CN107305627B - Vehicle video monitoring method, server and system - Google Patents
Vehicle video monitoring method, server and system Download PDFInfo
- Publication number
- CN107305627B CN107305627B CN201610256691.0A CN201610256691A CN107305627B CN 107305627 B CN107305627 B CN 107305627B CN 201610256691 A CN201610256691 A CN 201610256691A CN 107305627 B CN107305627 B CN 107305627B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target vehicle
- image data
- target
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The embodiment of the invention provides a vehicle video monitoring method, which comprises the steps of receiving first image data sent by a long-range camera, receiving second image data sent by a short-range camera, obtaining position information of a target vehicle in the first image data, finding the target vehicle in a second image according to shooting time and the obtained position information, and obtaining characteristic information of the target vehicle in the second image; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle. In the invention, the server receives second image data which is sent by the close-range camera and shot by the far-range camera on the same snapping line, and finds the target vehicle in the second image data according to shooting time and position information of the target vehicle, so that the process that the target vehicle carries out illegal activities can be obtained, the close-up image of the target vehicle can be obtained, the license plate information of the target vehicle can be determined, and the evidence of the illegal activities of the vehicle at high speed and in long distance can be obtained.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a vehicle video monitoring method, a server and a system.
Background
At present, a long-range camera and a short-range camera are generally used for illegal evidence collection of vehicles running on a road. When the close-range camera is used for carrying out illegal evidence obtaining on the vehicle, the process that the vehicle carries out illegal activities and the close-up image of the vehicle can be obtained, so that the license plate information of the vehicle is determined to finish the illegal evidence obtaining of the vehicle, however, for the illegal activities with high movement speed and large movement distance, such as vehicle illegal lane changing, snake-shaped driving, hurdle pursuit and the like, the complete process that the vehicle carries out illegal activities cannot be covered by the close-range camera, and therefore the evidence obtaining of the high-speed long-distance illegal activities of the vehicle cannot be realized.
When the long-range camera is used for carrying out illegal evidence collection on the vehicle, the complete process of illegal behaviors of the vehicle can be monitored, but the close-up image of the illegal behavior vehicle cannot be obtained, so that the license plate information of the vehicle cannot be determined, and therefore the evidence collection of the illegal behaviors of the vehicle at a high speed and in a long distance cannot be realized.
When illegal evidence taking is carried out on a vehicle in a mode of combining a close-range camera and a far-range camera, the far-range camera is used for monitoring illegal behaviors of the vehicle, when the illegal behaviors are detected, an instruction for adjusting the shooting angle and the lens focal length of the camera is sent to the close-range camera, the close-range camera is drawn close and tracks the vehicle with the illegal behaviors, a close-up image of the vehicle is obtained, and therefore the license plate information of the vehicle is determined to finish the illegal evidence taking of the vehicle, however, for the illegal behaviors with high movement speed and large movement distance, such as lane changing, snake-shaped driving, barrier vehicle stepping and the like, the time of about 1-3 s is generally needed when the close-range camera is drawn close and tracks the vehicle with the illegal behaviors, when the speed of the vehicle is high (more than 60km/h), the vehicle with the illegal behaviors in the close-range camera drawing process is far away from the view field of the close-range camera, at this time, a close-up view of the vehicle in which the illegal activity occurs cannot be obtained, and therefore, the evidence of the illegal activity at a high speed over a long distance cannot be obtained.
Disclosure of Invention
The embodiment of the invention aims to provide a vehicle video monitoring method, a server and a system so as to obtain evidence of vehicle illegal behaviors. The specific technical scheme is as follows:
a vehicle video monitoring method is applied to a server in a vehicle video monitoring system, and the system also comprises: the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; the method comprises the following steps that a monitoring view field range of a distant view camera completely covers a monitoring view field range of a close view camera, and a snapping line is arranged at the same position of the overlapped view fields of the distant view camera and the close view camera, and comprises the following steps:
receiving first image data sent by the long-range view camera, wherein the long-range view camera acquires moving tracks of all vehicles in a monitoring view field, and a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle are determined according to the acquired moving tracks; the first image data includes a plurality of first images photographed when the target vehicle has an illegal action, an illegal action type of the target vehicle, a first target image photographed when the target vehicle reaches a snapshot line, and a photographing time of the first target image;
receiving second image data sent by the close-range camera, wherein the close-range camera shoots a second image when monitoring that a vehicle reaches a snapshot line, and the second image data comprises a plurality of second images and shooting time of the second images;
acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information;
and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
Optionally, the finding the target vehicle in the second image according to the shooting time and the acquired position information of the target vehicle includes:
according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data, correspondingly determining a reference vehicle which is matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, and if so, determining that the reference vehicle is the target vehicle.
Optionally, the feature information further includes:
body color, vehicle type, and sub-brand of vehicle.
