A method and apparatus for restoring a traffic incident perception process

Abstract

This application discloses a method and apparatus for reconstructing the process of a perceived traffic incident, addressing the problem of lacking technical means to obtain the on-site conditions at the time of the incident in traffic incident judgment. The method involves acquiring the perception information of traffic participants during the incident; generating twin data of the traffic scene at the incident location; the twin data including graphic objects of the traffic participants; determining the location information and corresponding time information of the vehicles involved in the incident based on the perception information; and displaying the driving process of the vehicles involved in the incident in the playback image of the twin data. This application's embodiments fully utilize existing equipment, avoiding redundant construction, and integrate static and dynamic data to generate more comprehensive and accurate digital information, contributing to improved accuracy in traffic management and monitoring. It provides traffic management departments with richer data support, helping them make more scientific and rational management decisions.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method and apparatus for reconstructing traffic event processes based on perception information. Background Technology

[0002] With the increasing prevalence of private cars, there is a growing amount of information about road users. Existing public transportation systems, highways, and overpasses are becoming overburdened, leading to more severe traffic congestion and more frequent traffic accidents. Furthermore, current traffic accident investigations face three major challenges: difficulties in remote liability determination, difficulty in reaching the accident scene, and difficulty in clarifying accident responsibility. These challenges negatively impact the efficiency of accident handling and public satisfaction.

[0003] Through on-site video footage, for example, it can be seen that the vehicle stopped at the intersection, but the reason is unclear, and it is impossible to determine whether it stopped intentionally. At the same time, it is impossible to confirm whether the two vehicles collided due to the perspective. Therefore, there is a need for an accident reconstruction solution that can realistically reproduce the vehicle's operating status before, during and after the accident, fill the blind spots of video surveillance, clearly determine responsibility, and ensure that both parties involved in the accident have no objection and can quickly leave the accident scene.

[0004] In addition, in order to implement traffic management and optimization, it is usually necessary to examine and analyze some situations that occur in traffic, such as the results of the behavior of traffic participants in specific traffic scenarios, whether they have positive or negative effects, and the impact of changes in traffic facilities on traffic. A solution is also needed to reproduce the traffic scenario after the consequences occur. Summary of the Invention

[0005] This application proposes a method and apparatus for reconstructing the process of a traffic incident, which solves the technical problem of lacking technical means to know the on-site situation when an incident occurs in traffic incident judgment.

[0006] In a first aspect, embodiments of this application provide a method for reconstructing the process of a perceived traffic event, including:

[0007] Acquire perception information of traffic participants during the event;

[0008] Generate twin data of the traffic scene at the location of the event; the twin data includes graphical objects of the traffic participants;

[0009] Based on the perceived information, the location information of the incident vehicle and the corresponding time information are determined, and the driving process of the incident vehicle is displayed in the playback image of the twin data.

[0010] Furthermore, based on the license plate number, vehicle type, or body color of the incident vehicle, the perception information of the incident vehicle is matched from the perception information of the incident location.

[0011] Preferably, the playback image of the twin data includes a road plan and the trajectory of the event vehicle's graphic object on the road plan.

[0012] Preferably, the playback images of the twin data include simulated visual images in the three-dimensional scene with any location of the event as the origin.

[0013] In one embodiment, a tile map is generated using a point cloud map as the base data, and then a 3D model is overlaid on the tile map to construct a digital base.

[0014] In one embodiment, a real-time coordinate projection transformation is performed on a 3D model of the traffic scene at the event location to generate a simulated visual image from the driver's perspective of the vehicle involved in the event; the 3D model of the traffic scene at the event location includes road facilities and traffic participants during the event.

[0015] Preferably, the sensing information is acquired through at least one of the following sensing devices:

[0016] LiDAR for static or dynamic target localization, millimeter-wave radar for speed or distance detection, and high-definition surveillance cameras for acquiring video data.

[0017] Secondly, embodiments of this application also provide a traffic event process reconstruction device, used to implement the laser-sensing-based traffic event process reconstruction method described in any embodiment of the first aspect, comprising: an acquisition module, used to acquire perception information of traffic participants during the event; a determination module, used to determine the location information of the event vehicle and the corresponding time information based on the perception information; and a generation module, used to generate twin data of the traffic scene at the event location; the twin data includes graphical objects of the traffic participants, and a playback image of the twin data, showing the driving process of the event vehicle.

