WO2022247931A1 - Method and system for identifying illegal traffic participant, and computer-readable storage medium - Google Patents

Method and system for identifying illegal traffic participant, and computer-readable storage medium Download PDF

Info

Publication number
WO2022247931A1
WO2022247931A1 PCT/CN2022/095590 CN2022095590W WO2022247931A1 WO 2022247931 A1 WO2022247931 A1 WO 2022247931A1 CN 2022095590 W CN2022095590 W CN 2022095590W WO 2022247931 A1 WO2022247931 A1 WO 2022247931A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
traffic
target
sensing device
sensing
Prior art date
Application number
PCT/CN2022/095590
Other languages
French (fr)
Chinese (zh)
Inventor
房颜明
李智
孟令钊
董航
时兵兵
Original Assignee
北京万集科技股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from CN202110586458.XA external-priority patent/CN113470371B/en
Priority claimed from CN202110587444.XA external-priority patent/CN113362592A/en
Application filed by 北京万集科技股份有限公司 filed Critical 北京万集科技股份有限公司
Publication of WO2022247931A1 publication Critical patent/WO2022247931A1/en

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/017Detecting movement of traffic to be counted or controlled identifying vehicles

Definitions

  • the present disclosure relates generally to the field of intelligent traffic management. More specifically, the present disclosure relates to a method, system and computer-readable storage medium for identifying traffic violation objects.
  • the current intelligent traffic management involves the automatic identification of traffic objects such as people, vehicles and roads, and the automatic detection of illegal behaviors. Through automatic identification and detection, key traffic management objectives can be intelligently analyzed, thereby improving traffic efficiency and optimizing traffic order.
  • places such as tunnels, service areas where vehicles are parked, etc.
  • detection or notification scheme for various violations of vehicles driving in the tunnel and in the service area. Therefore, how to accurately judge and timely notify the vehicle violations in the above-mentioned similar places has become a problem to be solved by the current vehicle management.
  • this disclosure proposes a solution for identifying violating vehicles in scenarios such as tunnels.
  • vehicles violating tunnel driving regulations can be effectively determined, thereby helping to improve efficient and safe passage in tunnels, and expanding the application scenarios of intelligent traffic management.
  • the present disclosure provides solutions in the following aspects.
  • the present disclosure provides a method for identifying violating vehicles, including: acquiring the sensing information of a first sensing device at the entrance of a tunnel; taking a snapshot of the target vehicle based on the sensing information of the first sensing device to obtain the The identity information of the target vehicle, wherein the target vehicle is a vehicle entering the tunnel; the object characteristic information of the target vehicle is acquired according to the sensing information of the first sensing device; the identity information of the target vehicle and The corresponding object feature information is bound to obtain the binding information of the target vehicle, and the binding information of the target vehicle is recorded in the vehicle search set; the sensing information of the second sensing device in the tunnel is obtained; according to the The speed information in the sensing information of the second sensing device identifies the violating vehicle, so as to obtain the object characteristic information of the violating vehicle; obtain the target binding from the binding information of the vehicle search set according to the object characteristic information of the violating vehicle obtain the identity information of the violating vehicle based on the target binding information; and output the identity information of the
  • the capture position of the target vehicle includes a remote capture position and a near-end capture position
  • the target vehicle is captured based on the sensing information of the first sensing device, so as to obtain the target vehicle's
  • the identity information includes: selecting, based on the sensing information of the first sensing device, to capture the target vehicle at the far-end capture position or the near-end capture position, so as to obtain the identity information of the target vehicle.
  • selecting to capture the target vehicle at the far-end capture position or the near-end capture position based on the sensing information of the first sensing device includes: acquiring based on the sensing information of the first sensing device First distance and size information of a vehicle located in front of the target vehicle in the capture direction, wherein the first distance includes a distance between the front of the target vehicle and the rear of the vehicle in front thereof; and according to the first The distance and size information is compared with a preset threshold to select to capture the target vehicle at the far-end capture position or the near-end capture position.
  • selecting to capture the target vehicle at the far-end capture position or the near-end capture position according to the comparison between the first distance and size information and a preset threshold includes: responding to the first distance being less than The first preset threshold and the height of the vehicle in front is greater than the second preset threshold, select the near-end capture position to capture the target vehicle; in response to the first distance being greater than the first preset threshold, select the target vehicle The remote capture position is used to capture the target vehicle; or in response to the first distance being less than a first preset threshold and the height of the vehicle in front is less than a second preset threshold, selecting the remote capture position for the target vehicle Capture the target vehicle.
  • capturing the target vehicle based on the sensing information of the first sensing device, so as to obtain the identity information of the target vehicle further includes: a capture and identification frame for capturing and identifying the target vehicle; and using the capture and identification frame to capture and identify the target vehicle at the capture position, so as to obtain identity information of the target vehicle.
  • determining the capture identification frame according to the perception information and the capture position includes: acquiring a second distance between vehicles located in front of the target vehicle in the capture direction according to the perception information, wherein the The second distance includes a distance between the front of the target vehicle and the front of the vehicle in front thereof; and the snapshot recognition frame is determined based on the snapshot position and the second distance.
  • identifying the violating vehicle according to the speed information in the sensing information of the second sensing device includes: in response to the speed information of the target vehicle indicating that the speed is equal to zero, identifying the target vehicle as a violating vehicle with a stagnation behavior in violation vehicle; or in response to the speed information of the target vehicle indicating that the speed is lower than the minimum speed limit, identifying the target vehicle as a violating vehicle with illegal slow-moving behavior; or in response to the speed information of the target vehicle indicating that the speed is higher than the maximum speed limit, The target vehicle is identified as a violating vehicle with speeding violations.
  • the sensing information of the second sensing device further includes the location information of the violating vehicle, wherein outputting the identity information of the violating vehicle and the corresponding violation behavior includes: Violation information associated with one of the violation behavior, slow-moving behavior or speed violation behavior; and broadcast the violation information to the violation vehicle according to the location information of the violation vehicle.
  • the present disclosure provides a system for identifying violating vehicles, including: a first sensing device arranged at the entrance of a tunnel for acquiring sensing information at the entrance of the tunnel; a capture device arranged at the entrance of the tunnel At the entrance of the tunnel, it is used to capture the target vehicle based on the sensing information of the first sensing device, so as to obtain the identity information of the target vehicle, wherein the target vehicle is a vehicle entering the tunnel; the second sensing device , which is arranged in the tunnel, and is used to obtain the sensing information in the tunnel; and an information processing center, which communicates with the first sensing device, the capture device, and the second sensing device, and It is configured to: acquire the sensing information of the first sensing device at the entrance of the tunnel; acquire the object characteristic information of the target vehicle according to the sensing information of the first sensing device; combine the identity information of the target vehicle with the corresponding object characteristic information Perform binding to obtain the binding information of the target vehicle, and record the binding information of the target vehicle in the vehicle
  • the first sensing device includes a lidar and/or a camera.
  • the second sensing device includes a lidar and/or a camera.
  • the capture device includes a bayonet camera.
  • the present disclosure provides a computer-readable storage medium, on which computer-readable instructions for identifying violating vehicles are stored.
  • the computer-readable instructions are executed by one or more processors, the first aspect is implemented. and the methods described in its various embodiments.
  • the present disclosure can accurately identify and store the information of the vehicle entering the tunnel by utilizing the perception information and the capture operation. Further, by sensing the vehicle again in the tunnel, the solution of the present disclosure can accurately identify the vehicle that violates the driving regulations in the tunnel. Therefore, the solution disclosed in the present disclosure promotes effective management and monitoring of vehicles traveling in the tunnel, and effectively discovers and promptly handles violators.
  • this disclosure proposes a scheme for identifying violating traffic participants.
  • traffic participants violating regulations can be effectively determined in some scenarios, thereby helping to realize efficient intelligent traffic management.
  • the present disclosure provides solutions in the following aspects.
  • the present disclosure provides a method for identifying illegal traffic participation objects, including: acquiring the perception information of a first sensing device at the entrance of a scene; capturing a target traffic participation object based on the perception information of the first sensing device , to obtain the identity information of the target traffic participation object, wherein the target traffic participation object is a traffic participation object entering the scene; obtain the object characteristics of the target traffic participation object according to the perception information of the first sensing device information; bind the identity information of the target traffic participation object with the corresponding object feature information to obtain the binding information of the target traffic participation object, and record the binding information of the target traffic participation object in the traffic participation object Searching in the collection; obtaining the sensing information of the second sensing device in the scene; identifying the illegal traffic participating object according to the sensing information of the second sensing device, so as to obtain the object characteristic information of the illegal traffic participating object; according to the illegal The object feature information of the traffic participation object obtains target binding information from the binding information of the traffic participation object search set; obtains the identity information of
  • the scene includes a service area scene
  • the illegal traffic participation object is a traffic participation object that violates service area regulations.
  • the snapping position includes a far-end snapping position and a near-end snapping position
  • the target traffic participating object is captured based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object
  • the method includes: selecting, based on the sensing information of the first sensing device, to capture the target traffic participant object at the far-end capture position or the near-end capture position, so as to obtain the identity information of the target traffic participant object.
  • selecting to capture the target traffic participant object at the far-end capture position or the near-end capture position based on the perception information of the first sensing device includes: based on the perception of the first sensing device Information acquisition of the first distance and size information of the traffic participation object located in front of the target traffic participation object in the capture direction, wherein the first distance includes the distance between the front part of the target traffic participation object and the tail of the traffic participation object in front distance between them; and choose to capture the target traffic participating object at the far-end capture position or the near-end capture position according to the comparison between the first distance and size information and a preset threshold.
  • selecting to capture the target traffic participating object at the far-end capture position or the near-end capture position according to the comparison between the first distance and size information and a preset threshold includes: responding to the first If the distance is less than a first preset threshold and the height of the preceding traffic participating object is greater than a second preset threshold, the near-end capture position is selected to capture the target traffic participating object; in response to the first distance being greater than the first A preset threshold, selecting the remote capture position to capture the target traffic participating object; or in response to the first distance being less than a first preset threshold and the height of the preceding traffic participating object being less than a second preset threshold , selecting the remote capture position to capture the target traffic participant.
  • capturing the target traffic participating object based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object further includes: determining according to the sensing information and the captured position A capture recognition frame for capturing and identifying the target traffic participation object; and using the capture recognition frame to capture and identify the target traffic participation object at the capture position, so as to obtain the target traffic participation The identity information of the object.
  • determining the capture recognition frame according to the perception information and the capture position includes: obtaining the second position of the traffic participation object located in front of the target traffic participation object in the capture direction according to the perception information. distance, wherein the second distance includes the distance between the front part of the target traffic participating object and the front part of the traffic participating object in front thereof; the snapping identification frame is determined based on the snapping position and the second distance.
  • identifying the violating traffic participating object according to the sensing information of the second sensing device includes: acquiring object feature information and position of the target traffic participating object in the scene according to the sensing information of the second sensing device information and speed information, wherein the object feature information includes at least category information; and in response to the speed information indicating that the speed of the target traffic participating object is zero and the category information of the target traffic participating object is consistent with the The category information of the preset area does not match, identifying the target traffic participating object as an illegal traffic participating object; or in response to the speed information indicating that the speed of the target traffic participating object is zero and the position of the target traffic participating object The information does not match the position of the preset area in the scene, and the target traffic participating object is identified as an illegal traffic participating object.
  • outputting the identity information of the violation traffic participation object and the corresponding violation behavior includes: generating violation information associated with category information mismatch or location mismatch for the violation traffic participation object; The location information of the violation traffic participation object is used to broadcast the violation information to the violation traffic participation object in a directional manner.
  • the present disclosure provides a system for identifying illegal traffic participants, including: a first sensing device, arranged at the entrance of a scene, for acquiring sensing information at the entrance of the scene; a capture device, arranged At the entrance of the scene, it is used to capture the target traffic participating object based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object, wherein the target traffic participating object enters the The traffic participating objects of the scene; the second sensing device, which is arranged in the scene, and is used to obtain the sensing information in the scene; and an information processing center, which cooperates with the first sensing device, the capture device, and the The second sensing device is connected in communication, and is configured to: respectively obtain corresponding sensing information from the first sensing device and the second sensing device; obtain the target traffic participation object according to the sensing information of the first sensing device The object feature information of the target traffic participation object; bind the identity information of the target traffic participation object with the corresponding object feature information to obtain
  • the first sensing device and the second sensing device include a lidar and/or a camera.
  • the second sensing device includes a lidar and/or a camera.
  • the capture device includes a bayonet camera.
  • the present disclosure provides a computer-readable storage medium, on which are stored computer-readable instructions for identifying objects involved in traffic violations.
  • the computer-readable instructions are executed by one or more processors, the The method described in one aspect and various embodiments thereof.
  • the present disclosure can accurately identify and store information of traffic participants entering a scene by using perception information and snapping operations. Further, by re-perceiving the traffic participants in the scene, the solution of the present disclosure can accurately identify the traffic participants who violate the regulations in the scene. Therefore, the solution disclosed in the present disclosure promotes the effective management of traffic participants in the scene and effectively discovers and promptly handles violators.
  • FIG. 1 is an exemplary scene diagram schematically showing a scheme in which the present disclosure is applied for identifying an object involved in traffic violations;
  • Fig. 2 is another exemplary scene diagram schematically showing the scheme for identifying illegal traffic participating objects in which the present disclosure is applied;
  • FIG. 3 is a flowchart schematically showing a method for identifying illegal traffic participants according to an embodiment of the present disclosure
  • FIG. 4 is another flow chart schematically showing a method for identifying illegal traffic participating objects according to an embodiment of the present disclosure
  • Fig. 5 is a diagram schematically illustrating a capture operation according to an embodiment of the present disclosure
  • Fig. 6 is a schematic block diagram schematically showing an object used for identifying traffic violations according to an embodiment of the present disclosure.
  • FIG. 1 is a diagram schematically illustrating an exemplary scenario 100 in which the scheme of the present disclosure for identifying violating traffic participation objects is applied.
  • the aforementioned scenarios may include various environments for parking traffic participating objects, such as various service areas on expressways, various parking lots (such as commercial or civilian), various traffic tunnels or bridges Culverts, etc. Based on this, it can be understood that the exemplary scenario shown in FIG. 1 is a tunnel scenario.
  • the aforementioned traffic participation objects may be objects related to road activities/traffic activities, such as motor vehicles and/or non-motor vehicles.
  • a first sensing device 101 may be provided at the entrance of the tunnel, which is configured to collect sensing information within its sensing coverage range.
  • the aforementioned sensing coverage may cover an area within a certain distance around the tunnel entrance, so that vehicles entering and/or not entering the tunnel can be sensed.
  • the first sensing device may include a laser radar (shown as a dot in FIG. 1 ) and/or a camera. In the application scenario where the lidar and the camera are used together, the lidar and the camera can be used to obtain point cloud data and video data at the same time and in the same scene.
  • the aforementioned initial fusion results may, for example, include various types of information about the vehicle (such as vehicles 102 and 103 shown in FIG. 1 ), including but not limited to one or more of the following: Vehicle identity (ID) information, vehicle category information, vehicle location information, vehicle lane information, vehicle perception time information, vehicle size information, vehicle speed information, and the distance between the front and rear vehicles (as shown at 501 in Figure 5) , the distance between the front and the rear of the vehicle (as shown at 502 in FIG. 5 ) and/or vehicle image feature information.
  • ID Vehicle identity
  • a capture device 104 is provided within a certain distance behind the first sensing device and in front of the tunnel entrance, which is used to The sensing information of the sensing device 101 is used to capture the vehicle that is about to enter the tunnel, so as to obtain the identity information of the target vehicle (such as the license plate number of the vehicle).
  • the vehicle entering the tunnel is the target vehicle, and the solution of the present disclosure aims to monitor such one or more target vehicles, so as to determine the violating vehicle that violates the driving regulations in the tunnel.
  • the capture device of the present disclosure may be various types of cameras. As a preferred solution, the camera may be a bayonet camera.
  • the information processing center here can be implemented as a computing unit or module, and is used to perform information processing (including fusion operations of various data) and optionally perform main control operations on various interconnected devices .
  • the information processing center may acquire object feature information of the target vehicle, such as feature information of a vehicle entering a tunnel, according to the sensing information of the first sensing device. Further, the information processing center can bind the identity information of the target vehicle with the corresponding object feature information to obtain the binding information of the target vehicle, and record the binding information of the target vehicle in the vehicle search set.
  • the binding operation performed by the information processing center may be to combine the license plate number with the specific characteristics of the motor vehicle (such as the model, color or category of the vehicle) binding, and record such binding information (similar to the mapping correspondence) in the vehicle lookup set, for example, in a dedicated database.
  • the solution of the present disclosure establishes an effective way for vehicles entering the tunnel to conduct inquiries.
  • the solution of the present disclosure proposes to set the second sensing device 107 in the tunnel to realize the detection Sensing data collection of tunnels, which may include information about violating vehicles, such as speed information.
  • violations may include violations of driving regulations set for a tunnel.
  • a violation of tunnel regulations may involve the act of driving in a tunnel at an inappropriate driving speed.
  • the second sensing device and the first sensing device of the present disclosure have the same processing capability, so the foregoing technical descriptions about the first sensing device are also applicable to the second sensing device. Sensing device.
  • the second sensing device can also transmit the sensing information to the information processing center, so that it can obtain the object characteristic information of the violating vehicle, and obtain it from the binding information of the aforementioned vehicle search set according to the object characteristic information of the violating vehicle Target binding information. Then, the information processing center can obtain the identity information of the violating vehicle based on the target binding information. After determining the identity information of the violating vehicle, the information processing center can output the identity information of the violating vehicle and the corresponding violation behavior. According to different implementation manners, the output mode may be video display.
  • a plurality of large display screens can be arranged in different sections of the tunnel (for example, hung on the inner wall of the tunnel), so that the information processing center can select the violating vehicle to pass by.
  • a large display screen for display broadcast can be arranged in different sections of the tunnel (for example, hung on the inner wall of the tunnel), so that the information processing center can select the violating vehicle to pass by.
  • FIG. 2 is a diagram schematically illustrating yet another exemplary scenario 200 in which the scheme for identifying traffic violation participants of the present disclosure is applied. It can be understood that the exemplary scenario shown in FIG. 2 is a service area scenario. Further, in the context of the present disclosure, the aforementioned traffic participation objects may be objects related to road activities/traffic activities, such as motor vehicles and/or non-motor vehicles.
  • a first sensing device 101 may be set at the entrance of the service area, which is configured to collect sensing information within its service coverage.
  • the first sensing device may include a laser radar (shown by a dot in FIG. 2 ) and/or a camera.
  • the lidar and the camera can be used to obtain point cloud data and video data at the same time and in the same scene.
  • target detection is performed on point cloud data and video data respectively, and the detection results are fused, the initial fusion result can be obtained.
  • the aforementioned initial fusion result may, for example, include various types of information about the vehicle (such as vehicles 102 and 103 shown in FIG. 2 ), including but not limited to one of the following One or more items: the identity (ID) information of the vehicle in the sensing area, the vehicle category information, the vehicle position information, the vehicle lane information, the vehicle perception time information, the vehicle size information, the vehicle speed information, the distance between the front vehicle (such as 501 in FIG. 5 ), the distance between the front and the rear of the vehicle (as shown at 502 in FIG. 5 ), and/or vehicle image feature information.
