance, and judges whether the vehicle is illegal or not with higher accuracy; when a certain camera judges that no other vehicle exists on the adjacent second lane in the process that the vehicle passes through a group of positions, an instruction is sent to the adjacent next camera, so that the adjacent next camera acquires a second picture, and the camera and the adjacent next camera can be proved to be two adjacent cameras in positions through the second picture, so that the persuasion of illegal evidence is increased.

To specifically describe the example of two cameras disposed on the road, referring to fig. 2, a first camera 1011 and a second camera 1012 are disposed on the road, and the first camera 1011 is a camera through which the vehicle first passes on the first lane. A first lane in front of the lens of the first camera 1011 is provided with position 1, position 2 and position 3, and a first lane between the first camera 1011 and the second camera 1012 is provided with position 4, position 5 and position 6. Referring to fig. 8, the method for detecting an illegal activity includes the following steps.

Step 501: when the first camera 1011 detects that a vehicle runs on the first lane, the first camera 1011 acquires a first picture taken when the vehicle runs to the position 1, the position 2 and the position 3 respectively and license plate information corresponding to the first picture.

The first camera 1011 takes a picture of a road in front of the lens in real time, detects whether a vehicle runs on the first lane according to the picture when a picture is taken, and detects the current position of the vehicle if the vehicle runs. The first camera 1011 may detect the vehicle before the vehicle travels to position 1 or position 1, then the first camera 1011 acquires a first picture taken at position 1; then, when the first camera 1011 continues to take pictures and detects that the vehicle passes through the position 2 in the position group according to the pictures, the first picture taken at the position 2 is obtained; the first camera 1011 then continues to take pictures, taking the first picture taken at position 3.

The first camera 1011 may acquire the license plate information of the vehicle according to any one of the acquired three first pictures, and use the acquired license plate information as the license plate information of the vehicle in each of the three first pictures. The license plate information may include a license plate number, a license plate color, and the like.

Since the position 3 is closest to the first camera 1011 and the first picture taken at the position 3 is clearest, the accuracy of acquiring the license plate information of the vehicle from the first picture taken at the position 3 is highest.

Step 502: when the first camera 1011 determines that no vehicle is running on the second lane in the process of the vehicle passing through the position 1 to the position 3, an instruction including the license plate information is sent to the second camera 1012, and the first picture and the license plate information of the vehicle in the first picture are sent to the server.

In this step, the first camera 1011 determines that no vehicle is traveling in the second lane while the vehicle passes through its corresponding set of positions, which may be, but is not limited to, the two manners described above in step 202.

The first picture sent by the first camera 1011 to the server may be three first pictures obtained by the first camera, or may be one picture obtained by synthesizing the three first pictures obtained by the first camera. The first camera 1011 sends an instruction to the second camera 1012 to trigger the second camera 1012 to take a picture.

Step 503: the server receives and stores the first picture sent by the first camera 1011 and the license plate information of the vehicle in the first picture.

Step 504: the second camera 1012 receives an instruction sent by the first camera 1011 to obtain a second picture, the instruction sent by the first camera 1011 includes the license plate information of the vehicle in the first picture obtained by the instruction, and the second camera 1012 sends the second picture and the license plate information included in the instruction to the server.

In this step, the second camera 1012 may set the license plate information of the vehicle in the acquired second picture as the license plate information included in the instruction it receives.

Step 505: when the second camera 1012 detects that the vehicle runs on the first lane, the second camera 1012 acquires a first picture taken when the vehicle runs to the position 4, the position 5 and the position 6 and acquires the license plate information of the vehicle in the first picture.

The second camera 1012 takes a picture of the road in front of the lens in real time, detects whether a vehicle is running on the first lane according to a picture when the picture is taken every time, and detects the current position of the vehicle if the vehicle is running. The second camera 1012 may detect the vehicle before it travels to position 4 or position 4, then the second camera 1012 takes a first picture taken at position 4; then the second camera 1012 continues to take pictures and upon detecting that the vehicle passes position 5 based on the pictures, acquires the first picture taken at position 5; the second camera 1012 then continues to take pictures, taking the first picture taken at position 6.

Step 506: when the second camera 1012 determines that no vehicle is running in the second lane in the process of passing through the position 4 to the position 6, the first picture and the license plate information of the vehicle in the first picture are sent to the server.

