CN111968378A - Motor vehicle red light running snapshot method and device, computer equipment and storage medium - Google Patents
Motor vehicle red light running snapshot method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111968378A CN111968378A CN202010644124.9A CN202010644124A CN111968378A CN 111968378 A CN111968378 A CN 111968378A CN 202010644124 A CN202010644124 A CN 202010644124A CN 111968378 A CN111968378 A CN 111968378A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- line
- detection frame
- signal lamp
- detection
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a motor vehicle red light running snapshot method, a device, computer equipment and a storage medium, wherein a detection frame of a detection vehicle in video data is obtained, and a motion track of the detection frame is obtained through a target tracking model; acquiring a lane where a vehicle is detected and a rule line of the lane according to preset scene configuration information; the signal lamp state is acquired, the detection vehicle is captured in a snapshot mode according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line, the license plate does not need to be identified, the vehicle is not tracked, the problem that the vehicle is not caught when the red light running snapshot of a unlicensed vehicle or a stained license plate vehicle is carried out is avoided, and the accuracy of the motor vehicle red light running snapshot is better.
Description
Technical Field
The application relates to the technical field of intelligent traffic video monitoring, in particular to a method and a device for capturing a motor vehicle running a red light, computer equipment and a storage medium.
Background
Traffic lights are a way to manage and control and schedule traffic flow at intersections, however, vehicles often run red lights, causing potential safety hazards to pedestrians and other vehicles. Therefore, the traffic video monitoring system needs to shoot the vehicle running the red light, and the evidence is kept for the following fine or education of the vehicle owner running the red light. At present, motor vehicles are captured in three ways mainly by means of a ground induction coil, namely, when a vehicle passes by, the ground induction coil is triggered, and a camera captures and identifies a license plate; video detection snapshot, which is used for detecting and tracking a target and judging the state of a signal lamp according to the detection and identification of the license plate; the video and the ground sense are in linkage snapshot, namely, the video identification mode is relied on for identification, the ground sense trigger mode is used for uploading, and meanwhile, the license plate image needs to be set in an output area.
However, in the related art, the ground induction coil is difficult to set and construct, the failure rate is high, and the misjudgment rate caused by mutual interference of the coils is high; in the video detection, because the license plate is generally arranged at the tail of the vehicle, if the vehicle body is longer, the vehicle is seriously rushed out of the intersection when the license plate is detected, so that the capturing effect is poorer; in addition, the conditions of the stained and shielded license plate of the vehicle can lead to poor detection and identification effects of the license plate, even the license plate can not be detected, and the conditions can cause interference on the tracking of a vehicle target, so that the vehicle identification jumps, and finally the condition of missed grabbing is caused.
Aiming at the problem of low accuracy rate of motor vehicle red light running snapshot in the related technology, no effective solution is provided at present.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for capturing a red light running of a motor vehicle.
According to one aspect of the invention, a motor vehicle red light running snapshot method is provided, which comprises the following steps:
acquiring a detection frame for detecting a vehicle in video data, and acquiring a motion track of the detection frame through a target tracking model;
acquiring a lane where the detected vehicle is located and a rule line of the lane according to preset scene configuration information;
and acquiring the state of a signal lamp, and capturing the detection vehicle according to the state of the signal lamp, the motion track of the detection frame and the relative position of the rule line.
In one embodiment, the capturing the detected vehicle according to the signal lamp state and the relative position of the detection frame of the detected vehicle and the rule line comprises:
obtaining a stop line of a lane where the detected vehicle is located;
and under the condition that the signal lamp state is a red lamp and the head position of the detection frame crosses the stop line, capturing the detection vehicle.
In one embodiment, after the obtaining of the stop line of the lane in which the detected vehicle is located, the method includes:
and under the condition that the signal lamp state is a red lamp and the tail position of the detection frame crosses the stop line, capturing the detection vehicle.
In one embodiment, the capturing the detected vehicle according to the signal lamp state and the relative position of the detection frame of the detected vehicle and the rule line comprises:
determining the running direction of the detected vehicle according to the motion track of the detection frame and the rule line, and acquiring the signal lamp state of the running direction;
and capturing the detected vehicle according to the driving direction and the signal lamp state of the driving direction.
In one embodiment, the capturing the detected vehicle according to the driving direction and the signal lamp state of the driving direction includes:
when the tail position of the vehicle of the detection frame crosses a preset rear line and the signal lamp state in the straight-going direction is a red lamp, capturing the detected vehicle;
and under the condition that the detection frame crosses a turning line and the state of the signal lamp in the turning direction is a red light, capturing the detection vehicle.
In one embodiment, the acquiring a signal lamp state, and capturing the detected vehicle according to the signal lamp state, the motion trajectory of the detection frame, and the relative position of the rule line includes:
acquiring a front line, a middle line and a rear line preset by the lane;
and under the condition that the detection frame crosses the front line, the middle line and the rear line, respectively capturing the detection vehicle.
According to another aspect of the invention, there is also provided a motor vehicle red light running snapshot apparatus, the apparatus comprising an image acquisition device and a processor:
the image acquisition equipment is used for acquiring video data;
the processor is used for acquiring a detection frame of a detected vehicle in the video data through a target detection algorithm and acquiring a motion track of the detection frame through a target tracking model; acquiring a lane where the detected vehicle is located and a rule line of the lane according to preset scene configuration information; and acquiring a signal lamp state, and indicating the image acquisition equipment to snapshot the detection vehicle according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line.