[0018] Thirdly, this application also provides a traffic incident process reconstruction system, including a front-end device, a perception information fusion processor, and a reconstruction processor. The front-end device is used to acquire perception information during the incident. The perception information fusion processor is used to determine the operating status of traffic participants based on the perception information and to fuse static road data to generate digital information. The reconstruction processor is used to generate twin data of the traffic scene at the incident location; the twin data includes graphic objects of the incident vehicles; it determines the location information and corresponding time information of the incident vehicles based on the perception information, and displays the driving process of the incident vehicles in the playback image of the twin data.

[0019] Furthermore, it also includes a digital base containing temporal and spatial data of the traffic scene, and a 3D model overlaid on a tile map generated using point cloud maps as the basic data.

[0020] In one embodiment, the reconstruction processor includes a 3D engine. The 3D engine is used to perform real-time coordinate projection transformation on a 3D model of the traffic scene at the event location, generating a simulated visual image of the 3D scene with any location at the event location as the origin.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in any of the embodiments of the first aspect described above.

[0022] Fifthly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the method provided in any of the embodiments of the first aspect described above.

[0023] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0024] This application fully utilizes existing equipment, avoiding redundant construction and saving significant hardware investment and installation costs. Utilizing existing mature equipment shortens system deployment time, enabling faster system deployment. Combining multiple data sources—LiDAR, millimeter-wave radar, and high-definition monitoring—provides more comprehensive and accurate front-end data acquisition capabilities. This application can detect and acquire the status information of various road participation elements in real time, improving the system's ability to perceive dynamic environmental changes. The fusion of static and dynamic data generates more comprehensive and accurate digital information, contributing to improved accuracy in traffic management and monitoring. It provides richer data support for traffic management departments, helping them make more scientific and rational management decisions. This application employs high-precision map and time synchronization technology, ensuring high consistency and accuracy between the digital base and the real physical world. It unifies the time and space benchmarks within the virtual environment, enhancing the realism and consistency of the simulation. It achieves a digital reconstruction of the real physical world, laying a solid foundation for subsequent digital twin applications. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0026] Figure 1 An application environment diagram for the laser sensing-based traffic event process reconstruction method provided in the embodiments of this application;

[0027] Figure 2 A flowchart of a traffic event process reconstruction method based on laser sensing is provided for embodiments of this application;

[0028] Figure 3 This is a schematic diagram of the device deployment scheme of the sensing system provided in the embodiments of this application;

[0029] Figure 4 This is a schematic diagram of an event road video provided in an embodiment of this application;

[0030] Figure 5 This application provides a two-dimensional panoramic view of the event road in an embodiment of the present application.

[0031] Figure 6 A two-dimensional diagram of road traffic event reconstruction provided in the embodiments of this application;

[0032] Figure 7-1 A schematic diagram of the driver's frontal view provided in an embodiment of this application;

[0033] Figure 7-2 A schematic diagram of the driver's rear view provided in an embodiment of this application;

[0034] Figure 8 This is a structural diagram of a traffic event process reconstruction device based on laser sensing provided in an embodiment of this application;

[0035] Figure 9 A structural diagram of a traffic incident perception and reconstruction system provided in this application embodiment;

[0036] Figure 10 This is a structural diagram of the computer device in the embodiments of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0039] Figure 1This application describes a system for the traffic event perception process reconstruction method provided in this embodiment. The traffic event includes a computer 101, a network 102, a sensing device 103, and device posts 104. The computer device and the sensing system can communicate via a wired or wireless network. The computer device can be a roadside computing unit / terminal / edge server; optionally, it can also be a cloud server, a vehicle-mounted computing unit / terminal, etc. This embodiment does not specifically limit the type of computer device. Preferably, the sensing device is a roadside sensing device / roadside multi-source fusion sensing system installed at designated locations at the entrance to the traffic scene and within the traffic scene. For example, it can be device posts evenly distributed throughout the traffic scene. Alternatively, the sensing device can be at least one of a millimeter-wave radar sensor, a lidar sensor, and a camera.

[0040] The perceived information is acquired through a sensing system installed on the road. Preferably, the perceived information is acquired through at least one of the following sensing devices: lidar for static or dynamic target localization, millimeter-wave radar for detecting speed or distance, and high-definition surveillance cameras for acquiring video data.

[0041] This system can also visualize the current perceived information of a computer device's digital twin, creating a visual interface. The visualization module can be integrated into the computer device or set up separately in other locations.

[0042] The system may also include a data storage device (not shown) for storing data that the computer equipment needs to process. The data storage device may be integrated into one or more computer devices, or it may be located in a distributed storage network in the cloud or on other networks.

[0043] The traffic event in this application can refer to a traffic accident, or other behaviors or performances of traffic participants that affect traffic, or the impact of changes in the state of traffic facilities on traffic participants. In other words, it can refer to the behaviors or performances of traffic participants within any target spatiotemporal range to be examined in a traffic scenario.

[0044] Figure 2 This is a flowchart illustrating a method for reconstructing a traffic event process as provided in an embodiment of this application. Figure 1 Based on the system of the device application scenario shown, this application embodiment provides a method for reconstructing the process of sensing traffic events, including steps 210 to 230.

[0045] Step 210: Obtain the perception information of traffic participants during the event.

[0046] The event period is a preset time interval before and after the event. Traffic participant perception information is acquired within this preset time interval. The traffic participants include event-related vehicles (hereinafter referred to as "event vehicles"), event-related pedestrians (hereinafter referred to as "event pedestrians"), etc., and the traffic participant perception information of the event vehicles includes the event vehicle's driving status information.

[0047] The perception information of traffic participants is obtained through a perception system in the traffic scene. In this embodiment, the perception information refers to the perception information within a preset time range before and after an event occurs. This preset time range refers to a certain period of time before and after a vehicle event occurs in the road scene, meaning the computer equipment can receive the perception information of all traffic participants (vehicles and pedestrians) at any point within this time range. Preferably, the system of this application continuously performs traffic perception; therefore, at any moment an event occurs, the system can trace the perception information and extract the perception information of traffic participants related to the event within a preset time range from before the event to after the event.

[0048] The term "event vehicle" can refer to a vehicle that enters the coverage area of ​​the event scene perception system and causes a traffic incident, a third-party vehicle that influences the occurrence of the incident, or a third-party vehicle affected by the incident. Similarly, the term "event pedestrian" can refer to a pedestrian that enters the coverage area of ​​the event scene perception system and causes a traffic incident, a pedestrian that influences the occurrence of the incident, or a pedestrian affected by the incident. By sensing traffic participant events, the perception system obtains traffic participant perception information that includes event vehicles and / or event pedestrians.

[0049] Optionally, the perception system is a roadside perception device / roadside multi-source fusion perception system installed at predetermined locations at the entrance to the traffic scene and within the traffic scene. In one embodiment, such as Figure 3 As shown, the equipment deployment scheme of the sensing system includes at least one of the following:

[0050] LiDAR is used for high-precision detection and positioning of static and dynamic elements on the road surface and in the surrounding environment, such as vehicles, pedestrians, and obstacles. For example, the LiDAR is installed at the corner of an intersection or above an intersection.

[0051] Millimeter-wave radar is primarily used to detect vehicle speed and distance information, making it particularly suitable for complex traffic environments. For example, the millimeter-wave radar can be mounted on traffic lights, which are located at intersections.

[0052] High-definition surveillance cameras: Utilizing existing Skynet surveillance systems and monitoring equipment deployed by traffic police departments, these cameras collect high-resolution video data. Through equipment deployment, they achieve full coverage and seamless monitoring of the traffic environment, ensuring the comprehensiveness and high quality of the data.

[0053] In practical applications, a perception system deployed in a traffic scenario can detect vehicles in real time to obtain perception information about target vehicles. Understandably, the area that the perception system can detect can be determined by the location of the system based on actual needs.

[0054] In practical applications, the perception system set up in traffic scenarios can perceive vehicles in real time to obtain vehicle perception information.

[0055] Optionally, the vehicle's perceived information includes, but is not limited to, the vehicle's ID, category, location, time, size, speed information, heading angle information, etc. Here, the vehicle ID is the serial number generated for each vehicle after the perception system detects it; the category refers to the vehicle type, such as a large truck, a car, a motorcycle, a tricycle, etc.; the location refers to the perceived location of the event vehicle; the perceived time refers to the time corresponding to the perceived location of the event vehicle; the size refers to the perceived size information of each vehicle; the speed information refers to the speed of the event vehicle; and the heading angle information refers to the angle between the vehicle's center of mass velocity and the horizontal axis in the ground coordinate system.

[0056] Furthermore, based on the license plate number, vehicle type, and body color of the incident vehicle, the perception information of the incident vehicle is matched from the perception information of the incident location.

[0057] For example, vehicle matching based on license plate number, vehicle type, and body color. Matching based on sourceID, location, and time. First, check if original data exists using the sourceID. Consider the following four possibilities and rebind the optimal original cache to the global result:

[0058] (1) The same vehicle is captured multiple times, and the sourceID is the same on each capture, but the license plate is different (or present or absent).

[0059] (2) The same vehicle is captured multiple times, and the sourceID is the same on each capture, and the license plate is the same (or not).

[0060] (3) The same vehicle is captured multiple times, and the sourceIDs and license plates are different (or not present) on each capture.

[0061] (4) The same vehicle is captured multiple times with different sourceIds, and the license plate is the same (or not).

[0062] The system obtains vehicle type and body color information from AI fusion software and matches it with the vehicle information using a global ID. If the match is successful, the system returns the matching result; if it fails, it enters the fuzzy matching stage. In the fuzzy matching stage, if there are errors in the license plate number or body color, the matching conditions are adjusted using an algorithm to perform a fuzzy match.

[0063] Step 220: Generate twin data of the traffic scene at the location of the event; the twin data includes graphical objects of the traffic participants.

[0064] Twin data refers to the visual representation of traffic scenes presented on the screen, including but not limited to static or dynamic scene twin displays, visualization charts, rendering services, and interoperability tools.

[0065] Graphical objects refer to the visual representation of objects in the real physical world, including but not limited to static objects such as buildings, terrain features, and transportation facilities, as well as dynamic objects such as traffic participants (vehicles, pedestrians, etc.), weather conditions, and traffic time. For example, in the use of twin data, static objects can be retained, and only the generated dynamic objects are updated. Twin data of traffic scenarios includes graphical objects of roads, traffic facilities, and traffic participants. Among them, roads and some traffic facilities are static, traffic participants are dynamic, and some traffic facilities are also dynamic, such as tidal flow lanes, traffic lights, and electronic signs.

[0066] Twin data is data used to drive a computer GUI or display device to generate dynamic scenes. Twin data contains representational data of graphical objects in the dynamic scene to be displayed. Those skilled in the art will understand that existing technologies can achieve the acquisition and processing of perceptual information, identify various static and dynamic objects, determine object types and spatiotemporal location information, and generate twin data through a twin engine.

[0067] Step 230: Determine the location information of the event vehicle and the corresponding time information based on the perceived information, and display the driving process of the event vehicle in the playback image of the twin data.

[0068] Vehicle perception information includes corresponding location and time information. When a vehicle is within the perception system's sensing area, it has a corresponding location at each point in time. The time information is the location information corresponding to each time point. By determining the location and time information, the vehicle's trajectory within the perception system's sensing area, within a preset time frame before and after the event, can be determined. By comparing the trajectories of other participants in the traffic incident with their positions at the time of the incident, responsibility for the incident can be determined. Furthermore, perception information from other types of traffic participants within the preset time frame before and after the incident can be obtained to reconstruct the scenario of traffic incidents involving other types of participants, facilitating responsibility determination.

[0069] It should be noted that the playback images are simulated visual images further generated based on twin data. Here, the playback images of twin data are not the twin data itself. Twin data is generated alongside actual traffic scenarios and contains static or dynamic graphics containing information of interest in the actual traffic scenario. The playback images of twin data are generated through further processing of the twin data, simulating and displaying the actual traffic scenario that occurred previously. Based on the existing information in the twin data, the location and time information of traffic participants related to the traffic event are highlighted. The playback images may also include event-related indicator information 530, 630, such as time, location, event identifier, traffic participant identifier, or other information. To generate the playback images, other expressive data related to the traffic scenario, such as 3D graphic data, traffic management data, and traffic participant identity data, can be introduced on top of the twin data.

[0070] Display the movement of traffic participants during the event in the playback images, especially highlighting the movement of traffic participants related to the event, including graphics, animations, directional information and / or auxiliary signs.

[0071] For example, the driving process of the event vehicle can be highlighted in the playback image using auxiliary markers, such as trajectory lines, position markings, and distance markings. Another example is highlighting the driving process of the event vehicle in the playback image using indicator information, such as vehicle type, license plate number, speed, angle, and driving behavior characteristics. Yet another example is highlighting the driving process of the event vehicle in the playback image using graphics and animations, generating a display frame that distinguishes it from other traffic participants' graphic objects and loading the event scene display.

[0072] The playback images display the driving process of the vehicle involved in the incident, including subjective and / or objective perspectives. The objective perspective is the image presented from a spatial point other than the traffic participant, serving as the visual starting point (hereinafter referred to as the "origin"). The subjective perspective is the image presented from the location of the traffic participant, serving as the visual starting point (origin).

[0073] Preferably, the playback image of the twin data can be a road plan (origin at infinity in the elevation direction) and the trajectory of the graphic object of the event vehicle on the road plan, the trajectory showing the process of position change over time. Based on vehicle driving information, the corresponding position and time information of the event vehicles during the traffic event are determined, and the driving trajectory of the event vehicles within a preset time period is displayed in the twin data according to the position and time information.

[0074] Preferably, in the playback image of the twin data, a real-time coordinate projection transformation is performed on the 3D model of the traffic scene at the event location to generate a simulated visual image in the 3D scene with any location at the event location as the origin. The 3D model of the traffic scene at the event location includes road facilities and traffic participants during the event.

[0075] Simulated visual images present the process of simulated visual graphics changing over time. For example, using simulated visual images with any location as the origin, the perspective of any traffic participant can be simulated based on their location (this could be the subjective perspective of a traffic participant related to the event, or the subjective perspective of a traffic participant unrelated to the event, including drivers or pedestrians). The perspective of any traffic facility can also be simulated based on its location, and the perspective of an observation point in space can be simulated.

[0076] In one embodiment, a real-time coordinate projection transformation is performed on a 3D model of the traffic scene at the accident site to generate a simulated visual image from the driver's perspective of the vehicle involved in the incident. Since a simulated visual image can be generated with any location as the origin, once the positions of pedestrians or drivers among traffic participants are determined, their perspectives can be simulated using this location as the origin.

[0077] For example, at 0:47:37 on April 10, 2023, a rear-end collision occurred between two vehicles at the intersection of Xiangjiang Middle Road and Laodong West Road.

[0078] like Figures 4-5 As shown, all sensing systems along this road acquire holographic sensing information to generate a dynamic scene. This includes, for example, Figure 4 The video images shown, and the data generated, also include, for example, Figure 5The two-dimensional graphic data shown includes planar graphics of roads and vehicle graphics, as well as dynamic scenes formed by the change of vehicle positions over time.

[0079] By digitally reconstructing perceived information from before and after a traffic incident within a predetermined timeframe, it generates data such as... Figures 5-6 The simulated visual imagery of the traffic incident shown displays the driving process of the vehicles involved in the incident based on two-dimensional graphic data of the dynamic scene. It includes the vehicle markers 510 and 610 and the vehicle driving trajectories 520 and 620.

[0080] Furthermore, to achieve 3D graphics of traffic scenes, in one embodiment, the simulated visual imagery of the traffic scene is constructed using a high-precision map. For example, the 3D model adopts a digital base construction scheme, and based on data fusion, a spatiotemporally integrated digital base is further constructed. The high-precision map uses point cloud maps as basic data, and models static objects in real scenes, including but not limited to roads, building gantries, roadside poles, guardrails, LED screens, and trees, are built based on the high-precision map data. Terrain and landforms are modeled through perception data and imported 3D GSI data, digitally supporting the definition of urban terrain.

[0081] High-precision map construction uses point cloud images collected by a high-precision map acquisition vehicle as the base data, which are then processed to generate tile maps. 3D model overlay is based on overlaying 3D models onto the tile maps to create a detailed 3D traffic environment.

[0082] Spatiotemporal unification is achieved through high-precision time synchronization technology, ensuring that the time and space references in the 3D model are completely consistent with the real world, thus realizing spatiotemporal integration. The construction of this digital foundation enables the digital reconstruction of the real physical world, providing a reliable basis for digital twin restoration.

[0083] In one embodiment, the three-dimensional model is transformed by real-time coordinate projection to reflect the changes in the environment and vehicle status within a preset time before and after the event.

[0084] The camera angle is dynamically adjusted to simulate the perspective of the vehicle involved in the event.

[0085] By performing real-time coordinate projection transformation using a 3D model, the changes in the environment and vehicles within a preset time frame before and after an event are transformed into the perspective of traffic participants.

[0086] The simulated visual imagery data of the traffic scene includes simulated visual imagery graphic objects of the target vehicle; it also includes the perspectives of traffic participants, such as vehicles involved in the event, pedestrians involved in the event, and road signs involved in the event, used to display the simulated visual imagery from the perspective of each traffic participant within a preset time period before and after the event. Based on the location information and corresponding time information of the traffic participants, a frame is determined within their perspective. This frame contains the image from the perspective of the traffic participants.

[0087] The simulated visual image from the perspective of traffic participants, such as Figure 7-1 and Figure 7-2 As shown, in Figure 6 In the traffic incident shown, Figure 7-1 and Figure 7-2 These are the driver's front view and driver's rear view, that is, the view from the driver's seat of the vehicle involved in the incident looking forward and the view from the driver's seat of the vehicle involved in the incident looking backward. The first-person perspective of the driver of the following vehicle puts the viewer in the position of the driver of the following vehicle: the driver changes lanes from the auxiliary lane to the main lane and continues to drive straight. From the driver's perspective, the vehicle in front is driving straight normally without obstruction. The driver did not expect the vehicle in front to brake, resulting in a rear-end collision. Based on the playback images, traffic police can remotely judge the driver's driving situation through a visual interface, providing effective evidence for determining traffic accident liability and analyzing the cause of the accident.

[0088] In addition, based on the vehicle type, preset 3D graphic templates of the interior of that type of car, such as steering wheel and rearview mirror, can be obtained from the database to simulate the real car interior space.

[0089] This application utilizes perceptual digital reconstruction technology to realistically recreate the vehicle's operational status throughout the entire process before, during, and after an incident from a panoramic perspective, filling the gaps in video surveillance. By reviewing the video, responsibility is clear, there are no other disputes, and both parties can quickly leave the scene. Our solution determines responsibility from the driver's first-person perspective in an "immersive" way. It assists police officers in remotely assessing driver behavior, providing effective evidence for determining liability and analyzing the causes of traffic incidents. Laser perceptual digital reconstruction is crucial in this regard.

[0090] It should be noted that the execution subject of each step of the method provided in this application embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 210 and 220 can be device 1, and the execution subject of step 230 can be device 2; or the execution subject of step 210 can be device 1, and the execution subject of steps 220 and 230 can be device 2; and so on.

[0091] Figure 8This is a structural diagram of a laser-sensing-based traffic incident reconstruction device provided in an embodiment of this application, used to implement the laser-sensing-based traffic incident reconstruction method described in any embodiment of the first aspect, comprising:

[0092] The acquisition module 810 is used to acquire the perception information of traffic participants during the event. Its functions are as described in step 210 of the embodiment.

[0093] The determining module 820 is used to determine the location information of the event vehicle and the corresponding time information based on the perceived information. The function implemented is as described in step 220 of the embodiment.

[0094] The generation module 830 is used to generate twin data of the traffic scene at the location of the event, wherein the twin data includes graphical objects of the traffic participants. The functions implemented are as described in step 220 of the embodiment. Furthermore, it is also used to display the driving process of the event vehicle in the playback image of the twin data. The functions implemented are as described in step 230 of the embodiment of this application.

[0095] Furthermore, the acquisition module described in this application embodiment also includes a first acquisition unit, used to acquire the perception information of traffic participants during the event.

[0096] Furthermore, the determining module described in this application embodiment also includes a first determining unit, used to determine the location information of the event vehicle and the time information corresponding to the location based on the perceived information.

[0097] Furthermore, the generation module described in this application embodiment also includes a first generation unit, used to generate twin data of the traffic scene at the location where the event occurred; the twin data includes graphical objects of the traffic participants.

[0098] Furthermore, the display module described in this application embodiment also includes a first display unit for displaying the driving process of the event vehicle in the playback image of the twin data.

[0099] In one embodiment, the determining module further includes a second determining unit, used to match the perception information of the event vehicle from the perception information of the event location based on the license plate number, vehicle type and body color of the event vehicle.

[0100] In one embodiment, the display module further includes a second display unit for displaying the playback image of the twin data, including a road plan and the trajectory of the event vehicle's graphic object on the road plan.

[0101] In one embodiment, the display module further includes a third display unit for displaying a simulated visual image in the playback image of the twin data, including a three-dimensional scene with any location of the event occurrence as the origin.

[0102] In one embodiment, the generation module further includes a second generation unit for constructing a twin image of the traffic scene at the accident location using a high-precision map; the high-precision map uses point cloud images as basic data, performs indoor processing to generate a tile map, and uses the tiles... Figure 3 Dimensions are superimposed to form a three-dimensional model, thus constructing a three-dimensional traffic environment.

[0103] In one embodiment, the generation module further includes a third generation unit, which is also used to retrieve digital base and twin data to generate a playback image in which the driving process of the event vehicle is displayed.

[0104] In one embodiment, the determining module further includes a second determining unit, used to generate a tile map using a point cloud map as basic data, and then to overlay a three-dimensional model on the tile map to construct a digital base.

[0105] In one embodiment, the determining module further includes a third determining unit, used to perform real-time coordinate projection transformation on a three-dimensional model of the traffic scene at the event location to generate a simulated visual image from the driver's perspective of the vehicle involved in the event; the three-dimensional model of the traffic scene at the event location includes road facilities and traffic participants during the event.

[0106] In one embodiment, the acquisition module can acquire sensing information through at least one of the following sensing devices:

[0107] LiDAR for static or dynamic target localization, millimeter-wave radar for speed or distance detection, and high-definition surveillance cameras for acquiring video data.

[0108] Figure 9 A structural diagram of a traffic incident perception process reconstruction system provided in this application embodiment includes a front-end device 910, a perception information fusion processor 920, and a reconstruction processor 930.

[0109] The front-end device is used to acquire perceived information during the event. In one embodiment, the front-end device loads an acquisition module.

[0110] The perception information fusion processor is used to determine the operating status of traffic participants based on the perception information and to fuse static road data to generate digital information. In one embodiment, the perception information fusion processor loads a determination module, which includes first, second, and / or third determination units.

[0111] A reconstruction processor is used to generate twin data of the traffic scene at the location of the incident; the twin data includes a graphical object of the vehicle involved in the incident; the location information and corresponding time information of the vehicle are determined based on the perceived information, and the driving process of the vehicle is displayed in the playback image of the twin data. In one embodiment, the reconstruction processor loads a generation module, which includes a first generation unit and / or a second generation unit.

[0112] Furthermore, it also includes a digital base 940, which contains temporal and spatial data of the traffic scene, and a three-dimensional model is superimposed on a tile map generated using point cloud map as the basic data.

[0113] In one embodiment, the reconstruction processor includes a 3D engine. The 3D engine is used to perform real-time coordinate projection transformation on a 3D model of the traffic scene at the event location, generating a simulated visual image of the 3D scene with any location at the event location as the origin.

[0114] Combination Figure 1 The system in the described application scenario includes a front-end device 103 and a device pile 104. The computer 101 includes the described perception information fusion processor and the described reconstruction processor; the data storage device includes a digital base. When the visualization interface displays a twin image of the traffic scene driven by twin data, further, in response to an event occurrence indication, the visualization interface displays a playback image of the twin data.

[0115] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] Therefore, this application also proposes a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the methods described in any embodiment of this application.

[0117] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0118] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] Figure 10 This is a structural diagram of a computer device according to an embodiment of this application. Furthermore, this application also proposes a computer device (or electronic device) including a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, it implements the method described in any embodiment of this application.

[0120] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, a network interface, and memory. Memory may include non-persistent storage in computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media. Computer-readable media includes both permanent and non-persistent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage, or any other non-transfer medium that can be used to store information accessible by the computing device. As defined in this article, computer-readable media do not include transient media, such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0122] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for reconstructing the process of a perceived traffic incident, characterized in that, Including the following steps: Acquire perception information of traffic participants during the event; Generate twin data of the traffic scene at the location of the event; the twin data includes graphical objects of the traffic participants; Based on the perceived information, the location information of the incident vehicle and the corresponding time information are determined, and the driving process of the incident vehicle is displayed in the playback image of the twin data.

2. The method for reconstructing the process of perceived traffic events according to claim 1, characterized in that, Based on the license plate number, vehicle type, or body color of the vehicle involved in the incident, the sensory information of the vehicle involved in the incident is matched with the sensory information of the location where the incident occurred.

3. The method for reconstructing the process of perceived traffic events according to claim 1, characterized in that, The playback images of the twin data include a road plan and the trajectory of the event vehicle's graphic object on the road plan.

4. The method for reconstructing the process of a perceived traffic incident according to claim 1, characterized in that, The playback images of the twin data include simulated visual images in the three-dimensional scene with any location of the event as the origin.

5. The method for reconstructing the process of perceived traffic events according to claim 1, characterized in that, A tile map is generated using point cloud map as the basic data, and then a 3D model is overlaid on the tile map to construct a digital base.

6. The method for reconstructing the process of a perceived traffic event according to claim 1, characterized in that, A real-time coordinate projection transformation is performed on a 3D model of the traffic scene at the event location to generate a simulated visual image from the driver's perspective of the vehicle involved in the event; the 3D model of the traffic scene at the event location includes road facilities and traffic participants during the event.

7. The method for reconstructing the process of a perceived traffic event according to claim 1, characterized in that, The sensing information is acquired through at least one of the following sensing devices: LiDAR for static or dynamic target localization, millimeter-wave radar for speed or distance detection, and high-definition surveillance cameras for acquiring video data.

8. A device for reconstructing the process of a perceived traffic incident, characterized in that, The method for reconstructing traffic events based on laser sensing as described in any one of claims 1-7 comprises: The acquisition module is used to acquire the perception information of traffic participants during the event. The determination module is used to determine the location information of the event vehicle and the time information corresponding to the location based on the perceived information; A generation module is used to generate twin data of the traffic scene at the location of the event; the twin data includes graphical objects of the traffic participants; and to generate a playback image of the twin data, which shows the driving process of the vehicles involved in the event.

9. A system for reconstructing the process of a perceived traffic incident, characterized in that, This includes front-end devices, sensor information fusion processors, and restoration processors; The front-end device is used to acquire sensing information during the event; The perception information fusion processor is used to determine the operating status of traffic participants based on the perception information and to fuse static road data to generate digital information. A restoration processor is used to generate twin data of the traffic scene at the location where the event occurred; the twin data includes graphical objects of the vehicles involved in the event. Based on the perceived information, the location information of the incident vehicle and the corresponding time information are determined, and the driving process of the incident vehicle is displayed in the playback image of the twin data.

10. A traffic incident process reconstruction system according to claim 9, characterized in that, Also includes a digital dock, The digital base contains temporal and spatial data of traffic scenarios, and a 3D model is overlaid on a tile map generated using point cloud maps as the basic data.

11. A traffic incident process reconstruction system according to claim 9, characterized in that, The aforementioned restoration processor includes a 3D engine; The 3D engine is used to perform real-time coordinate projection transformation on the 3D model of the traffic scene at the event location, generating a simulated visual image in the 3D scene with any location at the event location as the origin.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

13. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-7.

Images