  • a capture device 104 is set within a certain distance behind the first sensing device, which is used to 101 perception information to capture the traffic participating objects entering the service area, so as to obtain the identity information of the target traffic participating objects (such as the license plate number of the vehicle).
  • the traffic participating objects entering the service area are also the target traffic participating objects, and the scheme of the present disclosure aims to monitor such one or more target traffic participating objects, so as to determine violations of service area regulations Objects involved in traffic violations.
  • the capture device of the present disclosure may be various types of cameras. As a preferred solution, the camera may be a bayonet camera.
  • the first sensing device and the capture device respectively acquire information about the traffic participating object or the target traffic participating object, they can transmit the acquired information to the information processing center 105 of the present disclosure.
  • the information processing center of the present disclosure may acquire object feature information of the target traffic participating object, such as feature information of vehicles entering the service area, according to the sensing information of the first sensing device. Further, the information processing center can bind the identity information of the target traffic participation object with the corresponding object feature information to obtain the binding information of the target traffic participation object, and record the binding information of the target traffic participation object in the traffic participation object Find in the collection.
  • the binding operation performed by the information processing center can be to combine the license plate number with the specific characteristics of the motor vehicle (such as the vehicle model, color or category), and record such binding information (similar to the mapping correspondence) in the traffic participation object lookup set, for example, stored in a dedicated database.
  • the solution of the present disclosure establishes an effective way for the traffic participating objects (such as the vehicle in this example) entering the scene (such as the service area in this example) to conduct inquiries.
  • the second sensing device 107 is set in the service area of the entrance to realize the collection of sensing data in the service area, and the sensing data may include information about illegal traffic participants.
  • a violation may include behavior that violates the norms set for the scene.
  • violations of service area regulations may involve wrong stops.
  • the second sensing device and the first sensing device of the present disclosure have the same processing capability, so the above technical description about the first sensing device is also applicable on the second sensing device.
  • the second sensing device can also transmit the sensing information to the information processing center, so that it can obtain the object feature information of the violating traffic participating object, and search the set from the aforementioned traffic participating object according to the object feature information of the violating traffic participating object
  • the target binding information is obtained from the binding information of the .
  • the information processing center can obtain the identity information of the object involved in the illegal traffic based on the target binding information.
  • the information processing center can output the identity information of the violating traffic participant and the corresponding violation behavior.
  • the input method may be voice announcement or video display, or a combination of both.
  • multiple large display screens can be arranged in the service area, so that the information processing center can select a large display screen closest to the violating traffic participant to display and broadcast.
  • the information processing center is shown in the figure as being separated from the first sensing device, the second sensing device and the capture device, in some scenarios, the information processing center may also be selected to be arranged close to one of the three, Thereby reducing the distance of data transmission and improving the stability of data transmission. Further, the information processing center can also be arranged at the remote end (such as the cloud). In this case, the identity information of the violating traffic participant and the violation information determined at the remote end can be sent to the broadcasting device in the scene, so as to promptly remind the violator (such as the car owner) to pay attention to and correct the violation.
  • Fig. 3 is a flow chart schematically showing a method 300 for identifying traffic violation participants according to an embodiment of the present disclosure. It can be understood that the method flow shown in FIG. 3 can be implemented in the exemplary tunnel scenario shown in FIG. 1 , so the content described in FIG. 1 (for example, about the sensing device) is also applicable to FIG. 3 .
  • the sensing information of a first sensing device (such as the first sensing device 101 in FIG. 1 ) at a tunnel entrance is acquired.
  • the sensing information may include point cloud data and video data within the sensing range.
  • the target vehicle is captured based on the sensing information of the first sensing device, so as to obtain the identity information of the target vehicle.
  • the snapping action can be performed, for example, by the snapping device 104 shown in FIG. 1 .
  • this disclosure proposes to set the remote capture position and the near-end capture position, so that the target vehicle can be selected at the far-end capture position or the near-end capture position based on the perception information of the first sensing device. Take a snapshot. The specific capture operation will be described in detail later with reference to FIG. 5 .
  • the object feature information of the target vehicle can be obtained according to the sensing information of the first sensing device.
  • the object feature information may include, for example, ID, category, location, lane, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information about the vehicle in the tunnel.
  • the process proceeds to step S304, where the identity information of the target vehicle is bound with the corresponding object feature information to obtain the binding information of the target vehicle, and at step S305, the binding information of the target vehicle is recorded in the vehicle Lookup in a collection (such as a database).
  • the sensing information of the second sensing device in the tunnel may be acquired.
  • the second sensing device is, for example, the second sensing device 107 shown in FIG. 1 .
  • the second sensing device performs sensing operation on the target vehicle in the tunnel, so as to obtain the sensing information of the target vehicle in the tunnel.
  • the violating vehicle may be identified according to the speed information in the sensing information of the second sensing device, so as to obtain object characteristic information of the violating vehicle.
  • the speed information of the target vehicle in the tunnel may be acquired according to the sensing information of the second sensing device.
  • the target vehicle violates the driving regulations in the tunnel in response to the indication of the speed information. For example, when the speed of the target vehicle is zero, that is, the target vehicle stops driving in the tunnel, thereby potentially causing congestion and vehicle collision risks in the tunnel, the target vehicle is identified as a violating vehicle.
  • the speed information of the target vehicle indicates that its speed is lower than the minimum speed limit or higher than the maximum speed limit, the target vehicle is correspondingly identified as a violating vehicle with illegal slow-moving or speeding.
  • the process proceeds to step S308.
  • the target binding information may be obtained from the binding information of the vehicle search set updated in step S305 according to the object feature information of the violating vehicle.
  • the identity information of the violating vehicle can be obtained based on the target binding information, so that at step S310, the identity information of the violating vehicle and the corresponding violation behavior can be output.
  • the illegal slow-moving behavior that is, the speed is lower than the minimum speed limit
  • the violation of the speeding behavior that is, the speed is higher than the maximum speed limit
  • Fig. 4 is another flowchart schematically showing a method 400 for identifying traffic violation participants according to an embodiment of the present disclosure. It can be understood that the method flow shown in FIG. 4 can be implemented in the exemplary server scenario shown in FIG. 2 , so the content described in FIG. 2 (for example, about the sensing device) is also applicable to FIG. 4 .
  • the sensing information of a first sensing device (such as the first sensing device 101 in FIG. 2 ) at a scene entrance is acquired.
  • the scenario may be a service area scenario.
  • a snapshot is taken of the target traffic participating object based on the sensing information of the first sensing device, so as to obtain identity information of the target traffic participating object.
  • the snapping action can be performed, for example, by the snapping device 104 shown in FIG. 2 .
  • the present disclosure proposes to set the far-end capture position and the near-end capture position, so that the target traffic can be selected at the far-end capture position or the near-end capture position based on the sensing information of the first sensing device. Participating objects are captured. The specific capture operation will be described in detail later with reference to FIG. 5 .
  • the object feature information of the target traffic participating object may be acquired according to the sensing information of the first sensing device.
  • the object feature information may include, for example, ID, category, location, lane, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information about the traffic participating objects in the scene.
  • the process proceeds to step S404, where the identity information of the target traffic participant object is bound with the corresponding object characteristic information to obtain the binding information of the target traffic participant object, and at step S405, the target traffic participant object’s Binding information is recorded in a traffic participation object lookup set (eg, a database).
  • a traffic participation object lookup set eg, a database
  • the sensing information of the second sensing device in the scene may be acquired.
  • the second sensing device is, for example, the second sensing device 107 shown in FIG. 2 .
  • the second sensing device performs sensing operations on the target traffic participants in the scene, so as to obtain the sensing information of the target traffic participants in the scene.
  • the violating traffic participating object may be identified according to the sensing information of the second sensing device, so as to obtain object characteristic information of the violating traffic participating object.
  • the object characteristic information, position information and speed information of the target traffic participating objects in the scene can be acquired according to the perception information of the second sensing device, wherein the object characteristic information includes at least category information .
  • the target traffic participating object is identified as an illegal traffic participating object.
  • the target traffic participant when it parks in the parking area preset for parking trucks, the target traffic participant (that is, a car in this example) will It is judged to have violated the parking regulations in the service area, so it becomes the object of violation traffic participation in the context of this disclosure. Additionally or alternatively, in response to the speed information indicating that the speed of the target traffic participating object is zero and the position information of the target traffic participating object does not match the position of a preset area within the scene, identifying the target traffic participating object as an illegal traffic participating object . For example, when the location information in the perception information indicates that the location where the vehicle is parked is not the preset parking location in the service area. In other words, at this time the vehicle is parked in a non-parking area within the service area, such as a pedestrian passage or a fire exit, so it will also be judged as a traffic participant in violation.
  • a non-parking area within the service area such as a pedestrian passage or a fire exit
  • the process proceeds to step S408.
  • the target binding information may be obtained from the binding information of the traffic participation object lookup set updated in step S405 according to the object characteristic information of the violation traffic participation object.
  • the identity information of the violating traffic participant can be obtained based on the target binding information, so that at step S410, the identity information of the violating traffic participant and the corresponding violation behavior can be output.
  • violation information associated with category information mismatch or location mismatch may be generated for the violation traffic participation object. Then, according to the location information of the violating traffic participating object, the violating information can be directionally broadcast to the violating traffic participating object, so that the violating traffic participants can be effectively reminded and warned.
  • Fig. 5 is a diagram schematically illustrating an operation for performing a snapshot in a scene according to an embodiment of the present disclosure.
  • the capture operation of the present disclosure by taking a vehicle as an example of the traffic participation object.
  • the present disclosure proposes to use the capture device 104 to capture it, so as to obtain the vehicle's Identity Information.
  • this disclosure proposes a far-end capture position and a near-end capture position for the capture position, and based on the perception information of the first sensing device (such as the first sensing device 101 in FIG. 1 or FIG.
  • the far-end snapping position and/or the near-end snapping position of the present disclosure also involves lane information of the lane on which the vehicle is driving.
  • the present disclosure proposes to obtain the traffic participation object (That is, the first spacing and size information of the vehicle 102 in this example), wherein the first spacing includes the distance between the front of the target traffic participating object and the rear of the preceding traffic participating object (that is, the spacing shown in 502 in the figure) . Then, according to the comparison between the first distance and size information and the preset threshold, the target traffic participating object can be captured at the far-end capture position or the near-end capture position. In other words, when the vehicle meets the requirements for capturing at the remote capturing position, when it enters the remote capturing position, the capturing device of the present disclosure is triggered to capture the vehicle. Similarly, when a vehicle meeting the near-end capture position is located at the near-end capture position, the capture device is triggered to capture the vehicle.
  • the traffic participation object That is, the first spacing and size information of the vehicle 102 in this example
  • the first spacing includes the distance between the front of the target traffic participating object and the rear of the preceding traffic participating object (that is, the spacing shown
  • selecting to capture the target traffic participant object at the far-end capture position or the near-end capture position according to the comparison between the above-mentioned first distance and size information and the preset threshold includes: responding to the first distance being smaller than the first preset threshold and the height of the traffic participating object in front is greater than the second preset threshold, select the near-end capture position to capture the target traffic participating object.
  • a remote capture position may be selected to capture the target traffic participant object.
  • a remote capture position is selected to capture the target traffic participating object.
  • the capture operation of the present disclosure will be described below by taking the truck 103 in FIG. 5 as a specific capture object as an example.
  • the information processing center in Fig. 1 obtains the aforementioned perception information, it can determine the distance between the rear of the car (that is, the distance shown in 502 in the figure) and the height of the car (that is, the above-mentioned size) according to the perception information. information) to judge.
  • the information processing center can select the trigger position as the near-end capture position (as indicated by arrow 504 in FIG. 5 ).
  • the present disclosure After determining the capture position, in order to accurately identify the identity information of the target traffic participant in the service area or tunnel, in one embodiment, the present disclosure also proposes to determine the target traffic participant based on the perception information and the capture position. Snapshot recognition frame for snapping and recognition.
  • the capture recognition frame can be used at the capture position to capture and identify the target traffic participant, so as to obtain the identity information of the target traffic participant.
  • the present disclosure proposes to obtain the second distance of the traffic participation object located in front of the target traffic participation object in the capture direction according to the sensing information (ie, the sensing information collected by the first sensing device), wherein the second distance includes the distance between the front part of the target traffic participating object and the front part of the traffic participating object in front thereof (that is, the distance shown in 501 in Figure 5), and then the snapping position can be determined based on the snapping position and the second distance
  • the recognition frame is used to capture and recognize the vehicle.
  • the capture device can recognize the license plate of the vehicle according to the selected capture position (which includes lane information) and the determined capture recognition frame, so as to obtain the identity information of the vehicle. Therefore, the present disclosure provides effective identification of target traffic participants in the scene through the snapshot operation, thereby providing a good basis for subsequent binding and determination of violating traffic participants.
  • FIG. 6 is a schematic block diagram schematically showing a system 600 for identifying illegal traffic participating objects according to an embodiment of the present disclosure. It can be understood that the system shown in FIG. 6 is only an implementation of the solution of the present disclosure, and those skilled in the art may also think of making changes to the system 600 to adapt to different application scenarios according to the teaching of the present disclosure. Further, since FIG. 6 is a simplified illustration of the system shown in FIG. 1 and FIG. 2 , the description about FIG. 1 and FIG. 2 is also applicable to the description for FIG. 6 .
  • the system 600 includes a first sensing device 101 , a capture device 104 , a second sensing device 107 , an information processing center 105 and a violation reporting device 601 .
  • the first sensing device 101, the capture device 104, the second sensing device 107, and the information processing center 105 cooperate to determine the violating traffic participants in the scene, and the violating playback device (such as shown in FIG. 1
  • the large-screen display 108 is used to broadcast to the violating traffic participants, for example, to carry out directional broadcasting for the violating traffic participants, thereby reminding them to correct the violating operation in time.
  • the present disclosure may also be implemented using a modular design.
  • the first sensing device and the second sensing device of the present disclosure can respectively constitute a scene entrance multi-source sensing module and a scene multi-source sensing module, both of which can sense traffic participants (such as vehicles) in the detection area in real time, thus obtaining Perception information about the vehicle, including but not limited to the vehicle's ID, category, location, lane, perception moment, size, speed information, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information.
  • Perception information about the vehicle including but not limited to the vehicle's ID, category, location, lane, perception moment, size, speed information, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information.
  • the capture and recognition operations of the present disclosure may also be implemented by triggering the position selection module, triggering the capture module and the license plate recognition module.
  • the trigger position selection module can make a judgment according to the distance between the rear of the front vehicle and the height of the front vehicle of the incoming vehicle perception information. When the distance between the rear of the vehicle is less than the preset threshold and the height of the front vehicle is greater than the preset threshold, the trigger position is selected as the near-end capture position; otherwise, the trigger area is selected as the far-end capture position. Additionally, the trigger position selection module can also update the perception information of the vehicle at the entrance of the scene, including the selected capture position.
  • the above-mentioned trigger capture module can make a judgment based on the vehicle position of the incoming vehicle perception information.
  • the trigger capture module can select the preset recognition frame position according to the distance between the front vehicle and the capture position of the incoming vehicle perception information. Then, the trigger capture module can send trigger capture information to the license plate recognition module, and the trigger capture information can include but not limited to the ID of the vehicle, the position of the identification frame, the lane, and the capture time.
  • the license plate recognition module In response to receiving the trigger capture information, the license plate recognition module recognizes the license plate at the capture position according to the position of the recognition frame in the corresponding lane according to the lane information in the trigger capture information, and outputs it to the information processing center to obtain the identity information of the vehicle,
  • the identity information may include, but is not limited to, the license plate number of the vehicle and trigger capture information.
  • the present disclosure can also be provided with an identity information binding module, which is used to uniquely determine the entrance vehicle perception information according to the vehicle ID in the trigger capture information of the vehicle identity information, so as to complete the identification of the vehicle identity information and the entrance vehicle perception information. binding.
  • vehicle fusion information can be formed through fusion, and the fusion information can include but not limited to ID, category, location, perception moment, size, speed information, license plate number and/or vehicle image feature information of the vehicle.
  • the present disclosure may also be provided with a vehicle violation judging module, which can be used to judge according to the speed information in the aforementioned vehicle fusion information. For example, when the speed information indicates that the vehicle speed is 0, it can be determined that the vehicle has stopped driving in the tunnel in violation of regulations. For another example, when the speed information indicates that the driving speed of the vehicle is lower than the prescribed minimum speed limit, it can also be determined that the vehicle is a violating vehicle. It can also be used to judge according to the speed information in the aforementioned vehicle fusion information. For example, when the speed information indicates that the vehicle speed is 0, it may be determined whether the vehicle is in the parking area according to the preset parking area and combined with the location information in the fusion information.
  • the position of the vehicle When the position of the vehicle is not within the parking area, it is judged as illegal parking. Further, it is also possible to determine whether the vehicle violates the regulations according to the preset parking area category and in combination with the category information in the fusion information. For example, when the position of the vehicle is in the parking area but the type of the vehicle does not match the type of the parking area, it can be determined that it does not park according to the type of vehicle and constitutes a violation. Based on this, the violation information for the violation vehicle can be formed, the violation information can include but not limited to vehicle ID, category, location, violation time, violation category, vehicle size, speed information, license plate number or vehicle image feature information.
  • the present disclosure can also be provided with an identity information search module and a broadcast module.
  • the identity information search module can match its own identity information in the vehicle fusion information according to the vehicle category, size, and vehicle image feature information in the aforementioned violation information, so as to form violation broadcast information, which may include but Not limited to the vehicle's ID, class, location, time of violation, category of violation, size, speed information and/or license plate number.
  • the playback module can automatically select the nearest broadcast device or display a large screen to the violation vehicle according to the violation broadcast information and combined with the location information in the violation broadcast information, and broadcast the violation category according to the license plate number.
  • the broadcasting device For example, for a vehicle that parks illegally, you can choose the broadcasting device closest to the vehicle or display a large screen to play the violation message. For a vehicle traveling at a speeding or low speed, it is possible to instruct the broadcasting device on the tunnel section that the vehicle is about to pass through or display a large screen to broadcast its violation behavior, so as to remind the driver to correct its violation behavior in time.
  • any module, unit, component, server, computer, or device performing operations of the examples of the present disclosure may include or otherwise access computer-readable media, such as storage media, computer storage media, or data storage devices (which may removable) and/or non-removable) such as magnetic disks, optical disks, or tapes.
  • Computer storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.
  • the present disclosure also discloses a computer-readable storage medium, on which are stored computer-readable instructions for identifying illegal traffic participation objects. When the computer-readable instructions are executed by one or more processors, the preceding combination The methods and operations described in the figures.
  • the term “if” may be interpreted as “when” or “once” or “in response to determining” or “in response to detecting” depending on the context.
  • the phrase “if determined” or “if [the described condition or event] is detected” may be construed, depending on the context, to mean “once determined” or “in response to the determination” or “once detected [the described condition or event] ]” or “in response to detection of [described condition or event]”.