In one embodiment, the processor is further configured to obtain a stop line of a lane in which the detected vehicle is located; and under the condition that the signal lamp state is a red lamp and the head position of the detection frame crosses the stop line, indicating the image acquisition equipment to capture the detection vehicle.
In one embodiment, the processor is further configured to instruct the image capturing device to capture the detected vehicle if the signal lamp status is a red lamp and the tail position of the vehicle of the detection frame crosses the stop line.
In one embodiment, the processor is further configured to determine a driving direction of the detected vehicle according to the motion track of the detection frame and the rule line, and acquire a signal lamp state of the driving direction; and indicating the image acquisition equipment to snapshot the detection vehicle according to the driving direction and the signal lamp state of the driving direction.
According to another aspect of the present invention, there is also provided a computer device, including a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the above-mentioned method for capturing a red light running of a motor vehicle when executing the computer program.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the above-mentioned motor vehicle red light running snapshot method.
According to the motor vehicle red light running snapshot method, the motor vehicle red light running snapshot device, the computer equipment and the storage medium, the motion trail of the detection frame is obtained through the target tracking model by obtaining the detection frame of the detection vehicle in the video data; acquiring a lane where a vehicle is detected and a rule line of the lane according to preset scene configuration information; the signal lamp state is acquired, the detection vehicle is captured in a snapshot mode according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line, the license plate does not need to be identified, the vehicle is not tracked, the problem that the vehicle is not caught when the red light running snapshot of a unlicensed vehicle or a stained license plate vehicle is carried out is avoided, and the accuracy of the motor vehicle red light running snapshot is better.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a diagram illustrating an application scenario of a method for capturing a red light violation of a vehicle according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for capturing a red light violation of a vehicle according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for capturing a red light violation of a vehicle according to another embodiment of the present invention;
FIG. 4 is a flow chart of a method for snapping a motor vehicle running red light according to yet another embodiment of the present invention;
FIG. 5 is a flow chart of a method for snapping a motor vehicle red light running according to another embodiment of the invention;
FIG. 6 is a diagram of scene configuration information in accordance with one embodiment of the present invention;
FIG. 7 is a flow chart of a method for snapping a motor vehicle running red light in accordance with an embodiment of the present invention;
fig. 8 is a schematic view of a motor vehicle red light running snapshot apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
Fig. 1 is a view of an application scenario of a motor vehicle red light running snapshot method according to an embodiment of the present invention, and the motor vehicle red light running snapshot method provided in the present application may be applied to the application environment shown in fig. 1. Wherein the image capture device 102 communicates with the computer device 104 over a network. The computer device 104 acquires a detection frame for detecting the vehicle in the video data acquired by the image acquisition device 102, and acquires a motion track of the detection frame through the target tracking model; acquiring a lane where a detected vehicle is located and a rule line of the lane according to preset scene configuration information; in addition, the computer device 104 acquires the signal lamp state, and captures the detection vehicle according to the signal lamp state, the relative position of the motion track of the detection frame and the rule line. The computer device 104 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and may also be implemented by an independent server or a server cluster formed by a plurality of servers. In some embodiments, the computer device 104 may also be a processor, and the processor is integrated with the image acquisition device 102.
In an embodiment, fig. 2 is a flowchart of a method for capturing a red light running of a motor vehicle according to an embodiment of the present invention, and as shown in fig. 2, a method for capturing a red light running of a motor vehicle is provided, which is exemplified by the application of the method to the computer device 104 in fig. 1, and includes the following steps:
step S210, a detection frame for detecting the vehicle in the video data is obtained, and the motion track of the detection frame is obtained through the target tracking model. And acquiring the acquired intersection video information, and detecting motor vehicle, pedestrian and non-motor vehicle targets in the video frame by a target detection algorithm. Optionally, the target detection algorithm may be a two-stage area-based convolutional neural network (RCNN) and its derived algorithms, such as Fast R-CNN, etc., or may be a single-stage YOLO algorithm, etc. And then screening out the motor vehicle targets from the detection targets, and tracking the detection frame of the motor vehicle. Optionally, the detection frame for a certain vehicle appears for the first time in the video image frame. The detection frame is marked with a unique identifier ID (identifier), and then the detection frame is used as an initial tracking coordinate to track the detected vehicle, so that the motion trail of the detected vehicle corresponding to each ID can be obtained. In some embodiments, a target tracking model is created, the target tracking is regarded as a binary classification problem through a discriminant model, simultaneously, target and background information are extracted to train the target tracking model, and a target is separated from an image sequence background, so that the target position of a current frame is obtained;
step S220, obtaining the lane where the detected vehicle is located and the rule line of the lane according to the preset scene configuration information. At the intersection, the shooting angle of the video capture device is usually fixed, so that in the shot video image, scene configuration information, such as lane lines, driving directions corresponding to lanes, stop lines, and the like, can be configured according to the actual road conditions. Under the condition that a detection frame of a detected vehicle is obtained, the position of the vehicle detection frame is compared with a lane line, so that the lane where the detected vehicle is located can be obtained, and a regular line, such as a stop line and the like, corresponding to the lane is obtained according to scene configuration information;
and step S230, acquiring the state of the signal lamp, and capturing the detected vehicle according to the state of the signal lamp and the relative position of the motion track of the detection frame and the rule line. Through external signal lamp, can acquire real-time signal lamp state, under the condition that the signal lamp state is the red light, detect the relative position of frame and rule line through the comparison, can judge whether need take a candid photograph the vehicle.
In steps S210 to S230, the detection frame for detecting the vehicle is tracked, the position of the detection frame is compared with the position of the rule line in the scene configuration information, and whether the vehicle is captured by running the red light is determined according to the state of the signal lamp. The license plate does not need to be identified in the embodiment, the problem that the license plate is missed in the process of red light running snapshot of a license plate-free vehicle or a stained license plate vehicle is avoided, and the accuracy of red light running snapshot of the motor vehicle is better.
In one embodiment, fig. 3 is a flow chart of a method for snapping a motor vehicle running red light according to another embodiment of the invention, the method comprising the following steps:
step S310, obtaining a stop line of a lane where the vehicle is detected;
and step S320, under the condition that the signal lamp state is red and the head position of the detection frame crosses the stop line, capturing the detected vehicle.
In steps S310 to S320, a stop line of a lane where the detected vehicle is located is obtained according to the preset scene configuration information, and when the traffic light state is a red light, the relative position relationship between the vehicle head position of the detection frame and the stop line is determined. According to the traffic flow direction of the lane, the side, located at the front end of the driving direction, of the detection frame is regarded as the vehicle head position in a default mode, and under the condition that the vehicle head position of the detection frame crosses a stop line, the image acquisition equipment shoots the detection vehicle. The scheme for capturing the behavior that the head of the vehicle rushes out of the stop line under the condition of the red light overcomes the problem that the capturing effect is poor because the license plate is generally arranged at the tail of the vehicle in video detection and the vehicle seriously rushes out of an intersection when the vehicle body is longer and the vehicle is detected, and improves the accuracy and the reliability of the capturing when the motor vehicle rushes out of the red light.
In one embodiment, fig. 4 is a flowchart of a method for capturing a red light violation of a motor vehicle according to yet another embodiment of the present invention, and after acquiring a stop line of a lane where a vehicle is located, as shown in fig. 4, the method further includes:
and step S410, capturing the detected vehicle under the condition that the signal lamp state is red and the tail position of the vehicle of the detection frame crosses the stop line.
According to the traffic flow direction of the lane, the side, located at the rear end in the driving direction, of the detection frame is regarded as the tail position of the vehicle in a default mode, and under the condition that the tail position of the detection frame crosses the stop line, the image acquisition equipment carries out snapshot on the detection vehicle again. The scheme for capturing the behavior that the whole vehicle rushes through a stop line to enter the intersection under the condition of the red light of the vehicle is provided by the embodiment, the scene that the vehicle rushes the red light to capture is increased, the accuracy of the vehicle rushing the red light to capture is improved, the integrity of the red light rushing process is also increased, and the reliability of the captured evidence is improved.
In one embodiment, in the case that the signal lamps at the intersection have different signal lamps for lanes in different driving directions, the capturing the detected vehicle according to the state of the signal lamps and the relative position of the detection frame of the detected vehicle and the rule line comprises: determining the driving direction of the detected vehicle according to the motion track and the rule line of the detection frame, and acquiring the signal lamp state of the driving direction; and capturing the detected vehicle according to the driving direction and the signal lamp state of the driving direction. In this embodiment, first, a driving direction of the vehicle, such as a straight-ahead driving direction, a left-turn driving direction, a right-turn driving direction, or a turning around direction, is acquired according to the motion trajectory of the detection frame and preset scene configuration information. Alternatively, the straight determination assist line, the turning determination assist line, and the like are included in the ruled lines arranged in the scene. For example, the intersection area may be divided into three left, center, and right regions by the auxiliary line, and when the vehicle moves out of the lane and enters the left region of the intersection, it is determined that the vehicle turns left. Then, the traffic light state in the traveling direction is acquired from the traveling direction of the vehicle, for example, the traffic light state in a straight road is acquired for a straight traveling vehicle, the traffic light state in a left-turn road is acquired for a left-turn vehicle, and the vehicle is captured when the traffic light state is red in the traveling direction of the vehicle. The embodiment provides a more detailed motor vehicle snapshot scheme of making a dash across red light, after the vehicle dashes the stop line and gets into the crossing region, still will continue to track the vehicle detection frame to judge the direction of travel of vehicle according to the motion trail that tracks, thereby further judge whether the vehicle makes a dash across red light according to the direction of travel of difference, and take a dash across under the condition of red light. Further improving the accuracy of the motor vehicle snapshot of running the red light.
In one embodiment, fig. 5 is a flowchart of a snapshot method for a motor vehicle running red light according to another embodiment of the present invention, and as shown in fig. 5, the snapshot of the detected vehicle according to the driving direction and the signal light state of the driving direction comprises the following steps:
and step S510, capturing the detected vehicle under the condition that the tail position of the detected vehicle crosses a preset rear line and the signal lamp state in the straight-going direction is a red lamp.
And step S520, under the condition that the detection frame crosses the turning line and the signal lamp state in the turning direction is red, capturing the detected vehicle.
In steps S510 to S520, the rear line and the turning line are included in the ruled lines configured in the scene, fig. 6 is a schematic diagram of scene configuration information according to an embodiment of the present invention, and as shown in fig. 6, the rear line, the left turning line and the right turning line are set in the intersection scene for determining the traveling direction of the vehicle. Optionally, according to the specific structure of the intersection, the rear line can be arranged at the rear part of the straight-going direction of the intersection, when the vehicle crosses the rear line, the vehicle is judged to be in the straight-going state, and when the signal light of the straight-going lane is the red light, the vehicle is captured; respectively arranging a left turning line and a rear turning line on the left side and the right side of the intersection, considering that the detected vehicle turns left under the condition that the center of the vehicle detection frame crosses the left turning line, and executing vehicle snapshot if a left turning light is a red light; and under the condition that the center of the vehicle detection frame crosses the right turning line, the vehicle is considered to turn right, and at the moment, if the right turning light is a red light, vehicle snapshot is executed. This embodiment provides a mode that the setting is used for carrying on the rule line that vehicle direction of travel judged, comes to contrast with the detection frame that detects the vehicle through configuration postposition line, left turn line and right turn line to judge the driving direction of vehicle, improved the accuracy that vehicle direction of travel judged, thereby improved the degree of accuracy of making a dash across the red light snapshot, also further improved the reliability of snapshot result.
In one embodiment, acquiring the state of a signal lamp, and capturing the detection vehicle according to the state of the signal lamp and the relative position of the motion track of the detection frame and the rule line comprises the following steps: acquiring a front line, a middle line and a rear line preset by a lane; and under the condition that the detection frame crosses the front line, the middle line and the rear line, respectively capturing the detected vehicle. In this embodiment, a more concise snapshot manner is further provided, that is, in the scene configuration information, according to the geographical characteristics of the intersection, the front line, the middle line and the rear line are directly calibrated in the image, wherein the front line is used for indicating that the detected vehicle crosses the stop line, and the first snapshot is performed when the tail part of the vehicle of the detection frame of the vehicle exceeds the front line and the signal lamp is red; the middle line is used for indicating that the tail part of the detected vehicle crosses the stop line, and the second snapshot is carried out under the condition that the tail part of the detected frame of the vehicle exceeds the middle line and the signal lamp is red; the rear line is used for indicating and detecting the driving direction of the vehicle, optionally, the rear line in this embodiment includes a straight rear line, a left turning line and a right turning line, and the third snapshot is performed when the tail portion of the vehicle detection frame exceeds the rear line and the signal lamp in the direction is a red lamp. In the embodiment, the rule line for snapshot judgment is directly set in the scene according to the specific conditions of the intersection and the historical experience value, so that the efficiency of snapshot of the motor vehicle running the red light is improved.
In an embodiment, fig. 7 is a flowchart of a method for capturing a red light running of a motor vehicle according to an embodiment of the present invention, and as shown in fig. 7, the method for capturing a red light running of a motor vehicle includes three capturing steps, including:
step S702, a camera captures video data. Video data are collected through a traffic video monitoring camera, the collected video data are subjected to algorithm analysis frame by frame, and meanwhile scene information corresponding to the camera needs to be configured: the lane, the stop line, the front line, the rear line, the middle line, the left turning line and the right turning line; and needs to be externally connected with a signal lamp so as to acquire the real-time signal lamp state
Step S704, target detection and tracking. Detecting the targets of vehicles, pedestrians and non-motor vehicles in each frame of picture by a target detection algorithm; taking a first target coordinate frame appearing in the target as an initial tracking coordinate of the target, giving an ID (identity), and tracking the vehicle target by using the coordinate frame of the target so as to obtain the motion track of each ID target;
step S710, a position of the vehicle is calculated. According to the coordinates of the vehicle detection frame detected by the target, the lane where the vehicle runs can be calculated, so that a stop line of the corresponding lane in the scene configuration is obtained, and the position of the vehicle in the scene is further obtained;
step 712, judging whether the vehicle head crosses the stop line;
step S714, judging whether the signal lamp is red;
in step S716, the first image is captured when the vehicle head crosses the stop line and the signal light is red.
And step S720, calculating the position of the vehicle. According to the coordinates of the vehicle detection frame detected by the target, the lane where the vehicle runs can be calculated, so that a stop line of the corresponding lane in the scene configuration is obtained, and the position of the vehicle in the scene is further obtained;
step S722, judging whether the vehicle tail crosses the stop line;
step S724, judging whether the signal lamp is a red lamp;
in step S726, a second image is captured when the vehicle tail crosses the stop line and the signal light is red.
Step S730, the position of the vehicle is calculated. Obtaining the position of the vehicle in the scene according to the coordinates of the vehicle detection frame detected by the target;
step S732, determining the vehicle running direction according to the vehicle motion track;
step S734, determining whether the signal light in the vehicle driving direction is red;
in step S736, when the driving direction of the vehicle is red, a third image is captured.
The motor vehicle red light running snapshot method adopts a video detection snapshot mode, does not need an operation ground induction coil, and is small in construction amount; the later maintenance cost is low, and the road cannot be damaged; multiple functional, can snapshot a plurality of illegal items: pressing lines, running red light, driving without guiding, giving no gift to pedestrians and the like; according to the scheme, only a vehicle target needs to be tracked, the license plate is not detected, and the tail lamp can be captured, so that the unlicensed vehicle can be captured; in addition, the first snapshot position is obtained when the vehicle head passes over the stop line, so that the problem that the first vehicle with a longer vehicle body rushes out of the intersection is effectively solved.
It should be understood that, although the respective steps in the flowcharts in fig. 2 to 7 are sequentially shown as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, fig. 8 is a schematic diagram of a motor vehicle red light running snapshot apparatus according to one embodiment of the present invention, and as shown in fig. 8, a motor vehicle red light running snapshot apparatus is provided, which includes an image acquisition device 82 and a processor 84: the image acquisition device 82 is used for acquiring video data; the processor 84 is configured to obtain a detection frame of a detected vehicle in the video data through a target detection algorithm, and obtain a motion trajectory of the detection frame through a target tracking model; acquiring a lane where a vehicle is detected and a rule line of the lane according to preset scene configuration information; and acquiring the state of a signal lamp, and indicating image acquisition equipment to snapshot the detected vehicle according to the state of the signal lamp and the relative position of the motion track of the detection frame and the rule line.
In one embodiment, the processor 84 is further configured to obtain a stop line for detecting a lane in which the vehicle is located; and under the condition that the signal lamp state is red and the head position of the detection frame crosses the stop line, indicating the image acquisition equipment 82 to snapshot the detected vehicle.
In one embodiment, processor 84 is further configured to instruct image-capturing device 82 to snap-capture the inspection vehicle if the signal light status is red and the rear-end position of the inspection box crosses the stop line.
In one embodiment, the processor 84 is further configured to determine a driving direction of the detected vehicle according to the movement track of the detection frame and the ruled line, and acquire a signal lamp state of the driving direction; and indicating the image acquisition equipment 82 to shoot the detected vehicle according to the driving direction and the signal lamp state of the driving direction.
For specific limitations of the device for capturing the red light running of the motor vehicle, reference may be made to the above limitations of the method for capturing the red light running of the motor vehicle, and details thereof are not repeated herein. All modules in the motor vehicle red light running snapshot device can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which includes a memory, a processor and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the vehicle red light running snapshot method is implemented.
The motor vehicle red light running snapshot computer equipment acquires the motion trail of a detection frame through a target tracking model by acquiring the detection frame of a detection vehicle in video data; acquiring a lane where a vehicle is detected and a rule line of the lane according to preset scene configuration information; the signal lamp state is acquired, the detection vehicle is captured in a snapshot mode according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line, the license plate does not need to be identified, the vehicle is not tracked, the problem that the vehicle is not caught when the red light running snapshot of a unlicensed vehicle or a stained license plate vehicle is carried out is avoided, and the accuracy of the motor vehicle red light running snapshot is better.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, implements the above-mentioned motor vehicle red light running snapshot method.
The motor vehicle red light running snapshot computer readable storage medium obtains a motion track of a detection frame through a target tracking model by obtaining the detection frame of the detection vehicle in the video data; acquiring a lane where a vehicle is detected and a rule line of the lane according to preset scene configuration information; the signal lamp state is acquired, the detection vehicle is captured in a snapshot mode according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line, the license plate does not need to be identified, the vehicle is not tracked, the problem that the vehicle is not caught when the red light running snapshot of a unlicensed vehicle or a stained license plate vehicle is carried out is avoided, and the accuracy of the motor vehicle red light running snapshot is better.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. A method for capturing a motor vehicle running red light, which is characterized by comprising the following steps:
acquiring a detection frame for detecting a vehicle in video data, and acquiring a motion track of the detection frame through a target tracking model;
acquiring a lane where the detected vehicle is located and a rule line of the lane according to preset scene configuration information;
and acquiring the state of a signal lamp, and capturing the detection vehicle according to the state of the signal lamp, the motion track of the detection frame and the relative position of the rule line.
2. The method of claim 1, wherein the snapping the detected vehicle according to the signal light state and the relative position of the detection frame of the detected vehicle and the rule line comprises:
obtaining a stop line of a lane where the detected vehicle is located;
and under the condition that the signal lamp state is a red lamp and the head position of the detection frame crosses the stop line, capturing the detection vehicle.
3. The method of claim 2, wherein after the obtaining of the stop line of the lane in which the detected vehicle is located, the method comprises:
and under the condition that the signal lamp state is a red lamp and the tail position of the detection frame crosses the stop line, capturing the detection vehicle.
4. The method of claim 1, wherein the snapping the detected vehicle according to the signal light state and the relative position of the detection frame of the detected vehicle and the rule line comprises:
determining the running direction of the detected vehicle according to the motion track of the detection frame and the rule line, and acquiring the signal lamp state of the running direction;
and capturing the detected vehicle according to the driving direction and the signal lamp state of the driving direction.
5. The method of claim 4, wherein the snapping the detected vehicle according to the driving direction and a signal light state of the driving direction comprises:
when the tail position of the vehicle of the detection frame crosses a preset rear line and the signal lamp state in the straight-going direction is a red lamp, capturing the detected vehicle;
and under the condition that the detection frame crosses a turning line and the state of the signal lamp in the turning direction is a red light, capturing the detection vehicle.
6. The method of claim 1, wherein the obtaining of the signal lamp state and the capturing of the detected vehicle according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line comprise:
acquiring a front line, a middle line and a rear line preset by the lane;
and under the condition that the detection frame crosses the front line, the middle line and the rear line, respectively capturing the detection vehicle.
7. The utility model provides a motor vehicle snapshot device that makes a dash across red light which characterized in that, the device includes image acquisition equipment and treater:
the image acquisition equipment is used for acquiring video data;
the processor is used for acquiring a detection frame of a detected vehicle in the video data through a target detection algorithm and acquiring a motion track of the detection frame through a target tracking model; acquiring a lane where the detected vehicle is located and a rule line of the lane according to preset scene configuration information; and acquiring a signal lamp state, and indicating the image acquisition equipment to snapshot the detection vehicle according to the signal lamp state, the motion track of the detection frame and the relative position of the rule line.
8. The apparatus of claim 7, wherein the processor is further configured to obtain a stop line of a lane in which the detected vehicle is located; and under the condition that the signal lamp state is a red lamp and the head position of the detection frame crosses the stop line, indicating the image acquisition equipment to capture the detection vehicle.
9. The apparatus of claim 8, wherein the processor is further configured to instruct the image capture device to snap the inspection vehicle if the signal light status is red and the tail position of the inspection box crosses the stop line.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 6 are implemented when the computer program is executed by the processor.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010644124.9A CN111968378A (en) | 2020-07-07 | 2020-07-07 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010644124.9A CN111968378A (en) | 2020-07-07 | 2020-07-07 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111968378A true CN111968378A (en) | 2020-11-20 |
Family
ID=73360597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010644124.9A Pending CN111968378A (en) | 2020-07-07 | 2020-07-07 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111968378A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446902A (en) * | 2020-11-24 | 2021-03-05 | 浙江大华技术股份有限公司 | Method and device for determining abnormality of target vehicle, storage medium, and electronic device |
| CN112598908A (en) * | 2020-12-09 | 2021-04-02 | 杭州鸿泉物联网技术股份有限公司 | Driver red light running recognition method and device, electronic equipment and storage medium |
| CN112651398A (en) * | 2020-12-28 | 2021-04-13 | 浙江大华技术股份有限公司 | Vehicle snapshot control method and device and computer readable storage medium |
| CN112767710A (en) * | 2021-01-20 | 2021-05-07 | 青岛以萨数据技术有限公司 | Vehicle illegal behavior detection method and device and storage medium |
| CN113329175A (en) * | 2021-05-21 | 2021-08-31 | 浙江大华技术股份有限公司 | Snapshot method, device, electronic device and storage medium |
| CN113420714A (en) * | 2021-07-12 | 2021-09-21 | 浙江大华技术股份有限公司 | Collected image reporting method and device and electronic equipment |
| CN114299414A (en) * | 2021-11-30 | 2022-04-08 | 无锡数据湖信息技术有限公司 | Deep learning-based vehicle red light running identification and determination method |
| CN114898563A (en) * | 2022-07-08 | 2022-08-12 | 之江实验室 | Intersection vehicle violation event detection method, electronic device and storage medium |
| 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 |
Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos |
| CN102903239A (en) * | 2012-09-27 | 2013-01-30 | 安科智慧城市技术（中国）有限公司 | Method and system for detecting illegal left-and-right steering of vehicle at traffic intersection |
| CN103021182A (en) * | 2012-12-10 | 2013-04-03 | 成都林海电子有限责任公司 | Method and device for monitoring motor vehicle in case of regulation violation for running red light |
| CN103065470A (en) * | 2012-12-18 | 2013-04-24 | 浙江工业大学 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
| CN103325258A (en) * | 2013-06-24 | 2013-09-25 | 武汉烽火众智数字技术有限责任公司 | Red light running detecting device and method based on video processing |
| CN103345618A (en) * | 2013-06-21 | 2013-10-09 | 银江股份有限公司 | Traffic violation detection method based on video technology |
| CN103606277A (en) * | 2013-11-18 | 2014-02-26 | 安徽大学 | Intersection temporary traffic signal lamp and red-light running snapshot device |
| CN105023439A (en) * | 2015-07-02 | 2015-11-04 | 湖北贝力思智能科技有限公司 | Intelligent dynamic license plate recognition alarm system |
| CN105389991A (en) * | 2015-12-03 | 2016-03-09 | 杭州中威电子股份有限公司 | Self-adaptive snapshot method for behavior of running red light |
| CN105427615A (en) * | 2015-12-03 | 2016-03-23 | 杭州中威电子股份有限公司 | Robust red-light-running snapshotting system and method under low illumination |
| CN105702045A (en) * | 2016-05-10 | 2016-06-22 | 万金林 | Intelligent detection processing system and method for motor vehicle traffic violation |
| CN105788286A (en) * | 2016-05-19 | 2016-07-20 | 湖南博广信息科技有限公司 | Intelligent red light running identifying system and vehicle behavior detecting and capturing method |
| CN105825680A (en) * | 2016-05-19 | 2016-08-03 | 湖南博广信息科技有限公司 | Intelligent red light running identification system and intelligent red light running identification device |
| CN107293116A (en) * | 2017-06-27 | 2017-10-24 | 浙江浩腾电子科技股份有限公司 | A kind of traffic incident detecting system based on video analysis |
| CN108269403A (en) * | 2016-12-30 | 2018-07-10 | 上海泓鎏智能科技有限公司 | Detect the grasp shoot device and grasp shoot method of break in traffic rules and regulations |
| CN108847032A (en) * | 2018-08-21 | 2018-11-20 | 北京深瞐科技有限公司 | A kind of traffic violation recognition methods and device |
| CN109035790A (en) * | 2018-07-27 | 2018-12-18 | 苏州科达科技股份有限公司 | The evidence acquisition methods and system of vehicular traffic violation |
| CN109615868A (en) * | 2018-12-20 | 2019-04-12 | 北京以萨技术股份有限公司 | A kind of video frequency vehicle based on deep learning is separated to stop detection method |
| CN109949579A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning |
| CN109949578A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method of vehicle crimping based on deep learning |
| CN110009913A (en) * | 2019-03-27 | 2019-07-12 | 江苏智通交通科技有限公司 | A kind of non-at-scene law enforcement picture intelligent checks method and system of vehicles running red light |
| CN110459064A (en) * | 2019-09-19 | 2019-11-15 | 上海眼控科技股份有限公司 | Vehicle illegal behavioral value method, apparatus, computer equipment |
| CN110619747A (en) * | 2019-09-27 | 2019-12-27 | 山东奥邦交通设施工程有限公司 | Intelligent monitoring method and system for highway road |
| WO2020051680A1 (en) * | 2018-09-11 | 2020-03-19 | Avigilon Corporation | Bounding box doubling as redaction boundary |
| CN111091023A (en) * | 2018-10-23 | 2020-05-01 | 中国移动通信有限公司研究院 | Vehicle detection method and device and electronic equipment |
| CN111179345A (en) * | 2019-12-27 | 2020-05-19 | 大连海事大学 | Method and system for automatically detecting violation behaviors of crossing lines of front vehicle based on vehicle-mounted machine vision |
| CN111199647A (en) * | 2018-11-16 | 2020-05-26 | 中电科新型智慧城市研究院有限公司 | Monitoring video detection method for continuous lane changing and illegal turning of road vehicles |
| WO2020122301A1 (en) * | 2018-12-13 | 2020-06-18 | 유니셈(주) | Deep learning based traffic violation enforcement system and method |
| 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 |
-
2020
- 2020-07-07 CN CN202010644124.9A patent/CN111968378A/en active Pending
Patent Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos |
| CN102903239A (en) * | 2012-09-27 | 2013-01-30 | 安科智慧城市技术（中国）有限公司 | Method and system for detecting illegal left-and-right steering of vehicle at traffic intersection |
| CN103021182A (en) * | 2012-12-10 | 2013-04-03 | 成都林海电子有限责任公司 | Method and device for monitoring motor vehicle in case of regulation violation for running red light |
| CN103065470A (en) * | 2012-12-18 | 2013-04-24 | 浙江工业大学 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
| CN103345618A (en) * | 2013-06-21 | 2013-10-09 | 银江股份有限公司 | Traffic violation detection method based on video technology |
| CN103325258A (en) * | 2013-06-24 | 2013-09-25 | 武汉烽火众智数字技术有限责任公司 | Red light running detecting device and method based on video processing |
| CN103606277A (en) * | 2013-11-18 | 2014-02-26 | 安徽大学 | Intersection temporary traffic signal lamp and red-light running snapshot device |
| CN105023439A (en) * | 2015-07-02 | 2015-11-04 | 湖北贝力思智能科技有限公司 | Intelligent dynamic license plate recognition alarm system |
| CN105389991A (en) * | 2015-12-03 | 2016-03-09 | 杭州中威电子股份有限公司 | Self-adaptive snapshot method for behavior of running red light |
| CN105427615A (en) * | 2015-12-03 | 2016-03-23 | 杭州中威电子股份有限公司 | Robust red-light-running snapshotting system and method under low illumination |
| CN105702045A (en) * | 2016-05-10 | 2016-06-22 | 万金林 | Intelligent detection processing system and method for motor vehicle traffic violation |
| CN105788286A (en) * | 2016-05-19 | 2016-07-20 | 湖南博广信息科技有限公司 | Intelligent red light running identifying system and vehicle behavior detecting and capturing method |
| CN105825680A (en) * | 2016-05-19 | 2016-08-03 | 湖南博广信息科技有限公司 | Intelligent red light running identification system and intelligent red light running identification device |
| CN108269403A (en) * | 2016-12-30 | 2018-07-10 | 上海泓鎏智能科技有限公司 | Detect the grasp shoot device and grasp shoot method of break in traffic rules and regulations |
| CN107293116A (en) * | 2017-06-27 | 2017-10-24 | 浙江浩腾电子科技股份有限公司 | A kind of traffic incident detecting system based on video analysis |
| CN109035790A (en) * | 2018-07-27 | 2018-12-18 | 苏州科达科技股份有限公司 | The evidence acquisition methods and system of vehicular traffic violation |
| CN108847032A (en) * | 2018-08-21 | 2018-11-20 | 北京深瞐科技有限公司 | A kind of traffic violation recognition methods and device |
| WO2020051680A1 (en) * | 2018-09-11 | 2020-03-19 | Avigilon Corporation | Bounding box doubling as redaction boundary |
| CN111091023A (en) * | 2018-10-23 | 2020-05-01 | 中国移动通信有限公司研究院 | Vehicle detection method and device and electronic equipment |
| CN111199647A (en) * | 2018-11-16 | 2020-05-26 | 中电科新型智慧城市研究院有限公司 | Monitoring video detection method for continuous lane changing and illegal turning of road vehicles |
| WO2020122301A1 (en) * | 2018-12-13 | 2020-06-18 | 유니셈(주) | Deep learning based traffic violation enforcement system and method |
| CN109615868A (en) * | 2018-12-20 | 2019-04-12 | 北京以萨技术股份有限公司 | A kind of video frequency vehicle based on deep learning is separated to stop detection method |
| CN109949578A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method of vehicle crimping based on deep learning |
| CN109949579A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning |
| CN110009913A (en) * | 2019-03-27 | 2019-07-12 | 江苏智通交通科技有限公司 | A kind of non-at-scene law enforcement picture intelligent checks method and system of vehicles running red light |
| CN110459064A (en) * | 2019-09-19 | 2019-11-15 | 上海眼控科技股份有限公司 | Vehicle illegal behavioral value method, apparatus, computer equipment |
| CN110619747A (en) * | 2019-09-27 | 2019-12-27 | 山东奥邦交通设施工程有限公司 | Intelligent monitoring method and system for highway road |
| CN111179345A (en) * | 2019-12-27 | 2020-05-19 | 大连海事大学 | Method and system for automatically detecting violation behaviors of crossing lines of front vehicle based on vehicle-mounted machine vision |
| 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 |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446902A (en) * | 2020-11-24 | 2021-03-05 | 浙江大华技术股份有限公司 | Method and device for determining abnormality of target vehicle, storage medium, and electronic device |
| CN112598908B (en) * | 2020-12-09 | 2022-03-15 | 杭州鸿泉物联网技术股份有限公司 | Driver red light running recognition method and device, electronic equipment and storage medium |
| CN112598908A (en) * | 2020-12-09 | 2021-04-02 | 杭州鸿泉物联网技术股份有限公司 | Driver red light running recognition method and device, electronic equipment and storage medium |
| CN112651398A (en) * | 2020-12-28 | 2021-04-13 | 浙江大华技术股份有限公司 | Vehicle snapshot control method and device and computer readable storage medium |
| CN112651398B (en) * | 2020-12-28 | 2024-02-13 | 浙江大华技术股份有限公司 | Snapshot control method and device for vehicle and computer readable storage medium |
| CN112767710A (en) * | 2021-01-20 | 2021-05-07 | 青岛以萨数据技术有限公司 | Vehicle illegal behavior detection method and device and storage medium |
| CN113329175A (en) * | 2021-05-21 | 2021-08-31 | 浙江大华技术股份有限公司 | Snapshot method, device, electronic device and storage medium |
| CN113420714A (en) * | 2021-07-12 | 2021-09-21 | 浙江大华技术股份有限公司 | Collected image reporting method and device and electronic equipment |
| CN113420714B (en) * | 2021-07-12 | 2023-08-22 | 浙江大华技术股份有限公司 | Method and device for reporting acquired image and electronic equipment |
| CN114299414A (en) * | 2021-11-30 | 2022-04-08 | 无锡数据湖信息技术有限公司 | Deep learning-based vehicle red light running identification and determination method |
| CN114299414B (en) * | 2021-11-30 | 2023-09-15 | 无锡数据湖信息技术有限公司 | Vehicle red light running recognition and judgment method based on deep learning |
| CN114898563A (en) * | 2022-07-08 | 2022-08-12 | 之江实验室 | Intersection vehicle violation event detection method, electronic device and storage medium |
| 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 |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111968378A (en) | Motor vehicle red light running snapshot method and device, computer equipment and storage medium | |
| CN110688992B (en) | Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle | |
| US20200097756A1 (en) | Object detection device and object detection method | |
| WO2018153211A1 (en) | Method and apparatus for obtaining traffic condition information, and computer storage medium | |
| US11308717B2 (en) | Object detection device and object detection method | |
| US20190122059A1 (en) | Signal light detection | |
| CN113492851B (en) | Vehicle control device, vehicle control method, and computer program for vehicle control | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN111891061B (en) | Vehicle collision detection method and device and computer equipment | |
| WO2023201904A1 (en) | Abnormal vehicle traveling detection method, and electronic device and storage medium | |
| CN105825495A (en) | Object detection apparatus and object detection method | |
| JP7115502B2 (en) | Object state identification device, object state identification method, computer program for object state identification, and control device | |
| CN113496201A (en) | Object state recognition device, object state recognition method, object state recognition computer program, and control device | |
| CN111583660B (en) | Vehicle steering behavior detection method, device, equipment and storage medium | |
| CN112364742A (en) | Parking space management method and device, computer equipment and storage medium | |
| JP7226368B2 (en) | Object state identification device | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| CN114627409A (en) | Method and device for detecting abnormal lane change of vehicle | |
| CN113420714A (en) | Collected image reporting method and device and electronic equipment | |
| CN113468911B (en) | Vehicle-mounted red light running detection method and device, electronic equipment and storage medium | |
| CN116152753A (en) | Vehicle information identification method and system, storage medium and electronic device | |
| CN105761501A (en) | Intelligent vehicle behavior detecting and snapshotting method | |
| CN107255470B (en) | Obstacle detection device | |
| CN112289040B (en) | Method and device for identifying vehicle driving direction and storage medium | |
| CN114333339B (en) | Deep neural network functional module de-duplication method |
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 |
Application publication date: 20201120 |
|
| RJ01 | Rejection of invention patent application after publication |