In this step, the second camera 1012 determines that no vehicle is traveling in the second lane while the vehicle is passing through its corresponding set of positions, which may be in the two manners described above in step 202, but is not limited to the two manners described above.

Step 507: the server receives and stores the first picture, the second picture, the license plate information of the vehicle in the first picture and the license plate information included in the instruction sent by the second camera 1012.

Step 508: the server determines that the license plate information included in the first picture instruction sent by the first camera 1011 and the second camera 1012 is the same, determines that the vehicle corresponding to the license plate information is illegal, and synthesizes the pictures sent by the first camera 1011 and the second camera 1012 into illegal process pictures.

Specifically, the server may determine whether the license plate information sent by the second camera 1012 is the same as the license plate information sent by the first camera 1011 according to the license plate information included in the instruction sent by the second camera 1012 and the license plate information of the vehicle in the first picture, and since the license plate information included in the instruction received by the second camera 1012 is the license plate information of the vehicle in the first picture sent by the first camera 1011, when the license plate information included in the instruction received by the second camera 1012 is the same as the license plate information of the vehicle in the first picture acquired by the second camera 1012, it may be determined that the license plate information acquired by the second camera 1012 is the same as the license plate information acquired by the first camera 1011, and then it may be determined that the vehicle corresponding to the license plate information is illegal. When the server judges that the license plate information of the vehicle in the first picture sent by the second camera 1012 is the same as the license plate information included in the instruction, the server finds out the first picture sent by the second camera 1012 according to the license plate information of the vehicle in the first picture, finds out the second picture sent by the second camera 1012 and the first picture sent by the first camera 1011 according to the license plate information included in the instruction, and synthesizes the first picture sent by the first camera 1011, the second picture sent by the second camera 1012 and the first picture sent by the second camera 1012 into illegal process pictures in sequence according to the shooting time sequence.

Referring to fig. 3, a concrete description will be given by taking an example in which three cameras are disposed on a road, a first camera 1011, a second camera 1012, and a third camera 1013 are disposed on the road, and the first camera 1011 is a camera through which a vehicle first passes on the road. A first lane in front of the lens of the first camera 1011 is provided with position 1, position 2 and position 3, a first lane between the first camera 1011 and the second camera 1012 is provided with position 4, position 5 and position 6, and a first lane between the second camera 1012 and the third camera 1013 is provided with position 7, position 8 and position 9. Referring to fig. 9, the method for detecting an illegal action includes the following steps.

Step 601: when the first camera 1011 detects that a vehicle runs on the first lane, the first camera 1011 acquires a first picture taken when the vehicle runs to each of the position 1, the position 2 and the position 3 and license plate information of the vehicle in the first picture.

The first camera 1011 takes a picture of a road in front of the lens in real time, detects whether a vehicle runs on the first lane according to the picture when a picture is taken, and detects the current position of the vehicle if the vehicle runs. The first camera 1011 may detect the vehicle before the vehicle travels to position 1 or position 1, then the first camera 1011 acquires a first picture taken at position 1; then, the first camera 1011 continues to take pictures and acquires a first picture taken at the position 2 when it is detected that the vehicle passes through the position 2 according to the pictures; the first camera 1011 then continues to take pictures, taking the first picture taken at position 3.

Since the position 3 is closest to the first camera and the first picture taken at the position 3 is clearest, the accuracy of obtaining the license plate information of the vehicle according to the first picture taken at the position 3 is highest.

Step 602: when the first camera 1011 determines that no vehicle runs on the second lane in the process that the vehicle passes through the position 1 to the position 3, an instruction including the acquired license plate information is sent to the second camera 1012, and the first picture and the license plate information of the vehicle in the first picture are sent to the server.

Step 603: the server receives and stores the first picture sent by the first camera 1011 and the license plate information of the vehicle in the first picture.

Step 604: the second camera 1012 receives an instruction sent by the first camera 1011 to obtain a second picture, the instruction sent by the first camera 1011 includes the license plate information of the vehicle in the first picture obtained by the instruction, and the second camera 1012 sends the second picture and the license plate information included in the instruction to the server.

Step 605: when the second camera 1012 detects that the vehicle runs on the first lane, the second camera 1012 acquires a first picture taken when the vehicle runs to the position 4, the position 5 and the position 6 and acquires the license plate information of the vehicle in the first picture.

Step 606: when the second camera 1012 determines that no vehicle runs on the second lane in the process that the vehicle passes through the position 4 to the position 6, an instruction including the acquired license plate information is sent to the third camera 1013, and the first picture and the license plate information of the vehicle in the first picture are sent to the server.

Step 607: the server receives and stores the first picture, the second picture, the license plate information of the vehicle in the first picture and the license plate information included in the instruction sent by the second camera 1012.

The server correspondingly stores the received license plate information of the vehicle in the first picture and the received license plate information of the vehicle in the first picture, the received license plate information included in the second picture and the received license plate information included in the command in a corresponding relation between the picture and the license plate information, and the corresponding relation can be located in a hard disk and a database, so that the license plate information of the vehicle in the first picture and the first picture can be directly called from the database and the hard disk in the subsequent illegal detection process.

Step 608: the third camera 1013 receives the instruction sent by the second camera 1012 to obtain a second picture, the instruction sent by the second camera 1012 includes the license plate information of the vehicle in the first picture obtained by the instruction, and the third camera 1013 sends the second picture and the license plate information included in the received instruction to the server.

In this step, the third camera 1013 may set the acquired license plate information of the vehicle in the second picture as the license plate information included in the received instruction.

Step 609: when the third camera 1013 detects that a vehicle is traveling in the first lane, the third camera 1013 acquires a first picture taken by the vehicle when the vehicle travels to the position 7, the position 8, and the position 9, and acquires license plate information of the vehicle in the first picture.

The third camera 1013 takes a picture of the road in front of its lens in real time, detects whether there is a vehicle running on the first lane according to one picture when the picture is taken, and detects the current position of the vehicle if there is a vehicle. The third camera 1013 may detect the vehicle before it is driven to position 7 or position 7, then the third camera 1013 takes a first picture taken at position 7; then the third camera 1013 continues to take pictures and from the pictures it is detected that the vehicle passes the position 8, the first picture taken at the position 8 is taken; the third camera 1013 then continues to take pictures, taking the first picture taken at position 9.

Step 610: when the third camera 1013 determines that no vehicle runs on the second lane in the process that the vehicle passes through the position 7 to the position 9, the first picture and the license plate information of the vehicle in the first picture are sent to the server.

In this step, the third camera 1013 determines that no vehicle is traveling in the second lane while the vehicle passes through the corresponding set of positions, which may be, but is not limited to, the two manners described in the above step 202.

Step 611: the server receives and stores the first picture, the second picture and the license plate information of the vehicle in the first picture and the license plate information included in the instruction sent by the third camera 1013.

Step 612: the server judges that the license plate information of the vehicles in the first pictures sent by the at least two adjacent cameras is the same, determines vehicle violation corresponding to the license plate information, and synthesizes the pictures sent by the at least two adjacent cameras into a violation process picture.

Specifically, when the server determines that the license plate information of the vehicle in the first picture sent by the first camera 1011 and the second camera 1012 is the same, it determines that the vehicle corresponding to the license plate information is illegal, and synthesizes the first picture sent by the first camera 1011, the first picture sent by the second camera 1012 and the second picture into illegal process pictures; when the server judges that the license plate information of the vehicle in the first picture sent by the second camera 1012 and the third camera 1013 is the same, determining that the license plate corresponding to the license plate information is illegal, and synthesizing the first picture sent by the second camera 1012, the first picture sent by the third camera 1013 and the second picture into illegal process pictures; when the server judges that the license plate information of the vehicles in the first pictures sent by the first camera 1011, the second camera 1012 and the third camera 1013 are the same, it is determined that the vehicles corresponding to the license plate information illegally occupy the first lane, and the first picture sent by the first camera 1011, the first picture and the second picture sent by the second camera 1012 and the first picture and the second picture sent by the third camera 1013 are synthesized into an illegal process picture.

When the number N of cameras in the camera system is greater than three, the detection method of the illegal activity is similar to that described above, and is not described again.

An embodiment of the present invention provides a camera, referring to fig. 10, where the camera is any one of camera systems, and the camera system may be the camera system described in any one of fig. 1 to 3, and the camera includes an acquiring module 701 and a sending module 702.