Abstract

A method and system for identifying an illegal traffic participant, and a computer-readable storage medium. The method comprises: obtaining sensing information of a first sensing device at an entrance of a scene and sensing information of a second sensing device in the scene (S301); capturing a snapshot of a target traffic participant on the basis of the sensing information of the first sensing device to obtain identity information thereof (S302); obtaining participant feature information of the target traffic participant according to the sensing information of the first sensing device (S303), and binding the identity information and the participant feature information (S304), so as to obtain binding information and record the binding information in a traffic participant search set (S305); obtaining sensing information of the second sensing device in the scene (S306); identifying an illegal traffic participant according to the sensing information of the second sensing device, so as to obtain participant feature information of the illegal traffic participant (S307); obtaining target binding information from the binding information of the traffic participant search set according to the participant feature information of the illegal traffic participant (S308); obtaining identity information of the illegal traffic participant on the basis of the target binding information (S309); and outputting the identity information of the illegal traffic participant and a corresponding illegal behavior (S310). By means of the method, traffic participants who violate regulations in the scene can be accurately identified.

Description

识别违规交通参与对象的方法、系统和计算机可读存储介质Method, system, and computer-readable storage medium for identifying traffic violation objects
相关申请的交叉引用Cross References to Related Applications
本公开要求于2021年5月27日申请的,申请号为202110586458X,名称为“识别违规车辆的方法、系统和计算机可读存储介质”;于2021年5月27日申请的,申请号为202110587444X,名称为“识别违规交通参与对象的方法、系统和计算机可读存储介质”的中国专利申请的优先权。This disclosure requires the application on May 27, 2021, the application number is 202110586458X, and the name is "method, system and computer-readable storage medium for identifying illegal vehicles"; the application on May 27, 2021, the application number is 202110587444X , the priority of the Chinese patent application titled "Method, system and computer-readable storage medium for identifying objects involved in traffic violations".
技术领域technical field
本公开一般地涉及智能交通管理领域。更具体地,本公开涉及一种识别违规交通参与对象的方法、系统和计算机可读存储介质。The present disclosure relates generally to the field of intelligent traffic management. More specifically, the present disclosure relates to a method, system and computer-readable storage medium for identifying traffic violation objects.
背景技术Background technique
当前的智能交通管理涉及对人、车和路等交通对象的自动识别以及对违法行为的自动检测。通过自动识别和检测,可以智能分析交通重点管理目标,从而提高通行效率和优化交通出行秩序。然而,对于例如隧道、停靠车辆的服务区等场所来说,当前并没有良好的管理方案。特别地,对于行驶在隧道内以及服务区内车辆的各种违规行为,当前并没有行之有效的检测或通告方案。因此,如何对上述类似场所的车辆违规行为进行准确判断和及时通告,成为当前车辆管理所要解决的问题。The current intelligent traffic management involves the automatic identification of traffic objects such as people, vehicles and roads, and the automatic detection of illegal behaviors. Through automatic identification and detection, key traffic management objectives can be intelligently analyzed, thereby improving traffic efficiency and optimizing traffic order. However, there are currently no good management solutions for places such as tunnels, service areas where vehicles are parked, etc. In particular, there is currently no effective detection or notification scheme for various violations of vehicles driving in the tunnel and in the service area. Therefore, how to accurately judge and timely notify the vehicle violations in the above-mentioned similar places has become a problem to be solved by the current vehicle management.
发明内容Contents of the invention
202110586458X为了至少解决上述背景技术部分所描述的技术问题,本公开提出了一种在例如隧道的场景中识别违规车辆的方案。利用本公开的方案,可以有效地确定违反隧道行驶规定的车辆,从而有助于提升隧道内的高效安全通行,并且扩展了智能化交通管理的应用场景。鉴于此,本公开在如下的多个方面提供解决方案。202110586458X In order to at least solve the technical problems described in the background technology section above, this disclosure proposes a solution for identifying violating vehicles in scenarios such as tunnels. By using the solution disclosed in the present disclosure, vehicles violating tunnel driving regulations can be effectively determined, thereby helping to improve efficient and safe passage in tunnels, and expanding the application scenarios of intelligent traffic management. In view of this, the present disclosure provides solutions in the following aspects.
在第一方面中,本公开提供一种识别违规车辆的方法,包括:获取隧道入口处第一感知设备的感知信息;基于所述第一感知设备的感知信息对目标车辆进行抓拍,以获取所述目标车辆的身份信息,其中所述目标车辆为进入所述隧道内的车辆;根据所述第一感知设备的感知信息获取所述目标车辆的对象特征信息;将所述目标车辆的身份信息和对应的对象特征信息进行绑定,以获得目标车辆的绑定信息,并且将所述目标车辆的绑定信息记录于车辆查找集合中;获取所述隧道内第二感知设备的感知信息;根据所述第二感知设备的感知信息中的速度信息识别违规车辆,以便获取所述违规车辆的对象特征信息;根据所述违规车辆的对象特征信息从所述车辆查找集合的绑定信息中获取目标绑定信息;基于所述目标绑定信息获取违规车辆的身份信息;以及输出所述违规车辆的身份信息和对应的违规行为。In the first aspect, the present disclosure provides a method for identifying violating vehicles, including: acquiring the sensing information of a first sensing device at the entrance of a tunnel; taking a snapshot of the target vehicle based on the sensing information of the first sensing device to obtain the The identity information of the target vehicle, wherein the target vehicle is a vehicle entering the tunnel; the object characteristic information of the target vehicle is acquired according to the sensing information of the first sensing device; the identity information of the target vehicle and The corresponding object feature information is bound to obtain the binding information of the target vehicle, and the binding information of the target vehicle is recorded in the vehicle search set; the sensing information of the second sensing device in the tunnel is obtained; according to the The speed information in the sensing information of the second sensing device identifies the violating vehicle, so as to obtain the object characteristic information of the violating vehicle; obtain the target binding from the binding information of the vehicle search set according to the object characteristic information of the violating vehicle obtain the identity information of the violating vehicle based on the target binding information; and output the identity information of the violating vehicle and the corresponding violation behavior.
在其中一个实施例中,对目标车辆进行抓拍的抓拍位置包括远端抓拍位置和近端抓拍位置,并且基于所述第一感知设备的感知信息对目标车辆进行抓拍,以获取所述目标车辆的身份信息包括:基于所述第一感知设备的感知信息选择在所述远端抓拍位置或近端抓拍位置对所述目标车辆进行抓拍,以获取所述目标车辆的身份信息。In one of the embodiments, the capture position of the target vehicle includes a remote capture position and a near-end capture position, and the target vehicle is captured based on the sensing information of the first sensing device, so as to obtain the target vehicle's The identity information includes: selecting, based on the sensing information of the first sensing device, to capture the target vehicle at the far-end capture position or the near-end capture position, so as to obtain the identity information of the target vehicle.
在其中一个实施例中,基于所述第一感知设备的感知信息选择在所述远端抓拍位置或近端抓拍位置对所述目标车辆进行抓拍包括:基于所述第一感知设备的感知信息获取在抓 拍方向上位于所述目标车辆前方的车辆的第一间距和尺寸信息,其中所述第一间距包括所述目标车辆的前部与其前方车辆的尾部之间的距离;以及根据所述第一间距和尺寸信息与预设阈值的比较选择在所述远端抓拍位置或近端抓拍位置对目标车辆进行抓拍。In one embodiment, selecting to capture the target vehicle at the far-end capture position or the near-end capture position based on the sensing information of the first sensing device includes: acquiring based on the sensing information of the first sensing device First distance and size information of a vehicle located in front of the target vehicle in the capture direction, wherein the first distance includes a distance between the front of the target vehicle and the rear of the vehicle in front thereof; and according to the first The distance and size information is compared with a preset threshold to select to capture the target vehicle at the far-end capture position or the near-end capture position.
在其中一个实施例中,根据所述第一间距和尺寸信息与预设阈值的比较选择在所述远端抓拍位置或近端抓拍位置对目标车辆进行抓拍包括:响应于所述第一间距小于第一预设阈值并且所述前方车辆的高度大于第二预设阈值,选择所述近端抓拍位置对所述目标车辆进行抓拍;响应于所述第一间距大于第一预设阈值,选择所述远端抓拍位置对所述目标车辆进行抓拍;或者响应于所述第一间距小于第一预设阈值并且所述前方车辆的高度小于第二预设阈值,选择所述远端抓拍位置对所述目标车辆进行抓拍。In one embodiment, selecting to capture the target vehicle at the far-end capture position or the near-end capture position according to the comparison between the first distance and size information and a preset threshold includes: responding to the first distance being less than The first preset threshold and the height of the vehicle in front is greater than the second preset threshold, select the near-end capture position to capture the target vehicle; in response to the first distance being greater than the first preset threshold, select the target vehicle The remote capture position is used to capture the target vehicle; or in response to the first distance being less than a first preset threshold and the height of the vehicle in front is less than a second preset threshold, selecting the remote capture position for the target vehicle Capture the target vehicle.
在其中一个实施例中,基于所述第一感知设备的感知信息对目标车辆进行抓拍,以获取所述目标车辆的身份信息还包括:根据所述感知信息和所述抓拍位置确定用于对所述目标车辆进行抓拍和识别的抓拍识别框;以及在所述抓拍位置处利用所述抓拍识别框对所述目标车辆进行抓拍和识别,以获取所述目标车辆的身份信息。In one embodiment, capturing the target vehicle based on the sensing information of the first sensing device, so as to obtain the identity information of the target vehicle further includes: a capture and identification frame for capturing and identifying the target vehicle; and using the capture and identification frame to capture and identify the target vehicle at the capture position, so as to obtain identity information of the target vehicle.
在其中一个实施例中,根据所述感知信息和所述抓拍位置确定所述抓拍识别框包括:根据所述感知信息获取在抓拍方向上位于所述目标车辆前方的车辆的第二间距,其中所述第二间距包括所述目标车辆的前部与其前方车辆的前部之间的距离;基于所述抓拍位置和所述第二间距确定所述抓拍识别框。In one of the embodiments, determining the capture identification frame according to the perception information and the capture position includes: acquiring a second distance between vehicles located in front of the target vehicle in the capture direction according to the perception information, wherein the The second distance includes a distance between the front of the target vehicle and the front of the vehicle in front thereof; and the snapshot recognition frame is determined based on the snapshot position and the second distance.
在其中一个实施例中,根据所述第二感知设备的感知信息中的速度信息识别违规车辆包括:响应于目标车辆的速度信息指示速度等于零,将所述目标车辆识别为存在违规停滞行为的违规车辆;或者响应于目标车辆的速度信息指示速度低于最低限速,将所述目标车辆识别为存在违规慢行行为的违规车辆;或者响应于目标车辆的速度信息指示速度高于最高限速,将所述目标车辆识别为存在违规超速行为的违规车辆。In one of the embodiments, identifying the violating vehicle according to the speed information in the sensing information of the second sensing device includes: in response to the speed information of the target vehicle indicating that the speed is equal to zero, identifying the target vehicle as a violating vehicle with a stagnation behavior in violation vehicle; or in response to the speed information of the target vehicle indicating that the speed is lower than the minimum speed limit, identifying the target vehicle as a violating vehicle with illegal slow-moving behavior; or in response to the speed information of the target vehicle indicating that the speed is higher than the maximum speed limit, The target vehicle is identified as a violating vehicle with speeding violations.
在其中一个实施例中,所述第二感知设备的感知信息中还包括违规车辆的位置信息,其中输出所述违规车辆的身份信息和对应的违规行为包括:针对所述违规车辆生成与违规停滞行为、违规慢行行为或违规超速行为之一关联的违规信息;以及根据所述违规车辆的位置信息向所述违规车辆播报所述违规信息。In one of the embodiments, the sensing information of the second sensing device further includes the location information of the violating vehicle, wherein outputting the identity information of the violating vehicle and the corresponding violation behavior includes: Violation information associated with one of the violation behavior, slow-moving behavior or speed violation behavior; and broadcast the violation information to the violation vehicle according to the location information of the violation vehicle.
在第二方面中,本公开提供一种识别违规车辆的系统,包括:第一感知设备,其布置于隧道入口处,用于获取所述隧道入口处的感知信息;抓拍设备,其布置于所述隧道入口处,用于基于所述第一感知设备的感知信息对目标车辆进行抓拍,以获取所述目标车辆的身份信息,其中所述目标车辆为进入所述隧道的车辆;第二感知设备,其布置于所述隧道内,用于获取所述隧道内的感知信息;以及信息处理中心,其与所述第一感知设备、所述抓拍设备、所述第二感知设备进行通信连接,并且配置用于:获取隧道入口处第一感知设备的感知信息;根据所述第一感知设备的感知信息获取所述目标车辆的对象特征信息;将所述目标车辆的身份信息和对应的对象特征信息进行绑定,以获得目标车辆的绑定信息,并且将所述目标车辆的绑定信息记录于车辆查找集合中;获取所述隧道内第二感知设备的感知信息;根据所述第二感知设备的感知信息中的速度信息识别违规车辆,以便获取所述违规车辆的对象特征信息;根据所述违规车辆的对象特征信息从所述车辆查找集合的绑定信息中获取目标绑定信息;基于所述目标绑定信息获取违规车辆的身份信息;以及输出所述违规车辆的身份信息和对应的违规行为。In the second aspect, the present disclosure provides a system for identifying violating vehicles, including: a first sensing device arranged at the entrance of a tunnel for acquiring sensing information at the entrance of the tunnel; a capture device arranged at the entrance of the tunnel At the entrance of the tunnel, it is used to capture the target vehicle based on the sensing information of the first sensing device, so as to obtain the identity information of the target vehicle, wherein the target vehicle is a vehicle entering the tunnel; the second sensing device , which is arranged in the tunnel, and is used to obtain the sensing information in the tunnel; and an information processing center, which communicates with the first sensing device, the capture device, and the second sensing device, and It is configured to: acquire the sensing information of the first sensing device at the entrance of the tunnel; acquire the object characteristic information of the target vehicle according to the sensing information of the first sensing device; combine the identity information of the target vehicle with the corresponding object characteristic information Perform binding to obtain the binding information of the target vehicle, and record the binding information of the target vehicle in the vehicle search set; acquire the sensing information of the second sensing device in the tunnel; according to the second sensing device The speed information in the perception information of the violating vehicle is identified to obtain the object feature information of the violating vehicle; the target binding information is obtained from the binding information of the vehicle search set according to the object feature information of the violating vehicle; based on the Obtaining the identity information of the violating vehicle through the target binding information; and outputting the identity information of the violating vehicle and the corresponding violation behavior.
在其中一个实施例中,所述第一感知设备包括激光雷达和/或摄像机。在一个实施例中, 所述第二感知设备包括激光雷达和/或摄像机。在一个实施例中,所述抓拍设备包括卡口相机。In one of the embodiments, the first sensing device includes a lidar and/or a camera. In one embodiment, the second sensing device includes a lidar and/or a camera. In one embodiment, the capture device includes a bayonet camera.
在第三方面中,本公开提供一种计算机可读存储介质,其上存储有识别违规车辆的计算机可读指令,该计算机可读指令被一个或多个处理器执行时,实现如第一方面及其多个实施例中所述的方法。In a third aspect, the present disclosure provides a computer-readable storage medium, on which computer-readable instructions for identifying violating vehicles are stored. When the computer-readable instructions are executed by one or more processors, the first aspect is implemented. and the methods described in its various embodiments.
利用本公开的上述方案,可以对隧道中的违规车辆进行有效识别。具体来说,通过利用感知信息和抓拍操作,本公开可以准确识别和存储进入隧道内的车辆的信息。进一步,通过在隧道内对车辆再次进行感知,本公开的方案可以准确识别出违反隧道内行驶规定的车辆。由此,本公开的方案促进了对隧道内行驶车辆的有效管理和监控,并对违规者进行有效地发现和及时处理。Utilizing the above solution of the present disclosure, it is possible to effectively identify illegal vehicles in the tunnel. Specifically, the present disclosure can accurately identify and store the information of the vehicle entering the tunnel by utilizing the perception information and the capture operation. Further, by sensing the vehicle again in the tunnel, the solution of the present disclosure can accurately identify the vehicle that violates the driving regulations in the tunnel. Therefore, the solution disclosed in the present disclosure promotes effective management and monitoring of vehicles traveling in the tunnel, and effectively discovers and promptly handles violators.
202110586458X202110586458X
202110587444X为了至少解决上述背景技术部分所描述的技术问题,本公开提出了一种识别违规交通参与者的方案。利用本公开的方案,可以在一些场景中有效地确定违反规定的交通参与者,从而有助于实现高效的智能化交通管理。鉴于此,本公开在如下的多个方面提供解决方案。202110587444X In order to at least solve the technical problems described in the background technology section above, this disclosure proposes a scheme for identifying violating traffic participants. By using the solution disclosed in the present disclosure, traffic participants violating regulations can be effectively determined in some scenarios, thereby helping to realize efficient intelligent traffic management. In view of this, the present disclosure provides solutions in the following aspects.
在第一方面中,本公开提供一种识别违规交通参与对象的方法,包括:获取场景入口处第一感知设备的感知信息;基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息,其中所述目标交通参与对象为进入所述场景的交通参与对象;根据所述第一感知设备的感知信息获取所述目标交通参与对象的对象特征信息;将所述目标交通参与对象的身份信息和对应的对象特征信息进行绑定,以获得目标交通参与对象的绑定信息,并且将所述目标交通参与对象的绑定信息记录于交通参与对象查找集合中;获取所述场景内第二感知设备的感知信息;根据所述第二感知设备的感知信息识别违规交通参与对象,以便获取所述违规交通参与对象的对象特征信息;根据所述违规交通参与对象的对象特征信息从所述交通参与对象查找集合的绑定信息中获取目标绑定信息;基于所述目标绑定信息获取违规交通参与对象的身份信息;以及输出所述违规交通参与对象的身份信息和对应的违规行为。In the first aspect, the present disclosure provides a method for identifying illegal traffic participation objects, including: acquiring the perception information of a first sensing device at the entrance of a scene; capturing a target traffic participation object based on the perception information of the first sensing device , to obtain the identity information of the target traffic participation object, wherein the target traffic participation object is a traffic participation object entering the scene; obtain the object characteristics of the target traffic participation object according to the perception information of the first sensing device information; bind the identity information of the target traffic participation object with the corresponding object feature information to obtain the binding information of the target traffic participation object, and record the binding information of the target traffic participation object in the traffic participation object Searching in the collection; obtaining the sensing information of the second sensing device in the scene; identifying the illegal traffic participating object according to the sensing information of the second sensing device, so as to obtain the object characteristic information of the illegal traffic participating object; according to the illegal The object feature information of the traffic participation object obtains target binding information from the binding information of the traffic participation object search set; obtains the identity information of the violation traffic participation object based on the target binding information; and outputs the violation traffic participation object identity information and corresponding violations.
在其中一个实施例中,所述场景包括服务区场景,并且所述违规交通参与对象是违反服务区规定的交通参与对象。In one of the embodiments, the scene includes a service area scene, and the illegal traffic participation object is a traffic participation object that violates service area regulations.
在其中一个实施例中,抓拍位置包括远端抓拍位置和近端抓拍位置,并且基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息包括:基于所述第一感知设备的感知信息选择在所述远端抓拍位置或近端抓拍位置对所述目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息。In one of the embodiments, the snapping position includes a far-end snapping position and a near-end snapping position, and the target traffic participating object is captured based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object The method includes: selecting, based on the sensing information of the first sensing device, to capture the target traffic participant object at the far-end capture position or the near-end capture position, so as to obtain the identity information of the target traffic participant object.
在其中一个实施例中,基于所述第一感知设备的感知信息选择在所述远端抓拍位置或近端抓拍位置对所述目标交通参与对象进行抓拍包括:基于所述第一感知设备的感知信息获取在抓拍方向上位于所述目标交通参与对象前方的交通参与对象的第一间距和尺寸信息,其中所述第一间距包括所述目标交通参与对象的前部与其前方交通参与对象的尾部之间的距离;以及根据所述第一间距和尺寸信息与预设阈值的比较选择在所述远端抓拍位置或近端抓拍位置对目标交通参与对象进行抓拍。In one embodiment, selecting to capture the target traffic participant object at the far-end capture position or the near-end capture position based on the perception information of the first sensing device includes: based on the perception of the first sensing device Information acquisition of the first distance and size information of the traffic participation object located in front of the target traffic participation object in the capture direction, wherein the first distance includes the distance between the front part of the target traffic participation object and the tail of the traffic participation object in front distance between them; and choose to capture the target traffic participating object at the far-end capture position or the near-end capture position according to the comparison between the first distance and size information and a preset threshold.
在其中一个实施例中,根据所述第一间距和尺寸信息与预设阈值的比较选择在所述远端抓拍位置或近端抓拍位置对目标交通参与对象进行抓拍包括:响应于所述第一间距小于 第一预设阈值并且所述前方交通参与对象的高度大于第二预设阈值,选择所述近端抓拍位置对所述目标交通参与对象进行抓拍;响应于所述第一间距大于第一预设阈值,选择所述远端抓拍位置对所述目标交通参与对象进行抓拍;或者响应于所述第一间距小于第一预设阈值并且所述前方交通参与对象的高度小于第二预设阈值,选择所述远端抓拍位置对所述目标交通参与对象进行抓拍。In one embodiment, selecting to capture the target traffic participating object at the far-end capture position or the near-end capture position according to the comparison between the first distance and size information and a preset threshold includes: responding to the first If the distance is less than a first preset threshold and the height of the preceding traffic participating object is greater than a second preset threshold, the near-end capture position is selected to capture the target traffic participating object; in response to the first distance being greater than the first A preset threshold, selecting the remote capture position to capture the target traffic participating object; or in response to the first distance being less than a first preset threshold and the height of the preceding traffic participating object being less than a second preset threshold , selecting the remote capture position to capture the target traffic participant.
在其中一个实施例中,基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息还包括:根据所述感知信息和所述抓拍位置确定用于对所述目标交通参与对象进行抓拍和识别的抓拍识别框;以及在所述抓拍位置处利用所述抓拍识别框对所述目标交通参与对象进行抓拍和识别,以获取所述目标交通参与对象的身份信息。In one of the embodiments, capturing the target traffic participating object based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object further includes: determining according to the sensing information and the captured position A capture recognition frame for capturing and identifying the target traffic participation object; and using the capture recognition frame to capture and identify the target traffic participation object at the capture position, so as to obtain the target traffic participation The identity information of the object.
在其中一个实施例中,根据所述感知信息和所述抓拍位置确定所述抓拍识别框包括:根据所述感知信息获取在抓拍方向上位于所述目标交通参与对象前方的交通参与对象的第二间距,其中所述第二间距包括所述目标交通参与对象的前部与其前方交通参与对象的前部之间的距离;基于所述抓拍位置和所述第二间距确定所述抓拍识别框。In one of the embodiments, determining the capture recognition frame according to the perception information and the capture position includes: obtaining the second position of the traffic participation object located in front of the target traffic participation object in the capture direction according to the perception information. distance, wherein the second distance includes the distance between the front part of the target traffic participating object and the front part of the traffic participating object in front thereof; the snapping identification frame is determined based on the snapping position and the second distance.
在其中一个实施例中,根据所述第二感知设备的感知信息识别违规交通参与对象包括:根据所述第二感知设备的感知信息获取所述场景内的目标交通参与对象的对象特征信息、位置信息和速度信息,其中所述对象特征信息至少包括类别信息;以及响应于所述速度信息指示所述目标交通参与对象的速度为零并且所述目标交通参与对象的类别信息与所述场景内的预设区域的类别信息不匹配,将所述目标交通参与对象识别为违规交通参与对象;或者响应于所述速度信息指示所述目标交通参与对象的速度为零并且所述目标交通参与对象的位置信息与所述场景内的预设区域的位置不匹配,将所述目标交通参与对象识别为违规交通参与对象。In one of the embodiments, identifying the violating traffic participating object according to the sensing information of the second sensing device includes: acquiring object feature information and position of the target traffic participating object in the scene according to the sensing information of the second sensing device information and speed information, wherein the object feature information includes at least category information; and in response to the speed information indicating that the speed of the target traffic participating object is zero and the category information of the target traffic participating object is consistent with the The category information of the preset area does not match, identifying the target traffic participating object as an illegal traffic participating object; or in response to the speed information indicating that the speed of the target traffic participating object is zero and the position of the target traffic participating object The information does not match the position of the preset area in the scene, and the target traffic participating object is identified as an illegal traffic participating object.
在其中一个实施例中,输出所述违规交通参与对象的身份信息和对应的违规行为包括:针对所述违规交通参与对象生成与类别信息不匹配或位置不匹配相关联的违规信息;以及根据所述违规交通参与对象的位置信息来定向地对所述违规交通参与对象播报所述违规信息。In one of the embodiments, outputting the identity information of the violation traffic participation object and the corresponding violation behavior includes: generating violation information associated with category information mismatch or location mismatch for the violation traffic participation object; The location information of the violation traffic participation object is used to broadcast the violation information to the violation traffic participation object in a directional manner.
在第二方面中,本公开提供一种识别违规交通参与对象的系统,包括:第一感知设备,其布置于场景入口处,用于获取所述场景入口处的感知信息;抓拍设备,其布置于所述场景入口处,用于基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息,其中所述目标交通参与对象为进入所述场景的交通参与对象;第二感知设备,其布置于所述场景内,用于获取所述场景内的感知信息;以及信息处理中心,其与所述第一感知设备、所述抓拍设备、所述第二感知设备进行通信连接,并且配置用于:分别从所述第一感知设备和第二感知设备获取对应的感知信息;根据所述第一感知设备的感知信息获取所述目标交通参与对象的对象特征信息;将所述目标交通参与对象的身份信息和对应的对象特征信息进行绑定,以获得目标交通参与对象的绑定信息,并且将所述目标交通参与对象的绑定信息记录于交通参与对象查找集合中;根据所述第二感知设备的感知信息识别违规交通参与对象,以便获取所述违规交通参与对象的对象特征信息;根据所述违规交通参与对象的对象特征信息从所述交通参与对象查找集合的绑定信息中获取目标绑定信息;基于所述目标绑定信息获取违规交通参与对象的身份信息;以及输出所述违规交通参与对象的身份信息和对应的违规行为。In a second aspect, the present disclosure provides a system for identifying illegal traffic participants, including: a first sensing device, arranged at the entrance of a scene, for acquiring sensing information at the entrance of the scene; a capture device, arranged At the entrance of the scene, it is used to capture the target traffic participating object based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object, wherein the target traffic participating object enters the The traffic participating objects of the scene; the second sensing device, which is arranged in the scene, and is used to obtain the sensing information in the scene; and an information processing center, which cooperates with the first sensing device, the capture device, and the The second sensing device is connected in communication, and is configured to: respectively obtain corresponding sensing information from the first sensing device and the second sensing device; obtain the target traffic participation object according to the sensing information of the first sensing device The object feature information of the target traffic participation object; bind the identity information of the target traffic participation object with the corresponding object feature information to obtain the binding information of the target traffic participation object, and record the binding information of the target traffic participation object in In the traffic participation object search set; according to the perception information of the second sensing device, identify the violation traffic participation object, so as to obtain the object feature information of the violation traffic participation object; according to the object feature information of the violation traffic participation object from the Obtain target binding information from the binding information of the traffic participation object search set; obtain identity information of the violation traffic participation object based on the target binding information; and output the identity information and corresponding violation behavior of the violation traffic participation object.
在其中一个实施例中,所述第一感知设备和第二感知设备包括激光雷达和/或摄像机。在一个实施例中,所述第二感知设备包括激光雷达和/或摄像机。在一个实施例中,所述抓拍设备包括卡口相机。In one of the embodiments, the first sensing device and the second sensing device include a lidar and/or a camera. In one embodiment, the second sensing device includes a lidar and/or a camera. In one embodiment, the capture device includes a bayonet camera.
在第三方面中,本公开提供一种计算机可读存储介质,其上存储有识别违规交通参与对象的计算机可读指令,该计算机可读指令被一个或多个处理器执行时,实现如第一方面及其多个实施例中所述的方法。In a third aspect, the present disclosure provides a computer-readable storage medium, on which are stored computer-readable instructions for identifying objects involved in traffic violations. When the computer-readable instructions are executed by one or more processors, the The method described in one aspect and various embodiments thereof.
利用本公开的上述方案,可以对场景中的违规交通参与者进行有效识别。具体来说,通过利用感知信息和抓拍操作,本公开可以准确识别和存储进入场景内的交通参与者的信息。进一步,通过在场景内对交通参与者再次进行感知,本公开的方案可以准确识别出违反场景内规定的交通参与者。由此,本公开的方案促进了对场景内交通参与者的有效管理并对违规者进行有效地发现和及时处理。Utilizing the above solution of the present disclosure, it is possible to effectively identify the violating traffic participants in the scene. Specifically, the present disclosure can accurately identify and store information of traffic participants entering a scene by using perception information and snapping operations. Further, by re-perceiving the traffic participants in the scene, the solution of the present disclosure can accurately identify the traffic participants who violate the regulations in the scene. Therefore, the solution disclosed in the present disclosure promotes the effective management of traffic participants in the scene and effectively discovers and promptly handles violators.
202110587444X202110587444X
附图说明Description of drawings
通过参考附图阅读下文的详细描述,本公开示例性实施方式的说明以及其他目的、特征和优点将变得易于理解。在附图中,以示例性而非限制性的方式示出了本公开的若干实施方式,并且相同或对应的标号表示相同或对应的部分,其中:The description of the exemplary embodiments of the present disclosure, as well as other objects, features and advantages will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are shown by way of illustration and not limitation, and the same or corresponding reference numerals indicate the same or corresponding parts, wherein:
图1是示意性示出其中应用本公开的用于识别违规交通参与对象的方案的示例性场景图;FIG. 1 is an exemplary scene diagram schematically showing a scheme in which the present disclosure is applied for identifying an object involved in traffic violations;
图2是示意性示出其中应用本公开的用于识别违规交通参与对象的方案的又一示例性场景图;Fig. 2 is another exemplary scene diagram schematically showing the scheme for identifying illegal traffic participating objects in which the present disclosure is applied;
图3是示意性示出根据本公开实施例的用于识别违规交通参与对象的方法的流程图;FIG. 3 is a flowchart schematically showing a method for identifying illegal traffic participants according to an embodiment of the present disclosure;
图4是示意性示出根据本公开实施例的用于识别违规交通参与对象的方法的又一流程图;FIG. 4 is another flow chart schematically showing a method for identifying illegal traffic participating objects according to an embodiment of the present disclosure;
图5是示意性示出根据本公开实施例的用于执行抓拍操作的示图;Fig. 5 is a diagram schematically illustrating a capture operation according to an embodiment of the present disclosure;
图6是示意性示出根据本公开实施例的用于识别违规交通参与对象的示意框图。Fig. 6 is a schematic block diagram schematically showing an object used for identifying traffic violations according to an embodiment of the present disclosure.
具体实施方式Detailed ways
下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述。显然,所描述的实施例是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some of the embodiments of the present disclosure, but not all of them. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present disclosure.
应当理解,本公开的权利要求、说明书及附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象,而不是用于描述特定顺序。本公开的说明书和权利要求书中使用的术语“包括”和“包含”指示所描述特征、整体、步骤、操作、元素和/或组件的存在,但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。It should be understood that the terms "first", "second", "third" and "fourth" in the claims, specification and drawings of the present disclosure are used to distinguish different objects, rather than to describe a specific order . The terms "comprising" and "comprises" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and/or components, but do not exclude one or more other features, integers , steps, operations, elements, components, and/or the presence or addition of collections thereof.
还应当理解,在此本公开说明书中所使用的术语仅仅是出于描述特定实施例的目的,而并不意在限定本公开。如在本公开说明书和权利要求书中所使用的那样,除非上下文清楚地指明其它情况,否则单数形式的“一”、“一个”及“该”意在包括复数形式。还应当进一步理解,在本公开说明书和权利要求书中使用的术语“和/或”是指相关联列出的 项中的一个或多个的任何组合以及所有可能组合,并且包括这些组合。It should also be understood that the terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in this disclosure and the claims, the singular forms "a", "an" and "the" are intended to include plural referents unless the context clearly dictates otherwise. It should be further understood that the term "and/or" used in the present disclosure and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
下面结合附图来详细描述本公开的具体实施方式。Specific embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings.
图1是示意性示出其中应用本公开的用于识别违规交通参与对象的方案的示例性场景100的示图。在本公开的上下文中,前述的场景可以包括用于停放交通参与对象的各类环境,例如高速路上的各种服务区、各类停车场(例如商业用或民用)、各种交通隧道或桥梁涵洞等。基于此,可以理解图1示例性场景示出为隧道场景。进一步,在本公开的上下文中,前述的交通参与对象可以是与道路活动/交通活动相关的对象,例如机动车辆和/或非机动车辆等。FIG. 1 is a diagram schematically illustrating an exemplary scenario 100 in which the scheme of the present disclosure for identifying violating traffic participation objects is applied. In the context of the present disclosure, the aforementioned scenarios may include various environments for parking traffic participating objects, such as various service areas on expressways, various parking lots (such as commercial or civilian), various traffic tunnels or bridges Culverts, etc. Based on this, it can be understood that the exemplary scenario shown in FIG. 1 is a tunnel scenario. Further, in the context of the present disclosure, the aforementioned traffic participation objects may be objects related to road activities/traffic activities, such as motor vehicles and/or non-motor vehicles.
如图1所示,根据本公开的方案,可以在隧道的入口处设置有第一感知设备101,其配置用于采集其感知覆盖范围内的感知信息。取决于第一感知设备的感知能力,前述的感知覆盖范围可以涵盖隧道口周边一定距离范围内的区域,从而可以感知驶入和/或不驶入隧道的车辆。在一个实施方式中,该第一感知设备可以包括激光雷达(图1中以圆点示出)和/或摄像机。在激光雷达和摄像机配合使用的应用场景中,激光雷达和摄像机可以用于获取同一时刻、同一场景下的点云数据和视频数据。当对点云数据和视频数据分别进行目标检测,并且对检测结果进行融合时,就可以得到初始融合结果。当目标为车辆时,前述的初始融合结果可以例如包括关于车辆(如图1中所示车辆102和103)的各类信息,包括但不限于以下中的一项或多项:感知区域内的车辆的身份(ID)信息、车辆类别信息、车辆位置信息、车辆所处车道的信息、车辆感知时刻信息、车辆尺寸信息、车辆速度信息、前车车头间距(如图5中501处所示)、前车车尾间距(如图5中502处所示)和/或车辆图像特征信息。As shown in FIG. 1 , according to the solution of the present disclosure, a first sensing device 101 may be provided at the entrance of the tunnel, which is configured to collect sensing information within its sensing coverage range. Depending on the sensing capabilities of the first sensing device, the aforementioned sensing coverage may cover an area within a certain distance around the tunnel entrance, so that vehicles entering and/or not entering the tunnel can be sensed. In one embodiment, the first sensing device may include a laser radar (shown as a dot in FIG. 1 ) and/or a camera. In the application scenario where the lidar and the camera are used together, the lidar and the camera can be used to obtain point cloud data and video data at the same time and in the same scene. When target detection is performed on point cloud data and video data respectively, and the detection results are fused, the initial fusion result can be obtained. When the target is a vehicle, the aforementioned initial fusion results may, for example, include various types of information about the vehicle (such as vehicles 102 and 103 shown in FIG. 1 ), including but not limited to one or more of the following: Vehicle identity (ID) information, vehicle category information, vehicle location information, vehicle lane information, vehicle perception time information, vehicle size information, vehicle speed information, and the distance between the front and rear vehicles (as shown at 501 in Figure 5) , the distance between the front and the rear of the vehicle (as shown at 502 in FIG. 5 ) and/or vehicle image feature information.
进一步,沿车辆进入场景内的方向,也即本例中沿车辆驶入隧道的方向,在第一感知设备的后方一定距离内并且在隧道入口前设置有抓拍设备104,其用于基于第一感知设备101的感知信息来对即将进入到隧道内的车辆进行抓拍,以便获取目标车辆的身份信息(例如车辆的车牌号)。在本公开的上下文,进入到隧道内的车辆即是目标车辆,而本公开的方案旨在对这样的一个或多个目标车辆进行监视,以便确定违反隧道内行驶规定的违规车辆。根据不同的实施方式,本公开的抓拍设备可以是各种类型的相机。作为优选方案,该相机可以是卡口相机。Further, along the direction in which the vehicle enters the scene, that is, in this example, along the direction in which the vehicle enters the tunnel, a capture device 104 is provided within a certain distance behind the first sensing device and in front of the tunnel entrance, which is used to The sensing information of the sensing device 101 is used to capture the vehicle that is about to enter the tunnel, so as to obtain the identity information of the target vehicle (such as the license plate number of the vehicle). In the context of the present disclosure, the vehicle entering the tunnel is the target vehicle, and the solution of the present disclosure aims to monitor such one or more target vehicles, so as to determine the violating vehicle that violates the driving regulations in the tunnel. According to different implementation manners, the capture device of the present disclosure may be various types of cameras. As a preferred solution, the camera may be a bayonet camera.
在第一感知设备和抓拍设备分别获取了关于车辆(或目标车辆)的信息后,二者可以将所获取的信息传输至本公开的信息处理中心105。在一个实施例中,此处的信息处理中心可以实施为计算单元或模块,并且用于执行信息的处理(包括各种数据的融合操作)以及可选地对互联的各类设备进行主控操作。在操作中,信息处理中心可以根据第一感知设备的感知信息,获取目标车辆的对象特征信息,例如进入隧道的车辆的特征信息。进一步,信息处理中心可以将目标车辆的身份信息和对应的对象特征信息进行绑定,以获得目标车辆的绑定信息,并且将目标车辆的绑定信息记录于车辆查找集合中。以目标车辆是隧道内的机动车辆并且其身份信息是车牌号为例,信息处理中心执行的绑定操作可以是将车牌号与该机动车辆的具体特征(例如车辆的车型、颜色或类别)进行绑定,并且将这样的绑定信息(类似于映射对应关系)记录于车辆查找集合中,例如存储于专用的数据库中。由此,本公开的方案为进入到隧道的车辆建立了可以进行查询的有效途径。After the first sensing device and the capture device respectively acquire information about the vehicle (or target vehicle), they can transmit the acquired information to the information processing center 105 of the present disclosure. In one embodiment, the information processing center here can be implemented as a computing unit or module, and is used to perform information processing (including fusion operations of various data) and optionally perform main control operations on various interconnected devices . In operation, the information processing center may acquire object feature information of the target vehicle, such as feature information of a vehicle entering a tunnel, according to the sensing information of the first sensing device. Further, the information processing center can bind the identity information of the target vehicle with the corresponding object feature information to obtain the binding information of the target vehicle, and record the binding information of the target vehicle in the vehicle search set. Taking the target vehicle as an example of a motor vehicle in a tunnel and its identity information as a license plate number, the binding operation performed by the information processing center may be to combine the license plate number with the specific characteristics of the motor vehicle (such as the model, color or category of the vehicle) binding, and record such binding information (similar to the mapping correspondence) in the vehicle lookup set, for example, in a dedicated database. Thus, the solution of the present disclosure establishes an effective way for vehicles entering the tunnel to conduct inquiries.
当目标车辆(例如图1示出的车辆106)行驶入隧道后,为了实现有效地确定违反隧道内行驶规定的违规车辆,本公开的方案提出在隧道内设置第二感知设备107,以实现对 隧道的感知数据采集,该感知数据可以包括关于违规车辆的信息,例如速度信息。在本公开的上下文中,违规可以包括违反针对隧道所设定的行驶规范的行为。例如,违反隧道规定可以涉及以不适当的驾驶速度在隧道内行驶的行为。在一个实施场景中,就感知隧道内的违规车辆而言,本公开的第二感知设备和第一感知设备具有相同的处理能力,因此前文关于第一感知设备的技术描述也同样适用于第二感知设备。When the target vehicle (such as the vehicle 106 shown in FIG. 1 ) drives into the tunnel, in order to effectively determine the violating vehicle that violates the driving regulations in the tunnel, the solution of the present disclosure proposes to set the second sensing device 107 in the tunnel to realize the detection Sensing data collection of tunnels, which may include information about violating vehicles, such as speed information. In the context of the present disclosure, violations may include violations of driving regulations set for a tunnel. For example, a violation of tunnel regulations may involve the act of driving in a tunnel at an inappropriate driving speed. In one implementation scenario, in terms of sensing illegal vehicles in the tunnel, the second sensing device and the first sensing device of the present disclosure have the same processing capability, so the foregoing technical descriptions about the first sensing device are also applicable to the second sensing device. Sensing device.
类似地,该第二感知设备也可以将感知信息传送到信息处理中心,以便由其获取违规车辆的对象特征信息,并且根据违规车辆的对象特征信息从前述的车辆查找集合的绑定信息中获取目标绑定信息。接着,信息处理中心可以基于目标绑定信息获取违规车辆的身份信息。在确定违规车辆的身份信息后,信息处理中心可以输出违规车辆的身份信息和对应的违规行为。根据不同的实施方式,该输出方式可以为视频显示。在一个实施场景中,可以在隧道内的不同区段布置(例如在隧道内壁上悬挂)多个大显示屏(如图中的108所示),以便由信息处理中心来选择违规车辆即将行驶经过的一个大显示屏进行显示播报。Similarly, the second sensing device can also transmit the sensing information to the information processing center, so that it can obtain the object characteristic information of the violating vehicle, and obtain it from the binding information of the aforementioned vehicle search set according to the object characteristic information of the violating vehicle Target binding information. Then, the information processing center can obtain the identity information of the violating vehicle based on the target binding information. After determining the identity information of the violating vehicle, the information processing center can output the identity information of the violating vehicle and the corresponding violation behavior. According to different implementation manners, the output mode may be video display. In an implementation scenario, a plurality of large display screens (as shown by 108 in the figure) can be arranged in different sections of the tunnel (for example, hung on the inner wall of the tunnel), so that the information processing center can select the violating vehicle to pass by. A large display screen for display broadcast.
图2是示意性示出其中应用本公开的用于识别违规交通参与对象的方案的又一示例性场景200的示图。可以理解的,图2示例性场景示出为服务区场景。进一步,在本公开的上下文中,前述的交通参与对象可以是与道路活动/交通活动相关的对象,例如机动车辆和/或非机动车辆等。FIG. 2 is a diagram schematically illustrating yet another exemplary scenario 200 in which the scheme for identifying traffic violation participants of the present disclosure is applied. It can be understood that the exemplary scenario shown in FIG. 2 is a service area scenario. Further, in the context of the present disclosure, the aforementioned traffic participation objects may be objects related to road activities/traffic activities, such as motor vehicles and/or non-motor vehicles.
如图2所示,根据本公开的方案,可以在服务区的入口处设置有第一感知设备101,其配置用于采集其业务覆盖范围内的感知信息。在一个实施场景中,该第一感知设备可以包括激光雷达(图2中以圆点示出)和/或摄像机。在激光雷达和摄像机配合使用的应用场景中,激光雷达和摄像机可以用于获取同一时刻、同一场景下的点云数据和视频数据。当对点云数据和视频数据分别进行目标检测,并且对检测结果进行融合时,就可以得到初始融合结果。当目标为交通参与者并且该交通参与者是车辆时,前述的初始融合结果可以例如包括关于车辆(如图2中所示车辆102和103)的各类信息,包括但不限于以下中的一项或多项:感知区域内的车辆的身份(ID)信息、车辆类别信息、车辆位置信息、车辆所处车道信息、车辆感知时刻信息、车辆尺寸信息、车辆速度信息、前车车头间距(如图5中501处所示)、前车车尾间距(如图5中502处所示)和/或车辆图像特征信息。As shown in FIG. 2 , according to the solution of the present disclosure, a first sensing device 101 may be set at the entrance of the service area, which is configured to collect sensing information within its service coverage. In an implementation scenario, the first sensing device may include a laser radar (shown by a dot in FIG. 2 ) and/or a camera. In the application scenario where the lidar and the camera are used together, the lidar and the camera can be used to obtain point cloud data and video data at the same time and in the same scene. When target detection is performed on point cloud data and video data respectively, and the detection results are fused, the initial fusion result can be obtained. When the target is a traffic participant and the traffic participant is a vehicle, the aforementioned initial fusion result may, for example, include various types of information about the vehicle (such as vehicles 102 and 103 shown in FIG. 2 ), including but not limited to one of the following One or more items: the identity (ID) information of the vehicle in the sensing area, the vehicle category information, the vehicle position information, the vehicle lane information, the vehicle perception time information, the vehicle size information, the vehicle speed information, the distance between the front vehicle (such as 501 in FIG. 5 ), the distance between the front and the rear of the vehicle (as shown at 502 in FIG. 5 ), and/or vehicle image feature information.
进一步,沿交通参与对象进入场景内的方向,也即本例中沿车辆驶入服务区的方向,在第一感知设备的后方一定距离内设置有抓拍设备104,其用于基于第一感知设备101的感知信息来对进入到服务区内的交通参与对象进行抓拍,以便获取目标交通参与对象的身份信息(例如车辆的车牌号)。在本公开的上下文,进入到服务区的交通参与对象也即是目标交通参与对象,而本公开的方案旨在对这样的一个或多个目标交通参与对象进行监视,以便确定违反服务区规定的违规交通参与对象。根据不同的实施方案,本公开的抓拍设备可以是各种类型的相机。作为优选方案,该相机可以是卡口相机。Further, along the direction of the traffic participation object entering the scene, that is, along the direction of the vehicle driving into the service area in this example, a capture device 104 is set within a certain distance behind the first sensing device, which is used to 101 perception information to capture the traffic participating objects entering the service area, so as to obtain the identity information of the target traffic participating objects (such as the license plate number of the vehicle). In the context of the present disclosure, the traffic participating objects entering the service area are also the target traffic participating objects, and the scheme of the present disclosure aims to monitor such one or more target traffic participating objects, so as to determine violations of service area regulations Objects involved in traffic violations. According to different implementations, the capture device of the present disclosure may be various types of cameras. As a preferred solution, the camera may be a bayonet camera.
在第一感知设备和抓拍设备分别获取了关于交通参与对象或目标交通参与对象的信息后,二者可以将所获取的信息传输至本公开的信息处理中心105。此后,本公开的信息处理中心可以根据第一感知设备的感知信息,获取目标交通参与对象的对象特征信息,例如进入服入区的车辆的特征信息。进一步,信息处理中心可以将目标交通参与对象的身份信息和对应的对象特征信息进行绑定,以获得目标交通参与对象的绑定信息,并且将目标交通参与对象的绑定信息记录于交通参与对象查找集合中。以目标交通参与对象是服务区内的机动车辆并且其身份信息是车牌号为例,信息处理中心执行的绑定操作可以是将车牌号 与该机动车辆的具体特征(例如车辆的车型、颜色或类别)进行绑定,并且将这样的绑定信息(类似于映射对应关系)记录于交通参与对象查找集合中,例如存储于专用的数据库中。由此,本公开的方案为进入到场景内(如本例中的服务区)的交通参与对象(如本例中的车辆)建立了可以进行查询的有效途径。After the first sensing device and the capture device respectively acquire information about the traffic participating object or the target traffic participating object, they can transmit the acquired information to the information processing center 105 of the present disclosure. Thereafter, the information processing center of the present disclosure may acquire object feature information of the target traffic participating object, such as feature information of vehicles entering the service area, according to the sensing information of the first sensing device. Further, the information processing center can bind the identity information of the target traffic participation object with the corresponding object feature information to obtain the binding information of the target traffic participation object, and record the binding information of the target traffic participation object in the traffic participation object Find in the collection. Taking the example where the target traffic participant is a motor vehicle in the service area and its identity information is the license plate number, the binding operation performed by the information processing center can be to combine the license plate number with the specific characteristics of the motor vehicle (such as the vehicle model, color or category), and record such binding information (similar to the mapping correspondence) in the traffic participation object lookup set, for example, stored in a dedicated database. Thus, the solution of the present disclosure establishes an effective way for the traffic participating objects (such as the vehicle in this example) entering the scene (such as the service area in this example) to conduct inquiries.
当目标交通参与对象(例如图2下部示出的多个车辆)停靠于服务区内后,为了实现有效地确定违反服务区停车规定的违规交通参与者,本公开的方案提出在相对于服务区入口的服务区内设置第二感知设备107,以实现对服务区内的感知数据采集,该感知数据可以包括关于违规交通参与对象的信息。在本公开的上下文中,违规可以包括违反针对场景所设定的规范的行为。就服务区而言,违反服务区规定可以涉及错误停靠的行为。在一个实施场景中,就感知服务区内的违规交通参与者而言,本公开的第二感知设备和第一感知设备具有相同的处理能力,因此前文关于第一感知设备的技术描述也同样适用于第二感知设备。When the target traffic participation objects (such as the multiple vehicles shown in the lower part of Figure 2) park in the service area, in order to effectively determine the violating traffic participants who violate the parking regulations in the service area, the scheme of the present disclosure proposes to The second sensing device 107 is set in the service area of the entrance to realize the collection of sensing data in the service area, and the sensing data may include information about illegal traffic participants. In the context of the present disclosure, a violation may include behavior that violates the norms set for the scene. As far as service areas are concerned, violations of service area regulations may involve wrong stops. In one implementation scenario, in terms of sensing violating traffic participants in the service area, the second sensing device and the first sensing device of the present disclosure have the same processing capability, so the above technical description about the first sensing device is also applicable on the second sensing device.
类似地,该第二感知设备也可以将感知信息传送到信息处理中心,以便由其获取违规交通参与对象的对象特征信息,并且根据违规交通参与对象的对象特征信息从前述的交通参与对象查找集合的绑定信息中获取目标绑定信息。接着,信息处理中心可以基于目标绑定信息获取违规交通参与对象的身份信息。在确定违规交通参与对象的身份信息后,信息处理中心可以输出违规交通参与对象的身份信息和对应的违规行为。根据不同的实施方式,该输入方式可以是语音播报或视频显示,或者二者的结合。在一个场景中,可以在服务区内布置有多个大显示屏,以便由信息处理中心来选择离距离违规交通参与者最近的一个大显示屏进行显示播报。Similarly, the second sensing device can also transmit the sensing information to the information processing center, so that it can obtain the object feature information of the violating traffic participating object, and search the set from the aforementioned traffic participating object according to the object feature information of the violating traffic participating object The target binding information is obtained from the binding information of the . Then, the information processing center can obtain the identity information of the object involved in the illegal traffic based on the target binding information. After determining the identity information of the violating traffic participant, the information processing center can output the identity information of the violating traffic participant and the corresponding violation behavior. According to different implementations, the input method may be voice announcement or video display, or a combination of both. In one scenario, multiple large display screens can be arranged in the service area, so that the information processing center can select a large display screen closest to the violating traffic participant to display and broadcast.
以上结合图1和图2对本公开的方案进行了描述,可以理解的是上面的描述仅仅是示例性的而非限制性的,本领域技术人员根据本公开的教导可以对图1和图2中所示场景进行改变而不脱离本公开的精神和实质。例如,尽管图中将信息处理中心示出为与第一感知设备、第二感知设备和抓拍设备相分离,但在一些场景中,也可以选择将信息处理中心布置于靠近于三者之一,从而减少数据传输的距离并且提升数据传输的稳定性。进一步,也可以将信息处理中心布置于远端(例如云端)。在该情形下,可以将远端确定的违规交通参与者身份信息和违规信息发送到场景内的播报设备处,以便及时提醒违规者(例如车主)注意并对违规行为做出纠正。The solution of the present disclosure has been described above in conjunction with FIG. 1 and FIG. 2 . It can be understood that the above description is only exemplary and not restrictive. Changes may be made from the scenes shown without departing from the spirit and substance of the disclosure. For example, although the information processing center is shown in the figure as being separated from the first sensing device, the second sensing device and the capture device, in some scenarios, the information processing center may also be selected to be arranged close to one of the three, Thereby reducing the distance of data transmission and improving the stability of data transmission. Further, the information processing center can also be arranged at the remote end (such as the cloud). In this case, the identity information of the violating traffic participant and the violation information determined at the remote end can be sent to the broadcasting device in the scene, so as to promptly remind the violator (such as the car owner) to pay attention to and correct the violation.
图3是示意性示出根据本公开实施例的用于识别违规交通参与对象的方法300的流程图。可以理解的是图3中所示出的方法流程可以在图1中所示出的示例性的隧道场景中实施,因此关于图1所描述内容(例如关于感知设备)也同样适用于图3。Fig. 3 is a flow chart schematically showing a method 300 for identifying traffic violation participants according to an embodiment of the present disclosure. It can be understood that the method flow shown in FIG. 3 can be implemented in the exemplary tunnel scenario shown in FIG. 1 , so the content described in FIG. 1 (for example, about the sensing device) is also applicable to FIG. 3 .
如图3中所示,在步骤S301处,获取隧道入口处第一感知设备(如图1中的第一感知设备101)的感知信息。如前所述,当第一感知设备实施为激光雷达和摄像机时,该感知信息可以包括感知范围内的点云数据和视频数据。As shown in FIG. 3 , at step S301 , the sensing information of a first sensing device (such as the first sensing device 101 in FIG. 1 ) at a tunnel entrance is acquired. As mentioned above, when the first sensing device is implemented as a lidar and a camera, the sensing information may include point cloud data and video data within the sensing range.
接着,在步骤S302处,基于第一感知设备的感知信息对目标车辆进行抓拍,以获取该目标车辆的身份信息。如前所述,该抓拍动作可以例如由图1中所示抓拍设备104执行。为了实现精确地抓拍以便获取准确的身份信息,本公开提出设置远端抓拍位置和近端抓拍位置,从而可以基于第一感知设备的感知信息选择在远端抓拍位置或近端抓拍位置对目标车辆进行抓拍。关于具体的抓拍操作,稍后将结合图5进行详细地描述。Next, at step S302, the target vehicle is captured based on the sensing information of the first sensing device, so as to obtain the identity information of the target vehicle. As mentioned above, the snapping action can be performed, for example, by the snapping device 104 shown in FIG. 1 . In order to achieve precise capture in order to obtain accurate identity information, this disclosure proposes to set the remote capture position and the near-end capture position, so that the target vehicle can be selected at the far-end capture position or the near-end capture position based on the perception information of the first sensing device. Take a snapshot. The specific capture operation will be described in detail later with reference to FIG. 5 .
在获取目标车辆的身份信息后,在步骤S303处,可以根据第一感知设备的感知信息获 取目标车辆的对象特征信息。如前所述,该对象特征信息例如可以包括关于隧道内车辆的ID、类别、位置、车道、前车车头间距、前车车尾间距和/或车辆图像特征信息。接着,流程前进到步骤S304处,将目标车辆的身份信息和对应的对象特征信息进行绑定,以获得目标车辆的绑定信息,并且在步骤S305处,将目标车辆的绑定信息记录于车辆查找集合(例如数据库)中。After obtaining the identity information of the target vehicle, at step S303, the object feature information of the target vehicle can be obtained according to the sensing information of the first sensing device. As mentioned above, the object feature information may include, for example, ID, category, location, lane, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information about the vehicle in the tunnel. Next, the process proceeds to step S304, where the identity information of the target vehicle is bound with the corresponding object feature information to obtain the binding information of the target vehicle, and at step S305, the binding information of the target vehicle is recorded in the vehicle Lookup in a collection (such as a database).
接着,在步骤S306处,可以获取隧道内第二感知设备的感知信息。该第二感知设备例如是图1中所示出的第二感知设备107。在操作中,该第二感知设备对包括隧道内的目标车辆进行感知操作,从而得到隧道内的目标车辆的感知信息。进一步,在步骤S307处,可以根据第二感知设备的感知信息中的速度信息来识别出违规车辆,以便获取违规车辆的对象特征信息。Next, at step S306, the sensing information of the second sensing device in the tunnel may be acquired. The second sensing device is, for example, the second sensing device 107 shown in FIG. 1 . In operation, the second sensing device performs sensing operation on the target vehicle in the tunnel, so as to obtain the sensing information of the target vehicle in the tunnel. Further, at step S307, the violating vehicle may be identified according to the speed information in the sensing information of the second sensing device, so as to obtain object characteristic information of the violating vehicle.
为了识别出违规车辆,在一个实施场景中,可以根据第二感知设备的感知信息获取隧道内的目标车辆的速度信息。接着,响应于速度信息的指示来判断目标车辆是否违反了隧道内的行驶规定。例如,当目标车辆的速度为零,也即目标车辆在隧道内停止行驶从而潜在导致隧道内发生拥塞和车辆碰撞风险,则将目标车辆识别为违规车辆。类似地,当目标车辆的速度信息指示其速度低于最低限速或高于最高限速时,也将目标车辆相应地识别为存在违规慢行或超速行驶的违规车辆。In order to identify the violating vehicle, in an implementation scenario, the speed information of the target vehicle in the tunnel may be acquired according to the sensing information of the second sensing device. Next, it is judged whether the target vehicle violates the driving regulations in the tunnel in response to the indication of the speed information. For example, when the speed of the target vehicle is zero, that is, the target vehicle stops driving in the tunnel, thereby potentially causing congestion and vehicle collision risks in the tunnel, the target vehicle is identified as a violating vehicle. Similarly, when the speed information of the target vehicle indicates that its speed is lower than the minimum speed limit or higher than the maximum speed limit, the target vehicle is correspondingly identified as a violating vehicle with illegal slow-moving or speeding.
在通过上述的各种方式识别出违规车辆并从而获得其对象特征信息后,流程前进到步骤S308。在步骤S308处,可以根据违规车辆的对象特征信息从步骤S305中更新的车辆查找集合的绑定信息中获取目标绑定信息。接着,在步骤S309处,可以基于该目标绑定信息获取违规车辆的身份信息,从而在步骤S310处,可以输出违规车辆的身份信息和对应的违规行为。在一个实施例中,针对所述违规车辆生成与违规停滞行为(即速度为零)、违规慢行行为(即速度低于最低限速)或违规超速行为(即速度高于最高限速)之一关联的违规信息,以及根据该违规车辆的位置信息向所述违规车辆播报所述违规信息,从而可以有效地对违规车辆进行提醒和警告。After the violating vehicle is identified through the above-mentioned various methods and its object characteristic information is obtained, the process proceeds to step S308. At step S308, the target binding information may be obtained from the binding information of the vehicle search set updated in step S305 according to the object feature information of the violating vehicle. Next, at step S309, the identity information of the violating vehicle can be obtained based on the target binding information, so that at step S310, the identity information of the violating vehicle and the corresponding violation behavior can be output. In one embodiment, for the illegal vehicle generation and the illegal stagnation behavior (that is, the speed is zero), the illegal slow-moving behavior (that is, the speed is lower than the minimum speed limit) or the violation of the speeding behavior (that is, the speed is higher than the maximum speed limit) An associated violation information, and broadcast the violation information to the violation vehicle according to the location information of the violation vehicle, so that the violation vehicle can be effectively reminded and warned.
图4是示意性示出根据本公开实施例的用于识别违规交通参与对象的方法400的又一流程图。可以理解的是图4中所示出的方法流程可以在图2中所示出的示例性的服务器场景中实施,因此关于图2所描述内容(例如关于感知设备)也同样适用于图4。Fig. 4 is another flowchart schematically showing a method 400 for identifying traffic violation participants according to an embodiment of the present disclosure. It can be understood that the method flow shown in FIG. 4 can be implemented in the exemplary server scenario shown in FIG. 2 , so the content described in FIG. 2 (for example, about the sensing device) is also applicable to FIG. 4 .
如图4中所示,在步骤S401处,获取场景入口处第一感知设备(如图2中的第一感知设备101)的感知信息。如前所述,在一个实施例中,该场景可以是服务区场景。As shown in FIG. 4 , at step S401 , the sensing information of a first sensing device (such as the first sensing device 101 in FIG. 2 ) at a scene entrance is acquired. As mentioned above, in an embodiment, the scenario may be a service area scenario.
接着,在步骤S402处,基于第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取目标交通参与对象的身份信息。如前所述,该抓拍动作可以例如由图2中所示抓拍设备104执行。为了实现精确地抓拍以便获取准确的身份信息,本公开提出设置远端抓拍位置和近端抓拍位置,从而可以基于第一感知设备的感知信息选择在远端抓拍位置或近端抓拍位置对目标交通参与对象进行抓拍。关于具体的抓拍操作,稍后将结合图5进行详细地描述。Next, at step S402, a snapshot is taken of the target traffic participating object based on the sensing information of the first sensing device, so as to obtain identity information of the target traffic participating object. As mentioned above, the snapping action can be performed, for example, by the snapping device 104 shown in FIG. 2 . In order to achieve accurate snapshots in order to obtain accurate identity information, the present disclosure proposes to set the far-end capture position and the near-end capture position, so that the target traffic can be selected at the far-end capture position or the near-end capture position based on the sensing information of the first sensing device. Participating objects are captured. The specific capture operation will be described in detail later with reference to FIG. 5 .
在获取目标交通参与对象的身份信息后,在步骤S403处,可以根据第一感知设备的感知信息获取目标交通参与对象的对象特征信息。如前所述,该对象特征信息例如可以包括关于场景内交通参与对象的ID、类别、位置、车道、前车车头间距、前车车尾间距和/或车辆图像特征信息。接着,流程前进到步骤S404处,将目标交通参与对象的身份信息和对应的对象特征信息进行绑定,以获得目标交通参与对象的绑定信息,并且在步骤S405 处,将目标交通参与对象的绑定信息记录于交通参与对象查找集合(例如数据库)中。After acquiring the identity information of the target traffic participating object, at step S403, the object feature information of the target traffic participating object may be acquired according to the sensing information of the first sensing device. As mentioned above, the object feature information may include, for example, ID, category, location, lane, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information about the traffic participating objects in the scene. Next, the process proceeds to step S404, where the identity information of the target traffic participant object is bound with the corresponding object characteristic information to obtain the binding information of the target traffic participant object, and at step S405, the target traffic participant object’s Binding information is recorded in a traffic participation object lookup set (eg, a database).
接着,在步骤S406处,可以获取场景内第二感知设备的感知信息。该第二感知设备例如是图2中所示出的第二感知设备107。在操作中,该第二感知设备对包括场景内的目标交通参与对象进行感知操作,从而得到场景内的目标交通参与者的感知信息。进一步,在步骤S407处,可以根据第二感知设备的感知信息来识别出违规交通参与对象,以便获取违规交通参与对象的对象特征信息。Next, at step S406, the sensing information of the second sensing device in the scene may be acquired. The second sensing device is, for example, the second sensing device 107 shown in FIG. 2 . In operation, the second sensing device performs sensing operations on the target traffic participants in the scene, so as to obtain the sensing information of the target traffic participants in the scene. Further, at step S407, the violating traffic participating object may be identified according to the sensing information of the second sensing device, so as to obtain object characteristic information of the violating traffic participating object.
为了识别出违规交通参与者,在一个实施场景中,可以根据第二感知设备的感知信息获取场景内的目标交通参与对象的对象特征信息、位置信息和速度信息,其中对象特征信息至少包括类别信息。接着,响应于速度信息指示目标交通参与对象的速度为零并且目标交通参与对象的类别信息与场景内的预设区域的类别信息不匹配,将目标交通参与对象识别为违规交通参与对象。以场景为服务区并且目标交通参与者的类别信息为轿车为例,当其停靠于预设用于停靠货车的停车区域时,则该目标交通参与者(也即本例的一辆轿车)将被判定为违反了服务区的停车规定,从而其成为本公开上下文所称的违规交通参与对象。附加地或替代地,响应于速度信息指示目标交通参与对象的速度为零并且目标交通参与对象的位置信息与场景内的预设区域的位置不匹配,将目标交通参与对象识别为违规交通参与对象。例如,当感知信息中的位置信息指示车辆停靠的位置并不是服务区预设的停车位置。换句话说,此时车辆停靠在服务区内的非停车区域,例如行人通道或消防通道处,因此其也将被判定为违规交通参与者。In order to identify illegal traffic participants, in an implementation scenario, the object characteristic information, position information and speed information of the target traffic participating objects in the scene can be acquired according to the perception information of the second sensing device, wherein the object characteristic information includes at least category information . Next, in response to the speed information indicating that the speed of the target traffic participating object is zero and the category information of the target traffic participating object does not match the category information of the preset area in the scene, the target traffic participating object is identified as an illegal traffic participating object. Taking the scene as the service area and the category information of the target traffic participant as a car as an example, when it parks in the parking area preset for parking trucks, the target traffic participant (that is, a car in this example) will It is judged to have violated the parking regulations in the service area, so it becomes the object of violation traffic participation in the context of this disclosure. Additionally or alternatively, in response to the speed information indicating that the speed of the target traffic participating object is zero and the position information of the target traffic participating object does not match the position of a preset area within the scene, identifying the target traffic participating object as an illegal traffic participating object . For example, when the location information in the perception information indicates that the location where the vehicle is parked is not the preset parking location in the service area. In other words, at this time the vehicle is parked in a non-parking area within the service area, such as a pedestrian passage or a fire exit, so it will also be judged as a traffic participant in violation.
在通过上述的各种方式识别出违规交通参与者并从而获得其对象特征信息后,流程前进到步骤S408。在步骤S408处,可以根据违规交通参与对象的对象特征信息从步骤S405中更新的交通参与对象查找集合的绑定信息中获取目标绑定信息。接着,在步骤S409处,可以基于该目标绑定信息获取违规交通参与对象的身份信息,从而在步骤S410处,可以输出违规交通参与对象的身份信息和对应的违规行为。在一个实施例中,可以针对违规交通参与对象生成与类别信息不匹配或位置不匹配相关联的违规信息。接着,可以根据违规交通参与对象的位置信息来定向地对违规交通参与对象播报违规信息,从而可以有效地对违规交通参与者进行提醒和警告。After the violating traffic participant is identified through the above-mentioned various methods and thus the object feature information is obtained, the process proceeds to step S408. At step S408, the target binding information may be obtained from the binding information of the traffic participation object lookup set updated in step S405 according to the object characteristic information of the violation traffic participation object. Next, at step S409, the identity information of the violating traffic participant can be obtained based on the target binding information, so that at step S410, the identity information of the violating traffic participant and the corresponding violation behavior can be output. In one embodiment, violation information associated with category information mismatch or location mismatch may be generated for the violation traffic participation object. Then, according to the location information of the violating traffic participating object, the violating information can be directionally broadcast to the violating traffic participating object, so that the violating traffic participants can be effectively reminded and warned.
图5是示意性示出根据本公开实施例的用于场景内执行抓拍操作的示图。仅为了方便描述的目的,下面以交通参与对象为车辆作为示例来描述本公开的抓拍操作。Fig. 5 is a diagram schematically illustrating an operation for performing a snapshot in a scene according to an embodiment of the present disclosure. For the convenience of description only, the following describes the capture operation of the present disclosure by taking a vehicle as an example of the traffic participation object.
如图5中所示,当车辆进入到场景内时,例如图中的机动车辆102和103驶入到服务区或者隧道口时,本公开提出利用抓拍设备104对其进行抓拍,以便获取车辆的身份信息。鉴于此,为了准确无误地识别身份,本公开针对抓拍位置提出远端抓拍位置和近端抓拍位置,并且基于第一感知设备(例如图1或者图2中的第一感知设备101)的感知信息选择在远端抓拍位置(如图5中箭头503所指位置)或近端抓拍位置(如图5中箭头504所指位置)对目标交通参与对象进行抓拍,以获取目标交通参与对象的身份信息。在一个实施方式中,本公开的远端抓拍位置和/或近端抓拍位置还涉及车辆所行驶车道的车道信息。As shown in FIG. 5, when a vehicle enters the scene, for example, when the motor vehicles 102 and 103 in the figure drive into the service area or tunnel entrance, the present disclosure proposes to use the capture device 104 to capture it, so as to obtain the vehicle's Identity Information. In view of this, in order to identify the identity accurately, this disclosure proposes a far-end capture position and a near-end capture position for the capture position, and based on the perception information of the first sensing device (such as the first sensing device 101 in FIG. 1 or FIG. 2 ) Choose to capture the target traffic participation object at the far-end capture position (as indicated by the arrow 503 in Figure 5) or near-end capture position (as indicated by the arrow 504 in Figure 5), to obtain the identity information of the target traffic participation object . In one embodiment, the far-end snapping position and/or the near-end snapping position of the present disclosure also involves lane information of the lane on which the vehicle is driving.
就选择远端抓拍位置或近端抓拍位置而言,本公开提出基于第一感知设备的感知信息获取在抓拍方向上位于目标交通参与对象(即本例中的车辆103)前方的交通参与对象(即本例中的车辆102)的第一间距和尺寸信息,其中第一间距包括目标交通参与对象的前部与其前方交通参与对象的尾部之间的距离(即图中502所示出的间距)。接着,可以根据该第一间距和尺寸信息与预设阈值的比较选择在远端抓拍位置或近端抓拍位置对目标交通参与 对象进行抓拍。换句话说,当车辆满足在远端抓拍位置进行抓拍时,则其进入到远端抓拍位置时,则触发本公开的抓拍设备对其进行抓拍。类似地,满足近端抓拍位置的车辆在其位于近端抓拍位置时,触发抓拍设备对其进行抓拍。In terms of selecting the far-end capture position or the near-end capture position, the present disclosure proposes to obtain the traffic participation object ( That is, the first spacing and size information of the vehicle 102 in this example), wherein the first spacing includes the distance between the front of the target traffic participating object and the rear of the preceding traffic participating object (that is, the spacing shown in 502 in the figure) . Then, according to the comparison between the first distance and size information and the preset threshold, the target traffic participating object can be captured at the far-end capture position or the near-end capture position. In other words, when the vehicle meets the requirements for capturing at the remote capturing position, when it enters the remote capturing position, the capturing device of the present disclosure is triggered to capture the vehicle. Similarly, when a vehicle meeting the near-end capture position is located at the near-end capture position, the capture device is triggered to capture the vehicle.
在一个实现方式中,根据上述第一间距和尺寸信息与预设阈值的比较选择在远端抓拍位置或近端抓拍位置对目标交通参与对象进行抓拍包括:响应于第一间距小于第一预设阈值并且前方交通参与对象的高度大于第二预设阈值,选择近端抓拍位置对目标交通参与对象进行抓拍。与前述条件相反,响应于第一间距大于第一预设阈值,则可以选择远端抓拍位置对目标交通参与对象进行抓拍。或者,响应于第一间距小于第一预设阈值并且前方交通参与对象的高度小于第二预设阈值,选择远端抓拍位置对目标交通参与对象进行抓拍。In an implementation manner, selecting to capture the target traffic participant object at the far-end capture position or the near-end capture position according to the comparison between the above-mentioned first distance and size information and the preset threshold includes: responding to the first distance being smaller than the first preset threshold and the height of the traffic participating object in front is greater than the second preset threshold, select the near-end capture position to capture the target traffic participating object. Contrary to the foregoing conditions, in response to the first distance being greater than the first preset threshold, a remote capture position may be selected to capture the target traffic participant object. Or, in response to the fact that the first distance is smaller than the first preset threshold and the height of the preceding traffic participating object is smaller than the second preset threshold, a remote capture position is selected to capture the target traffic participating object.
下面以图5中的货车103为具体抓拍对象为例来描述本公开的抓拍操作。在货车103和轿车102驶入进服务区内前,二者已经在服务区或者隧道的入口处由第一感知设备进行感知,由此获取到包含二者的感知信息。接着,例如图1中的信息处理中心在获取到前述的感知信息后,其可以根据该感知信息来对轿车车尾间距(也即图中502所示间距)和轿车高度(也即上述的尺寸信息)进行判断。当轿车车尾间距小于第一预设阈值并且轿车高度大于第二预设阈值时,则信息处理中心可以将触发位置选择为近端抓拍位置(如图5中箭头504所指位置)。The capture operation of the present disclosure will be described below by taking the truck 103 in FIG. 5 as a specific capture object as an example. Before the truck 103 and the car 102 drive into the service area, they have already been sensed by the first sensing device at the entrance of the service area or tunnel, thereby obtaining sensing information including both. Then, for example, after the information processing center in Fig. 1 obtains the aforementioned perception information, it can determine the distance between the rear of the car (that is, the distance shown in 502 in the figure) and the height of the car (that is, the above-mentioned size) according to the perception information. information) to judge. When the distance between the rear of the car is less than the first preset threshold and the height of the car is greater than the second preset threshold, the information processing center can select the trigger position as the near-end capture position (as indicated by arrow 504 in FIG. 5 ).
上面结合图5对本公开的抓拍操作进行了详细地描述。在确定抓拍位置后,为了精准地识别出服务区或者隧道内的目标交通参与对象的身份信息,在一个实施方式中,本公开还提出根据感知信息和抓拍位置确定用于对目标交通参与对象进行抓拍和识别的抓拍识别框。由此,可以在抓拍位置处利用该抓拍识别框对目标交通参与对象进行抓拍和识别,以获取目标交通参与对象的身份信息。在一个实施方式中,为了确定抓拍识别框,本公开提出根据感知信息(即第一感知设备所采集的感知信息)获取在抓拍方向上位于目标交通参与对象前方的交通参与对象的第二间距,其中第二间距包括目标交通参与对象的前部与其前方交通参与对象的前部之间的距离(也即图5中501所示出的间距),并且接着可以基于抓拍位置和第二间距确定抓拍识别框,以便对车辆进行抓拍和识别。例如,抓拍设备可以根据选择的抓拍位置(其包括车道信息)和确定的抓拍识别框来对车辆的车牌进行识别,从而得到车辆的身份信息。由此,本公开通过抓拍操作来提供场景内目标交通参与者的有效识别,从而为后续的绑定和违规交通参与者的确定提供了良好的基础。The snapshot operation of the present disclosure has been described in detail above with reference to FIG. 5 . After determining the capture position, in order to accurately identify the identity information of the target traffic participant in the service area or tunnel, in one embodiment, the present disclosure also proposes to determine the target traffic participant based on the perception information and the capture position. Snapshot recognition frame for snapping and recognition. Thus, the capture recognition frame can be used at the capture position to capture and identify the target traffic participant, so as to obtain the identity information of the target traffic participant. In one embodiment, in order to determine the snapshot recognition frame, the present disclosure proposes to obtain the second distance of the traffic participation object located in front of the target traffic participation object in the capture direction according to the sensing information (ie, the sensing information collected by the first sensing device), Wherein the second distance includes the distance between the front part of the target traffic participating object and the front part of the traffic participating object in front thereof (that is, the distance shown in 501 in Figure 5), and then the snapping position can be determined based on the snapping position and the second distance The recognition frame is used to capture and recognize the vehicle. For example, the capture device can recognize the license plate of the vehicle according to the selected capture position (which includes lane information) and the determined capture recognition frame, so as to obtain the identity information of the vehicle. Therefore, the present disclosure provides effective identification of target traffic participants in the scene through the snapshot operation, thereby providing a good basis for subsequent binding and determination of violating traffic participants.
图6是示意性示出根据本公开实施例的用于识别违规交通参与对象的系统600的示意框图。可以理解的是,图6所示系统仅仅是本公开方案的一种实现方式,本领域技术人员根据本公开的教导也可以想到对系统600进行改动以适应不同的应用场景。进一步,由于图6是对图1、图2所示系统的简化示出,因此关于图1、图2的描述同样适用于针对图6的描述。Fig. 6 is a schematic block diagram schematically showing a system 600 for identifying illegal traffic participating objects according to an embodiment of the present disclosure. It can be understood that the system shown in FIG. 6 is only an implementation of the solution of the present disclosure, and those skilled in the art may also think of making changes to the system 600 to adapt to different application scenarios according to the teaching of the present disclosure. Further, since FIG. 6 is a simplified illustration of the system shown in FIG. 1 and FIG. 2 , the description about FIG. 1 and FIG. 2 is also applicable to the description for FIG. 6 .
如图6所示,系统600包括第一感知设备101、抓拍设备104、第二感知设备107、信息处理中心105和违规播报设备601。如前所述,第一感知设备101、抓拍设备104、第二感知设备107和信息处理中心105协同操作,以确定出场景内的违规交通参与者,而违规播放设备(例如图1中所示出的大屏显示器108)用于对违规交通参与者进行播报,例如针对违规交通参与者来进行定向地播报,从而提醒其对违规操作进行及时纠正。As shown in FIG. 6 , the system 600 includes a first sensing device 101 , a capture device 104 , a second sensing device 107 , an information processing center 105 and a violation reporting device 601 . As mentioned above, the first sensing device 101, the capture device 104, the second sensing device 107, and the information processing center 105 cooperate to determine the violating traffic participants in the scene, and the violating playback device (such as shown in FIG. 1 The large-screen display 108) is used to broadcast to the violating traffic participants, for example, to carry out directional broadcasting for the violating traffic participants, thereby reminding them to correct the violating operation in time.
尽管上文中以多个设备和信息处理中心的方式描述了本公开的系统架构,但在一些实现场景中,本公开也可以采用模块化的设计来实现。Although the above describes the system architecture of the present disclosure in the form of multiple devices and information processing centers, in some implementation scenarios, the present disclosure may also be implemented using a modular design.
例如,本公开的第一感知设备和第二感知设备可以分别构成场景入口多源感知模块和场景内多源感知模块,二者可以实时感知检测区域内的交通参与者(例如车辆),从而得到关于车辆的感知信息,包括但不限于车辆的ID、类别、位置、车道、感知时刻、尺寸、速度信息、前车车头间距、前车车尾间距和/或车辆图像特征信息。For example, the first sensing device and the second sensing device of the present disclosure can respectively constitute a scene entrance multi-source sensing module and a scene multi-source sensing module, both of which can sense traffic participants (such as vehicles) in the detection area in real time, thus obtaining Perception information about the vehicle, including but not limited to the vehicle's ID, category, location, lane, perception moment, size, speed information, distance between the head of the vehicle in front, distance between the rear of the vehicle in front and/or vehicle image feature information.
再例如,本公开的抓拍和识别操作也可以通过触发位置选择模块、触发抓拍模块和车牌识别模块来实现。具体来说,触发位置选择模块可以根据入口车辆感知信息的前车车尾间距和前车高度进行判断。当车尾间距小于预设阈值并且前车高度大于预设阈值时,则将触发位置选择为近端抓拍位置;否则,将触发区域选择为远端抓拍位置。附加地,触发位置选择模块还可以更新场景入口处车辆的感知信息,包括选择的抓拍位置。For another example, the capture and recognition operations of the present disclosure may also be implemented by triggering the position selection module, triggering the capture module and the license plate recognition module. Specifically, the trigger position selection module can make a judgment according to the distance between the rear of the front vehicle and the height of the front vehicle of the incoming vehicle perception information. When the distance between the rear of the vehicle is less than the preset threshold and the height of the front vehicle is greater than the preset threshold, the trigger position is selected as the near-end capture position; otherwise, the trigger area is selected as the far-end capture position. Additionally, the trigger position selection module can also update the perception information of the vehicle at the entrance of the scene, including the selected capture position.
进一步,上述的触发抓拍模块可以根据入口车辆感知信息的车辆位置进行判断。当车辆刚进入触发区域,触发抓拍模块可以根据入口车辆感知信息的前车车头间距和抓拍位置,选择预设的识别框位置。接着,触发抓拍模块可以给车牌识别模块发送触发抓拍信息,该触发抓拍信息可以包括但不限于车辆的ID、识别框位置、车道和抓拍时刻。响应于接收到触发抓拍信息,车牌识别模块根据触发抓拍信息中的车道信息,在相应车道根据识别框位置对抓拍位置处的车牌进行识别,并输出给信息处理中心,从而得到车辆的身份信息,该身份信息可以包括但不限于车辆的车牌号码和触发抓拍信息。Further, the above-mentioned trigger capture module can make a judgment based on the vehicle position of the incoming vehicle perception information. When the vehicle has just entered the trigger area, the trigger capture module can select the preset recognition frame position according to the distance between the front vehicle and the capture position of the incoming vehicle perception information. Then, the trigger capture module can send trigger capture information to the license plate recognition module, and the trigger capture information can include but not limited to the ID of the vehicle, the position of the identification frame, the lane, and the capture time. In response to receiving the trigger capture information, the license plate recognition module recognizes the license plate at the capture position according to the position of the recognition frame in the corresponding lane according to the lane information in the trigger capture information, and outputs it to the information processing center to obtain the identity information of the vehicle, The identity information may include, but is not limited to, the license plate number of the vehicle and trigger capture information.
针对绑定操作,本公开也可以设置有身份信息绑定模块,其用于根据车辆身份信息的触发抓拍信息中的车辆ID,唯一确定入口车辆感知信息,从而完成车辆身份信息与入口车辆感知信息的绑定。由此,可以经融合形成车辆融合信息,该融合信息可以包括但不限于车辆的ID、类别、位置、感知时刻、尺寸、速度信息、车牌号码和/或车辆图像特征信息。For the binding operation, the present disclosure can also be provided with an identity information binding module, which is used to uniquely determine the entrance vehicle perception information according to the vehicle ID in the trigger capture information of the vehicle identity information, so as to complete the identification of the vehicle identity information and the entrance vehicle perception information. binding. Thus, vehicle fusion information can be formed through fusion, and the fusion information can include but not limited to ID, category, location, perception moment, size, speed information, license plate number and/or vehicle image feature information of the vehicle.
针对违规操作的识别,本公开也可以设置有车辆违规判断模块,其可以用于根据前述车辆融合信息中的速度信息进行判断。例如当速度信息指示车辆速度为0时,则可以认定该车辆违规在隧道内停驶。又例如,当速度信息指示车辆的行驶速度低于规定的最低限速,从而也可以认定该车辆是违规车辆。也可以用于根据前述车辆融合信息中的速度信息进行判断。例如当速度信息指示车辆速度为0时,则可以根据预设的停车区域,并结合融合信息中的位置信息来判断车辆是否在停车区域内。当车辆位置不在停车区域内时,则判定为非法违规停车。进一步,还可以根据预设的停车区类别,结合融合信息中的类别信息来判断车辆是否违规。例如,当车辆位置处于停车区域内但车辆类别与停车区类别不符时,则可以判定其未按照车型停车而构成违规。基于此,可以形成针对于违规车辆的违规信息,该违规信息可以包括但不限于车辆ID、类别、位置、违规时刻、违规类别、车辆尺寸、速度信息、车牌号码或车辆图像特征信息。For the identification of illegal operations, the present disclosure may also be provided with a vehicle violation judging module, which can be used to judge according to the speed information in the aforementioned vehicle fusion information. For example, when the speed information indicates that the vehicle speed is 0, it can be determined that the vehicle has stopped driving in the tunnel in violation of regulations. For another example, when the speed information indicates that the driving speed of the vehicle is lower than the prescribed minimum speed limit, it can also be determined that the vehicle is a violating vehicle. It can also be used to judge according to the speed information in the aforementioned vehicle fusion information. For example, when the speed information indicates that the vehicle speed is 0, it may be determined whether the vehicle is in the parking area according to the preset parking area and combined with the location information in the fusion information. When the position of the vehicle is not within the parking area, it is judged as illegal parking. Further, it is also possible to determine whether the vehicle violates the regulations according to the preset parking area category and in combination with the category information in the fusion information. For example, when the position of the vehicle is in the parking area but the type of the vehicle does not match the type of the parking area, it can be determined that it does not park according to the type of vehicle and constitutes a violation. Based on this, the violation information for the violation vehicle can be formed, the violation information can include but not limited to vehicle ID, category, location, violation time, violation category, vehicle size, speed information, license plate number or vehicle image feature information.
为了实现违规车辆的查找和播报,本公开还可以设置有身份信息查找模块和播报模块。在一个实施例中,身份信息查找模块可以根据前述违规信息中的车辆类别、尺寸、车辆图像特征信息等在车辆融合信息中匹配属于自身的身份信息,从而形成违规播报信息,该信息可以包括但不限于车辆的ID、类别、位置、违规时刻、违规类别、尺寸、速度信息和/或车牌号码。此后,播放模块可以根据违规播报信息,结合违规播报信息中的位置信息,自动选择离违规车辆最近的广播设备或显示大屏,按照车牌号码进行违规类别播报。例如,对于违规停车的车辆,可以选择离车辆最近的广播设备或显示大屏对其进行播放违规消息。对于超速或低速行驶的车辆,则可以指示该车辆即将行驶经过的隧道路段上的广播设备或显示大屏对其违规行为进行播报,以及时提醒驾驶人员纠正其违规行为。In order to realize the search and broadcast of violating vehicles, the present disclosure can also be provided with an identity information search module and a broadcast module. In one embodiment, the identity information search module can match its own identity information in the vehicle fusion information according to the vehicle category, size, and vehicle image feature information in the aforementioned violation information, so as to form violation broadcast information, which may include but Not limited to the vehicle's ID, class, location, time of violation, category of violation, size, speed information and/or license plate number. Afterwards, the playback module can automatically select the nearest broadcast device or display a large screen to the violation vehicle according to the violation broadcast information and combined with the location information in the violation broadcast information, and broadcast the violation category according to the license plate number. For example, for a vehicle that parks illegally, you can choose the broadcasting device closest to the vehicle or display a large screen to play the violation message. For a vehicle traveling at a speeding or low speed, it is possible to instruct the broadcasting device on the tunnel section that the vehicle is about to pass through or display a large screen to broadcast its violation behavior, so as to remind the driver to correct its violation behavior in time.
从上面关于本公开模块化设计的描述可以看出,本公开的系统可以根据应用场景或需求进行灵活地布置而不限于附图所示出的架构。进一步,还应当理解,本公开示例的执行操作的任何模块、单元、组件、服务器、计算机或设备可以包括或以其他方式访问计算机可读介质,诸如存储介质、计算机存储介质或数据存储设备(可移除的)和/或不可移动的)例如磁盘、光盘或磁带。计算机存储介质可以包括以用于存储信息的任何方法或技术实现的易失性和非易失性、可移动和不可移动介质,例如计算机可读指令、数据结构、程序模块或其他数据。基于此,本公开也公开了一种计算机可读存储介质,其上存储有识别违规交通参与对象的计算机可读指令,该计算机可读指令被一个或多个处理器执行时,实现在前结合附图所描述的方法和操作。It can be seen from the above description about the modular design of the present disclosure that the system of the present disclosure can be flexibly arranged according to application scenarios or requirements and is not limited to the architecture shown in the accompanying drawings. Further, it should also be understood that any module, unit, component, server, computer, or device performing operations of the examples of the present disclosure may include or otherwise access computer-readable media, such as storage media, computer storage media, or data storage devices (which may removable) and/or non-removable) such as magnetic disks, optical disks, or tapes. Computer storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Based on this, the present disclosure also discloses a computer-readable storage medium, on which are stored computer-readable instructions for identifying illegal traffic participation objects. When the computer-readable instructions are executed by one or more processors, the preceding combination The methods and operations described in the figures.
如在本说明书和权利要求书中所使用的那样,术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地,短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。As used in this specification and claims, the term "if" may be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined" or "in response to the determination" or "once detected [the described condition or event] ]” or “in response to detection of [described condition or event]”.
虽然本公开的实施方式如上,但所述内容只是为便于理解本公开而采用的实施例,并非用以限定本公开的范围和应用场景。任何本公开所述技术领域内的技术人员,在不脱离本公开所揭露的精神和范围的前提下,可以在实施的形式上及细节上作任何的修改与变化,但本公开的专利保护范围,仍须以所附的权利要求书所界定的范围为准。Although the embodiments of the present disclosure are as above, the content described is only an embodiment adopted for the convenience of understanding the present disclosure, and is not intended to limit the scope and application scenarios of the present disclosure. Anyone skilled in the technical field described in the present disclosure can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the patent protection scope of the present disclosure , must still be subject to the scope defined by the appended claims.

Claims (16)

  1. 一种识别违规交通参与对象的方法,其特征在于,包括:A method for identifying illegal traffic participants, characterized in that it includes:
    获取场景入口处第一感知设备的感知信息;Obtain the perception information of the first perception device at the entrance of the scene;
    基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息,其中所述目标交通参与对象为进入所述场景的交通参与对象;taking a snapshot of a target traffic participant based on the sensing information of the first sensing device, to obtain identity information of the target traffic participant, wherein the target traffic participant is a traffic participant entering the scene;
    根据所述第一感知设备的感知信息获取所述目标交通参与对象的对象特征信息;Acquiring object feature information of the target traffic participating object according to the sensing information of the first sensing device;
    将所述目标交通参与对象的身份信息和对应的对象特征信息进行绑定,以获得目标交通参与对象的绑定信息,并且将所述目标交通参与对象的绑定信息记录于交通参与对象查找集合中;Binding the identity information of the target traffic participation object with the corresponding object characteristic information to obtain the binding information of the target traffic participation object, and recording the binding information of the target traffic participation object in the traffic participation object search set middle;
    获取所述场景内第二感知设备的感知信息;Acquiring sensing information of a second sensing device in the scene;
    根据所述第二感知设备的感知信息识别违规交通参与对象,以便获取所述违规交通参与对象的对象特征信息;Identifying illegal traffic participating objects according to the sensing information of the second sensing device, so as to obtain object characteristic information of the illegal traffic participating objects;
    根据所述违规交通参与对象的对象特征信息从所述交通参与对象查找集合的绑定信息中获取目标绑定信息;Obtain target binding information from the binding information of the traffic participation object lookup set according to the object characteristic information of the violation traffic participation object;
    基于所述目标绑定信息获取违规交通参与对象的身份信息;以及Obtaining the identity information of the violating traffic participant object based on the target binding information; and
    输出所述违规交通参与对象的身份信息和对应的违规行为。Outputting the identity information of the violation traffic participant and the corresponding violation behavior.
  2. 根据权利要求1所述的方法,其特征在于,所述场景包括服务区场景或隧道场景,并且所述违规交通参与对象是违反服务区规定的交通参与对象。The method according to claim 1, wherein the scene includes a service area scene or a tunnel scene, and the violation traffic participation object is a traffic participation object that violates service area regulations.
  3. 根据权利要求1所述的方法,其特征在于,其中抓拍位置包括远端抓拍位置和近端抓拍位置,并且基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息包括:The method according to claim 1, wherein the snapping position includes a far-end snapping position and a near-end snapping position, and the target traffic participant object is snapped based on the sensing information of the first sensing device, so as to obtain the The identity information of the target traffic participants includes:
    基于所述第一感知设备的感知信息选择在所述远端抓拍位置或近端抓拍位置对所述目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息。Selecting to capture the target traffic participating object at the far-end capture position or the near-end capture position based on the sensing information of the first sensing device, so as to obtain the identity information of the target traffic participating object.
  4. 根据权利要求3所述的方法,其特征在于,基于所述第一感知设备的感知信息选择在所述远端抓拍位置或近端抓拍位置对所述目标交通参与对象进行抓拍包括:The method according to claim 3, wherein selecting to capture the target traffic participating object at the far-end capture position or the near-end capture position based on the perception information of the first sensing device comprises:
    基于所述第一感知设备的感知信息获取在抓拍方向上位于所述目标交通参与对象前方的交通参与对象的第一间距和尺寸信息,其中所述第一间距包括所述目标交通参与对象的前部与其前方交通参与对象的尾部之间的距离;以及Obtain the first distance and size information of the traffic participating object located in front of the target traffic participating object in the capture direction based on the sensing information of the first sensing device, wherein the first distance includes the front of the target traffic participating object the distance between the head and the tail of the traffic participating object in front of it; and
    根据所述第一间距和尺寸信息与预设阈值的比较选择在所述远端抓拍位置或近端抓拍位置对目标交通参与对象进行抓拍。According to the comparison between the first distance and size information and a preset threshold, the target traffic participating object is selected to be captured at the far-end capture position or the near-end capture position.
  5. 根据权利要求4所述的方法,其特征在于,根据所述第一间距和尺寸信息与预设阈值的比较选择在所述远端抓拍位置或近端抓拍位置对目标交通参与对象进行抓拍包括:The method according to claim 4, wherein, according to the comparison between the first distance and size information and a preset threshold, selecting to capture the target traffic participation object at the far-end capture position or the near-end capture position comprises:
    响应于所述第一间距小于第一预设阈值并且所述前方交通参与对象的高度大于第二预设阈值,选择所述近端抓拍位置对所述目标交通参与对象进行抓拍;In response to the first distance being less than a first preset threshold and the height of the preceding traffic participating object being greater than a second preset threshold, selecting the near-end capture position to capture the target traffic participating object;
    响应于所述第一间距大于第一预设阈值,选择所述远端抓拍位置对所述目标交通参与对象进行抓拍;或者In response to the first distance being greater than a first preset threshold, selecting the remote capture position to capture the target traffic participant object; or
    响应于所述第一间距小于第一预设阈值并且所述前方交通参与对象的高度小于第二预设阈值,选择所述远端抓拍位置对所述目标交通参与对象进行抓拍。In response to the first distance being smaller than a first preset threshold and the height of the preceding traffic participating object being smaller than a second preset threshold, the remote capture position is selected to capture the target traffic participating object.
  6. 根据权利要求3所述的方法,其特征在于,基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息还包括:The method according to claim 3, wherein capturing the target traffic participation object based on the perception information of the first sensing device, so as to obtain the identity information of the target traffic participation object further comprises:
    根据所述感知信息和所述抓拍位置确定用于对所述目标交通参与对象进行抓拍和识别的抓拍识别框;以及determining a capture recognition frame for capturing and identifying the target traffic participant object according to the perception information and the capture position; and
    在所述抓拍位置处利用所述抓拍识别框对所述目标交通参与对象进行抓拍和识别,以获取所述目标交通参与对象的身份信息。The target traffic participant object is captured and identified by using the snapshot identification frame at the snapshot position, so as to obtain the identity information of the target traffic participant object.
  7. 根据权利要求6所述的方法,其特征在于,根据所述感知信息和所述抓拍位置确定所述抓拍识别框包括:The method according to claim 6, wherein determining the capture recognition frame according to the perception information and the capture position comprises:
    根据所述感知信息获取在抓拍方向上位于所述目标交通参与对象前方的交通参与对象的第二间距,其中所述第二间距包括所述目标交通参与对象的前部与其前方交通参与对象的前部之间的距离;以及Obtain the second distance between the traffic participating object located in front of the target traffic participating object in the capture direction according to the perception information, wherein the second distance includes the front part of the target traffic participating object and the front part of the traffic participating object in front of it. the distance between parts; and
    基于所述抓拍位置和所述第二间距确定所述抓拍识别框。The snapping identification frame is determined based on the snapping position and the second distance.
  8. 根据权利要求1所述的方法,其特征在于,所述场景为服务区场景,根据所述第二感知设备的感知信息识别违规交通参与对象包括:The method according to claim 1, wherein the scene is a service area scene, and identifying illegal traffic participation objects according to the sensing information of the second sensing device includes:
    根据所述第二感知设备的感知信息获取所述场景内的目标交通参与对象的对象特征信息、位置信息和速度信息,其中所述对象特征信息至少包括类别信息;Acquiring object feature information, position information and speed information of target traffic participating objects in the scene according to the sensing information of the second sensing device, wherein the object feature information includes at least category information;
    响应于所述速度信息指示所述目标交通参与对象的速度为零并且所述目标交通参与对象的类别信息与所述场景内的预设区域的类别信息不匹配,将所述目标交通参与对象识别为违规交通参与对象;或者Responding to the speed information indicating that the speed of the target traffic participating object is zero and the category information of the target traffic participating object does not match the category information of a preset area in the scene, identifying the target traffic participating object Participate in traffic violations; or
    响应于所述速度信息指示所述目标交通参与对象的速度为零并且所述目标交通参与对象的位置信息与所述场景内的预设区域的位置不匹配,将所述目标交通参与对象识别为违规交通参与对象。identifying the target traffic participating object as Objects involved in traffic violations.
  9. 根据权利要求8所述的方法,其特征在于,其中输出所述违规交通参与对象的身份信息和对应的违规行为包括:The method according to claim 8, wherein outputting the identity information of the violation traffic participation object and the corresponding violation behavior comprises:
    针对所述违规交通参与对象生成与类别信息不匹配或位置不匹配相关联的违规信息;以及generating violation information associated with category information mismatch or location mismatch for the violation traffic participation object; and
    根据所述违规交通参与对象的位置信息来定向地对所述违规交通参与对象播报所述违规信息。The violation information is directionally broadcasted to the violation traffic participation object according to the position information of the violation traffic participation object.
  10. 根据权利要求1所述的方法,其特征在于,所述场景为隧道场景,根据所述第二感知设备的感知信息中的速度信息识别违规交通参与对象包括:The method according to claim 1, wherein the scene is a tunnel scene, and identifying the illegal traffic participation object according to the speed information in the sensing information of the second sensing device includes:
    响应于目标交通参与对象的速度信息指示速度等于零,将所述目标交通参与对象识别为存在违规停滞行为的违规交通参与对象;或者Responsive to the speed information of the target traffic participating object indicating that the speed is equal to zero, identifying the target traffic participating object as an illegal traffic participating object having a stagnation violation behavior; or
    响应于目标交通参与对象的速度信息指示速度低于最低限速,将所述目标交通参与对象识别为存在违规慢行行为的违规交通参与对象;或者Responding to the speed information of the target traffic participating object indicating that the speed is lower than the minimum speed limit, identifying the target traffic participating object as an illegal traffic participating object that has an illegal slow-moving behavior; or
    响应于目标交通参与对象的速度信息指示速度高于最高限速,将所述目标交通参与对象识别为存在违规超速行为的违规交通参与对象。In response to the speed information of the target traffic participating object indicating that the speed is higher than the maximum speed limit, the target traffic participating object is identified as a traffic participating object that violates the speeding behavior.
  11. 根据权利要求10所述的方法,其特征在于,其中所述第二感知设备的感知信息中还包括违规交通参与对象的位置信息,其中输出所述违规交通参与对象的身份信息和对应的违规行为包括:The method according to claim 10, wherein the sensing information of the second sensing device further includes the location information of the illegal traffic participating object, wherein the identity information of the illegal traffic participating object and the corresponding violation behavior are output include:
    针对所述违规交通参与对象生成与违规停滞行为、违规慢行行为或违规超速行为之一关联的违规信息;以及Generate violation information associated with one of the illegal stagnation behavior, illegal slow-moving behavior or illegal speeding behavior for the illegal traffic participation object; and
    根据所述违规交通参与对象的位置信息向所述违规交通参与对象播报所述违规信息。broadcasting the violation information to the violation traffic participation object according to the location information of the violation traffic participation object.
  12. 一种识别违规交通参与对象的系统,其特征在于,包括:A system for identifying illegal traffic participants, characterized in that it includes:
    第一感知设备,其布置于场景入口处,用于获取所述场景入口处的感知信息;A first sensing device, which is arranged at the entrance of the scene, and is used to acquire the sensing information at the entrance of the scene;
    抓拍设备,其布置于所述场景入口处,用于基于所述第一感知设备的感知信息对目标交通参与对象进行抓拍,以获取所述目标交通参与对象的身份信息,其中所述目标交通参与对象为进入所述场景的交通参与对象;A capture device, which is arranged at the entrance of the scene, and is used to capture the target traffic participant object based on the perception information of the first sensing device, so as to obtain the identity information of the target traffic participant object, wherein the target traffic participant The object is a traffic participant entering the scene;
    第二感知设备,其布置于所述场景内,用于获取所述场景内的感知信息;以及A second sensing device, which is arranged in the scene and used to acquire sensing information in the scene; and
    信息处理中心,其与所述第一感知设备、所述抓拍设备、所述第二感知设备进行通信连接,并且配置用于:An information processing center, which communicates with the first sensing device, the capture device, and the second sensing device, and is configured to:
    分别从所述第一感知设备和第二感知设备获取对应的感知信息;Obtain corresponding sensing information from the first sensing device and the second sensing device respectively;
    根据所述第一感知设备的感知信息获取所述目标交通参与对象的对象特征信息;Acquiring object feature information of the target traffic participating object according to the sensing information of the first sensing device;
    将所述目标交通参与对象的身份信息和对应的对象特征信息进行绑定,以获得目标交通参与对象的绑定信息,并且将所述目标交通参与对象的绑定信息记录于交通参与对象查找集合中;Binding the identity information of the target traffic participation object with the corresponding object characteristic information to obtain the binding information of the target traffic participation object, and recording the binding information of the target traffic participation object in the traffic participation object search set middle;
    根据所述第二感知设备的感知信息识别违规交通参与对象,以便获取所述违规交通参与对象的对象特征信息;Identifying illegal traffic participating objects according to the sensing information of the second sensing device, so as to obtain object characteristic information of the illegal traffic participating objects;
    根据所述违规交通参与对象的对象特征信息从所述交通参与对象查找集合的绑定信息中获取目标绑定信息;Obtain target binding information from the binding information of the traffic participation object lookup set according to the object characteristic information of the violation traffic participation object;
    基于所述目标绑定信息获取违规交通参与对象的身份信息;以及Obtaining the identity information of the violating traffic participant object based on the target binding information; and
    输出所述违规交通参与对象的身份信息和对应的违规行为。Outputting the identity information of the violation traffic participant and the corresponding violation behavior.
  13. 根据权利要求12所述的系统,其特征在于,所述第一感知设备包括激光雷达和/或摄像机。The system according to claim 12, wherein the first sensing device comprises a lidar and/or a camera.
  14. 根据权利要求12所述的系统,其特征在于,所述抓拍设备包括卡口相机。The system according to claim 12, wherein the capturing device comprises a bayonet camera.
  15. 根据权利要求12所述的系统,其特征在于,所述第二感知设备包括激光雷达和/或摄像机。The system according to claim 12, wherein the second sensing device comprises a lidar and/or a camera.
  16. 一种计算机可读存储介质,其上存储有识别违规交通参与对象的计算机可读指令,该计算机可读指令被一个或多个处理器执行时,实现如权利要求1-11中任意一项所述的方法。A computer-readable storage medium, on which computer-readable instructions for identifying illegal traffic participation objects are stored. When the computer-readable instructions are executed by one or more processors, the computer-readable instructions described in any one of claims 1-11 can be realized. described method.
PCT/CN2022/095590 2021-05-27 2022-05-27 Method and system for identifying illegal traffic participant, and computer-readable storage medium WO2022247931A1 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202110586458.XA CN113470371B (en) 2021-05-27 2021-05-27 Method, system, and computer-readable storage medium for identifying an offending vehicle
CN202110586458.X 2021-05-27
CN202110587444.X 2021-05-27
CN202110587444.XA CN113362592A (en) 2021-05-27 2021-05-27 Method, system, and computer-readable storage medium for identifying an offending traffic participant

Publications (1)

Publication Number Publication Date
WO2022247931A1 true WO2022247931A1 (en) 2022-12-01

Family

ID=84228447

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/095590 WO2022247931A1 (en) 2021-05-27 2022-05-27 Method and system for identifying illegal traffic participant, and computer-readable storage medium

Country Status (1)

Country Link
WO (1) WO2022247931A1 (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007058618A1 (en) * 2005-11-18 2007-05-24 St Electronics (Info-Comm Systems) Pte. Ltd. System and method for detecting road traffic violations
CN105788292A (en) * 2016-04-07 2016-07-20 四川巡天揽胜信息技术有限公司 Method and apparatus for obtaining driving vehicle information
CN107305627A (en) * 2016-04-22 2017-10-31 杭州海康威视数字技术股份有限公司 A kind of automobile video frequency monitoring method, server and system
CN107808534A (en) * 2017-11-24 2018-03-16 北京百纳友为科技有限公司 A kind of tunnel safety protector and system
CN107978156A (en) * 2017-12-22 2018-05-01 武汉万集信息技术有限公司 Vehicle checking method and system in a kind of tunnel
CN109377763A (en) * 2018-10-29 2019-02-22 冼钇冰 A kind of vehicles management method, device, terminal and computer readable storage medium
CN109584573A (en) * 2018-12-20 2019-04-05 武汉万集信息技术有限公司 The identifying system and method for hazardous vehicles in tunnel
CN109979242A (en) * 2019-05-08 2019-07-05 司文 A kind of freeway tunnel lane change, overtake other vehicles prior-warning device and method
CN110796869A (en) * 2018-08-03 2020-02-14 杭州海康威视系统技术有限公司 Method and device for detecting illegal car following
WO2020141504A1 (en) * 2019-01-01 2020-07-09 Elta Systems Ltd. System, method and computer program product for speeding detection
CN113362592A (en) * 2021-05-27 2021-09-07 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending traffic participant
CN113470371A (en) * 2021-05-27 2021-10-01 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending vehicle
CN113470372A (en) * 2021-05-27 2021-10-01 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending vehicle

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007058618A1 (en) * 2005-11-18 2007-05-24 St Electronics (Info-Comm Systems) Pte. Ltd. System and method for detecting road traffic violations
CN105788292A (en) * 2016-04-07 2016-07-20 四川巡天揽胜信息技术有限公司 Method and apparatus for obtaining driving vehicle information
CN107305627A (en) * 2016-04-22 2017-10-31 杭州海康威视数字技术股份有限公司 A kind of automobile video frequency monitoring method, server and system
CN107808534A (en) * 2017-11-24 2018-03-16 北京百纳友为科技有限公司 A kind of tunnel safety protector and system
CN107978156A (en) * 2017-12-22 2018-05-01 武汉万集信息技术有限公司 Vehicle checking method and system in a kind of tunnel
CN110796869A (en) * 2018-08-03 2020-02-14 杭州海康威视系统技术有限公司 Method and device for detecting illegal car following
CN109377763A (en) * 2018-10-29 2019-02-22 冼钇冰 A kind of vehicles management method, device, terminal and computer readable storage medium
CN109584573A (en) * 2018-12-20 2019-04-05 武汉万集信息技术有限公司 The identifying system and method for hazardous vehicles in tunnel
WO2020141504A1 (en) * 2019-01-01 2020-07-09 Elta Systems Ltd. System, method and computer program product for speeding detection
CN109979242A (en) * 2019-05-08 2019-07-05 司文 A kind of freeway tunnel lane change, overtake other vehicles prior-warning device and method
CN113362592A (en) * 2021-05-27 2021-09-07 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending traffic participant
CN113470371A (en) * 2021-05-27 2021-10-01 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending vehicle
CN113470372A (en) * 2021-05-27 2021-10-01 北京万集科技股份有限公司 Method, system, and computer-readable storage medium for identifying an offending vehicle

Similar Documents

Publication Publication Date Title
CN113724416B (en) Vehicle-mounted video processing method and device based on vehicle-road cooperative system and storage medium
WO2019165737A1 (en) Safe passing system and method for vehicle
JP7218535B2 (en) Traffic violation vehicle identification system and server
CN113470371B (en) Method, system, and computer-readable storage medium for identifying an offending vehicle
CN111028529A (en) Vehicle-mounted device installed in vehicle, and related device and method
CN113470372B (en) Method, system, and computer-readable storage medium for identifying an offending vehicle
KR100835085B1 (en) A real time processing system and method of a traffic accident using an unmanned recording device
CN108765975B (en) Roadside vertical parking lot management system and method
CN103577412B (en) High-definition video based traffic incident frame tagging method
CN102254429A (en) Video identification-based detection apparatus and method of vehicles against regulations
CN112712697B (en) Lane-level traffic state discrimination method oriented to vehicle-road cooperative application
CN108932849B (en) Method and device for recording low-speed running illegal behaviors of multiple motor vehicles
WO2022127273A1 (en) Wifi 6-based method and system for acquiring traffic information
WO2021159310A1 (en) Violation monitoring system and violation monitoring method
CN108932850B (en) Method and device for recording low-speed driving illegal behaviors of motor vehicle
CN113362610B (en) Method, system, and computer-readable storage medium for identifying an offending traffic participant
CN113362592A (en) Method, system, and computer-readable storage medium for identifying an offending traffic participant
WO2022247932A1 (en) Method and system for recognizing traffic violation participant, and computer-readable storage medium
CN114419885A (en) Vehicle violation snapshot method and system based on high-precision positioning and vehicle-mounted sensing capability
WO2022247931A1 (en) Method and system for identifying illegal traffic participant, and computer-readable storage medium
KR102484789B1 (en) Intelligent crossroad integration management system with unmanned control and traffic information collection function
KR101372843B1 (en) Traffic regulation system and method for bumper-to-bumper violation detection using stereo
CN114299744A (en) Panoramic parking lot system and management scheme
CN114863690B (en) Method, device, medium and electronic equipment for identifying solid line lane change
CN113593239A (en) Method and server for monitoring violation among vehicles and vehicle

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22810655

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE