CN111754781A - Method, device and system for detecting vehicle violation and camera - Google Patents
Method, device and system for detecting vehicle violation and camera Download PDFInfo
- Publication number
- CN111754781A CN111754781A CN201910237545.7A CN201910237545A CN111754781A CN 111754781 A CN111754781 A CN 111754781A CN 201910237545 A CN201910237545 A CN 201910237545A CN 111754781 A CN111754781 A CN 111754781A
- Authority
- CN
- China
- Prior art keywords
- target vehicle
- vehicle
- straight
- going
- turning
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The application provides a method, a device, a system and a camera for detecting vehicle violation, wherein the method comprises the following steps: carrying out vehicle detection on the acquired video frames to detect a target vehicle in the video frames, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet; when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked, if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle, determining that violation behaviors which do not give the straight-going target vehicle in courtesy occur in the left-turning target vehicle; and extracting video frames related to the violation behaviors from the collected video frames. The embodiment can realize the detection of the violation behaviors of the left-turn vehicles which do not give the right-hand vehicles, enriches the types of the violation behaviors determined based on the monitoring scene, and has higher detection efficiency and strong real-time property.
Description
Technical Field
The application relates to the technical field of monitoring, in particular to a method, a device and a system for detecting vehicle violation and a camera.
Background
Urban road intersections are the bottleneck of urban road network operation and are also the key points of urban road traffic jam. The passing space and the passing order of each traffic flow are reasonably organized, and the passing efficiency of the intersection can be effectively improved. Among the traffic flows of each flow direction at an urban road intersection, the conflict caused by the left-turn traffic flow is the most serious.
To alleviate the conflict caused by left turn traffic, relevant traffic regulations dictate that a left turn vehicle needs to lead a straight going vehicle. However, there are still a lot of left-turning vehicles with violation behaviors that do not give the right-going vehicles a good idea, and monitoring the violation behaviors in time can improve the enforcement of the traffic police department, thereby reducing traffic accidents caused by the left-turning vehicles that do not give the right-going vehicles a good idea.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, a system and a camera for vehicle violation detection.
Specifically, the method is realized through the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for detecting vehicle violation, where the method includes:
carrying out vehicle detection on the acquired video frames to detect a target vehicle in the video frames, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked, if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle, determining that violation behaviors which do not give the straight-going target vehicle in courtesy occur in the left-turning target vehicle;
and extracting video frames related to the violation behaviors from the collected video frames.
In a possible embodiment, the vehicle detection on the captured video frames to detect the target vehicle in the video frames includes:
identifying vehicles in the video frame and obtaining the positions of the vehicles;
acquiring license plate information of the vehicle;
and tracking the vehicle according to the license plate information and the position to determine a left-turn target vehicle and a straight-going target vehicle.
In one possible embodiment, the identifying vehicles in the video frame and acquiring the positions of the vehicles includes:
inputting the collected video frame into a trained YOLO model, dividing the video frame into at least one grid by the YOLO model, identifying vehicles in each grid, and determining the positions of the vehicles.
In a possible embodiment, the tracking the vehicle according to the license plate information and the position to determine a left-turn target vehicle and a straight-going target vehicle includes:
judging whether the vehicle is a left-turn candidate vehicle running on a left-turn lane or not according to the position of the vehicle;
if so, tracking the left-turning candidate vehicle based on the license plate information of the left-turning candidate vehicle;
when the left-turn candidate vehicle is tracked to enter the intersection, determining the left-turn candidate vehicle as a left-turn target vehicle;
and detecting a straight-ahead candidate vehicle which is positioned in a preset range above and to the left of the driving direction of the left-turn target vehicle and is opposite to the driving direction of the left-turn target vehicle, and if the overlapping proportion of the horizontal direction of the straight-ahead candidate vehicle and the horizontal direction of the left-turn target vehicle exceeds a preset threshold value, determining the straight-ahead candidate vehicle as the straight-ahead target vehicle.
In one possible embodiment, the determining whether the left-turn target vehicle passes through the position of the vehicle-crossing before the straight-ahead target vehicle is performed in the following manner:
and if the straight-going target vehicle is positioned at the upper right side of the driving direction of the left-turning target vehicle, determining that the left-turning target vehicle passes through the meeting position before the straight-going target vehicle.
In a possible embodiment, the video frame related to the violation behavior at least comprises one or a combination of the following video frames:
the whole body of the left-turn target vehicle is positioned in a stop line of a left-turn lane, and the distance between the vehicle head position and the stop line is smaller than a preset distance threshold value;
when the left-turning target vehicle meets the straight-going target vehicle;
when it is determined that the left-turn target vehicle passes through the position of the vehicle crossing before the straight-ahead target vehicle;
and the left-turning target vehicle passes through the meeting position and then the driving direction is left-turning.
In one possible embodiment, after the extracting the video frame related to the violation behavior from the captured video frame, the method further comprises:
acquiring license plate information of the left-turn target vehicle, and generating violation information of the left-turn target vehicle according to the license plate information;
and displaying and/or outputting the violation information and/or the extracted video frame to an external device.
In a second aspect, an embodiment of the present application provides a vehicle violation detection device, including:
the target vehicle detection module is used for carrying out vehicle detection on the acquired video frames so as to detect a target vehicle in the video frames, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
the violation behavior determining module is used for judging that violation behaviors which do not give the straight-going target vehicle any more are generated on the left-turning target vehicle if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked;
and the video frame extraction module is used for extracting the video frame related to the violation behaviors from the collected video frame.
In a third aspect, an embodiment of the present application provides a camera, where the camera includes:
the video frame acquisition module is used for acquiring video frames and transmitting the video frames to the target vehicle detection module;
the target vehicle detection module is used for carrying out vehicle detection on the video frame so as to detect a target vehicle in the video frame, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
the violation behavior determining module is used for judging that violation behaviors which do not give the straight-going target vehicle any more are generated on the left-turning target vehicle if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked;
and the video frame extraction module is used for extracting the video frame related to the violation behaviors from the collected video frame.
In a fourth aspect, an embodiment of the present application provides a vehicle violation detection system, where the system includes a camera and a violation detection platform:
the camera is used for collecting video frames and transmitting the video frames to the violation detection platform;
the violation detection platform includes:
the target vehicle detection module is used for carrying out vehicle detection on the video frame transmitted by the camera so as to detect a target vehicle in the video frame, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
the violation behavior determining module is used for judging that violation behaviors which do not give the straight-going target vehicle any more are generated on the left-turning target vehicle if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked;
and the video frame extraction module is used for extracting the video frame related to the violation behaviors from the collected video frame.
The embodiment of the application has the following beneficial effects:
in the embodiment of the application, based on image analysis of video frames, a left-turn target vehicle and a straight-going target vehicle which are possibly met are determined, when the left-turn target vehicle and the straight-going target vehicle are tracked to be met, if the left-turn target vehicle is detected to pass through the meeting position before the straight-going target vehicle, the violation behaviors of the straight-going target vehicle can be judged to be caused if the left-turn target vehicle is determined to be not courtesy, so that the violation behaviors of the straight-going target vehicle are detected, the violation behaviors determined based on a monitoring scene are enriched, the detection efficiency is high, and the real-time performance is strong.
Meanwhile, the embodiment can extract the video frame related to the violation behavior from the collected video frame, and the video frame is used as a forensics image, so that the vehicle owner or related parts can conveniently obtain the forensics of the violation behavior.
Drawings
FIG. 1 is a flow chart illustrating the steps of one embodiment of a method for vehicle violation detection as shown in an exemplary embodiment of the present application;
FIG. 2 is a schematic illustration of a target vehicle within an intersection stop line as shown in an exemplary embodiment of the present application;
fig. 3 is a schematic view showing a positional relationship between a left-turn target vehicle and a straight-ahead target vehicle according to an exemplary embodiment of the present application;
fig. 4 is a schematic diagram illustrating position determination of a left-turn target vehicle and a straight-ahead target vehicle during vehicle crossing according to an exemplary embodiment of the present application;
FIG. 5 is a schematic diagram illustrating a left turn target vehicle first passing through a meeting space and then turning left in accordance with an exemplary embodiment of the present application;
FIG. 6 is a hardware block diagram of the device in which the apparatus of the present application is located;
FIG. 7 is a block diagram illustrating the configuration of an embodiment of a vehicle violation detection device in accordance with an exemplary embodiment of the present application;
FIG. 8 is a block diagram illustrating the structure of one embodiment of a camera according to an exemplary embodiment of the present application;
FIG. 9 is a block diagram illustrating the architecture of an embodiment of a vehicle violation detection system according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, a flow chart of steps of an embodiment of a method for detecting vehicle violations is shown, which may specifically include the following steps:
In one example, the video frames may be video frames captured by a camera. The camera can be erected near a road intersection and used for monitoring vehicles driving into the intersection.
In one embodiment, the road intersection may include left-turn lanes and straight lanes, which are oppositely oriented, and the driving direction of the vehicle in the left-turn lane is opposite to that of the vehicle in the straight lane. For example, as shown in the intersection schematic diagram of fig. 2, the lane in which the vehicle a is located is a left-turn lane, the lane in which the vehicle B is located is a straight lane, and the traveling directions of the two lanes are opposite.
The embodiment can perform vehicle detection on the video frame acquired by the camera to detect whether the target vehicle exists in the video frame. As one example, the target vehicle may include, but is not limited to: a left-turn target vehicle and a straight-ahead target vehicle.
The left-turning target vehicle and the straight-going target vehicle are vehicles which are possible to meet. The meeting refers to the traffic phenomenon that motor vehicles running in opposite directions pass through at the same place and at the same time in a staggered manner. This phenomenon may involve the risk of a frontal collision, a side collision, etc., and is particularly more dangerous in narrow road sections.
In a possible implementation manner of this embodiment, step 101 may include the following sub-steps:
and a substep S11 of identifying vehicles in the video frame and obtaining the position of each vehicle.
In one possible implementation, a vehicle detection algorithm may be employed on the video frames to detect the vehicle and the position of the vehicle in the video frames.
For example, a captured video frame may be input to a trained YOLO model to divide the video frame into at least one mesh by the YOLO model, identify vehicles in each mesh, and determine the location of the vehicles.
In the implementation of the YOLO model, the whole video frame is input into the model once, then the model divides the video frame into different grids, frame prediction and probability of each grid are given, and weight is distributed to all frames according to the probability. Finally, a threshold value is set, and only the detection result of which the score (probability value) exceeds the threshold value is output. The YOLO model has the advantages of high target detection speed and good detection effect on the shielded target.
In one embodiment, the process of the YOLO model performing vehicle detection on the input video frame includes the following steps:
1. dividing a video frame into S multiplied by S grids, and if the center of a vehicle falls into a certain grid, the grid is responsible for predicting the vehicle;
2. each grid predicts B target frames (each target frame refers to a rectangular area containing a vehicle), each target frame needs to return to its own position, and also predicts a confidence score (confidence) which reflects the accuracy of whether the current bounding box contains the vehicle, wherein the confidence score is calculated by the following formula:
in the above formula, pr (object) takes a value of 1 if the vehicle falls within a grid, and 0 otherwise.
Is the IOU (cross-over ratio) value between the predicted target box and the actual true value.
Each target frame is predicted to have 5 values (x, y, w, h) (wherein x, y refers to the coordinates of the center position of the target frame of the vehicle predicted by the current grid, w, h refers to the width and height of the target frame), and the confidence score, and each grid is also predicted to have one category information which is marked as C. Then S × S grids, each of which predicts B target frames and also C categories, the output is a quantity of S × S (5 × B + C).
3. At the time of testing, multiplying the category information of each grid prediction and the confidence information of the target frame prediction to obtain a category confidence score of each target frame:
4. after the category confidence score of each target frame is obtained, a threshold value is set to filter out the target frames with low scores, and the retained target frames are subjected to non-maximum value suppression processing, so that the final detection result of the vehicle is obtained, wherein the detection result comprises the position of the vehicle, the target frame corresponding to the vehicle and the like.
And a substep S12 of obtaining the license plate information of the vehicle.
In one embodiment, the license plate information of the vehicle can be obtained through the license plate recognition module. Illustratively, the license plate recognition module can recognize license plate information of a vehicle according to a license plate recognition technology, the license plate recognition technology can extract and recognize a moving license plate from a complex background, and information such as license plate number and color of the vehicle is recognized through technologies such as license plate extraction, image preprocessing, feature extraction and license plate character recognition.
The license plate recognition technology of this embodiment may be a general license plate recognition technology, and this embodiment does not limit this.
And a substep S13, tracking the vehicle according to the license plate information and the position to determine a left-turn target vehicle and a straight-going target vehicle.
In one embodiment, after the vehicles are identified from the video frames and the positions of the vehicles and the license plate information are obtained, the vehicles can be locked according to the license plate information and tracked by adopting a tracking algorithm to determine left-turn target vehicles and straight-going target vehicles.
In a possible implementation, the sub-step S13 may further include the following sub-steps:
a substep S131 of judging whether the vehicle is a left-turn candidate vehicle running on a left-turn lane according to the position of the vehicle; if yes, go to step S132.
For example, the present embodiment may determine a left-turn lane by detecting a left-turn sign of a road. In other examples, the project personnel may also configure the left-turn lane in the camera in advance, such as inputting the image marked with the left-turn lane in advance for the camera to recognize.
After determining the left-turn lane, it may be further determined whether the position of the vehicle is located on the left-turn lane, and if the position of the vehicle is located on the left-turn lane, it is determined that the vehicle is a left-turn candidate vehicle.
And a substep S132 of tracking the left-turn candidate vehicle based on the license plate information of the left-turn candidate vehicle.
After the left-turn candidate vehicle is determined, license plate information of the left-turn candidate vehicle can be obtained, and the left-turn candidate vehicle is tracked by adopting a tracking algorithm based on the license plate information.
The tracking of the vehicle is to establish the position relation of the vehicle to be tracked in continuous video frames to obtain the track information of the vehicle running.
The present embodiment does not limit the specific tracking algorithm, for example, the tracking algorithm may include an optical flow method, an area matching algorithm, a feature point tracking algorithm, and the like, and a person skilled in the art may select any one of the general tracking algorithms to perform vehicle tracking according to actual needs.
And a substep S133, determining the left-turn candidate vehicle as a left-turn target vehicle when the left-turn candidate vehicle is tracked to enter the intersection.
In one embodiment, in the process of tracking the left-turn candidate vehicle, if it is detected that the left-turn candidate vehicle enters the intersection, the left-turn target vehicle may be determined by combining the trajectory information obtained by tracking the left-turn candidate vehicle. For example, if the trajectory information shows that the left-turn candidate vehicle has a left-turn tendency or a left-turn occurs, the left-turn candidate vehicle may be determined to be the left-turn target vehicle.
For example, in fig. 2, the vehicle a is tracked as a left turn candidate vehicle, and when it is determined that the vehicle a has a left turn tendency based on the trajectory information of the vehicle a when the left turn candidate vehicle is tracked to enter the intersection, the left turn candidate vehicle is regarded as a left turn target vehicle, and for example, when the vehicle a in fig. 2 enters the intersection, the vehicle a may be regarded as a left turn target vehicle, as shown in fig. 3.
And a substep S134 of detecting a straight-ahead candidate vehicle located in a preset range on the upper left of the traveling direction of the left turn target vehicle, the straight-ahead candidate vehicle being opposite to the traveling direction of the left turn target vehicle, and determining the straight-ahead candidate vehicle as the straight-ahead target vehicle if the overlap ratio of the horizontal direction of the straight-ahead candidate vehicle to the horizontal direction of the left turn target vehicle exceeds a preset threshold value.
In one embodiment, a left-turn target vehicle is first identified, and then a vehicle with which a meeting is likely to occur is determined as a straight-ahead target vehicle based on the position of the left-turn target vehicle.
After the left-turn target vehicle is identified, a straight-ahead target vehicle that may meet the left-turn target vehicle may be determined according to the position of the left-turn target vehicle. In one embodiment, it may be determined whether a straight-ahead candidate vehicle whose traveling direction is opposite to that of the left-turn target vehicle exists within a preset range above and to the left according to the position of the left-turn target vehicle. For example, as shown in fig. 3, it may be determined whether or not a straight-ahead candidate vehicle exists within a preset range dist _ y _ th (dist _ y _ th may be configured as needed) in the upper left vertical direction of the position of the left-turn target vehicle a, and if there is a vehicle B, it is further calculated whether or not the horizontal direction of the vehicle B overlaps with the horizontal direction of the vehicle a, and if there is an overlap and the overlap ratio exceeds a preset threshold, the vehicle B may be regarded as a straight-ahead target vehicle.
102, when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked, if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle, determining that the violation behavior of not giving the straight-going target vehicle occurs in the left-turning target vehicle.
After the left-turning target vehicle and the straight-going target vehicle are determined, the left-turning target vehicle and the straight-going target vehicle are continuously tracked, and whether the two vehicles meet is judged according to the position relation of the left-turning target vehicle and the straight-going target vehicle. In one embodiment, when it is detected that the left-turn target vehicle and the straight traveling target vehicle travel to the same position area at the same time, it is determined that the meeting of the left-turn target vehicle and the straight traveling target vehicle occurs.
When two vehicles meet, if the left-turning target vehicle is judged to pass through the meeting position before the straight-going target vehicle according to the change of the position relation of the two vehicles, and the driving direction of the left-turning target vehicle after passing through the meeting position is left-turning, the violation behavior that the left-turning target vehicle does not give way to the straight-going target vehicle can be judged.
In one possible embodiment, whether the left-turn target vehicle passes through the position of the vehicle-crossing before the straight-ahead target vehicle may be determined as follows:
and if the straight-going target vehicle is positioned at the upper right side of the driving direction of the left-turning target vehicle, determining that the left-turning target vehicle passes through the meeting position before the straight-going target vehicle.
Under normal conditions, as shown in fig. 3, since the straight lane is located on the left side of the left-turn lane, the vehicle B will be at the upper left in the traveling direction of the vehicle a. According to the related traffic rules, when a vehicle A turns, a straight vehicle B needs to be courtesy, the vehicle B firstly passes through the meeting position, and then the vehicle B is courtesy and is positioned at the lower left of the driving direction of the vehicle A. However, if the vehicle a does not give the vehicle B a good idea, the vehicle a may cross the vehicle B to pass through the meeting position as shown in fig. 4, and the vehicle B may be right above the traveling direction of the vehicle a at this time. Therefore, it is possible to determine whether the vehicle a passes through the meeting position prior to the vehicle B by determining whether the vehicle B is positioned at the upper right in the traveling direction of the vehicle a.
It should be noted that, the above exemplary shows a scenario in which the left-turn vehicle does not give a gift to the straight-ahead vehicle, and actually, a scenario in which other left-turn vehicles do not give a gift to the straight-ahead vehicle may also be included, and the gift judgment may be performed by referring to the above gift judgment logic. It should be understood by those skilled in the art that the method provided by the embodiment of the present application can be applied to other car meeting etiquette scenarios besides those specific to left-turn etiquette straight-driving vehicles.
And 103, extracting a video frame related to the violation behavior from the collected video frames.
In one embodiment, in order to facilitate image forensics, an image extraction rule may be preset for a violation that a left-turn vehicle does not give a courtesy to a straight vehicle, and image extraction may be performed according to the image extraction rule when the violation is detected, and the extracted video frame may be cached.
As an example, one image extraction rule may be: one or a combination of the following video frames are extracted, however, the following time instants should not be construed as a limitation to the embodiment, and it is possible for those skilled in the art to extract images at more or less time instants according to actual needs:
time corresponding to the first image: the whole body of the left-turn target vehicle is arranged in a stop line of a left-turn lane, and the distance between the vehicle head position and the stop line is smaller than a preset distance threshold value. The extracted image may be as shown in fig. 2, where in fig. 2 the entire body of vehicle a is within the stop-line (the stop-line is not pressed), and the vehicle head is not beyond the stop-line and is as close to the stop-line as possible.
Time corresponding to the second image: when the left-turn target vehicle meets the straight-going target vehicle. The extracted image may be as shown in fig. 3, the vehicle a enters the intersection across the stop line, and the vehicle B exists within the range of the upper left vertical direction dist _ y _ th of the vehicle a, where the distance dist _ y _ th may be configured, and the vehicle a and the vehicle B have overlap in the horizontal direction and the overlap ratio exceeds a preset threshold.
Time corresponding to the third image: when it is determined that the left-turn target vehicle passes through the position of the vehicle-crossing before the straight-ahead target vehicle. The extracted image may be as shown in fig. 4, where vehicle a first passes the meeting location, the left boundary of vehicle a is larger than the left boundary of vehicle B, and vehicle a is below vehicle B in fig. 4.
Time corresponding to the fourth image: when the left-turn target vehicle passes through the meeting position and the driving direction is left-turn. The extracted image may be as shown in fig. 5, in which fig. 5, the traveling direction of the vehicle a is determined as a left turn.
In a possible implementation manner of this embodiment, after step 103, the following steps may be further included:
acquiring license plate information of a left-turn target vehicle, and generating violation information of the left-turn target vehicle according to the license plate information; and displaying and/or outputting the violation information and/or the extracted video frame to an external device.
When it is determined that the violation of the left-turn target vehicle does not give an etiquette of going straight, the violation information of the vehicle can be generated according to the license plate information of the left-turn target vehicle (the license plate information is obtained through the substep S12 and is obtained all the time in the tracking process), and the violation information is used for describing the violation of the left-turn target vehicle that does not give an etiquette of going straight.
It should be noted that, in the process of tracking the vehicle, if the currently obtained license plate information is inconsistent with the license plate information that has been tracked all the time before, the vehicle may be matched according to other characteristics of the vehicle, such as vehicle type, color, license plate brand, and the like, and if the currently obtained characteristic information of the vehicle other than the license plate information is consistent with that has been tracked all the time before, the current license plate information may be corrected to be the license plate information that has been tracked all the time before.
In one embodiment, after the violation information is obtained, the violation information may be displayed via a display device. In other embodiments, the violation information may also be associated with the extracted video frame, and when the violation information is displayed, the video frame related to the violation information may also be displayed.
In another embodiment, after obtaining the violation information, the violation information and/or the extracted related video frame may be sent to an external device, for example, a mobile phone of a vehicle owner corresponding to the violation vehicle, so as to notify the vehicle owner of the violation information. Or the abnormal driving behavior is sent to equipment of a traffic police department, so that the abnormal driving behavior can be effectively monitored by the traffic management department.
In the embodiment of the application, based on image analysis of video frames, a left-turn target vehicle and a straight-going target vehicle which are possibly met are determined, when the left-turn target vehicle and the straight-going target vehicle are tracked to be met, if the left-turn target vehicle is detected to pass through the meeting position before the straight-going target vehicle, the violation behaviors of the straight-going target vehicle can be judged to be caused if the left-turn target vehicle is determined to be not courtesy, so that the violation behaviors of the straight-going target vehicle are detected, the violation behaviors determined based on a monitoring scene are enriched, the detection efficiency is high, and the real-time performance is strong.
Meanwhile, the embodiment can extract the video frame related to the violation behavior from the collected video frame, and the video frame is used as a forensics image, so that the vehicle owner or related parts can conveniently obtain the forensics of the violation behavior.
Corresponding to the embodiment of the method, the application also provides an embodiment of the vehicle violation detecting device.
The device embodiment of the application can be applied to computing equipment. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor of the device where the software implementation is located as a logical means. From a hardware aspect, as shown in fig. 6, the hardware structure diagram of the device in the present application is a hardware structure diagram, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 6, the device in the embodiment may also include other hardware according to an actual function of the device, which is not described again.
Referring to fig. 7, a block diagram of a structure of an embodiment of a vehicle violation detection device according to an exemplary embodiment of the present application is shown, which may specifically include the following modules:
a target vehicle detection module 701, configured to perform vehicle detection on a captured video frame to detect a target vehicle in the video frame, where the target vehicle includes a left-turn target vehicle and a straight-going target vehicle, and the left-turn target vehicle and the straight-going target vehicle are vehicles about to meet;
the violation behavior determination module 702 is configured to, when it is tracked that the left-turn target vehicle meets the straight-ahead target vehicle, determine that a violation behavior that does not give the straight-ahead target vehicle is caused by the left-turn target vehicle if the left-turn target vehicle passes through the meeting position before the straight-ahead target vehicle;
and the video frame extraction module 703 is configured to extract a video frame related to the violation from the acquired video frames.
In a possible implementation manner of this embodiment, the target vehicle detection module 701 includes:
the vehicle identification submodule is used for identifying vehicles in the video frame and acquiring the positions of the vehicles;
the license plate recognition submodule is used for acquiring license plate information of the vehicle;
and the target vehicle determining submodule is used for tracking the vehicle according to the license plate information and the position so as to determine a left-turning target vehicle and a straight-going target vehicle.
In a possible implementation manner of this embodiment, the vehicle identification submodule is specifically configured to:
inputting the collected video frame into a trained YOLO model, dividing the video frame into at least one grid by the YOLO model, identifying vehicles in each grid, and determining the positions of the vehicles.
In one possible implementation manner of this embodiment, the target vehicle determination submodule is specifically configured to:
judging whether the vehicle is a left-turn candidate vehicle running on a left-turn lane or not according to the position of the vehicle;
if so, tracking the left-turning candidate vehicle based on the license plate information of the left-turning candidate vehicle;
when the left-turn candidate vehicle is tracked to enter the intersection, determining the left-turn candidate vehicle as a left-turn target vehicle;
and detecting a straight-ahead candidate vehicle which is positioned in a preset range above and to the left of the driving direction of the left-turn target vehicle and is opposite to the driving direction of the left-turn target vehicle, and if the overlapping proportion of the horizontal direction of the straight-ahead candidate vehicle and the horizontal direction of the left-turn target vehicle exceeds a preset threshold value, determining the straight-ahead candidate vehicle as the straight-ahead target vehicle.
In a possible implementation manner of this embodiment, the violation behavior determination module 702 is specifically configured to:
and if the straight-going target vehicle is positioned at the upper right side of the driving direction of the left-turning target vehicle, determining that the left-turning target vehicle passes through the meeting position before the straight-going target vehicle.
In a possible implementation manner of this embodiment, the video frame related to the violation behavior at least includes one or a combination of the following video frames:
the whole body of the left-turn target vehicle is positioned in a stop line of a left-turn lane, and the distance between the vehicle head position and the stop line is smaller than a preset distance threshold value;
when the left-turning target vehicle meets the straight-going target vehicle;
when it is determined that the left-turn target vehicle passes through the position of the vehicle crossing before the straight-ahead target vehicle;
and the left-turning target vehicle passes through the meeting position and then the driving direction is left-turning.
In a possible implementation manner of this embodiment, the apparatus may further include the following modules:
the violation information generating module is used for acquiring license plate information of the left-turn target vehicle and generating violation information of the left-turn target vehicle according to the license plate information;
and the violation information processing module is used for displaying and/or outputting the violation information and/or the extracted video frame to external equipment.
Referring to fig. 8, a block diagram of a structure of an embodiment of a camera according to an exemplary embodiment of the present application is shown, and the structure may specifically include the following modules:
the video frame acquisition module 801 is used for acquiring video frames and transmitting the video frames to the target vehicle detection module;
a target vehicle detection module 802, configured to perform vehicle detection on the video frame to detect a target vehicle in the video frame, where the target vehicle includes a left-turn target vehicle and a straight-going target vehicle, and the left-turn target vehicle and the straight-going target vehicle are vehicles about to meet;
the violation behavior determination module 803 is configured to, when it is tracked that the left-turn target vehicle meets the straight-ahead target vehicle, determine that a violation behavior that does not give the straight-ahead target vehicle due to the left-turn target vehicle passing through the meeting position before the straight-ahead target vehicle;
and the video frame extraction module 804 is used for extracting the video frame related to the violation behavior from the collected video frames.
In one possible implementation manner of this embodiment, the target vehicle detection module 802 includes:
the vehicle identification submodule is used for identifying vehicles in the video frame and acquiring the positions of the vehicles;
the license plate recognition submodule is used for acquiring license plate information of the vehicle;
and the target vehicle determining submodule is used for tracking the vehicle according to the license plate information and the position so as to determine a left-turning target vehicle and a straight-going target vehicle.
In a possible implementation manner of this embodiment, the vehicle identification submodule is specifically configured to:
inputting the collected video frame into a trained YOLO model, dividing the video frame into at least one grid by the YOLO model, identifying vehicles in each grid, and determining the positions of the vehicles.
In one possible implementation manner of this embodiment, the target vehicle determination submodule is specifically configured to:
judging whether the vehicle is a left-turn candidate vehicle running on a left-turn lane or not according to the position of the vehicle;
if so, tracking the left-turning candidate vehicle based on the license plate information of the left-turning candidate vehicle;
when the left-turn candidate vehicle is tracked to enter the intersection, determining the left-turn candidate vehicle as a left-turn target vehicle;
and detecting a straight-ahead candidate vehicle which is positioned in a preset range above and to the left of the driving direction of the left-turn target vehicle and is opposite to the driving direction of the left-turn target vehicle, and if the overlapping proportion of the horizontal direction of the straight-ahead candidate vehicle and the horizontal direction of the left-turn target vehicle exceeds a preset threshold value, determining the straight-ahead candidate vehicle as the straight-ahead target vehicle.
In a possible implementation manner of this embodiment, the violation behavior determination module 803 is specifically configured to:
and if the straight-going target vehicle is positioned at the upper right side of the driving direction of the left-turning target vehicle, determining that the left-turning target vehicle passes through the meeting position before the straight-going target vehicle.
In a possible implementation manner of this embodiment, the video frame related to the violation behavior at least includes one or a combination of the following video frames:
the whole body of the left-turn target vehicle is positioned in a stop line of a left-turn lane, and the distance between the vehicle head position and the stop line is smaller than a preset distance threshold value;
when the left-turning target vehicle meets the straight-going target vehicle;
when it is determined that the left-turn target vehicle passes through the position of the vehicle crossing before the straight-ahead target vehicle;
and the left-turning target vehicle passes through the meeting position and then the driving direction is left-turning.
In a possible implementation manner of this embodiment, the apparatus may further include the following modules:
the violation information generating module is used for acquiring license plate information of the left-turn target vehicle and generating violation information of the left-turn target vehicle according to the license plate information;
and the violation information processing module is used for displaying and/or outputting the violation information and/or the extracted video frame to external equipment.
Referring to fig. 9, a block diagram of an embodiment of a vehicle violation detection system is shown in an exemplary embodiment of the present application, the system including a camera 90 and a violation detection platform 100:
the camera 90 is used for collecting video frames and transmitting the video frames to the violation detection platform;
the violation detection platform 100 includes:
a target vehicle detection module 1001, configured to perform vehicle detection on a video frame transmitted by the camera to detect a target vehicle in the video frame, where the target vehicle includes a left-turn target vehicle and a straight-ahead target vehicle, and the left-turn target vehicle and the straight-ahead target vehicle are vehicles about to meet;
the violation behavior determining module 1002 is configured to, when it is tracked that the left-turn target vehicle meets the straight-going target vehicle, determine that a violation behavior that does not give the straight-going target vehicle a good idea exists in the left-turn target vehicle if the left-turn target vehicle passes through the meeting position before the straight-going target vehicle;
and the video frame extraction module 1003 is used for extracting a video frame related to the violation behavior from the acquired video frames.
In one possible implementation manner of this embodiment, the target vehicle detection module 1001 includes:
the vehicle identification submodule is used for identifying vehicles in the video frame and acquiring the positions of the vehicles;
the license plate recognition submodule is used for acquiring license plate information of the vehicle;
and the target vehicle determining submodule is used for tracking the vehicle according to the license plate information and the position so as to determine a left-turning target vehicle and a straight-going target vehicle.
In a possible implementation manner of this embodiment, the vehicle identification submodule is specifically configured to:
inputting the collected video frame into a trained YOLO model, dividing the video frame into at least one grid by the YOLO model, identifying vehicles in each grid, and determining the positions of the vehicles.
In one possible implementation manner of this embodiment, the target vehicle determination submodule is specifically configured to:
judging whether the vehicle is a left-turn candidate vehicle running on a left-turn lane or not according to the position of the vehicle;
if so, tracking the left-turning candidate vehicle based on the license plate information of the left-turning candidate vehicle;
when the left-turn candidate vehicle is tracked to enter the intersection, determining the left-turn candidate vehicle as a left-turn target vehicle;
and detecting a straight-ahead candidate vehicle which is positioned in a preset range above and to the left of the driving direction of the left-turn target vehicle and is opposite to the driving direction of the left-turn target vehicle, and if the overlapping proportion of the horizontal direction of the straight-ahead candidate vehicle and the horizontal direction of the left-turn target vehicle exceeds a preset threshold value, determining the straight-ahead candidate vehicle as the straight-ahead target vehicle.
In a possible implementation manner of this embodiment, the violation behavior determining module 1002 is specifically configured to:
and if the straight-going target vehicle is positioned at the upper right side of the driving direction of the left-turning target vehicle, determining that the left-turning target vehicle passes through the meeting position before the straight-going target vehicle.
In a possible implementation manner of this embodiment, the video frame related to the violation behavior at least includes one or a combination of the following video frames:
the whole body of the left-turn target vehicle is positioned in a stop line of a left-turn lane, and the distance between the vehicle head position and the stop line is smaller than a preset distance threshold value;
when the left-turning target vehicle meets the straight-going target vehicle;
when it is determined that the left-turn target vehicle passes through the position of the vehicle crossing before the straight-ahead target vehicle;
and the left-turning target vehicle passes through the meeting position and then the driving direction is left-turning.
In a possible implementation manner of this embodiment, the apparatus may further include the following modules:
the violation information generating module is used for acquiring license plate information of the left-turn target vehicle and generating violation information of the left-turn target vehicle according to the license plate information;
and the violation information processing module is used for displaying and/or outputting the violation information and/or the extracted video frame to external equipment.
For the device, camera and system embodiments, since they correspond substantially to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points.
The above-described embodiments of the apparatus, the camera and the system are only schematic, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
Embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the above-described method embodiments.
The embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method embodiments when executing the program.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Computers suitable for executing computer programs include, for example, general and/or special purpose microprocessors, or any other type of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and/or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer does not necessarily have such a device. Further, the computer may be embedded in another device, e.g., a vehicle-mounted terminal, a mobile telephone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., an internal hard disk or a removable disk), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. In other instances, features described in connection with one embodiment may be implemented as discrete components or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Further, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (10)
1. A method of vehicle violation detection, the method comprising:
carrying out vehicle detection on the acquired video frames to detect a target vehicle in the video frames, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked, if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle, determining that violation behaviors which do not give the straight-going target vehicle in courtesy occur in the left-turning target vehicle;
and extracting video frames related to the violation behaviors from the collected video frames.
2. The method of claim 1, wherein the performing vehicle detection on the captured video frames to detect a target vehicle in the video frames comprises:
identifying vehicles in the video frame and obtaining the positions of the vehicles;
acquiring license plate information of the vehicle;
and tracking the vehicle according to the license plate information and the position to determine a left-turn target vehicle and a straight-going target vehicle.
3. The method of claim 2, wherein the identifying vehicles in the video frame and obtaining the location of each vehicle comprises:
inputting the collected video frame into a trained YOLO model, dividing the video frame into at least one grid by the YOLO model, identifying vehicles in each grid, and determining the positions of the vehicles.
4. The method of claim 2 or 3, wherein tracking the vehicle according to the license plate information and the position to determine a left-turn target vehicle and a straight-ahead target vehicle comprises:
judging whether the vehicle is a left-turn candidate vehicle running on a left-turn lane or not according to the position of the vehicle;
if so, tracking the left-turning candidate vehicle based on the license plate information of the left-turning candidate vehicle;
when the left-turn candidate vehicle is tracked to enter the intersection, determining the left-turn candidate vehicle as a left-turn target vehicle;
and detecting a straight-ahead candidate vehicle which is positioned in a preset range above and to the left of the driving direction of the left-turn target vehicle and is opposite to the driving direction of the left-turn target vehicle, and if the overlapping proportion of the horizontal direction of the straight-ahead candidate vehicle and the horizontal direction of the left-turn target vehicle exceeds a preset threshold value, determining the straight-ahead candidate vehicle as the straight-ahead target vehicle.
5. The method according to claim 4, wherein the determining whether the left-turn target vehicle passes through the position of the vehicle-crossing before the straight-ahead target vehicle is performed in such a manner that:
and if the straight-going target vehicle is positioned at the upper right side of the driving direction of the left-turning target vehicle, determining that the left-turning target vehicle passes through the meeting position before the straight-going target vehicle.
6. The method of any one of claims 1-3 wherein the video frames associated with the violation include at least one or a combination of video frames at times:
the whole body of the left-turn target vehicle is positioned in a stop line of a left-turn lane, and the distance between the vehicle head position and the stop line is smaller than a preset distance threshold value;
when the left-turning target vehicle meets the straight-going target vehicle;
when it is determined that the left-turn target vehicle passes through the position of the vehicle crossing before the straight-ahead target vehicle;
and the left-turning target vehicle passes through the meeting position and then the driving direction is left-turning.
7. The method of claim 1 wherein after said extracting the video frame associated with the violation from the captured video frame, the method further comprises:
acquiring license plate information of the left-turn target vehicle, and generating violation information of the left-turn target vehicle according to the license plate information;
and displaying and/or outputting the violation information and/or the extracted video frame to an external device.
8. A vehicle violation detection device, comprising:
the target vehicle detection module is used for carrying out vehicle detection on the acquired video frames so as to detect a target vehicle in the video frames, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
the violation behavior determining module is used for judging that violation behaviors which do not give the straight-going target vehicle any more are generated on the left-turning target vehicle if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked;
and the video frame extraction module is used for extracting the video frame related to the violation behaviors from the collected video frame.
9. A camera, characterized in that the camera comprises:
the video frame acquisition module is used for acquiring video frames and transmitting the video frames to the target vehicle detection module;
the target vehicle detection module is used for carrying out vehicle detection on the video frame so as to detect a target vehicle in the video frame, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
the violation behavior determining module is used for judging that violation behaviors which do not give the straight-going target vehicle any more are generated on the left-turning target vehicle if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked;
and the video frame extraction module is used for extracting the video frame related to the violation behaviors from the collected video frame.
10. A vehicle violation detection system, comprising a camera and a violation detection platform:
the camera is used for collecting video frames and transmitting the video frames to the violation detection platform;
the violation detection platform includes:
the target vehicle detection module is used for carrying out vehicle detection on the video frame transmitted by the camera so as to detect a target vehicle in the video frame, wherein the target vehicle comprises a left-turning target vehicle and a straight-going target vehicle, and the left-turning target vehicle and the straight-going target vehicle are vehicles which are about to meet;
the violation behavior determining module is used for judging that violation behaviors which do not give the straight-going target vehicle any more are generated on the left-turning target vehicle if the left-turning target vehicle passes through the meeting position before the straight-going target vehicle when meeting between the left-turning target vehicle and the straight-going target vehicle is tracked;
and the video frame extraction module is used for extracting the video frame related to the violation behaviors from the collected video frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910237545.7A CN111754781A (en) | 2019-03-27 | 2019-03-27 | Method, device and system for detecting vehicle violation and camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910237545.7A CN111754781A (en) | 2019-03-27 | 2019-03-27 | Method, device and system for detecting vehicle violation and camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111754781A true CN111754781A (en) | 2020-10-09 |
Family
ID=72671420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910237545.7A Pending CN111754781A (en) | 2019-03-27 | 2019-03-27 | Method, device and system for detecting vehicle violation and camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754781A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114241748A (en) * | 2021-11-22 | 2022-03-25 | 浙江大华技术股份有限公司 | Method and device for identifying whether right-turning vehicle gives way to straight-going vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592450A (en) * | 2012-02-22 | 2012-07-18 | 杭州海康威视数字技术股份有限公司 | System and method for snapshotting behavior of motor vehicles not giving precedence to pedestrians on zebra stripes |
| CN104361747A (en) * | 2014-11-11 | 2015-02-18 | 杭州新迪数字工程系统有限公司 | Automatic capture system and recognition method for vehicles not giving way to passengers on zebra crossing |
| CN104537360A (en) * | 2015-01-15 | 2015-04-22 | 上海博康智能信息技术有限公司 | Method and system for detecting vehicle violation of not giving way |
| CN104574980A (en) * | 2014-12-01 | 2015-04-29 | 北京尚易德科技有限公司 | System and method for recording unlawful behaviors that motor vehicles turning at intersections do not park to yield to pedestrians |
| CN104574955A (en) * | 2014-11-28 | 2015-04-29 | 北京尚易德科技有限公司 | System and method for recording behaviors that motor vehicles do not yield in accordance with law when passing through crossroad with Stop/Yield sign |
| CN104751638A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团公司 | Vehicle monitoring method and device |
| CN107134144A (en) * | 2017-04-27 | 2017-09-05 | 武汉理工大学 | A kind of vehicle checking method for traffic monitoring |
| CN109241938A (en) * | 2018-09-27 | 2019-01-18 | 深圳金三立视频科技股份有限公司 | Congestion in road detection method and terminal |
-
2019
- 2019-03-27 CN CN201910237545.7A patent/CN111754781A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592450A (en) * | 2012-02-22 | 2012-07-18 | 杭州海康威视数字技术股份有限公司 | System and method for snapshotting behavior of motor vehicles not giving precedence to pedestrians on zebra stripes |
| CN104751638A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团公司 | Vehicle monitoring method and device |
| CN104361747A (en) * | 2014-11-11 | 2015-02-18 | 杭州新迪数字工程系统有限公司 | Automatic capture system and recognition method for vehicles not giving way to passengers on zebra crossing |
| CN104574955A (en) * | 2014-11-28 | 2015-04-29 | 北京尚易德科技有限公司 | System and method for recording behaviors that motor vehicles do not yield in accordance with law when passing through crossroad with Stop/Yield sign |
| CN104574980A (en) * | 2014-12-01 | 2015-04-29 | 北京尚易德科技有限公司 | System and method for recording unlawful behaviors that motor vehicles turning at intersections do not park to yield to pedestrians |
| CN104537360A (en) * | 2015-01-15 | 2015-04-22 | 上海博康智能信息技术有限公司 | Method and system for detecting vehicle violation of not giving way |
| CN107134144A (en) * | 2017-04-27 | 2017-09-05 | 武汉理工大学 | A kind of vehicle checking method for traffic monitoring |
| CN109241938A (en) * | 2018-09-27 | 2019-01-18 | 深圳金三立视频科技股份有限公司 | Congestion in road detection method and terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114241748A (en) * | 2021-11-22 | 2022-03-25 | 浙江大华技术股份有限公司 | Method and device for identifying whether right-turning vehicle gives way to straight-going vehicle |
| CN114241748B (en) * | 2021-11-22 | 2022-11-22 | 浙江大华技术股份有限公司 | Method and device for identifying whether right-turning vehicle gives way to straight-going vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11074813B2 (en) | Driver behavior monitoring | |
| US11840239B2 (en) | Multiple exposure event determination | |
| CN110400478A (en) | A kind of road condition notification method and device | |
| CN111382768A (en) | Multi-sensor data fusion method and device | |
| CN110738857B (en) | Vehicle violation evidence obtaining method, device and equipment | |
| CN109871787B (en) | Obstacle detection method and device | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN102997900A (en) | Vehicle systems, devices, and methods for recognizing external worlds | |
| KR102001002B1 (en) | Method and system for recognzing license plate based on deep learning | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| JP2021165080A (en) | Vehicle control device, vehicle control method, and computer program for vehicle control | |
| WO2021227586A1 (en) | Traffic accident analysis method, apparatus, and device | |
| CN105303823A (en) | Vehicle violation monitoring method and system | |
| CN111932881A (en) | Traffic intersection management method and device, terminal device and storage medium | |
| CN113674523A (en) | Traffic accident analysis method, device and equipment | |
| CN113012436B (en) | Road monitoring method and device and electronic equipment | |
| CN112749622A (en) | Emergency lane occupation identification method and device | |
| CN113516099A (en) | Traffic behavior recognition method and device, electronic equipment and storage medium | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN114694060A (en) | Road shed object detection method, electronic equipment and storage medium | |
| CN111754781A (en) | Method, device and system for detecting vehicle violation and camera | |
| CN113787997B (en) | Emergency braking control method, electronic device, and storage medium | |
| CN114202936B (en) | Traffic guidance robot and control method thereof | |
| CN115520216A (en) | Driving state judging method and device, computer equipment and storage medium | |
| CN114419889A (en) | Time interval dividing method and device, electronic equipment 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201009 |