A server is applied to a vehicle video monitoring system, and the system further comprises: the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring field of view scope of distant view camera covers completely the monitoring field of view scope of close view camera be provided with the line of taking a candid photograph on the same position of the overlapping field of view of distant view camera and close view camera, the server includes:
the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for performing the steps of:
receiving first image data sent by the long-range view camera, wherein the long-range view camera acquires moving tracks of all vehicles in a monitoring view field, and a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle are determined according to the acquired moving tracks; the first image data includes a plurality of first images photographed when the target vehicle has an illegal action, an illegal action type of the target vehicle, a first target image photographed when the target vehicle reaches a snapshot line, and a photographing time of the first target image;
receiving second image data sent by the close-range camera, wherein the close-range camera shoots a second image when monitoring that a vehicle reaches a snapshot line, and the second image data comprises a plurality of second images and shooting time of the second images;
acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information;
and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
A vehicle video monitoring method is applied to a vehicle video monitoring system, and the system comprises the following steps: the system comprises a server, a long-range camera and a short-range camera, wherein the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; the method comprises the following steps that a monitoring view field range of a distant view camera completely covers a monitoring view field range of a close view camera, and a snapping line is arranged at the same position of the overlapped view fields of the distant view camera and the close view camera, and comprises the following steps:
the long-range view camera acquires the moving tracks of all vehicles in the monitoring field of view, and determines a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle according to the acquired moving tracks; associating a plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and shooting time of the first target image to generate first image data, and sending the first image data to the server;
when the close-range camera monitors that a vehicle arrives at a capturing line, shooting a second image, associating the plurality of shot second images with shooting time of the second image to generate second image data, and sending the second image data to the server;
the server receives first image data sent by the distant view camera and second image data sent by the close view camera, position information of a target vehicle is obtained in the first image data, the target vehicle is found in the second image according to shooting time and the obtained position information of the target vehicle, and feature information of the target vehicle is obtained in the second image, wherein the feature information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
Optionally, the long-range view camera acquires moving tracks of all vehicles in the monitoring field of view, and determines a target vehicle in which an illegal action occurs and an illegal action type of the target vehicle according to the acquired moving tracks, including:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; and carrying out illegal behavior analysis on the vehicle according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear part of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle, and determining the type of the illegal behaviors of the vehicle.
Optionally, the determining the type of the illegal action of the vehicle includes:
judging whether the lane number of the vehicle changes or not, if so, determining the number of times of the change of the lane number of the vehicle, and if the number of times of the change of the lane number of the vehicle in a first preset time is 1 time and the distance between the vehicle and the vehicle entering the rear part of the lane is greater than a first preset threshold value, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is illegal lane change; if the lane number change times of the vehicle in the second preset time is more than 1 time, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is snake-shaped driving; and if the lane number of the vehicle is changed alternately with the lane numbers of other vehicles within the third preset time, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is the violent vehicle pursuit.
Optionally, the finding the target vehicle in the second image according to the shooting time and the acquired position information of the target vehicle includes:
according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data; and correspondingly determining a reference vehicle matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, and if so, determining that the reference vehicle is the target vehicle.
Optionally, the feature information further includes:
body color, vehicle type, and sub-brand of vehicle.
A vehicle video surveillance system, the system comprising: the system comprises a server, a long-range camera and a short-range camera, wherein the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring field of view scope of distant view camera covers completely the monitoring field of view scope of close view camera, be provided with the snap shot line on the same position of the overlapping field of view of distant view camera and close view camera:
the long-range camera is used for acquiring the moving tracks of all vehicles in the monitoring field, and determining a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle according to the acquired moving tracks; associating a plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and shooting time of the first target image to generate first image data, and sending the first image data to the server;
the close-range camera is used for shooting a second image when a vehicle is monitored to arrive at the snapshot line, associating the plurality of shot second images with shooting time of the second image to generate second image data, and sending the second image data to the server;
the server is used for receiving first image data sent by the distant view camera and second image data sent by the close view camera, acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
Optionally, the long-range camera is specifically configured to:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; analyzing the vehicle for illegal behaviors according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear part of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle and determining the type of the illegal behaviors of the vehicle; associating the plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, the first target image shot when the target vehicle reaches the snapshot line and the shooting time of the first target image to generate first image data, and sending the first image data to the server.
Optionally, the long-range camera is specifically configured to:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; carrying out illegal behavior analysis on the vehicle according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle, judging whether the lane number of the vehicle is changed, if so, determining the number of times of lane number change of the vehicle, and if the number of times of lane number change of the vehicle in first preset time is 1 time and the distance between the vehicle and the vehicle entering the rear of the lane is greater than a first preset threshold value, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is an illegal lane change; if the lane number change times of the vehicle in the second preset time is more than 1 time, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is snake-shaped driving; and if the lane number of the vehicle is changed alternately with the lane numbers of other vehicles within the third preset time, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is the violent vehicle pursuit.
Optionally, the server is specifically configured to:
receiving first image data sent by the long-range view camera and second image data sent by the short-range view camera, and acquiring position information of a target vehicle in the first image data; according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data; correspondingly determining a reference vehicle matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, if so, determining that the reference vehicle is the target vehicle, and obtaining the characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
In the embodiment of the invention, a server in vehicle video monitoring receives first image data sent by a distant view camera, receives second image data sent by a close view camera and shot by the distant view camera on the same snapping line, and finds a target vehicle in the second image data according to shooting time and position information of the target vehicle which is acquired from the first image data and has illegal behaviors. Therefore, the process that the target vehicle is subjected to the illegal action can be obtained, the close-up image of the target vehicle can be obtained, the license plate information of the target vehicle can be determined, the evidence of the illegal action of the vehicle is obtained, and the evidence of the illegal action of the vehicle in a high speed and long distance can be obtained. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a vehicle video monitoring method according to an embodiment of the present invention;
FIG. 2 is a flow chart diagram of a machine-learned vehicle detection method;
fig. 3 is a schematic structural diagram of a server according to an embodiment of the present invention;
FIG. 4 is another schematic flow chart of a vehicle video monitoring method according to an embodiment of the present invention;
FIG. 5 is a schematic view of a snake;
fig. 6 is a schematic structural diagram of a vehicle video monitoring system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
First, a vehicle video monitoring method according to an embodiment of the present invention will be described below.
As shown in fig. 1, in the vehicle video monitoring method provided in the embodiment of the present invention, the method shown in fig. 1 may be applied to a server in a vehicle video monitoring system, and the system may further include: the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring view field range of the distant view camera completely covers the monitoring view field range of the close view camera, and a snapping line is arranged at the same position of the overlapping view fields of the distant view camera and the close view camera, and the method may include the following steps:
s101: receiving first image data sent by a distant view camera, wherein the distant view camera acquires moving tracks of all vehicles in a monitoring field, and determines a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle according to the acquired moving tracks; the first image data includes a plurality of first images captured when the target vehicle has an illegal action, an illegal action type of the target vehicle, a first target image captured when the target vehicle reaches a snapshot line, and a shooting time of the first target image.
