CN114333344A - Motor vehicle violation snapshot method and device and electronic equipment - Google Patents
Motor vehicle violation snapshot method and device and electronic equipment Download PDFInfo
- Publication number
- CN114333344A CN114333344A CN202111640082.2A CN202111640082A CN114333344A CN 114333344 A CN114333344 A CN 114333344A CN 202111640082 A CN202111640082 A CN 202111640082A CN 114333344 A CN114333344 A CN 114333344A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- video frame
- area
- signal lamp
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000001514 detection method Methods 0.000 claims abstract description 76
- 230000033228 biological regulation Effects 0.000 claims description 19
- 238000010586 diagram Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a motor vehicle violation snapshot method, a device and electronic equipment, wherein the method comprises the following steps: acquiring a video frame sequence to be detected; each frame of image in the video frame sequence to be detected is marked with a lane area, a signal lamp area and a driving area in advance, and the lane area of the same frame of image is associated with the signal lamp area; obtaining the moving track of a vehicle contained in a video frame sequence to be detected through a pre-trained vehicle detection model; acquiring the state of a signal lamp in a video frame sequence to be detected through a pre-trained signal lamp detection model; judging whether the vehicle breaks rules or not according to the relative position relation among the moving track of the vehicle, the lane area and the driving area and the state of a signal lamp; and if the vehicle is judged to be illegal, capturing video frames related to the vehicle from the video frame sequence to be detected according to a preset capturing mode. The invention can realize automatic detection and evidence collection of motor vehicle violation, thereby improving the management level of traffic departments.
Description
Technical Field
The invention relates to the technical field of traffic monitoring, in particular to a motor vehicle violation snapshot method, a motor vehicle violation snapshot device and electronic equipment.
Background
With the development of economy, the number of motor vehicles in cities increases year by year, and the problems of urban road congestion, frequent traffic accidents, frequent prohibition of motor vehicle violation behaviors and the like become more and more serious. The motor vehicle violation mainly means that the motor vehicle violates the regulations of signal lamps, runs without following a guide lane, turns around illegally and the like, and the traffic order is seriously influenced.
Aiming at the problems, in order to automatically detect and evidence the motor vehicle violation, in the prior art, a single chip microcomputer, a high-definition camera, a red light signal detector and the like are used for detecting the violation vehicle, or a ground induction coil is arranged on each lane, and a camera is triggered to shoot the violation vehicle for evidence collection when the vehicle passes through.
Above-mentioned implementation all needs multiple auxiliary assembly to support, and the construction is loaded down with trivial details and the cost is higher.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus and an electronic device for capturing motor vehicle violations, so as to implement automatic detection and evidence collection for motor vehicle violations, thereby improving the management level of the transportation department.
In a first aspect, an embodiment of the present invention provides a method for capturing a violation of a motor vehicle, where the method is applied to an electronic device, and the method includes: acquiring a video frame sequence to be detected; each frame of image in the video frame sequence to be detected is marked with a lane area, a signal lamp area and a driving area in advance, and the lane area of the same frame of image is associated with the signal lamp area; obtaining the moving track of a vehicle contained in the video frame sequence to be detected through a pre-trained vehicle detection model; acquiring the state of a signal lamp in the video frame sequence to be detected through a pre-trained signal lamp detection model; judging whether the vehicle breaks rules or not according to the moving track of the vehicle, the relative position relation among the lane area and the driving area and the state of the signal lamp; and if the vehicle is judged to be illegal, capturing the video frame associated with the vehicle from the video frame sequence to be detected according to a preset capturing mode.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the lane area includes a stop line and multiple lanes for indicating different driving directions, the signal light area includes multiple signal lights for indicating different driving directions, and the driving area includes multiple driving areas located in the intersection and corresponding to positions of the different lanes; the method for acquiring the video frame sequence to be detected comprises the following steps: acquiring a real-time video frame sequence, and marking the lane area, the signal lamp area and the driving area for each frame image in the real-time video frame sequence; and for each frame of image in the real-time video frame sequence, correspondingly associating lanes used for indicating the same driving direction in the image with a signal lamp to obtain the video frame sequence to be detected.
With reference to the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where the step of obtaining a moving track of a vehicle included in the video frame sequence to be detected through a pre-trained vehicle detection model includes: detecting each frame image in the video frame sequence to be detected through the vehicle detection model to obtain a detection frame of the vehicle; and determining the movement track of the detection frame through a tracking algorithm according to the position coordinates of the detection frame in different frame images, and determining the movement track of the detection frame as the movement track of the vehicle.
With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the step of determining whether the vehicle violates a regulation or not according to a moving track of the vehicle, a relative positional relationship among the lane area and the driving area, and a state of the signal lamp includes at least one of: judging whether the vehicle runs the red light or not according to the state of the signal lamp and the relative position relation between the moving track of the vehicle and the stop line; judging whether the vehicle does not run according to a guide lane or not according to the relative position relation among the moving track of the vehicle, the stop line and the running area; and judging whether the vehicle turns around illegally according to the relative position relation among the moving track of the vehicle, the stop line and the driving area.
With reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the lanes are divided into a turn-around lane, a left-turn lane, a straight lane, and a right-turn lane; the driving area is divided into a turning driving area, a left-turning driving area, a straight driving area and a right-turning driving area; the step of judging whether the vehicle runs the red light or not according to the state of the signal lamp and the relative position relation between the moving track of the vehicle and the stop line comprises one of the following steps: if the signal lamp corresponding to the lane where the vehicle is located is a circular red lamp and the vehicle passes through the stop line along a non-right-turn lane, judging that the vehicle runs the red lamp; and if the signal lamp corresponding to the lane where the vehicle is located is an arrow-shaped red light and the vehicle passes through the stop line, judging that the vehicle runs the red light.
With reference to the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, wherein the step of determining whether the vehicle does not travel along a guidance lane according to a relative positional relationship among a moving track of the vehicle, the stop line, and the travel area includes one of: if the vehicle passes through the stop line along the turn-around lane and enters a left-turn driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; if the vehicle passes through the stop line along the left-turn lane and enters a U-turn driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; if the vehicle passes through the stop line along the straight lane and enters a U-turn driving area, a left-turn driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; and if the vehicle passes through the stop line along the right-turn lane and enters a U-turn driving area, a left-turn driving area or a straight driving area, judging that the vehicle does not drive according to the guide lane.
With reference to the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where the step of determining whether the vehicle makes an illegal turn according to a relative positional relationship among the moving track of the vehicle, the stop line, and the driving area includes: and if the vehicle passes through the stop line along a left-turn lane, a straight lane or a right-turn lane and enters a U-turn driving area, judging that the vehicle turns around illegally.
With reference to the first aspect, an embodiment of the present invention provides a seventh possible implementation manner of the first aspect, where the step of capturing the video frame associated with the vehicle from the video frame sequence to be detected according to a preset capturing mode includes: when it is determined from a first video frame subsequence in the video frame sequence to be detected that the vehicle enters the lane area and does not reach the stop line, carrying out first snapshot on the vehicle in the first video frame subsequence to obtain a first evidence picture of the vehicle; when the fact that the vehicle passes through the stop line and does not reach the driving area is determined from a second video frame subsequence in the video frame sequence to be detected, carrying out second snapshot on the vehicle in the second video frame subsequence to obtain a second evidence picture of the vehicle; and when the fact that the vehicle enters a driving area is determined from a third video frame subsequence in the video frame sequence to be detected and the fact that the vehicle runs a red light or does not run according to guidance or illegally turns around is judged, carrying out third-time snapshot on the vehicle in the third video frame subsequence to obtain a third evidence picture of the vehicle.
In a second aspect, an embodiment of the present invention further provides a motor vehicle violation snapshot device, where the device is applied to an electronic device, and the device includes: the video frame sequence acquisition module is used for acquiring a video frame sequence to be detected; each frame of image in the video frame sequence to be detected is marked with a lane area, a signal lamp area and a driving area in advance, and the lane area of the same frame of image is associated with the signal lamp area; the moving track acquisition module is used for acquiring a moving track of a vehicle contained in the video frame sequence to be detected through a pre-trained vehicle detection model; the signal lamp state acquisition module is used for acquiring the state of a signal lamp in the video frame sequence to be detected through a pre-trained signal lamp detection model; the violation judging module is used for judging whether the vehicle violates the regulations or not according to the moving track of the vehicle, the relative position relation among the lane area and the driving area and the state of the signal lamp; and the snapshot module is used for snapshotting the video frame associated with the vehicle from the video frame sequence to be detected according to a preset snapshot mode when the vehicle violation is judged.
In a third aspect, the embodiment of the present invention further provides an electronic device, which includes a processor and a memory, where the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the above-mentioned motor vehicle violation snapshot method.
According to the motor vehicle violation snapshot method, the motor vehicle violation snapshot device and the electronic equipment, after the video frame sequence to be detected is obtained, the moving track of a vehicle contained in the video frame sequence to be detected is obtained through the pre-trained vehicle detection model, the state of a signal lamp in the video frame sequence to be detected is obtained through the pre-trained signal lamp detection model, whether the vehicle violates the regulations or not is judged according to the relative position relation among the moving track of the vehicle, a lane area and a driving area and the state of the signal lamp, and the video frame related to the vehicle is snapshot from the video frame sequence to be detected in the preset snapshot mode when the vehicle violation is judged. By adopting the technology, after the vehicle video frame marked with the lane area, the signal lamp area and the driving area is obtained, the moving track of the vehicle can be accurately positioned through the vehicle detection model, the real-time state of the signal lamp can be accurately judged through the signal lamp detection model, and then whether the vehicle breaks rules and regulations or not is judged according to the position relation among the vehicle moving track, the lane area and the driving area and the signal lamp state, and the vehicle is shot and evidence is obtained for the vehicle breaking rules and regulations.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of a motor vehicle violation snapshot method according to an embodiment of the present invention;
fig. 2 is an exemplary diagram of a frame image in a sequence of video frames to be detected according to an embodiment of the present invention;
fig. 3 is an exemplary diagram of a vehicle movement track obtaining manner according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a motor vehicle violation snapshot device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the embodiments, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, aiming at the problems, in order to automatically detect and evidence the violation of the motor vehicle, in the prior art, a violation vehicle is detected by utilizing a single chip microcomputer, a high-definition camera, a red light signal detector and the like, or a ground induction coil is arranged on each lane, and a camera is triggered to shoot and evidence the violation vehicle when the vehicle passes through. However, the above implementation methods all need to be supported by various auxiliary devices, and are complex in construction and high in cost. Based on the method, the device and the electronic equipment for snapshotting the motor vehicle violation, provided by the embodiment of the invention, the motor vehicle violation can be automatically detected and evidence can be obtained, and the management level of a traffic department can be further improved.
In order to facilitate understanding of the embodiment, first, a method for capturing a violation of regulation of a motor vehicle disclosed in the embodiment of the present invention is described in detail, referring to a flow diagram of a method for capturing a violation of regulation of a motor vehicle shown in fig. 1, an execution main body of the method is an electronic device, and the electronic device may be a device (such as a camera or the like) having a video acquisition function; the method may comprise the steps of:
step S102, acquiring a video frame sequence to be detected; the method comprises the steps that a lane area, a signal lamp area and a driving area are marked in advance on each frame of image in a video frame sequence to be detected, and the lane area of the same frame of image is related to the signal lamp area.
The video frame sequence to be detected can be a section of video which is collected by a camera arranged near a traffic intersection in a period of time and contains vehicles. When a vehicle passes through a traffic intersection, the vehicle usually travels a certain distance along a lane for indicating the traveling direction, and then can cross a stop line under the condition that a signal lamp corresponding to the lane where the vehicle is located is a green lamp; based on this, in order to further determine the way of the vehicle passing through the traffic intersection, the lane area may be defined to include a stop line and a plurality of lanes (e.g., a straight lane, a left-turn lane, a right-turn lane, a u-turn lane, etc.) for indicating different driving directions, the signal lamp area may be defined to include a plurality of signal lamps (e.g., a straight signal lamp, a left-turn signal lamp, a right-turn signal lamp, a u-turn signal lamp, etc.) for indicating different driving directions, and the driving area may be defined to include a plurality of driving areas (e.g., an area where the vehicle passes through the traffic intersection straight after passing through the stop line along the straight lane, and an area where the vehicle passes through the traffic intersection left after passing through the stop line along the left-turn lane) corresponding to the positions of the different lanes. In addition, in the practical application process, the lane area may further include a lane with indication significance, such as a non-motor lane, the signal light area may further include a signal light with indication significance, such as a non-motor signal light, and the driving area may further include an area where the vehicle passes through a traffic intersection after passing through a stop line along the lane with indication significance, such as the non-motor lane, and therefore, the definition modes of the lane area, the signal light area, and the driving area may be determined by themselves according to actual needs, and are not limited.
After defining the good lane area, the signal light area and the driving area, as a possible implementation, the step S102 may adopt the following operation modes: acquiring a real-time video frame sequence, and marking a lane area, a signal lamp area and a driving area for each frame image in the real-time video frame sequence; and for each frame of image in the real-time video frame sequence, correspondingly associating lanes used for indicating the same driving direction in the image with a signal lamp to obtain the video frame sequence to be detected.
Specifically, taking fig. 2 as an example, in fig. 2, the lane area includes a stop line, a turn-around lane, a left-turn lane, a straight lane and a right-turn lane, the driving area includes a turn-around driving area, a left-turn driving area, a straight driving area and a right-turn driving area, the signal lamp area includes a signal lamp 1 for indicating turning around of the vehicle, a signal lamp 2 for indicating left-turn of the vehicle, a signal lamp 3 for indicating straight running of the vehicle and a signal lamp 4 for indicating right-turn of the vehicle, wherein the turn-around lane is associated with the signal lamp 1, the left-turn lane is associated with the signal lamp 2, the straight lane is associated with the signal lamp 3, and the right-turn lane is associated with the signal lamp 4.
And step S104, obtaining the movement track of the vehicle contained in the video frame sequence to be detected through a pre-trained vehicle detection model.
Before the vehicle detection model is trained, an offline video of a traffic intersection containing a vehicle in a historical time period needs to be acquired, then a specified number of frames of images in the offline video are selected as image samples, a rectangular frame surrounding the whole vehicle body of the vehicle and position coordinate information (x, y, w, h) corresponding to the rectangular frame are marked for the position of the vehicle in the image samples, wherein x represents an abscissa of the center of the rectangular frame, y represents an ordinate of the center of the rectangular frame, w represents a width of the rectangular frame, and h represents a height of the rectangular frame. And after the labeling is finished, inputting the image samples labeled with the rectangular frame surrounding the whole vehicle body of the vehicle and the position coordinate information corresponding to the rectangular frame as training samples into an initial target detection neural network model, and stopping training after the model is converged or the iteration times reach preset times to obtain the vehicle detection model. The initial target detection neural network model may be, but is not limited to, an existing target detection neural network model such as YOLOv 5.
After the vehicle detection model is trained, the following operation may be performed in step S104: detecting each frame image in a video frame sequence to be detected through a vehicle detection model to obtain a vehicle detection frame; and determining the moving track of the detection frame through a tracking algorithm according to the position coordinates of the detection frame in different frame images, and determining the moving track of the detection frame as the moving track of the vehicle. Specifically, each frame of image in the sequence of video frames to be detected is input into the vehicle detection model, a rectangular detection frame is generated for the position of the vehicle body of the same vehicle in each input image through the vehicle detection model (the position coordinate of the center of the detection frame is the position coordinate of the detection frame), an ID number is generated for the detection frame of the same vehicle, then a tracking algorithm can be adopted to track the detection frames with the same ID number in different frame images, the detection frames with the same ID number in different frame images are correspondingly associated to obtain the movement track of the detection frame with the same ID number, the movement track is determined as the movement track of the same vehicle, and finally the movement track of the vehicle contained in the sequence of video frames to be detected is obtained. The tracking algorithm may specifically use a sort algorithm, a deep sort algorithm, and the like, which is not limited. Continuing with fig. 2, taking fig. 3 as an example, in fig. 3, a rectangular detection frame with position coordinates is generated for the position of the vehicle body of a certain vehicle in each input image through a vehicle detection model, an ID number (B1 in fig. 3) for uniquely characterizing the vehicle is generated for the detection frame of the vehicle, and then the detection frame with B1 in different frame images is tracked by using a sort algorithm; in order to generate the tracking result of the vehicle at the time t, a sort algorithm is adopted to correspondingly associate a detection frame with a belt B1 in the image at the time t (namely, a bold rectangular frame with a belt B1 in FIG. 3) with a detection frame with a belt B1 in the image at the time t-1 (namely, a dotted rectangular frame with a belt B1 in FIG. 3); and obtaining the tracking result at all the moments in a similar way, namely the moving track of the vehicle.
And S106, acquiring the state of a signal lamp in the video frame sequence to be detected through a pre-trained signal lamp detection model.
Specifically, before the signal lamp detection model is trained, an offline video of a traffic intersection including a signal lamp in a historical time period needs to be acquired, then a specified number of frame images in the offline video are selected as image samples, and signal lamp attribute information is labeled for the signal lamp in the image samples (for example, "100100" represents that the signal lamp is a turn signal lamp and is a green lamp, "010010" represents that the signal lamp is a left turn signal lamp and is a yellow lamp, and "001001" represents that the signal lamp is a straight signal lamp and is a red lamp). And after the labeling is finished, inputting the image samples labeled with the signal lamp attribute information into an initial classification neural network model as training samples, and stopping training after the model is converged or the iteration times reach preset times to obtain the signal lamp detection model. The initial classification neural network model may specifically adopt an existing classification neural network model such as RepVGG, and the like, which is not limited thereto. After the signal lamp detection model is obtained through training, each frame of image in the video frame sequence to be detected can be input into the signal lamp detection model, and the state of a signal lamp of each frame of image in the video frame sequence to be detected is output through the signal lamp detection model.
And S108, judging whether the vehicle violates regulations or not according to the moving track of the vehicle, the relative position relation among the lane area and the driving area and the state of the signal lamp.
For different violations of the vehicle, the step S108 may adopt at least one of the following three operation modes: (1) judging whether the vehicle runs the red light or not according to the state of the signal lamp and the relative position relation between the moving track of the vehicle and the stop line; (2) judging whether the vehicle does not run according to the guide lane or not according to the relative position relation among the moving track, the stop line and the running area of the vehicle; (3) and judging whether the vehicle turns around illegally according to the relative position relation among the moving track, the stop line and the driving area of the vehicle.
As an example, the operation manner of the step S108 for different violations of the vehicle is described as follows by taking fig. 2 as an example:
in fig. 2, the lanes are divided into a turnaround lane, a left-turn lane, a straight lane and a right-turn lane, and the driving zones are divided into a turnaround driving zone, a left-turn driving zone, a straight driving zone and a right-turn driving zone; based on this, considering that the signal lamp is generally divided into two types of shapes, namely an arrow-shaped signal lamp and a circular signal lamp in the practical application process, the step of judging whether the vehicle runs the red light according to the state of the signal lamp and the relative position relationship between the moving track of the vehicle and the stop line may specifically adopt one of the following operation modes: (11) if the signal lamp corresponding to the lane where the vehicle is located is a circular red lamp and the vehicle passes through the stop line along the non-right-turn lane, judging that the vehicle runs the red lamp; (12) and if the signal lamp corresponding to the lane where the vehicle is located is an arrow-shaped red light and the vehicle passes through the stop line, judging that the vehicle runs the red light.
Continuing with fig. 2, the step of determining whether the vehicle does not travel along the guidance lane according to the relative position relationship among the moving track, the stop line and the traveling region of the vehicle may specifically adopt one of the following operation modes: (21) if the vehicle passes through the stop line along the turn-around lane and enters a left-turn driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; (22) if the vehicle passes through the stop line along the left-turn lane and enters a turn-around driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; (23) if the vehicle passes through the stop line along the straight lane and enters a U-turn driving area, a left-turn driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; (24) and if the vehicle passes through the stop line along the right-turn lane and enters a turn-around driving area, a left-turn driving area or a straight driving area, judging that the vehicle does not drive according to the guide lane.
The step of determining whether the vehicle turns around illegally according to the relative position relationship among the moving track, the stop line and the driving area of the vehicle may specifically adopt the following operation modes: and if the vehicle passes through the stop line along the left-turn lane, the straight lane or the right-turn lane and enters the U-turn driving area, judging that the vehicle turns around illegally.
And step S110, if the vehicle violation is judged, capturing a video frame associated with the vehicle from the video frame sequence to be detected according to a preset capturing mode.
The video frame related to the vehicle is a video frame containing the vehicle, which needs to be captured at a certain moment in the video frame sequence to be detected. For convenience of operation, the step S110 may specifically adopt the following operation modes: when the fact that the vehicle enters a lane area and does not reach a stop line is determined from a first video frame subsequence in a video frame sequence to be detected, carrying out first snapshot on the vehicle in the first video frame subsequence to obtain a first evidence picture of the vehicle; when the vehicle is determined to pass through the stop line and not reach the driving area from a second video frame subsequence in the video frame sequence to be detected, carrying out second snapshot on the vehicle in the second video frame subsequence to obtain a second evidence picture of the vehicle; and when the vehicle enters a driving area and the vehicle is judged to run a red light or not run according to the guidance or illegally turn around from a third video frame subsequence in the video frame sequence to be detected, carrying out third snapshot on the vehicle in the third video frame subsequence to obtain a third evidence picture of the vehicle.
The first video frame subsequence is a video frame sequence in a period of time from the time when the vehicle enters a lane area to the time when the vehicle will reach a stop line in the video frame sequence to be detected, the second video frame subsequence is a video frame sequence in a period of time from the time when the vehicle crosses the stop line to the time when the vehicle will reach a driving area in the video frame sequence to be detected, and the second video frame subsequence is a video frame sequence in a period of time from the time when the vehicle enters the driving area to the time when the vehicle is judged to have run a red light or not run according to guidance or illegally and turn around. In addition, the preset snapshot mode can be adjusted according to actual conditions, and is not limited.
In order to facilitate the relevant personnel to master the vehicle violation condition, the relevant evidence of the vehicle violation can be pushed, the evidence can comprise vehicle information (such as vehicle model number, license plate number, ID number and the like), the three evidence pictures and the like, the evidence can be selected by the personnel according to the actual condition, and the evidence is not limited.
According to the motor vehicle violation snapshot method provided by the embodiment of the invention, after the video frame sequence to be detected is obtained, the moving track of the vehicle contained in the video frame sequence to be detected is obtained through the pre-trained vehicle detection model, the state of the signal lamp in the video frame sequence to be detected is obtained through the pre-trained signal lamp detection model, whether the vehicle violates the regulations or not is judged according to the relative position relation among the moving track of the vehicle, the lane area and the driving area and the state of the signal lamp, and the video frame related to the vehicle is snapshot from the video frame sequence to be detected when the vehicle violates the regulations. By adopting the technology, after the vehicle video frame marked with the lane area, the signal lamp area and the driving area is obtained, the moving track of the vehicle can be accurately positioned through the vehicle detection model, the real-time state of the signal lamp can be accurately judged through the signal lamp detection model, and then whether the vehicle breaks rules and regulations or not is judged according to the position relation among the vehicle moving track, the lane area and the driving area and the signal lamp state, and the vehicle is shot and evidence is obtained for the vehicle breaking rules and regulations.
Based on the motor vehicle violation snapshot method, the embodiment of the invention also provides a motor vehicle violation snapshot device, which is shown in fig. 4 and comprises the following steps:
a video frame sequence obtaining module 41, configured to obtain a video frame sequence to be detected; the method comprises the steps that a lane area, a signal lamp area and a driving area are marked in advance on each frame of image in a video frame sequence to be detected, and the lane area of the same frame of image is related to the signal lamp area.
And a moving track obtaining module 42, configured to obtain, through a pre-trained vehicle detection model, a moving track of a vehicle included in the to-be-detected video frame sequence.
And a signal lamp state obtaining module 43, configured to obtain, through a pre-trained signal lamp detection model, a state of a signal lamp in the video frame sequence to be detected.
And the violation judging module 44 is used for judging whether the vehicle violates the regulations or not according to the moving track of the vehicle, the relative position relation among the lane area and the driving area and the state of the signal lamp.
And the snapshot module 45 is used for snapshotting the video frame associated with the vehicle from the video frame sequence to be detected according to a preset snapshot mode when the vehicle violation is judged.
According to the motor vehicle violation snapshot device provided by the embodiment of the invention, after the video frame sequence to be detected is obtained, the moving track of the vehicle contained in the video frame sequence to be detected is obtained through the pre-trained vehicle detection model, the state of the signal lamp in the video frame sequence to be detected is obtained through the pre-trained signal lamp detection model, whether the vehicle violates the regulations or not is judged according to the relative position relation among the moving track of the vehicle, the lane area and the driving area and the state of the signal lamp, and the video frame related to the vehicle is snapshot from the video frame sequence to be detected according to the preset snapshot mode when the vehicle violation is judged. By adopting the technology, after the vehicle video frame marked with the lane area, the signal lamp area and the driving area is obtained, the moving track of the vehicle can be accurately positioned through the vehicle detection model, the real-time state of the signal lamp can be accurately judged through the signal lamp detection model, and then whether the vehicle breaks rules and regulations or not is judged according to the position relation among the vehicle moving track, the lane area and the driving area and the signal lamp state, and the vehicle is shot and evidence is obtained for the vehicle breaking rules and regulations.
The lane area may include a stop line and a plurality of lanes for indicating different driving directions, the signal light area includes a plurality of signal lights for indicating different driving directions, and the driving area includes a plurality of driving areas which are located in the traffic intersection and correspond to positions of the different lanes; based on this, the video frame sequence obtaining module 41 may further be configured to: acquiring a real-time video frame sequence, and marking the lane area, the signal lamp area and the driving area for each frame image in the real-time video frame sequence; and for each frame of image in the real-time video frame sequence, correspondingly associating lanes used for indicating the same driving direction in the image with a signal lamp to obtain the video frame sequence to be detected.
The movement track obtaining module 42 may further be configured to: detecting each frame image in the video frame sequence to be detected through the vehicle detection model to obtain a detection frame of the vehicle; and determining the movement track of the detection frame through a tracking algorithm according to the position coordinates of the detection frame in different frame images, and determining the movement track of the detection frame as the movement track of the vehicle.
The violation determination module 44 may also be configured to: and judging whether the vehicle runs the red light or not according to the state of the signal lamp and the relative position relation between the moving track of the vehicle and the stop line.
The violation determination module 44 may also be configured to: and judging whether the vehicle does not run according to a guide lane or not according to the relative position relation among the moving track of the vehicle, the stop line and the running area.
The violation determination module 44 may also be configured to: and judging whether the vehicle turns around illegally according to the relative position relation among the moving track of the vehicle, the stop line and the driving area.
The lanes are divided into a turning lane, a left-turn lane, a straight lane and a right-turn lane; the driving area is divided into a turning driving area, a left-turning driving area, a straight driving area and a right-turning driving area; based on this, the violation determination module 44 may also be configured to: when the signal lamp corresponding to the lane where the vehicle is located is a circular red lamp and the vehicle passes through the stop line along a non-right-turn lane, judging that the vehicle runs the red lamp; and when the signal lamp corresponding to the lane where the vehicle is located is an arrow-shaped red light and the vehicle passes through the stop line, judging that the vehicle runs the red light.
The violation determination module 44 may also be configured to: when the vehicle passes through the stop line along the turn-around lane and enters a left-turn driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; when the vehicle passes through the stop line along the left-turn lane and enters a turn-around driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; when the vehicle passes through the stop line along the straight lane and enters a U-turn driving area, a left-turn driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane; and when the vehicle passes through the stop line along the right-turn lane and enters a turn-around driving area, a left-turn driving area or a straight driving area, judging that the vehicle does not drive according to the guide lane.
The violation determination module 44 may also be configured to: and when the vehicle passes through the stop line along a left-turn lane, a straight-going lane or a right-turn lane and enters a turn-around driving area, judging that the vehicle turns around illegally.
The above-mentioned snapshot module 45 may also be used to: when it is determined from a first video frame subsequence in the video frame sequence to be detected that the vehicle enters the lane area and does not reach the stop line, carrying out first snapshot on the vehicle in the first video frame subsequence to obtain a first evidence picture of the vehicle; when the fact that the vehicle passes through the stop line and does not reach the driving area is determined from a second video frame subsequence in the video frame sequence to be detected, carrying out second snapshot on the vehicle in the second video frame subsequence to obtain a second evidence picture of the vehicle; and when the fact that the vehicle enters a driving area is determined from a third video frame subsequence in the video frame sequence to be detected and the fact that the vehicle runs a red light or does not run according to guidance or illegally turns around is judged, carrying out third-time snapshot on the vehicle in the third video frame subsequence to obtain a third evidence picture of the vehicle.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
An embodiment of the present invention provides an electronic device, and fig. 5 is a schematic structural diagram of an electronic device provided in an embodiment of the present invention, where the electronic device 100 includes: the device comprises a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is arranged to execute executable modules, such as computer programs, stored in the memory 51.
The Memory 51 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 52 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
The memory 51 is used for storing a program, the processor 50 executes the program after receiving an execution instruction, and the method executed by the apparatus defined by the flow process disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 50, or implemented by the processor 50.
The processor 50 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the motor vehicle violation capture method can be implemented by integrated logic of hardware in the processor 50 or instructions in the form of software. The Processor 50 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the motor vehicle violation snapshot method disclosed by the embodiment of the invention can be directly embodied as the execution of a hardware decoding processor, or the combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and completes the steps of the motor vehicle violation snapshot method in combination with the hardware.
The computer program product of the readable storage medium provided by the embodiment of the present invention includes a computer readable storage medium storing a program code, and instructions included in the program code may be used to execute the motor vehicle violation snapshot method described in the foregoing method embodiment, and specific implementation may refer to the foregoing method embodiment, and details are not described here.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A motor vehicle violation snapshot method is applied to an electronic device, and comprises the following steps:
acquiring a video frame sequence to be detected; each frame of image in the video frame sequence to be detected is marked with a lane area, a signal lamp area and a driving area in advance, and the lane area of the same frame of image is associated with the signal lamp area;
obtaining the moving track of a vehicle contained in the video frame sequence to be detected through a pre-trained vehicle detection model;
acquiring the state of a signal lamp in the video frame sequence to be detected through a pre-trained signal lamp detection model;
judging whether the vehicle breaks rules or not according to the moving track of the vehicle, the relative position relation among the lane area and the driving area and the state of the signal lamp;
and if the vehicle is judged to be illegal, capturing the video frame associated with the vehicle from the video frame sequence to be detected according to a preset capturing mode.
2. The method of claim 1, wherein the lane area comprises a stop line and a plurality of lanes for indicating different driving directions, the signal light area comprises a plurality of signal lights for indicating different driving directions, and the driving area comprises a plurality of driving areas located in the traffic intersection and corresponding to positions of the different lanes;
the method for acquiring the video frame sequence to be detected comprises the following steps:
acquiring a real-time video frame sequence, and marking the lane area, the signal lamp area and the driving area for each frame image in the real-time video frame sequence;
and for each frame of image in the real-time video frame sequence, correspondingly associating lanes used for indicating the same driving direction in the image with a signal lamp to obtain the video frame sequence to be detected.
3. The method according to claim 1, wherein the step of obtaining the moving track of the vehicle included in the video frame sequence to be detected by using a pre-trained vehicle detection model comprises:
detecting each frame image in the video frame sequence to be detected through the vehicle detection model to obtain a detection frame of the vehicle;
and determining the movement track of the detection frame through a tracking algorithm according to the position coordinates of the detection frame in different frame images, and determining the movement track of the detection frame as the movement track of the vehicle.
4. The method of claim 2, wherein the step of determining whether the vehicle violates a regulation or not according to the moving track of the vehicle, the relative positional relationship between the lane area and the driving area, and the state of the signal lamp includes at least one of:
judging whether the vehicle runs the red light or not according to the state of the signal lamp and the relative position relation between the moving track of the vehicle and the stop line;
judging whether the vehicle does not run according to a guide lane or not according to the relative position relation among the moving track of the vehicle, the stop line and the running area;
and judging whether the vehicle turns around illegally according to the relative position relation among the moving track of the vehicle, the stop line and the driving area.
5. The method of claim 4, wherein the lanes are divided into a turnaround lane, a left turn lane, a straight lane, and a right turn lane; the driving area is divided into a turning driving area, a left-turning driving area, a straight driving area and a right-turning driving area;
the step of judging whether the vehicle runs the red light or not according to the state of the signal lamp and the relative position relation between the moving track of the vehicle and the stop line comprises one of the following steps:
if the signal lamp corresponding to the lane where the vehicle is located is a circular red lamp and the vehicle passes through the stop line along a non-right-turn lane, judging that the vehicle runs the red lamp;
and if the signal lamp corresponding to the lane where the vehicle is located is an arrow-shaped red light and the vehicle passes through the stop line, judging that the vehicle runs the red light.
6. The method according to claim 5, wherein the step of determining whether the vehicle is not traveling in the guide lane according to the relative positional relationship among the moving track of the vehicle, the stop line, and the traveling region includes one of:
if the vehicle passes through the stop line along the turn-around lane and enters a left-turn driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane;
if the vehicle passes through the stop line along the left-turn lane and enters a U-turn driving area, a straight driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane;
if the vehicle passes through the stop line along the straight lane and enters a U-turn driving area, a left-turn driving area or a right-turn driving area, judging that the vehicle does not drive according to the guide lane;
and if the vehicle passes through the stop line along the right-turn lane and enters a U-turn driving area, a left-turn driving area or a straight driving area, judging that the vehicle does not drive according to the guide lane.
7. The method according to claim 5, wherein the step of determining whether the vehicle turns around illegally according to the relative position relationship among the moving track of the vehicle, the stop line and the driving area comprises:
and if the vehicle passes through the stop line along a left-turn lane, a straight lane or a right-turn lane and enters a U-turn driving area, judging that the vehicle turns around illegally.
8. The method according to any one of claims 4 to 7, wherein the step of snapping the video frames associated with the vehicle from the sequence of video frames to be detected according to a preset snapping manner comprises:
when it is determined from a first video frame subsequence in the video frame sequence to be detected that the vehicle enters the lane area and does not reach the stop line, carrying out first snapshot on the vehicle in the first video frame subsequence to obtain a first evidence picture of the vehicle;
when the fact that the vehicle passes through the stop line and does not reach the driving area is determined from a second video frame subsequence in the video frame sequence to be detected, carrying out second snapshot on the vehicle in the second video frame subsequence to obtain a second evidence picture of the vehicle;
and when the fact that the vehicle enters a driving area is determined from a third video frame subsequence in the video frame sequence to be detected and the fact that the vehicle runs a red light or does not run according to guidance or illegally turns around is judged, carrying out third-time snapshot on the vehicle in the third video frame subsequence to obtain a third evidence picture of the vehicle.
9. A motor vehicle violation snapshot device, characterized in that the device is applied to an electronic device, the device comprises:
the video frame sequence acquisition module is used for acquiring a video frame sequence to be detected; each frame of image in the video frame sequence to be detected is marked with a lane area, a signal lamp area and a driving area in advance, and the lane area of the same frame of image is associated with the signal lamp area;
the moving track acquisition module is used for acquiring a moving track of a vehicle contained in the video frame sequence to be detected through a pre-trained vehicle detection model;
the signal lamp state acquisition module is used for acquiring the state of a signal lamp in the video frame sequence to be detected through a pre-trained signal lamp detection model;
the violation judging module is used for judging whether the vehicle violates the regulations or not according to the moving track of the vehicle, the relative position relation among the lane area and the driving area and the state of the signal lamp;
and the snapshot module is used for snapshotting the video frame associated with the vehicle from the video frame sequence to be detected according to a preset snapshot mode when the vehicle violation is judged.
10. An electronic device comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the vehicle violation capture method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111640082.2A CN114333344A (en) | 2021-12-29 | 2021-12-29 | Motor vehicle violation snapshot method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111640082.2A CN114333344A (en) | 2021-12-29 | 2021-12-29 | Motor vehicle violation snapshot method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114333344A true CN114333344A (en) | 2022-04-12 |
Family
ID=81016027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111640082.2A Pending CN114333344A (en) | 2021-12-29 | 2021-12-29 | Motor vehicle violation snapshot method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114333344A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114973165A (en) * | 2022-07-14 | 2022-08-30 | 浙江大华技术股份有限公司 | Event recognition algorithm testing method and device and electronic equipment |
| 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 |
| CN115440053A (en) * | 2022-08-04 | 2022-12-06 | 浙江大华技术股份有限公司 | Vehicle violation snapshot method, device and system, electronic device and storage medium |
| CN116030388A (en) * | 2022-12-30 | 2023-04-28 | 以萨技术股份有限公司 | Processing method for identifying task, electronic equipment and storage medium |
| CN117746641A (en) * | 2023-12-11 | 2024-03-22 | 北京卓视智通科技有限责任公司 | A non-motor vehicle red light incident monitoring method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | High-definition video-based evidence collection method for motor vehicles running red lights |
| WO2020000251A1 (en) * | 2018-06-27 | 2020-01-02 | 潍坊学院 | Method for identifying video involving violation at intersection based on coordinated relay of video cameras |
| CN110909699A (en) * | 2019-11-28 | 2020-03-24 | 北京以萨技术股份有限公司 | Video vehicle non-guide driving detection method and device and readable storage medium |
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN111627217A (en) * | 2020-05-29 | 2020-09-04 | 济南博观智能科技有限公司 | Method, device and equipment for judging vehicle illegal turning around and storage medium |
-
2021
- 2021-12-29 CN CN202111640082.2A patent/CN114333344A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | High-definition video-based evidence collection method for motor vehicles running red lights |
| WO2020000251A1 (en) * | 2018-06-27 | 2020-01-02 | 潍坊学院 | Method for identifying video involving violation at intersection based on coordinated relay of video cameras |
| CN110909699A (en) * | 2019-11-28 | 2020-03-24 | 北京以萨技术股份有限公司 | Video vehicle non-guide driving detection method and device and readable storage medium |
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN111627217A (en) * | 2020-05-29 | 2020-09-04 | 济南博观智能科技有限公司 | Method, device and equipment for judging vehicle illegal turning around and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114973165A (en) * | 2022-07-14 | 2022-08-30 | 浙江大华技术股份有限公司 | Event recognition algorithm testing method and device and electronic equipment |
| CN114973165B (en) * | 2022-07-14 | 2022-10-25 | 浙江大华技术股份有限公司 | Event recognition algorithm testing method and device and electronic equipment |
| CN115440053A (en) * | 2022-08-04 | 2022-12-06 | 浙江大华技术股份有限公司 | Vehicle violation snapshot method, device and system, electronic device and storage medium |
| CN115440053B (en) * | 2022-08-04 | 2024-09-03 | 浙江大华技术股份有限公司 | Vehicle violation snapshot method, device, system, electronic device and 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 |
| CN116030388A (en) * | 2022-12-30 | 2023-04-28 | 以萨技术股份有限公司 | Processing method for identifying task, electronic equipment and storage medium |
| CN116030388B (en) * | 2022-12-30 | 2023-08-11 | 以萨技术股份有限公司 | Processing method for identifying task, electronic equipment and storage medium |
| CN117746641A (en) * | 2023-12-11 | 2024-03-22 | 北京卓视智通科技有限责任公司 | A non-motor vehicle red light incident monitoring method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114333344A (en) | Motor vehicle violation snapshot method and device and electronic equipment | |
| CN109801508B (en) | Method and device for predicting movement track of obstacle at intersection | |
| US9805474B1 (en) | Pedestrian tracking at a traffic intersection to identify vulnerable roadway users for traffic signal timing, pedestrian safety, and traffic intersection control | |
| CN104537841B (en) | Unlicensed vehicle violation detection method and detection system thereof | |
| CN113420748B (en) | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium | |
| US11607994B2 (en) | Vehicle, object warning apparatus and method | |
| CN113011331B (en) | Method and device for detecting whether motor vehicle gives way to pedestrians, electronic equipment and medium | |
| CN110032947B (en) | Method and device for monitoring occurrence of event | |
| WO2016145626A1 (en) | Traffic abnormity detection method and device, and image monitoring system | |
| CN109427191A (en) | A kind of traveling detection method and device | |
| CN115292435B (en) | High-precision map updating method and device, electronic equipment and storage medium | |
| CN113968229A (en) | Road area determination method and device and electronic equipment | |
| CN104575047A (en) | System and method for preventing motor vehicle from rushing for green light to block road junction and running red light in reminding mode | |
| CN113469075A (en) | Method, device and equipment for determining traffic flow index and storage medium | |
| CN116745831A (en) | Map generation device, map generation program, and in-vehicle device | |
| CN114693722B (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
| Dinh et al. | Development of a tracking-based system for automated traffic data collection for roundabouts | |
| CN114092902B (en) | Method and device for detecting illegal behavior of electric bicycles | |
| Suttiponpisarn et al. | Detection of wrong direction vehicles on two-way traffic | |
| CN115690716A (en) | Lane change detection method and device, electronic equipment and storage medium | |
| CN115762153A (en) | Reversing detection method and device | |
| CN114202936A (en) | Traffic command robot and control method thereof | |
| CN113711630B (en) | Understanding Road Signs | |
| Zaki et al. | Comprehensive safety diagnosis using automated video analysis: Applications to an urban intersection in Edmonton, Alberta, Canada | |
| CN115063764B (en) | State estimation method and device of traffic signal lamp and electronic equipment |
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: 20220412 |