The acquiring module 701 is used for acquiring a first picture shot by a vehicle when the vehicle is detected to run to each position in a group of positions set on a first lane corresponding to a camera and license plate information of the vehicle when the vehicle runs to the first lane;

a sending module 702, configured to send the first picture and the license plate information of the vehicle to the server when it is determined that no vehicle is running on the second lane in the process that the vehicle passes through each position in the group of positions corresponding to the camera, so that the server detects whether the vehicle is illegal.

Optionally, the sending module 702 is further configured to send an instruction including license plate information of the vehicle to a next camera adjacent to the camera when it is determined that no vehicle is running on the second lane in the process that the vehicle passes through each position in the group of positions, where the instruction is used to trigger the next camera to take a picture.

Optionally, the camera further comprises:

the receiving module is used for receiving an instruction sent by the previous camera adjacent to the camera when the camera does not allow the vehicle to pass through the first camera of the N cameras, wherein the instruction comprises license plate information acquired by the previous adjacent camera;

optionally, the sending module 702 is further configured to send the second picture and the license plate information included in the instruction to the server when it is determined that no vehicle is running on the second lane in the process that the vehicle passes through each position in the group of positions.

Optionally, the sending module 702 is configured to send the first picture and the license plate information of the vehicle to the server when the license plate type of the vehicle is a license plate type corresponding to a large vehicle.

In the embodiment of the invention, the illegal behaviors of the vehicle are detected through the pictures shot by the camera, so that the efficiency is higher. The method comprises the steps that a camera obtains a first picture shot when a vehicle passes through each position in a group of positions on a corresponding first lane, when the camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the corresponding group of positions according to the obtained first picture, the obtained license plate information of the vehicle is sent to a server, the server judges that the license plate information sent by at least two adjacent cameras is the same, vehicle violation corresponding to the license plate information is determined, the distance for detecting illegal behaviors can be increased through at least two adjacent cameras, the fact that the vehicle occupies a express lane in a long distance is effectively proved, and the accuracy for judging whether the vehicle violates the law is higher.

With regard to the camera in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

An embodiment of the present invention provides a server, and referring to fig. 11, the server includes a receiving module 801 and a determining module 802.

The system comprises a receiving module 801, a processing module and a display module, wherein the receiving module is used for receiving pictures and license plate information sent by at least two adjacent cameras in a camera system, the camera system comprises N cameras, N is an integer greater than or equal to 2, the N cameras are arranged on a road, and the adjacent cameras are spaced by a preset distance;

the determining module 802 is configured to detect that the license plate information sent by the at least two cameras are the same, determine a vehicle violation corresponding to the license plate information, and synthesize pictures sent by the at least two cameras into a violation process picture.

In the embodiment of the invention, the illegal behaviors of the vehicle are detected through the pictures shot by the camera, so that the efficiency is higher. The method comprises the steps that a camera obtains a first picture shot when a vehicle passes through each position in a group of positions on a corresponding first lane, when the camera judges that no other vehicle exists on an adjacent second lane in the process that the vehicle passes through the corresponding group of positions, the obtained license plate information of the vehicle is sent to a server, the server judges that the license plate information sent by at least two adjacent cameras is the same, vehicle violation corresponding to the license plate information is determined, the illegal behaviors are detected through at least two adjacent cameras, the detection distance can be increased, the fact that the vehicle occupies a express lane in a long distance is effectively proved, and the accuracy of judging whether the vehicle is illegal or not is higher.

The above description is only for facilitating the understanding of the technical solutions of the present invention by those skilled in the art, and is not intended to limit the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting illegal activities, wherein the method is applied to a camera system, the camera system comprises N cameras, N is an integer greater than or equal to 2, the N cameras are arranged on a road and adjacent cameras are spaced apart by a preset distance, the road comprises a first lane and a second lane which are adjacent in position, and the method comprises:

when the ith camera is not the last camera in the N cameras, and the ith camera determines that no vehicle runs on the second lane in the process that the vehicle passes through each position in the group of positions, sending an instruction including the license plate information of the vehicle to a next camera adjacent to the ith camera, and sending the first picture and the license plate information of the vehicle to a server so that the server judges whether the vehicle is illegal, wherein the instruction is used for triggering the next camera to take a picture, and the next camera is used for sending the picture taken by the next camera and the license plate information contained in the instruction to the server;

the server is used for correspondingly storing the first picture, the license plate information of the vehicle, the picture shot by the next camera and the license plate information contained in the instruction in a corresponding relation between the picture and the license plate information, and the server is also used for determining vehicle violation corresponding to the license plate information when judging that the license plate information sent by at least two adjacent cameras is the same, and synthesizing the pictures sent by the at least two cameras into a picture of the violation process;

the method further comprises the following steps:

when the ith camera is not the first camera of the N cameras, the ith camera receives an instruction sent by the last camera adjacent to the ith camera, wherein the instruction comprises the license plate information acquired by the last camera; and the ith camera shoots a second picture according to the instruction and sends the second picture and the license plate information included by the instruction to the server.

2. The method for detecting illegal activities according to claim 1, wherein before sending the first picture and the license plate information of the vehicle to a server, the method comprises:

3. A method for detecting an illegal activity, the method comprising:

the method comprises the steps that a server receives pictures and license plate information sent by at least two adjacent cameras in a camera system, the pictures and the license plate information are correspondingly stored in a corresponding relation between the pictures and the license plate information, the camera system comprises N cameras, N is an integer larger than or equal to 2, the N cameras are arranged on a road, the adjacent cameras are spaced at a preset distance, the ith camera in the N cameras is used for sending an instruction comprising the license plate information of a vehicle to the next adjacent camera when the ith camera is determined not to pass through the last camera in the N cameras and no vehicle runs on a second lane in the process that the vehicle passes through each position in a group of positions is determined, and sending a first picture and the license plate information of the vehicle to the server, wherein the instruction is used for triggering the next camera to take pictures, the next camera is used for sending the picture shot by the next camera and the license plate information contained in the instruction to the server, and i is an integer from 1 to N;

the ith camera in the N cameras is further used for receiving an instruction sent by the last camera adjacent to the ith camera when the ith camera is determined not to pass by the first camera in the N cameras, taking a second picture according to the instruction, and sending the second picture and the license plate information included in the instruction to the server, wherein the instruction includes the license plate information acquired by the last camera;

and the server judges that the license plate information sent by the at least two adjacent cameras is the same, determines vehicle violation corresponding to the license plate information, and synthesizes pictures sent by the at least two cameras into a violation process picture.

4. A camera, wherein the camera is any one of a camera system, the camera system includes N cameras, N being an integer greater than or equal to 2, the N cameras being disposed on a road and adjacent two cameras being spaced apart by a preset distance, the road including a first lane and a second lane which are located adjacent to each other, the camera includes:

a sending module, configured to send, when an ith camera is not a last camera that the vehicle passes through among the N cameras, and the ith camera determines that no vehicle is traveling on the second lane in a process where the vehicle passes through each position in a group of positions corresponding to the cameras, an instruction including license plate information of the vehicle to a next camera adjacent to the ith camera, and send the first picture and the license plate information of the vehicle to a server, so that the server determines whether the vehicle is illegal, where the instruction is used to trigger the next camera to take a picture, and the next camera is used to send the picture taken by the next camera and the license plate information included in the instruction to the server;

the camera further includes:

5. The camera of claim 4,

the sending module is used for sending the first picture and the license plate information of the vehicle to a server when the license plate type of the vehicle is the license plate type corresponding to the large vehicle.

6. A server, characterized in that the server comprises:

a receiving module, configured to receive pictures and license plate information sent by at least two cameras in a camera system that are adjacent to each other, and store the pictures and the license plate information in a corresponding relationship between the pictures and the license plate information, where the camera system includes N cameras, where N is an integer greater than or equal to 2, the N cameras are disposed on a road, and a preset distance is provided between the adjacent two cameras, an ith camera of the N cameras is configured to send an instruction including the license plate information of a vehicle to a next camera adjacent to the ith camera when it is determined that the ith camera is not a vehicle that passes through a last camera of the N cameras, and it is determined that no vehicle is traveling on a second lane during a process in which the vehicle passes through each position of a group of positions, and send a first picture and the license plate information of the vehicle to the server, where the instruction is used to trigger the next camera to take a picture, the next camera is used for sending the picture shot by the next camera and the license plate information contained in the instruction to the server, and i is an integer from 1 to N;

the determining module is used for determining vehicle violation corresponding to the license plate information when the license plate information sent by the at least two cameras is judged to be the same, and synthesizing pictures sent by the at least two cameras into a violation process picture.