In order to obtain the illegal information of the vehicle, a distant view camera and a close view camera are required to be arranged on the moving path of the vehicle, and the passing vehicle is detected and tracked, wherein the monitoring view field range of the distant view camera completely covers the monitoring view field range of the close view camera, and a snapshot line is arranged at the same position of the overlapped view fields of the distant view camera and the close view camera. And analyzing the vehicle track through the long-range camera to judge whether the vehicle has illegal driving behaviors, thereby determining the target vehicle with the illegal behaviors and the illegal behavior type of the target vehicle.
The method for detecting and tracking the vehicle is multiple, and the machine learning algorithm has higher detection performance, so that as an implementation mode of the invention, a machine learning vehicle detection method can be selected, a specific model training and vehicle target detection process is shown in fig. 2, the detector training process is to select sample data, obtain a positive sample and a negative sample, then perform feature extraction on the positive sample and the negative sample, and place the positive sample and the negative sample into a training classifier for training; and in the dynamic area, the target detection process is to input pictures, to perform sliding window detection on the input pictures, to perform feature extraction, to perform feature calculation and threshold comparison on the extracted features through a training classifier, and to finally classify and detect results and output the results. Since the vehicle detection method of machine learning is the prior art, it is not described herein again. A target detection method based on Haar characteristics and an AdaBoost learning algorithm can be adopted, the method can process target detection in real time and can obtain a better detection effect; or adopting detection based on HOG characteristics and SVM learning algorithm; or a DPM (deformable Parts model) target detection algorithm is adopted, the method is a detection method based on components, the method has strong robustness on deformation of the target, and the method is reasonable and is not repeated in the invention.
The method comprises the steps that a long-range camera can shoot the complete process of illegal behaviors of a vehicle, but cannot obtain a close-up image of the illegal behaviors, so that the license plate information of the vehicle cannot be determined, and therefore, a plurality of first images shot when the target vehicle is subjected to illegal behaviors, sent by the long-range camera, types of the illegal behaviors of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and first image data generated by correlation of shooting time of the first target image are received, and the vehicle subjected to illegal behaviors is determined through the close-up image shot by a short-range camera in the following process.
S102: and receiving second image data sent by a close-range camera, wherein the close-range camera shoots a second image when monitoring that a vehicle reaches a snapshot line, and the second image data comprises a plurality of second images and shooting time of the second images.
The close-range camera shoots the second image when monitoring that the vehicle reaches the capture line, so that the close-up image of the vehicle can be shot, and the license plate information of the vehicle can be determined.
S103: and acquiring the position information of a target vehicle in the first image data, finding the target vehicle in the second image according to the shooting time and the acquired position information of the target vehicle, and acquiring the characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information.
After receiving the first image data and the second image data, acquiring position information of a target vehicle in the first image data, searching a best matched vehicle in the second image according to shooting time and the position information of the target vehicle, determining the best matched vehicle as the target vehicle, and acquiring characteristic information of the target vehicle, wherein the characteristic information of the target vehicle is information which is identified from a close-up image shot by a close-up camera and at least comprises license plate information, and can also comprise information such as a vehicle body color, a vehicle type, a vehicle sub-brand, a cab characteristic and a driver characteristic.
S104: and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
And associating the information containing the illegal behaviors of the target vehicle to generate the illegal information of the target vehicle, and uploading the illegal information to the central platform through the network to be used as a punishment basis for the illegal vehicle.
In the embodiment of the invention, a server in vehicle video monitoring receives first image data sent by a distant view camera, receives second image data sent by a close view camera and shot by the distant view camera on the same snapping line, and finds a target vehicle in the second image data according to shooting time and position information of the target vehicle which is acquired from the first image data and has illegal behaviors. Therefore, the process that the target vehicle is subjected to the illegal action can be obtained, the close-up image of the target vehicle can be obtained, the license plate information of the target vehicle can be determined, the evidence of the illegal action of the vehicle is obtained, and the evidence of the illegal action of the vehicle in a high speed and long distance can be obtained.
Specifically, finding the target vehicle in the second image according to the shooting time and the acquired position information of the target vehicle may include:
according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data, correspondingly determining a reference vehicle which is matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, and if so, determining that the reference vehicle is the target vehicle.
Since the snapping lines are arranged at the same positions of the overlapped view fields of the long-range view camera and the short-range view camera, when the target vehicle reaches the snapping lines, the long-range view camera and the short-range view camera shoot images at the same time, and therefore a second image with the same shooting time as that of the first target image can be found in the second image data according to the shooting time of the first target image.
And correspondingly determining a reference vehicle with the same coordinates as the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, performing similarity measurement on the target vehicle and the reference vehicle, and determining that the reference vehicle and the target vehicle are the same vehicle when the similarity is greater than a second preset threshold value. The similarity measurement method may adopt normalized product correlation, phase correlation, mean square error or mean square error removal, which are all reasonable and are not described in detail herein.
Specifically, the feature information may further include:
body color, vehicle type, and sub-brand of vehicle.
Correspondingly, as shown in fig. 3, an embodiment of the present application further provides a server, which is applied in a vehicle video monitoring system, and the system may further include: the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring field of view scope of the distant view camera completely covers the monitoring field of view scope of the close view camera, a snapshot line is arranged at the same position of the overlapping field of view of the distant view camera and the close view camera, and the server may include:
the device comprises a shell 301, a processor 302, a memory 303, a circuit board 304 and a power circuit 305, wherein the circuit board 304 is arranged inside a space enclosed by the shell, and the processor 302 and the memory 303 are arranged on the circuit board 304; a power supply circuit 305 for supplying power to each circuit or device of the electronic apparatus; memory 303 is used to store executable program code; the processor 302 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 303 for performing the steps of:
receiving first image data sent by the long-range view camera, wherein the long-range view camera acquires moving tracks of all vehicles in a monitoring view field, and a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle are determined according to the acquired moving tracks; the first image data includes a plurality of first images photographed when the target vehicle has an illegal action, an illegal action type of the target vehicle, a first target image photographed when the target vehicle reaches a snapshot line, and a photographing time of the first target image;
receiving second image data sent by the close-range camera, wherein the close-range camera shoots a second image when monitoring that a vehicle reaches a snapshot line, and the second image data comprises a plurality of second images and shooting time of the second images;
acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information;
and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
As shown in fig. 4, a vehicle video monitoring method provided in an embodiment of the present invention is applied to a vehicle video monitoring system, and the system may include: the system comprises a server, a long-range camera and a short-range camera, wherein the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring view field range of the distant view camera completely covers the monitoring view field range of the close view camera, and a snapping line is arranged at the same position of the overlapping view fields of the distant view camera and the close view camera, and the method may include:
s401: the long-range view camera acquires the moving tracks of all vehicles in the monitoring field of view, and determines a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle according to the acquired moving tracks; associating the plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, the first target image shot when the target vehicle reaches the snapshot line and the shooting time of the first target image to generate first image data, and sending the first image data to the server.
In order to shoot the complete process of the illegal behaviors of the vehicles, a long-range camera is required to collect the moving tracks of all vehicles in a monitoring view field, and a target vehicle with the illegal behaviors and the illegal behavior type of the target vehicle are determined according to the obtained moving tracks. After a target vehicle with illegal behaviors is determined, associating a plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and shooting time of the first target image to generate first image data, and sending the first image data to the server so that the server can perform subsequent steps.
S402: the close-range camera shoots a second image when monitoring that a vehicle arrives at the snapshot line, associates the shot second images with shooting time of the second images to generate second image data, and sends the second image data to the server.
In order to capture a close-up view of a vehicle, the close-up camera is required to capture a second image when the vehicle is detected to arrive at a capture line, record the position of the vehicle in the second image, associate the captured second images with the capturing time of the second images to generate second image data, and send the second image data to the server
S403: the server receives first image data sent by the distant view camera and second image data sent by the close view camera, position information of a target vehicle is obtained in the first image data, the target vehicle is found in the second image according to shooting time and the obtained position information of the target vehicle, and feature information of the target vehicle is obtained in the second image, wherein the feature information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
Because the snapping lines are arranged at the same positions of the overlapped view fields of the long-range view camera and the short-range view camera, when the target vehicle reaches the snapping lines, the long-range view camera and the short-range view camera shoot images at the same time, and therefore after the server receives the first image data and the second image data, the second image with the same shooting time as that of the first target image can be found in the second image data according to the shooting time of the first target image.
And acquiring the position information of the target vehicle in the first image data, searching the best matched vehicle in the second image according to the position information of the target vehicle, and determining the best matched vehicle as the target vehicle.
Since the second image is a close-up image taken by the close-up camera, the feature information of the target vehicle can be obtained in the second image, wherein the feature information at least contains the license plate information. And correlating the first image data containing the illegal behaviors of the target vehicle, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle, and uploading the illegal information to a central platform through a network to serve as a punishment basis for the illegal vehicle.
In the embodiment of the invention, a server in vehicle video monitoring receives first image data sent by a distant view camera, receives second image data sent by a close view camera and shot by the distant view camera on the same snapping line, and finds a target vehicle in the second image data according to shooting time and position information of the target vehicle which is acquired from the first image data and has illegal behaviors. Therefore, the process that the target vehicle is subjected to the illegal action can be obtained, the close-up image of the target vehicle can be obtained, the license plate information of the target vehicle can be determined, the evidence of the illegal action of the vehicle is obtained, and the evidence of the illegal action of the vehicle in a high speed and long distance can be obtained.
Specifically, the collecting and monitoring of the moving tracks of all vehicles in the field of view by the long-range view camera and the determining of the target vehicle having the illegal activity and the illegal activity type of the target vehicle according to the obtained moving tracks may include:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; and carrying out illegal behavior analysis on the vehicle according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear part of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle, and determining the type of the illegal behaviors of the vehicle.
The illegal behaviors of the vehicle are generally represented by the change of the lane number and the blockage of other vehicles in the driving process, wherein the blockage of the other vehicles is represented by the distance between the vehicle and the vehicle entering the rear part of the lane, and meanwhile, in order to analyze the illegal behaviors of the vehicle, a picture of the line pressing behaviors of the vehicle needs to be obtained.
Therefore, when the distant view camera collects the moving tracks of all vehicles in the monitoring view field, the lane number where each vehicle is located is identified, wherein the lane line in the monitoring view field can be manually set or automatically identified through lane line detection. When the vehicle enters the monitoring field of the distant view camera for the first time, the lane number of the vehicle is recorded, and when the lane number of the vehicle is identified to be changed, the lane number of the vehicle is updated, so that the lane number and the line pressing state of the vehicle in each frame of picture are calculated.
And calculating the distance between the vehicle and the vehicle entering the rear of the lane according to the moving track of the vehicle and the moving track of the vehicle entering the rear of the lane to which the vehicle belongs, so that illegal behaviors of the vehicle are analyzed according to the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane, whether the vehicle is subjected to illegal behaviors is determined, if yes, the vehicle is determined as a target vehicle, and the illegal behavior type of the vehicle is determined.
Specifically, the determining the type of the illegal behavior of the vehicle may include:
judging whether the lane number of the vehicle changes or not, if so, determining the number of times of the change of the lane number of the vehicle, and if the number of times of the change of the lane number of the vehicle in a first preset time is 1 time and the distance between the vehicle and the vehicle entering the rear part of the lane is greater than a first preset threshold value, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is illegal lane change; if the lane number change times of the vehicle in the second preset time is more than 1 time, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is snake-shaped driving; and if the lane number of the vehicle is changed alternately with the lane numbers of other vehicles within the third preset time, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is the violent vehicle pursuit.
Types of illegal activities include: illegal lane changing, snake driving and hurdle pursuing. Illegal lane change, snake-shaped driving and hurdle pursuit are lane change driving modes that vehicles continuously run for more than 2 (including) times within a specified time, and snake-shaped driving is shown in figure 5. Therefore, the illegal behavior type of the vehicle is judged according to the lane change times of the vehicle and the distance between the vehicle and other vehicles, specifically, the lane change is carried out for 1 time in the preset time and the condition of blocking other vehicles from passing belongs to the illegal lane change, the lane change is carried out in a snake shape for more than 2 times in the preset time, and the behavior that the two vehicles alternately have the illegal lane change in the preset time belongs to the law enforcement pursuit.
Specifically, the finding the target vehicle in the second image according to the shooting time and the acquired position information of the target vehicle may include:
according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data; and correspondingly determining a reference vehicle matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, and if so, determining that the reference vehicle is the target vehicle.
Since the snapping lines are arranged at the same positions of the overlapped view fields of the long-range view camera and the short-range view camera, when the target vehicle reaches the snapping lines, the long-range view camera and the short-range view camera shoot images at the same time, and therefore a second image with the same shooting time as that of the first target image can be found in the second image data according to the shooting time of the first target image.
And correspondingly determining a reference vehicle with the same coordinates as the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, performing similarity measurement on the target vehicle and the reference vehicle, and determining that the reference vehicle and the target vehicle are the same vehicle when the similarity is greater than a second preset threshold value. The similarity measurement method may adopt normalized product correlation, phase correlation, mean square error or mean square error removal, which are all reasonable and are not described in detail herein.
Specifically, the feature information may further include:
body color, vehicle type, and sub-brand of vehicle.
As shown in fig. 6, an embodiment of the present invention provides a structural schematic diagram of a vehicle video monitoring system, where the system includes: a server 61, and a distant view camera 62 and a close view camera 63 connected to the server 61; the long-range camera 62 and the short-range camera 63 are arranged on a moving path of the vehicle; wherein, the monitoring field range of the distant view camera 62 completely covers the monitoring field range of the close view camera 63, and a snapping line is arranged at the same position of the overlapping fields of the distant view camera 62 and the close view camera 63:
the long-range view camera 62 is configured to acquire moving tracks of all vehicles in the monitoring field, and determine a target vehicle in which an illegal action occurs and an illegal action type of the target vehicle according to the acquired moving tracks; associating a plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and shooting time of the first target image to generate first image data, and sending the first image data to the server;
the close-range camera 63 is configured to shoot a second image when it is monitored that a vehicle arrives at the capture line, associate the shot second images with shooting times of the second images to generate second image data, and send the second image data to the server;
the server 61 is configured to receive first image data sent by the distant view camera 62 and second image data sent by the close view camera 63, acquire position information of a target vehicle in the first image data, find the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquire feature information of the target vehicle in the second image, where the feature information at least includes license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
In the embodiment of the invention, a server in vehicle video monitoring receives first image data sent by a distant view camera, receives second image data sent by a close view camera and shot by the distant view camera on the same snapping line, and finds a target vehicle in the second image data according to shooting time and position information of the target vehicle which is acquired from the first image data and has illegal behaviors. Therefore, the process that the target vehicle is subjected to the illegal action can be obtained, the close-up image of the target vehicle can be obtained, the license plate information of the target vehicle can be determined, the evidence of the illegal action of the vehicle is obtained, and the evidence of the illegal action of the vehicle in a high speed and long distance can be obtained.
Specifically, the long-range camera 63 may be specifically configured to:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; analyzing the vehicle for illegal behaviors according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear part of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle and determining the type of the illegal behaviors of the vehicle; associating the plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, the first target image shot when the target vehicle reaches the snapshot line and the shooting time of the first target image to generate first image data, and sending the first image data to the server.
Specifically, the long-range camera 63 may be specifically configured to:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; carrying out illegal behavior analysis on the vehicle according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle, judging whether the lane number of the vehicle is changed, if so, determining the number of times of lane number change of the vehicle, and if the number of times of lane number change of the vehicle in first preset time is 1 time and the distance between the vehicle and the vehicle entering the rear of the lane is greater than a first preset threshold value, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is an illegal lane change; if the lane number change times of the vehicle in the second preset time is more than 1 time, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is snake-shaped driving; and if the lane number of the vehicle is changed alternately with the lane numbers of other vehicles within the third preset time, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is the violent vehicle pursuit.
Specifically, the server 61 may specifically be configured to:
receiving first image data sent by the long-range view camera and second image data sent by the short-range view camera, and acquiring position information of a target vehicle in the first image data; according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data; correspondingly determining a reference vehicle matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, if so, determining that the reference vehicle is the target vehicle, and obtaining the characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (13)
1. A vehicle video monitoring method is applied to a server in a vehicle video monitoring system, and the system further comprises the following steps: the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; the method comprises the following steps that a monitoring view field range of a distant view camera completely covers a monitoring view field range of a close view camera, and a snapping line is arranged at the same position of the overlapped view fields of the distant view camera and the close view camera, and comprises the following steps:
receiving first image data sent by the long-range view camera, wherein the long-range view camera acquires moving tracks of all vehicles in a monitoring view field, and a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle are determined according to the acquired moving tracks; the first image data includes a plurality of first images photographed when the target vehicle has an illegal action, an illegal action type of the target vehicle, a first target image photographed when the target vehicle reaches a snapshot line, and a photographing time of the first target image;
receiving second image data sent by the close-range camera, wherein the close-range camera shoots a second image when monitoring that a vehicle reaches a snapshot line, and the second image data comprises a plurality of second images and shooting time of the second images;
acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information;
and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
2. The method according to claim 1, wherein the finding the target vehicle in the second image according to the photographing time and the acquired position information of the target vehicle comprises:
according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data, correspondingly determining a reference vehicle which is matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, and if so, determining that the reference vehicle is the target vehicle.
3. The method of claim 1, wherein the feature information further comprises:
body color, vehicle type, and sub-brand of vehicle.
4. A server, for use in a vehicle video surveillance system, the system further comprising: the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring field of view scope of distant view camera covers completely the monitoring field of view scope of close view camera be provided with the line of taking a candid photograph on the same position of the overlapping field of view of distant view camera and close view camera, the server includes:
the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for performing the steps of:
receiving first image data sent by the long-range view camera, wherein the long-range view camera acquires moving tracks of all vehicles in a monitoring view field, and a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle are determined according to the acquired moving tracks; the first image data includes a plurality of first images photographed when the target vehicle has an illegal action, an illegal action type of the target vehicle, a first target image photographed when the target vehicle reaches a snapshot line, and a photographing time of the first target image;
receiving second image data sent by the close-range camera, wherein the close-range camera shoots a second image when monitoring that a vehicle reaches a snapshot line, and the second image data comprises a plurality of second images and shooting time of the second images;
acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information;
and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
5. A vehicle video monitoring method is characterized by being applied to a vehicle video monitoring system, and the system comprises: the system comprises a server, a long-range camera and a short-range camera, wherein the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; the method comprises the following steps that a monitoring view field range of a distant view camera completely covers a monitoring view field range of a close view camera, and a snapping line is arranged at the same position of the overlapped view fields of the distant view camera and the close view camera, and comprises the following steps:
the long-range view camera acquires the moving tracks of all vehicles in the monitoring field of view, and determines a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle according to the acquired moving tracks; associating a plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and shooting time of the first target image to generate first image data, and sending the first image data to the server;
when the close-range camera monitors that a vehicle arrives at a capturing line, shooting a second image, associating the plurality of shot second images with shooting time of the second image to generate second image data, and sending the second image data to the server;
the server receives first image data sent by the distant view camera and second image data sent by the close view camera, position information of a target vehicle is obtained in the first image data, the target vehicle is found in the second image according to shooting time and the obtained position information of the target vehicle, and feature information of the target vehicle is obtained in the second image, wherein the feature information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
6. The method according to claim 5, wherein the long-range view camera collects the moving tracks of all vehicles in the monitoring field of view, and determines the target vehicle with the illegal activity and the illegal activity type of the target vehicle according to the obtained moving tracks, comprising:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; and carrying out illegal behavior analysis on the vehicle according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear part of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle, and determining the type of the illegal behaviors of the vehicle.
7. The method of claim 6, wherein determining the type of unlawful act of the vehicle comprises:
judging whether the lane number of the vehicle changes or not, if so, determining the number of times of the change of the lane number of the vehicle, and if the number of times of the change of the lane number of the vehicle in a first preset time is 1 time and the distance between the vehicle and the vehicle entering the rear part of the lane is greater than a first preset threshold value, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is illegal lane change; if the lane number change times of the vehicle in the second preset time is more than 1 time, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is snake-shaped driving; and if the lane number of the vehicle is changed alternately with the lane numbers of other vehicles within the third preset time, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is the violent vehicle pursuit.
8. The method according to claim 5, wherein the finding the target vehicle in the second image according to the photographing time and the acquired position information of the target vehicle comprises:
according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data; and correspondingly determining a reference vehicle matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, and if so, determining that the reference vehicle is the target vehicle.
9. The method of claim 5, wherein the feature information further comprises:
body color, vehicle type, and sub-brand of vehicle.
10. A vehicle video surveillance system, the system comprising: the system comprises a server, a long-range camera and a short-range camera, wherein the long-range camera and the short-range camera are connected with the server; the long-range view camera and the short-range view camera are arranged on a moving path of the vehicle; wherein, the monitoring field of view scope of distant view camera covers completely the monitoring field of view scope of close view camera, be provided with the snap shot line on the same position of the overlapping field of view of distant view camera and close view camera:
the long-range camera is used for acquiring the moving tracks of all vehicles in the monitoring field, and determining a target vehicle with illegal behaviors and the illegal behavior type of the target vehicle according to the acquired moving tracks; associating a plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, a first target image shot when the target vehicle reaches a snapshot line and shooting time of the first target image to generate first image data, and sending the first image data to the server;
the close-range camera is used for shooting a second image when a vehicle is monitored to arrive at the snapshot line, associating the plurality of shot second images with shooting time of the second image to generate second image data, and sending the second image data to the server;
the server is used for receiving first image data sent by the distant view camera and second image data sent by the close view camera, acquiring position information of a target vehicle in the first image data, finding the target vehicle in the second image according to shooting time and the acquired position information of the target vehicle, and acquiring characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
11. The system of claim 10, wherein the vision camera is specifically configured to:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; analyzing the vehicle for illegal behaviors according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear part of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle and determining the type of the illegal behaviors of the vehicle; associating the plurality of first images shot when the target vehicle has illegal behaviors, the illegal behavior type of the target vehicle, the first target image shot when the target vehicle reaches the snapshot line and the shooting time of the first target image to generate first image data, and sending the first image data to the server.
12. The system of claim 10, wherein the vision camera is specifically configured to:
for each vehicle, calculating the lane number, the line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane in each frame of picture according to the acquired moving track; carrying out illegal behavior analysis on the vehicle according to the calculated lane number, the calculated line pressing state and the distance between the vehicle and the vehicle entering the rear of the lane, determining whether the vehicle has illegal behaviors, if so, determining the vehicle as a target vehicle, judging whether the lane number of the vehicle is changed, if so, determining the number of times of lane number change of the vehicle, and if the number of times of lane number change of the vehicle in first preset time is 1 time and the distance between the vehicle and the vehicle entering the rear of the lane is greater than a first preset threshold value, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is an illegal lane change; if the lane number change times of the vehicle in the second preset time is more than 1 time, determining that the vehicle is a target vehicle and the illegal behavior type of the vehicle is snake-shaped driving; and if the lane number of the vehicle is changed alternately with the lane numbers of other vehicles within the third preset time, determining that the vehicle is the target vehicle and the illegal behavior type of the vehicle is the violent vehicle pursuit.
13. The system of claim 10, wherein the server is specifically configured to:
receiving first image data sent by the long-range view camera and second image data sent by the short-range view camera, and acquiring position information of a target vehicle in the first image data; according to the shooting time of a first target image in first image data, finding a second image which is the same as the shooting time in second image data; correspondingly determining a reference vehicle matched with the target vehicle in the second image according to the coordinates of the target vehicle in the first target image, judging whether the similarity between the reference vehicle and the target vehicle is greater than a second preset threshold value, if so, determining that the reference vehicle is the target vehicle, and obtaining the characteristic information of the target vehicle in the second image, wherein the characteristic information at least comprises license plate information; and associating the first image data, the second image data and the characteristic information of the target vehicle to generate illegal information of the target vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610256691.0A CN107305627B (en) | 2016-04-22 | 2016-04-22 | Vehicle video monitoring method, server and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610256691.0A CN107305627B (en) | 2016-04-22 | 2016-04-22 | Vehicle video monitoring method, server and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107305627A CN107305627A (en) | 2017-10-31 |
| CN107305627B true CN107305627B (en) | 2020-03-27 |
Family
ID=60152574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610256691.0A Active CN107305627B (en) | 2016-04-22 | 2016-04-22 | Vehicle video monitoring method, server and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107305627B (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109905641B (en) * | 2017-12-08 | 2021-03-12 | 杭州海康威视数字技术股份有限公司 | Target monitoring method, device, equipment and system |
| CN110070724A (en) * | 2018-01-24 | 2019-07-30 | 北京英泰智科技股份有限公司 | A kind of video monitoring method, device, video camera and image information supervisory systems |
| CN108447091B (en) * | 2018-03-27 | 2022-09-06 | 北京颂泽科技有限公司 | Target positioning method and device, electronic equipment and storage medium |
| CN110855733B (en) * | 2018-08-21 | 2023-05-26 | 上海擎感智能科技有限公司 | Vehicle introduction method, system, server and vehicle |
| CN109147341B (en) * | 2018-09-14 | 2019-11-22 | 杭州数梦工场科技有限公司 | Violation vehicle detection method and device |
| CN111081025B (en) * | 2018-10-18 | 2022-02-08 | 北京小米松果电子有限公司 | Traffic supervision method, device and storage medium |
| CN111243281A (en) * | 2018-11-09 | 2020-06-05 | 杭州海康威视系统技术有限公司 | Road multi-video joint detection system and detection method |
| CN111241325B (en) * | 2018-11-28 | 2023-04-28 | 杭州海康威视系统技术有限公司 | Matching method, device and system of vehicle detection data and storage medium |
| CN111932901B (en) * | 2019-05-13 | 2022-08-09 | 斑马智行网络(香港)有限公司 | Road vehicle tracking detection apparatus, method and storage medium |
| CN110299013A (en) * | 2019-07-10 | 2019-10-01 | 深圳成谷科技有限公司 | A kind of detection processing method, device and equipment of vehicle risk driving behavior |
| CN112489448A (en) * | 2019-09-11 | 2021-03-12 | 浙江宇视科技有限公司 | Snapshot output filtering method and device |
| CN110672111B (en) * | 2019-09-24 | 2021-06-25 | 广州大学 | Vehicle driving path planning method, device, system, medium and equipment |
| CN110853363A (en) * | 2019-10-30 | 2020-02-28 | 北京市公安局公安交通管理局 | Vehicle traffic violation identification and video extraction device and method based on multiple algorithms |
| CN110855883B (en) * | 2019-11-05 | 2021-07-20 | 浙江大华技术股份有限公司 | Image processing system, method, device equipment and storage medium |
| CN111768630A (en) * | 2019-12-24 | 2020-10-13 | 上海高德威智能交通系统有限公司 | Violation waste image detection method and device and electronic equipment |
| CN111260932A (en) * | 2020-01-19 | 2020-06-09 | 上海眼控科技股份有限公司 | Method and device for determining vehicle illegal behavior, computer equipment and storage medium |
| CN113390766B (en) * | 2020-03-12 | 2023-07-25 | 杭州海康威视数字技术股份有限公司 | Tail gas emission detection method, device and equipment and storage medium |
| CN111596090A (en) * | 2020-06-17 | 2020-08-28 | 中国第一汽车股份有限公司 | Method and device for measuring vehicle running speed, vehicle and medium |
| CN112601049B (en) * | 2020-12-08 | 2023-07-25 | 北京精英路通科技有限公司 | Video monitoring method and device, computer equipment and storage medium |
| WO2022247931A1 (en) * | 2021-05-27 | 2022-12-01 | 北京万集科技股份有限公司 | Method and system for identifying illegal traffic participant, and computer-readable storage medium |
| CN114302320A (en) * | 2021-12-03 | 2022-04-08 | 湖南湘江智芯云途科技有限公司 | Vehicle moving reminding method, device, terminal, server and storage medium |
| CN114566043B (en) * | 2022-02-09 | 2023-09-22 | 浙江大华技术股份有限公司 | Evidence obtaining method and device for target parking and readable storage medium |
| CN114677841B (en) * | 2022-02-10 | 2023-12-29 | 浙江大华技术股份有限公司 | Vehicle lane change detection method and vehicle lane change detection system |
| CN115472014B (en) * | 2022-09-16 | 2023-10-10 | 苏州映赛智能科技有限公司 | Traffic tracing method, system, server and computer storage medium |
| CN115240435A (en) * | 2022-09-21 | 2022-10-25 | 广州市德赛西威智慧交通技术有限公司 | AI technology-based vehicle illegal driving detection method and device |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2718699Y (en) * | 2004-07-21 | 2005-08-17 | 上海高德威智能交通系统有限公司 | Intelligent monitoring and recording system based on video trigger and velocity measurement for vehicle |
| CN1710625A (en) * | 2005-06-01 | 2005-12-21 | 曲宏巍 | Automatic recording system for running the red light |
| CN201655023U (en) * | 2010-04-12 | 2010-11-24 | 天津大学 | Traffic violation monitoring device of large truck |
| CN102467652A (en) * | 2010-11-04 | 2012-05-23 | 北京时代凌宇科技有限公司 | Wireless intelligent identification management device, system and method |
| CN202003539U (en) * | 2011-01-07 | 2011-10-05 | 北京精英智通交通系统科技有限公司 | Subject 3 video tracking examination system of motor vehicle drivers |
| CN202352077U (en) * | 2011-11-15 | 2012-07-25 | 上海宝康电子控制工程有限公司 | Multifunctional video-detecting and law violation evidence obtaining system |
| CN103730009A (en) * | 2012-10-12 | 2014-04-16 | 博隆建亚科技(北京)有限公司 | Method and system for detecting vehicle with one number plate missing |
| CN103646550A (en) * | 2013-12-30 | 2014-03-19 | 中国科学院自动化研究所 | Intelligent vehicle license plate recognition system |
| CN103927878B (en) * | 2014-04-10 | 2016-05-25 | 中海网络科技股份有限公司 | A kind of automatic shooting device for parking offense and automatically grasp shoot method |
| CN103886763B (en) * | 2014-04-14 | 2016-03-09 | 北京易华录信息技术股份有限公司 | One utilizes video tracking technology to realize hypervelocity illegal activities photographic method and system |
| US9275286B2 (en) * | 2014-05-15 | 2016-03-01 | Xerox Corporation | Short-time stopping detection from red light camera videos |
| KR20160038944A (en) * | 2014-09-30 | 2016-04-08 | 주식회사 디아이랩 | traffic monitoring system |
| CN104537841B (en) * | 2014-12-23 | 2017-01-25 | 上海博康智能信息技术有限公司 | Unlicensed vehicle violation detection method and detection system thereof |
| CN204884166U (en) * | 2015-05-08 | 2015-12-16 | 天津大学 | Regional violating regulations parking monitoring devices is stopped to traffic taboo |
| CN105427619B (en) * | 2015-12-24 | 2017-06-23 | 上海新中新猎豹交通科技股份有限公司 | Vehicle following distance automatic production record and method |
-
2016
- 2016-04-22 CN CN201610256691.0A patent/CN107305627B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107305627A (en) | 2017-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107305627B (en) | Vehicle video monitoring method, server and system | |
| CN109886078B (en) | Retrieval positioning method and device for target object | |
| CN108447091B (en) | Target positioning method and device, electronic equipment and storage medium | |
| CN111372037B (en) | Target snapshot system and method | |
| CN106952477B (en) | Roadside parking management method based on multi-camera image joint processing | |
| CN109325429B (en) | Method, device, storage medium and terminal for associating feature data | |
| CN112907982B (en) | Method, device and medium for detecting vehicle illegal parking behavior | |
| US11263446B2 (en) | Method for person re-identification in closed place, system, and terminal device | |
| CN110706247B (en) | Target tracking method, device and system | |
| US8860815B2 (en) | Apparatus, method and computer program for image-based tracking of surveillance objects | |
| CN105654733A (en) | Front and back vehicle license plate recognition method and device based on video detection | |
| EP1560160A2 (en) | A multiple camera system for obtaining high resolution images of objects | |
| CN106503622A (en) | A kind of vehicle antitracking method and device | |
| EP3700180A1 (en) | Video blocking region selection method and apparatus, electronic device, and system | |
| CN105744223A (en) | Video data processing method and apparatus | |
| CN111881322B (en) | Target searching method and device, electronic equipment and storage medium | |
| CN109905641B (en) | Target monitoring method, device, equipment and system | |
| CN112836683A (en) | License plate recognition method, device, equipment and medium for portable camera equipment | |
| CN114898326A (en) | Method, system and equipment for detecting reverse running of one-way vehicle based on deep learning | |
| CN112651398A (en) | Vehicle snapshot control method and device and computer readable storage medium | |
| CN114724131A (en) | Vehicle tracking method and device, electronic equipment and storage medium | |
| CN112949439A (en) | Method and system for monitoring invasion of personnel in key area of oil tank truck | |
| KR101595334B1 (en) | Method and apparatus for movement trajectory tracking of moving object on animal farm | |
| KR101154350B1 (en) | Multiple Images Processing system using Detection of Objects and segmenting - recognizing of High- resolution Image and there of. | |
| CN110706250B (en) | Object tracking method, device and system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |