[go: up one dir, main page]

CN119808385A - Traffic accident reconstruction method and device based on automobile event data recording system - Google Patents

Traffic accident reconstruction method and device based on automobile event data recording system Download PDF

Info

Publication number
CN119808385A
CN119808385A CN202411862950.5A CN202411862950A CN119808385A CN 119808385 A CN119808385 A CN 119808385A CN 202411862950 A CN202411862950 A CN 202411862950A CN 119808385 A CN119808385 A CN 119808385A
Authority
CN
China
Prior art keywords
accident
data
vehicle
information
edr
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202411862950.5A
Other languages
Chinese (zh)
Inventor
纪伟
袁泉
程刚
许庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Original Assignee
Tsinghua University
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
Application filed by Tsinghua University filed Critical Tsinghua University
Priority to CN202411862950.5A priority Critical patent/CN119808385A/en
Publication of CN119808385A publication Critical patent/CN119808385A/en
Pending legal-status Critical Current

Links

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02TCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00Road transport of goods or passengers
    • Y02T10/10Internal combustion engine [ICE] based vehicles
    • Y02T10/40Engine management systems

Landscapes

  • Traffic Control Systems (AREA)

Abstract

本发明公开了基于汽车事件数据记录系统的交通事故重建方法及装置,本发明的方法包括获取交通事故现场后的现场勘查数据信息、监控视频图像信息以及事故车辆的EDR数据;对现场勘查数据信息、监控视频图像信息以及验证后的事故车辆的EDR数据进行数据融合补全得到数据融合结果;基于数据融合结果进行自动化建模以构建标准化事故重建流程得到事故重建结果,并验证事故重建结果。本发明采用更科学的方法来高效、准确地获取事发过程中车辆的工况信息,可以显著提高事故重现的效率和准确性。

The present invention discloses a traffic accident reconstruction method and device based on an automobile event data recording system. The method of the present invention comprises obtaining on-site investigation data information, monitoring video image information and EDR data of the accident vehicle after the traffic accident scene; performing data fusion and completion on the on-site investigation data information, monitoring video image information and the verified EDR data of the accident vehicle to obtain a data fusion result; performing automatic modeling based on the data fusion result to construct a standardized accident reconstruction process to obtain an accident reconstruction result, and verifying the accident reconstruction result. The present invention adopts a more scientific method to efficiently and accurately obtain the working condition information of the vehicle during the accident, which can significantly improve the efficiency and accuracy of accident reconstruction.

Description

Traffic accident reconstruction method and device based on automobile event data recording system
Technical Field
The invention relates to the technical field of accident reconstruction, in particular to a traffic accident reconstruction method and device based on an automobile event data recording system.
Background
With the rapid increase of motor vehicles on roads, the occurrence rate of traffic accidents is increased, and the safety of lives and property of the public is greatly threatened. In order to effectively prevent and reduce such accidents, it is particularly critical to understand and analyze the cause of the accidents in depth. Traditional accident reconstruction work mainly relies on manual field investigation and descriptions of accident parties, and the efficiency and accuracy of the method are limited and are easily affected by personal subjective factors. However, with the widespread use of the automobile Event Data Recorder (EDR), we have obtained new technological means to reconstruct traffic accidents.
The existing accident reconstruction method basically comprises two technical bases, namely a reconstruction work which is carried out on the basis of data and scenes obtained by traditional field investigation, and a traffic accident reconstruction method based on monitoring video images. (1) The data obtained by conventional in-situ investigation means is generally limited to damage to vehicles, road surface spills, road surface marks, road facilities, buildings and the like at the site after an accident. These data do not directly reveal the situation before the accident, such as the driving track, speed, acceleration and deceleration, braking, etc. of the vehicle. Technicians need to analyze and calculate from the survey data to infer pre-accident conditions. This process not only tests the technical capabilities of the technician's individual, but also depends greatly on the accuracy of the survey data. Therefore, this approach results in difficult standardization of accident reproduction work and weak scientific continuity. (2) Although surveillance video can reflect the course of an accident, there are often limitations. Video shot by the road fixed probe can not accurately and clearly reproduce the accident process due to the limitation of factors such as shooting angles, distances, pixels and the like, so that the video shot by the road fixed probe is difficult to be used for accurate reconstruction. However, the vehicle-mounted monitoring video usually only records the picture information in front of the vehicle, and often cannot fully display the collision accident occurring on the side or the rear of the vehicle. Therefore, the image-based reconstruction method cannot accurately reflect the operation conditions of personnel in the vehicle, particularly for vehicles with problems in technical conditions such as braking, steering and the like. (3) The existing field reconstruction method cannot fully cover the working conditions of passive safety systems in the vehicle, such as airbags, safety belts and the like, and part of active safety systems, such as automatic emergency braking systems, anti-lock systems, vehicle body stability control systems and the like, in the accident process. Such limitations may result in an inability to accurately restore accident procedures, particularly those of personnel within the vehicle.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, the invention provides a traffic accident reconstruction method based on an automobile event data recording system, and an EDR-based traffic accident reconstruction platform is based on traditional investigation data, takes EDR data as a core, and realizes accurate, efficient, scientific and objective reconstruction of an accident process.
Another object of the present invention is to provide a traffic accident reconstruction device based on an automobile event data recording system.
In order to achieve the above object, an aspect of the present invention provides a traffic accident reconstruction method based on an automobile event data recording system, including:
acquiring site investigation data information, monitoring video image information and EDR data of an accident vehicle after a traffic accident site;
Carrying out data fusion and complementation on the on-site investigation data information, the monitoring video image information and the EDR data of the accident vehicle after verification to obtain a data fusion result;
And carrying out automatic modeling based on the data fusion result to construct a standardized accident reconstruction flow to obtain an accident reconstruction result, and verifying the accident reconstruction result.
The traffic accident reconstruction method based on the automobile event data recording system provided by the embodiment of the invention can also have the following additional technical characteristics:
In one embodiment of the invention, the field investigation data information comprises static space information and accident related information, the monitoring video image information comprises image basic information and accident reflecting information, and the EDR data comprises basic information and working condition information.
In one embodiment of the present invention, the static spatial information includes road surface spatial dimensions, road sign markings, road construction information, road adhesion coefficients;
the accident related information comprises driver information, in-vehicle driving relation, vehicle damage marks and road surface left marks;
the basic image information comprises names, sizes, formats, frame rates, integrity check values and whether the images are recorded clearly or not;
The reflected accident information comprises a vehicle running track, a vehicle collision process, braking before collision and steering before collision;
The basic information comprises vehicle basic information, system state during reading, software and hardware used for reading, data record integrity, data source description and data limitation;
the working condition information comprises running speed, longitudinal acceleration change, transverse acceleration change, collision type, vehicle braking condition, vehicle steering condition, vehicle acceleration condition, engine speed, safety belt and air bag, ABS and AEB working condition and ACC and LDW working condition.
In one embodiment of the invention, EDR data for an accident vehicle is validated, including correlation validation, integrity validation, and validity validation, wherein,
The correlation verification comprises the steps of verifying the consistency of a vehicle identification code of an EDR data record and an accident vehicle identification code to obtain a vehicle identification code consistency result, verifying that the power-on period of the EDR data record is similar to the power-on period of the EDR data record when the accident happens to obtain a power-on period consistency verification result, verifying that the deployment condition of an air bag of the EDR data record is consistent with the initiation time period condition of the air bag shown by an accident vehicle inspection photo and a vehicle-mounted video to obtain an air bag deployment condition consistency verification result, and verifying that the two collision forms and time intervals of the EDR data record are consistent with the content shown by the accident vehicle inspection photo, the vehicle-mounted video and a site photo to obtain a collision form and time interval consistency verification result;
verifying that event data of EDR data records are all successful complete records so as to obtain a data record integrity verification result;
and the validity verification is carried out by carrying out tire specification verification, collision analysis and time node analysis so as to obtain a validity verification result.
In one embodiment of the present invention, performing automated modeling based on the data fusion result to construct a standardized accident reconstruction procedure to obtain an accident reconstruction result, including:
processing the on-site investigation data information by utilizing an OCR technology and a natural language processing technology to automatically identify and directionally extract text information and perform structural processing; processing the monitoring video image information by utilizing a computer vision technology, analyzing the EDR data to be converted into a format which can be identified by a PC-crash model so as to obtain preprocessing data;
The method comprises the steps of establishing a vehicle model library and a scene model library, dynamically updating and managing, automatically matching corresponding vehicle models and scene models according to an accident data set, setting parameters, running PC-crash simulation calculation, and generating an accident reconstruction animation;
Analyzing accident reconstruction animation, obtaining related parameters of the accident occurrence process, visually displaying the accident reconstruction result, comparing the accident reconstruction result with the exploration trace, the monitoring video and the EDR data, verifying the accuracy of the accident reconstruction result, and automatically generating an accident reconstruction report.
To achieve the above object, a second aspect of the present invention provides a traffic accident reconstruction device based on an automobile event data recording system, including:
The data acquisition module is used for acquiring on-site investigation data information, monitoring video image information and EDR data of the accident vehicle after the traffic accident site;
the data judging module is used for judging whether the EDR data has relevance, integrity and effectiveness according to the on-site investigation data information and the monitoring video image information so as to obtain a data judging result;
the data fusion module is used for carrying out data fusion on the EDR data, the on-site investigation data information and the monitoring video image information based on the data judgment result to obtain a data fusion result;
and the accident reconstruction module is used for carrying out accident reconstruction according to the data fusion result to obtain a reconstruction result.
According to the traffic accident reconstruction method and device based on the automobile event data recording system, firstly, the data in the EDR can be automatically extracted and analyzed, and the accident process is rapidly reproduced, so that the accuracy and efficiency of reconstruction are improved, the difference of manual intervention and subjective judgment is reduced, the standardability is enhanced, and the influence caused by the experience difference of technicians is reduced. Secondly, based on objective EDR data analysis, a more scientific and visual basis can be provided for judging accident responsibility, fairness and scientificity of traffic accident handling are promoted, disputes of all parties are reduced, and legal rights and interests of parties are protected.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of a traffic accident reconstruction method based on an automotive event data recording system according to an embodiment of the present invention;
FIG. 2 is a platform architecture diagram of a traffic accident reconstruction method based on an automotive event data recording system according to an embodiment of the present invention;
Fig. 3 is a schematic structural view of a traffic accident heavy device based on an automobile event data recording system according to an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The following describes a traffic accident reconstruction method and device based on an automobile event data recording system according to an embodiment of the present invention with reference to the accompanying drawings.
At present, in the research field of traffic accident scene investigation, an EDR data-based comprehensive accident reconstruction platform is not available. The invention aims to combine EDR data with traditional data and perform mutual authentication through system design. According to the relevant regulations of the automobile event data recording system, the invention is based on the traditional investigation data, and takes EDR data as the technical core to reconstruct the fusion accident. The invention particularly emphasizes the acquisition of EDR data, defines the data acquisition range, and adopts a more scientific method to efficiently and accurately acquire the working condition information of the vehicle in the accident process, thereby obviously improving the efficiency and accuracy of accident reproduction. In the reconstruction of the concept, the invention provides the concepts of 'key complement' and 'mutual verification'. EDR information is used as an important scientific supplement of traditional on-site investigation information, and meanwhile on-site investigation data such as vehicle damage conditions, road surface marks, monitoring videos and the like can be used as a basis for verifying relevance, integrity and effectiveness of EDR data. The information such as the speed of a vehicle recorded in EDR data can also be used for verifying the calculation of the speed of a vehicle in the traditional investigation or identification process. The invention systematically combs the flow of carrying out accident reconstruction based on EDR, and establishes a set of perfect and generalized standardized accident reconstruction flow. By the functions of intelligent character recognition, information fixed-point grabbing, automatic butt joint of a model database and the like, the automation level of accident reconstruction is greatly improved, and therefore the efficiency of product technology work is improved. The overall platform structure is shown in fig. 2.
Fig. 1 is a flowchart of a traffic accident reconstruction method based on an automobile event data recording system according to an embodiment of the present invention, and the method of the present invention is as shown in fig. 1, and includes:
s1, acquiring site investigation data information, monitoring video image information and EDR data of an accident vehicle after a traffic accident site.
It can be understood that the method for acquiring the on-site investigation data information comprises static space information and accident related information, monitoring video image information comprising image basic information and accident reflecting information, and EDR data comprising basic information and working condition information.
In particular, the on-site investigation information after the traffic accident scene comprises, but is not limited to, road width, mark marks, road facilities, vehicle damage conditions, road surface left-behind mark scatterers, road facilities and building damage conditions, case personnel damage conditions and the like. Image information acquisition, acquisition of monitoring video of a fixed probe of a road section of an incident and vehicle-mounted monitoring video information acquisition.
The field investigation data information includes static space information (pavement space size, road mark line, road construction information and road adhesion coefficient), accident related information (driver information, in-vehicle driving relationship, vehicle damage trace and pavement carryover trace).
The monitoring video image information includes basic image information (name and size, format and frame rate, integrity check value, clear record or not) and accident information (vehicle running track, vehicle collision process, brake before collision and special item before collision).
Specifically, the obtained traffic accident weight information includes:
static space information, such as space dimension of the pavement at the accident site, road facilities, marking conditions and dimension information of marking marks, gradient, curvature of the pavement, road adhesion coefficient and the like.
The information of the damage trace of the person, the vehicle and the road formed after the accident comprises basic information of a driver, health conditions, drinking or toxin absorbing conditions, driving relation and the like, basic information of the vehicle (including but not limited to model, size, weight, structure, gravity center, materials and the like), the damage trace of the vehicle after the accident, trace left by a tire body and the like on the road surface, road surface scattered matters, blood traces, road facilities, building damage conditions and the like.
The image information comprises the name, the size, the format, the integrity check value, the frame rate, the pixels and the like of the image, the running track, the acceleration and deceleration and braking conditions, the collision process, the accident scene left marks after the collision, other related information and the like of the vehicle in the accident process recorded by the image.
Edr are used for reflecting the running speed, braking condition, acceleration condition, steering angle and engine/motor rotation speed of the vehicle in 5s before the vehicle is started, the transverse, longitudinal and vertical acceleration change process of the vehicle in the starting process, and the state of a vehicle auxiliary driving system (which can comprise constant-speed cruising, self-adaptive cruising, lane keeping, departure early warning, lane changing auxiliary, collision early warning and the like).
Edr to reflect the working conditions of safety belts, safety airbags and the like, automatic emergency braking systems, vehicle body stability control systems, anti-lock systems and the like.
It will be appreciated that the automobile Event Data Recorder (EDR) is commonly referred to as "EVENTDATA RECORDER", a system for recording data before and after a vehicle accident, often referred to as a "black box" on an automobile. The primary function of the EDR system is to record data in the event of a vehicle crash or emergency, including pre-crash, upon crash, post-crash data. Such data includes, but is not limited to, vehicle speed, steering angle, engine operating status, throttle pedal position, belt usage status, airbag status, driving assistance system status, and vehicle speed change. EDR information plays an important role in accident investigation, accident cause analysis, accident prevention, vehicle safety performance improvement and the like.
The invention uses special EDR (EVENT DATA Recorder ) reading equipment to acquire EDR data, which is a key step in the traffic accident reconstruction process. EDR is an in-vehicle device for recording key operation data and vehicle state information of a vehicle before and after a specific event (such as a collision) occurs. The invention uses special edr reading equipment to read and store data at the automobile end or disassembles the equipment carrying edr information to a laboratory.
S2, carrying out data fusion and complementation on the on-site investigation data information, the monitoring video image information and the EDR data of the accident vehicle after verification to obtain a data fusion result.
Specifically, the data fusion content related to the invention is the complement and screening of the data information, so that the data information of the case is more comprehensive. For example, information such as road surface trace, vehicle collision position, vehicle running track and the like can be obtained through on-site investigation records, but information such as vehicle running speed, accident occurrence specific time and the like cannot be reflected, the accident time can be determined through the completion of the video content of the monitoring video, the vehicle running speed can be obtained through calculation, but meanwhile, whether the vehicle running speed calculated based on video is accurate or not, the braking or accelerating condition during the accident of the vehicle and the like cannot be determined, and the situation information can be further completed through continuing to fuse EDR information. But if the EDR information is valid and accurate, verification of the data is required.
Judging and verifying the relevance, integrity and validity of edr information, namely judging edr information is left by the accident according to the existing accident information, judging whether recorded data can completely reflect the content of the accident occurrence process, judging whether recorded data information (such as vehicle speed, direction rotation angle and the like) is objective and accurate, judging to obtain a judging result, and determining whether the obtained edr data can be used for field reconstruction.
In the embodiment of the invention, the relevance, the integrity and the validity of edr information are judged and verified:
and (3) verifying relevance:
and the vehicle identification code consistency is that the vehicle identification code of the EDR data record is consistent with the accident vehicle identification code, and the EDR data is derived from the accident vehicle.
The consistency of the power-on period is that the power-on period of the EDR data record during the accident is similar to that of the EDR data read, and the EDR data is further confirmed to be related to the accident.
The consistency of the air bag unfolding condition is that the air bag unfolding condition recorded by EDR data is consistent with the air bag initiation period condition shown by an accident vehicle inspection photo and a vehicle-mounted video, and the relevance of EDR data and the accident is further supported.
The collision form and the time interval are matched, namely the two collision forms and the time interval recorded by the EDR data are matched with the content shown by the accident vehicle inspection photo, the vehicle-mounted video and the scene photo, so that the EDR data reflect the situation of the two collision in the accident.
Integrity verification:
And the integrity of the data record, namely the event data of the EDR data record are all successfully and completely recorded, and the EDR data completely reflect the movement working condition of the accident vehicle in the accident process.
And (3) validity verification:
Tire specification the tire specification when accident vehicle happens accords with factory setting, and the tire is free from abnormal damage, eliminates the influence of the tire specification on EDR vehicle speed accuracy.
And (3) collision analysis, namely matching the two collisions recorded by EDR data with the contents shown by the accident vehicle inspection photo, the vehicle-mounted video and the scene photo, and indicating that the EDR data effectively reflects the accident process.
And analyzing the time node, namely if the EDR data record the two accident data, recording the time interval of the two collision and the driving state in the vehicle, and judging whether braking measures are taken or not, wherein the time node can be used for proving the effectiveness of the EDR data.
In an embodiment of the invention, EDR information is applied to cross-verify the accuracy of traditional information.
And (5) time consistency, namely confirming whether EDR recording time is consistent with investigation recording and monitoring video time.
And (3) in the collision process, comparing the collision form and time recorded by the EDR with the investigation trace and monitoring whether the video content is consistent.
And comparing the EDR speed with the investigation estimated speed and monitoring whether the video estimated speed is consistent or not.
And (3) comparing the driver operation data recorded by the EDR with the driver behaviors in the investigation record and the monitoring video.
And S3, carrying out automatic modeling based on the data fusion result to construct a standardized accident reconstruction flow to obtain an accident reconstruction result, and verifying the accident reconstruction result.
The invention aims at the recombined information and carries out reconstruction application of the information according to the definition of field reconstruction in the technical Specification of road traffic accident reconstruction based on image (SF/T0160-2023).
The invention mainly uses software such as PC-crash or COMSOL Multiphysics and the like to construct and input static space information, and uses the damage trace of people, vehicles and roads added after the accident as a reconstruction target to reconstruct the accident occurrence process more accurately and scientifically.
It will be appreciated that intelligent word recognition is applied to the extraction of Chinese information in incident reports, maintenance logs and other documents. Through OCR technology (Optical Character Recognition ), text in a paper document or scanned item can be converted into an editable text format, thereby facilitating further data processing and analysis. And key information such as accident occurrence time, accident location, accident participators and the like is automatically extracted, so that the workload and the error rate of manual input are reduced.
It can be appreciated that fixed point information capture, namely, by setting specific data capture rules, specific information related to the accident is automatically extracted from a database, a sensor record and other sources. For example, data records are extracted from the sensor network for a period of time before and after the occurrence of an accident. And the unified processing of the data sources with different formats is supported, so that all relevant information is ensured to be completely captured.
It can be understood that the model library is automatically docked, namely, a library containing multiple types of accident analysis models is established, and the most suitable analysis model is automatically selected according to the characteristics of different accidents. For example, for rock burst events, a predictive model specifically designed for such events may be selected. When new data enters the system, an appropriate model is automatically called for processing, and the model configuration does not need to be manually specified or adjusted.
It will be appreciated that efficient automated modeling techniques utilize machine learning algorithms to automatically create or optimize models for accident analysis. This includes the steps of automatically selecting features, adjusting hyper-parameters, training models, etc. The model development process is accelerated through an automation technology, so that the model can adapt to new data and scenes more quickly, and the prediction accuracy and the processing speed are improved.
It can be understood that the standardized accident reconstruction process integrates the technology into one standardized accident reconstruction process, so that each accident analysis is ensured to be carried out according to the same steps, and the consistency and the comparability of the results are ensured. The flow includes, but is not limited to, links of data collection, information extraction, model selection, analysis execution, result interpretation and the like, and each link has definite operation guidelines and technical support.
The application of the techniques helps to construct an efficient accident handling system, not only to quickly and accurately reconstruct the process of accident occurrence, but also to provide powerful data support for future preventive measures. In this way, various potential safety hazards can be better understood and handled, and the probability and influence of accidents are reduced.
Specifically, the reconstruction step of the present invention specifically includes:
and a data acquisition step:
Text information processing, namely automatically identifying and directionally extracting text information by utilizing an OCR technology and a natural language processing technology, and carrying out structural processing.
And the automatic EDR data reading is integrated with EDR data reading equipment, so that automatic reading and analysis of EDR data are realized, and important information related to modeling, such as vehicle speed, steering, braking and the like, is automatically extracted.
And a data processing step:
and (3) image information processing, namely preprocessing the monitoring video image by utilizing a computer vision technology, and extracting information such as vehicle track, collision process and the like.
EDR data processing, namely analyzing the EDR data and converting the EDR data into a format which can be recognized by PC-crash.
And merging and summarizing the preprocessed data to form a complete accident data set, and performing data consistency verification.
PC-crash modeling step:
and (3) model library management, namely establishing a vehicle model library, a scene model library and the like, and carrying out dynamic updating and management.
And the automatic modeling engine is used for automatically matching the corresponding vehicle model and scene model according to the accident data set and setting parameters such as vehicle size, weight, material, collision speed, collision angle and the like.
And the simulation calculation engine runs PC-crash simulation calculation, generates accident reconstruction animation and analyzes the result.
And a result analysis step:
Analyzing accident reconstruction animation, obtaining relevant parameters of the accident occurrence process, and performing visual display.
And comparing the accident reconstruction result with the investigation trace, the monitoring video and the EDR data, and verifying the accuracy of the reconstruction result.
And automatically generating an accident reconstruction report, including accident process description, parameter analysis, result conclusion and the like.
Further, the reconstructed accident procedure requires accurate application edr of the reflected pre-event vehicle conditions and the influence that the passive safety system in the vehicle may have on the damage process of the in-vehicle personnel during the accident procedure. The reconstructed result can be further compared and verified with the information of the accident process image information reaction, and the accuracy of the reconstructed result is ensured.
The platform can be used for further analyzing accident occurrence causes in the accident occurrence process after the reconstruction result is given, and suggesting possible accident causes such as unlegal driving of a driver, distraction or fatigue of the driver, problems in safety technical conditions such as braking or steering of a vehicle, problems in gradient or bending of a road, problems in road adhesion coefficient or drainage function and the like can be carried out, so that support is provided for accident rules, perfection of traffic rules and improvement of traffic facilities, and therefore, the road traffic safety level is improved, and traffic accidents are reduced.
According to the traffic accident reconstruction method based on the automobile event data recording system, a set of perfect and generalized standardized accident reconstruction flow is established. By the functions of intelligent character recognition, information fixed-point grabbing, automatic butt joint of a model database and the like, the automation level of accident reconstruction is greatly improved, and therefore the efficiency of product technology work is improved.
In order to implement the above-described embodiment, as shown in fig. 3, there is also provided a traffic accident reconstruction apparatus 10 based on an automobile event data recording system, comprising,
The data acquisition module 100 is used for acquiring on-site investigation data information, monitoring video image information and EDR data of the accident vehicle after the traffic accident site;
the data fusion module 200 is configured to perform data fusion and complement on the on-site investigation data information, the monitoring video image information and the verified EDR data of the accident vehicle to obtain a data fusion result;
The accident reconstruction module 300 is configured to perform automated modeling based on the data fusion result to construct a standardized accident reconstruction procedure to obtain an accident reconstruction result, and verify the accident reconstruction result.
In one embodiment of the invention, the field investigation data information comprises static space information and accident related information, the monitoring video image information comprises image basic information and accident reflecting information, and the EDR data comprises basic information and working condition information.
In one embodiment of the present invention, the static spatial information includes road surface spatial dimensions, road sign markings, road construction information, road adhesion coefficients;
the accident related information comprises driver information, in-vehicle driving relation, vehicle damage marks and road surface left marks;
the basic image information comprises names, sizes, formats, frame rates, integrity check values and whether the images are recorded clearly or not;
The reflected accident information comprises a vehicle running track, a vehicle collision process, braking before collision and steering before collision;
The basic information comprises vehicle basic information, system state during reading, software and hardware used for reading, data record integrity, data source description and data limitation;
the working condition information comprises running speed, longitudinal acceleration change, transverse acceleration change, collision type, vehicle braking condition, vehicle steering condition, vehicle acceleration condition, engine speed, safety belt and air bag, ABS and AEB working condition and ACC and LDW working condition.
In one embodiment of the invention, EDR data for an accident vehicle is validated, including correlation validation, integrity validation, and validity validation, wherein,
The correlation verification comprises the steps of verifying the consistency of a vehicle identification code of an EDR data record and an accident vehicle identification code to obtain a vehicle identification code consistency result, verifying that the power-on period of the EDR data record is similar to the power-on period of the EDR data record when the accident happens to obtain a power-on period consistency verification result, verifying that the deployment condition of an air bag of the EDR data record is consistent with the initiation time period condition of the air bag shown by an accident vehicle inspection photo and a vehicle-mounted video to obtain an air bag deployment condition consistency verification result, and verifying that the two collision forms and time intervals of the EDR data record are consistent with the content shown by the accident vehicle inspection photo, the vehicle-mounted video and a site photo to obtain a collision form and time interval consistency verification result;
verifying that event data of EDR data records are all successful complete records so as to obtain a data record integrity verification result;
and the validity verification is carried out by carrying out tire specification verification, collision analysis and time node analysis so as to obtain a validity verification result.
In one embodiment of the present invention, the accident reconstruction module is further configured to:
processing the on-site investigation data information by utilizing an OCR technology and a natural language processing technology to automatically identify and directionally extract text information and perform structural processing; processing the monitoring video image information by utilizing a computer vision technology, analyzing the EDR data to be converted into a format which can be identified by a PC-crash model so as to obtain preprocessing data;
The method comprises the steps of establishing a vehicle model library and a scene model library, dynamically updating and managing, automatically matching corresponding vehicle models and scene models according to an accident data set, setting parameters, running PC-crash simulation calculation, and generating an accident reconstruction animation;
Analyzing accident reconstruction animation, obtaining related parameters of the accident occurrence process, visually displaying the accident reconstruction result, comparing the accident reconstruction result with the exploration trace, the monitoring video and the EDR data, verifying the accuracy of the accident reconstruction result, and automatically generating an accident reconstruction report.
According to the traffic accident reconstruction device based on the automobile event data recording system, a set of perfect and generalized standardized accident reconstruction flow is established. By the functions of intelligent character recognition, information fixed-point grabbing, automatic butt joint of a model database and the like, the automation level of accident reconstruction is greatly improved, and therefore the efficiency of product technology work is improved.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.

Claims (10)

1.一种基于汽车事件数据记录系统的交通事故重建方法,其特征在于,包括:1. A traffic accident reconstruction method based on an automobile event data recording system, characterized by comprising: 获取交通事故现场后的现场勘查数据信息、监控视频图像信息以及事故车辆的EDR数据;Obtain on-site investigation data information, surveillance video image information and EDR data of the accident vehicle after the traffic accident scene; 对所述现场勘查数据信息、监控视频图像信息以及验证后的事故车辆的EDR数据进行数据融合补全得到数据融合结果;Performing data fusion and completion on the on-site investigation data information, the monitoring video image information, and the verified EDR data of the accident vehicle to obtain a data fusion result; 基于所述数据融合结果进行自动化建模以构建标准化事故重建流程得到事故重建结果,并验证事故重建结果。Based on the data fusion results, automated modeling is performed to construct a standardized accident reconstruction process to obtain accident reconstruction results, and the accident reconstruction results are verified. 2.根据权利要求1所述的方法,其特征在于,所述现场勘查数据信息,包括:静态空间信息和事故相关信息;所述监控视频图像信息,包括图像基本信息和反映事故信息;所述EDR数据,包括基本信息和工况信息。2. The method according to claim 1 is characterized in that the on-site investigation data information includes: static space information and accident-related information; the monitoring video image information includes basic image information and information reflecting the accident; the EDR data includes basic information and working condition information. 3.根据权利要求2所述的方法,其特征在于,3. The method according to claim 2, characterized in that 所述静态空间信息,包括路面空间尺寸、道路标志标线、道路建设信息、路面附着系数;The static spatial information includes road surface spatial dimensions, road signs and markings, road construction information, and road surface adhesion coefficient; 所述事故相关信息,包括驾驶员信息、车内驾乘关系、车辆损坏痕迹、路面遗留痕迹;The accident-related information includes driver information, driving and passenger relationships in the vehicle, signs of vehicle damage, and marks left on the road surface; 所述图像基本信息,包括名称及大小、格式及帧率、完整性校验值、是否清晰记录;The basic information of the image, including name and size, format and frame rate, integrity check value, and whether it is recorded clearly; 所述反映事故信息,包括车辆行驶轨迹、车辆碰撞过程、碰撞前的制动和碰撞前的转向;The accident information includes the vehicle's driving trajectory, the vehicle's collision process, braking before the collision, and steering before the collision; 所述基本信息,包括车辆基本信息、读取时系统状态、读取所用软硬件、数据记录完整度、数据的来源说明和数据的局限性;The basic information includes basic vehicle information, system status during reading, software and hardware used for reading, data record completeness, data source description and data limitations; 所述工况信息,包括行驶速度、纵向加速度变化、横向加速度变化、碰撞种类、车辆制动情况、车辆转向情况、车辆加速情况、发动机转速、安全带及气囊、ABS及AEB工作情况和ACC及LDW工作情况。The operating condition information includes driving speed, longitudinal acceleration change, lateral acceleration change, collision type, vehicle braking condition, vehicle steering condition, vehicle acceleration condition, engine speed, seat belt and airbag working conditions, ABS and AEB working conditions, and ACC and LDW working conditions. 4.根据权利要求2所述的方法,其特征在于,对事故车辆的EDR数据进行验证,包括:关联性验证、完整性验证和有效性验证;其中,4. The method according to claim 2 is characterized in that the EDR data of the accident vehicle is verified, including: relevance verification, integrity verification and validity verification; wherein, 所述关联性验证:对EDR数据记录的车辆识别代号与事故车辆识别代号一致性的验证,以得到车辆识别码一致性结果;验证EDR数据记录的事故时上电周期与EDR数据读取时的上电周期相近,以得到上电周期一致性验证结果;验证EDR数据记录的安全气囊展开情况与事故车辆检验照片及车载视频所示安全气囊起爆时段情况一致,以得到安全气囊展开情况一致性验证结果;验证EDR数据记录的两次碰撞形态及时间间隔与事故车辆检验照片、车载视频、现场照片所示内容吻合,以得到碰撞形态及时间间隔吻合验证结果;The correlation verification is as follows: verification of the consistency between the vehicle identification code recorded in the EDR data and the accident vehicle identification code, so as to obtain the consistency result of the vehicle identification code; verification that the power-on cycle at the time of the accident recorded in the EDR data is similar to the power-on cycle when the EDR data is read, so as to obtain the consistency verification result of the power-on cycle; verification that the airbag deployment recorded in the EDR data is consistent with the airbag detonation period shown in the accident vehicle inspection photos and the on-board video, so as to obtain the consistency verification result of the airbag deployment; verification that the two collision forms and time intervals recorded in the EDR data are consistent with those shown in the accident vehicle inspection photos, on-board videos, and on-site photos, so as to obtain the collision form and time interval consistency verification result; 所述完整性验证:验证EDR数据记录的事件数据均应表现为成功完整记录,以得到数据记录完整性验证结果;The integrity verification: verifying that the event data recorded in the EDR data should all be represented as successfully and completely recorded, so as to obtain the data record integrity verification result; 所述有效性验证:进行轮胎规格验证、碰撞分析和时间节点分析以得到有效性验证结果。The validity verification: performs tire specification verification, collision analysis and time node analysis to obtain validity verification results. 5.根据权利要求1所述的方法,其特征在于,基于所述数据融合结果进行自动化建模以构建标准化事故重建流程得到事故重建结果,包括:5. The method according to claim 1, characterized in that the automatic modeling is performed based on the data fusion result to construct a standardized accident reconstruction process to obtain the accident reconstruction result, comprising: 利用OCR技术和自然语言处理技术对现场勘查数据信息进行处理,以自动识别和定向提取文本信息,并进行结构化处理;利用计算机视觉技术对监控视频图像信息进行处理,并解析EDR数据以转换为PC-crash模型可识别的格式,以得到预处理数据;将预处理后的数据进行融合得到完整的事故数据集;Use OCR technology and natural language processing technology to process on-site investigation data information to automatically identify and extract text information in a targeted manner, and perform structured processing; use computer vision technology to process surveillance video image information, and parse EDR data to convert it into a format recognizable by the PC-crash model to obtain pre-processed data; fuse the pre-processed data to obtain a complete accident data set; 建立车辆模型库和场景模型库,并进行动态更新和管理;根据事故数据集,自动匹配相应的车辆模型和场景模型,并进行参数设置;运行PC-crash模拟计算,生成事故重建动画;Establish vehicle model library and scene model library, and dynamically update and manage them; automatically match the corresponding vehicle model and scene model according to the accident data set, and set parameters; run PC-crash simulation calculations to generate accident reconstruction animations; 分析事故重建动画,获取事故发生过程的相关参数,并对事故重建结果进行可视化展示;将事故重建结果与勘查痕迹、监控视频和EDR数据进行对比,验证事故重建结果的准确性;自动生成事故重建报告。Analyze the accident reconstruction animation, obtain relevant parameters of the accident process, and visualize the accident reconstruction results; compare the accident reconstruction results with investigation traces, surveillance videos and EDR data to verify the accuracy of the accident reconstruction results; automatically generate an accident reconstruction report. 6.一种基于汽车事件数据记录系统的交通事故重建装置,其特征在于,包括:6. A traffic accident reconstruction device based on an automobile event data recording system, characterized in that it comprises: 数据获取模块,用于获取交通事故现场后的现场勘查数据信息、监控视频图像信息以及事故车辆的EDR数据;The data acquisition module is used to obtain on-site investigation data information, monitoring video image information and EDR data of the accident vehicle after the traffic accident scene; 数据融合模块,用于对所述现场勘查数据信息、监控视频图像信息以及验证后的事故车辆的EDR数据进行数据融合补全得到数据融合结果;A data fusion module is used to perform data fusion and completion on the on-site investigation data information, the monitoring video image information and the verified EDR data of the accident vehicle to obtain a data fusion result; 事故重建模块,用于基于所述数据融合结果进行自动化建模以构建标准化事故重建流程得到事故重建结果,并验证事故重建结果。The accident reconstruction module is used to automatically model the accident based on the data fusion result to construct a standardized accident reconstruction process to obtain the accident reconstruction result, and verify the accident reconstruction result. 7.根据权利要求6所述的装置,其特征在于,所述现场勘查数据信息,包括:静态空间信息和事故相关信息;所述监控视频图像信息,包括图像基本信息和反映事故信息;所述EDR数据,包括基本信息和工况信息。7. The device according to claim 6 is characterized in that the on-site investigation data information includes: static space information and accident-related information; the monitoring video image information includes basic image information and information reflecting the accident; the EDR data includes basic information and working condition information. 8.根据权利要求6所述的装置,其特征在于,8. The device according to claim 6, characterized in that 所述静态空间信息,包括路面空间尺寸、道路标志标线、道路建设信息、路面附着系数;The static spatial information includes road surface spatial dimensions, road signs and markings, road construction information, and road surface adhesion coefficient; 所述事故相关信息,包括驾驶员信息、车内驾乘关系、车辆损坏痕迹、路面遗留痕迹;The accident-related information includes driver information, driving and passenger relationships in the vehicle, signs of vehicle damage, and marks left on the road surface; 所述图像基本信息,包括名称及大小、格式及帧率、完整性校验值、是否清晰记录;The basic information of the image, including name and size, format and frame rate, integrity check value, and whether it is recorded clearly; 所述反映事故信息,包括车辆行驶轨迹、车辆碰撞过程、碰撞前的制动和碰撞前的转向;The accident information includes the vehicle's driving trajectory, the vehicle's collision process, braking before the collision, and steering before the collision; 所述基本信息,包括车辆基本信息、读取时系统状态、读取所用软硬件、数据记录完整度、数据的来源说明和数据的局限性;The basic information includes basic vehicle information, system status during reading, software and hardware used for reading, data record completeness, data source description and data limitations; 所述工况信息,包括行驶速度、纵向加速度变化、横向加速度变化、碰撞种类、车辆制动情况、车辆转向情况、车辆加速情况、发动机转速、安全带及气囊、ABS及AEB工作情况和ACC及LDW工作情况。The operating condition information includes driving speed, longitudinal acceleration change, lateral acceleration change, collision type, vehicle braking condition, vehicle steering condition, vehicle acceleration condition, engine speed, seat belt and airbag working conditions, ABS and AEB working conditions, and ACC and LDW working conditions. 9.根据权利要求7所述的装置,其特征在于,对事故车辆的EDR数据进行验证,包括:关联性验证、完整性验证和有效性验证;其中,9. The device according to claim 7 is characterized in that the verification of the EDR data of the accident vehicle includes: relevance verification, integrity verification and validity verification; wherein, 所述关联性验证:对EDR数据记录的车辆识别代号与事故车辆识别代号一致性的验证,以得到车辆识别码一致性结果;验证EDR数据记录的事故时上电周期与EDR数据读取时的上电周期相近,以得到上电周期一致性验证结果;验证EDR数据记录的安全气囊展开情况与事故车辆检验照片及车载视频所示安全气囊起爆时段情况一致,以得到安全气囊展开情况一致性验证结果;验证EDR数据记录的两次碰撞形态及时间间隔与事故车辆检验照片、车载视频、现场照片所示内容吻合,以得到碰撞形态及时间间隔吻合验证结果;The correlation verification is as follows: verification of the consistency between the vehicle identification code recorded in the EDR data and the accident vehicle identification code, so as to obtain the consistency result of the vehicle identification code; verification that the power-on cycle at the time of the accident recorded in the EDR data is similar to the power-on cycle when the EDR data is read, so as to obtain the consistency verification result of the power-on cycle; verification that the airbag deployment recorded in the EDR data is consistent with the airbag detonation period shown in the accident vehicle inspection photos and the on-board video, so as to obtain the consistency verification result of the airbag deployment; verification that the two collision forms and time intervals recorded in the EDR data are consistent with those shown in the accident vehicle inspection photos, on-board videos, and on-site photos, so as to obtain the collision form and time interval consistency verification result; 所述完整性验证:验证EDR数据记录的事件数据均应表现为成功完整记录,以得到数据记录完整性验证结果;The integrity verification: verifying that the event data recorded in the EDR data should all be represented as successfully and completely recorded, so as to obtain the data record integrity verification result; 所述有效性验证:进行轮胎规格验证、碰撞分析和时间节点分析以得到有效性验证结果。The validity verification: performs tire specification verification, collision analysis and time node analysis to obtain validity verification results. 10.根据权利要求6所述的装置,其特征在于,所述事故重建模块,还用于:10. The device according to claim 6, wherein the accident reconstruction module is further used for: 利用OCR技术和自然语言处理技术对现场勘查数据信息进行处理,以自动识别和定向提取文本信息,并进行结构化处理;利用计算机视觉技术对监控视频图像信息进行处理,并解析EDR数据以转换为PC-crash模型可识别的格式,以得到预处理数据;将预处理后的数据进行融合得到完整的事故数据集;Use OCR technology and natural language processing technology to process on-site investigation data information to automatically identify and extract text information in a targeted manner, and perform structured processing; use computer vision technology to process surveillance video image information, and parse EDR data to convert it into a format recognizable by the PC-crash model to obtain pre-processed data; fuse the pre-processed data to obtain a complete accident data set; 建立车辆模型库和场景模型库,并进行动态更新和管理;根据事故数据集,自动匹配相应的车辆模型和场景模型,并进行参数设置;运行PC-crash模拟计算,生成事故重建动画;Establish vehicle model library and scene model library, and dynamically update and manage them; automatically match the corresponding vehicle model and scene model according to the accident data set, and set parameters; run PC-crash simulation calculations to generate accident reconstruction animations; 分析事故重建动画,获取事故发生过程的相关参数,并对事故重建结果进行可视化展示;将事故重建结果与勘查痕迹、监控视频和EDR数据进行对比,验证事故重建结果的准确性;自动生成事故重建报告。Analyze the accident reconstruction animation, obtain relevant parameters of the accident process, and visualize the accident reconstruction results; compare the accident reconstruction results with investigation traces, surveillance videos and EDR data to verify the accuracy of the accident reconstruction results; automatically generate an accident reconstruction report.
CN202411862950.5A 2024-12-17 2024-12-17 Traffic accident reconstruction method and device based on automobile event data recording system Pending CN119808385A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411862950.5A CN119808385A (en) 2024-12-17 2024-12-17 Traffic accident reconstruction method and device based on automobile event data recording system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411862950.5A CN119808385A (en) 2024-12-17 2024-12-17 Traffic accident reconstruction method and device based on automobile event data recording system

Publications (1)

Publication Number Publication Date
CN119808385A true CN119808385A (en) 2025-04-11

Family

ID=95267092

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411862950.5A Pending CN119808385A (en) 2024-12-17 2024-12-17 Traffic accident reconstruction method and device based on automobile event data recording system

Country Status (1)

Country Link
CN (1) CN119808385A (en)

Similar Documents

Publication Publication Date Title
CN107195024B (en) Universal vehicle operation data record system and processing method
CN110738842A (en) Accident responsibility division and behavior analysis method, device, equipment and storage medium
Lu et al. Performance evaluation of surrogate measures of safety with naturalistic driving data
CN113343461A (en) Simulation method and device for automatic driving vehicle, electronic equipment and storage medium
CN107833312A (en) Driving dangerousness coefficient appraisal procedure and device based on multi-modal information
CN105976450A (en) Unmanned vehicle data processing method and device, and black box system
TW202514491A (en) Non-transitory computer-readable media, method and computing system for measuring a performance of a driver of a vehicle
KR102400842B1 (en) Service methods for providing information on traffic accidents
CN113496213B (en) Method, device, system and storage medium for determining target perception data
CN108364476B (en) Method and device for acquiring Internet of Vehicles information
CN111341106B (en) Traffic early warning method, device and equipment
Schicktanz et al. Detection and analysis of corner case scenarios at a signalized urban intersection
CN119205354B (en) Automobile monitoring method and system for automobile finance
US20230237584A1 (en) Systems and methods for evaluating vehicle insurance claims
CN119808385A (en) Traffic accident reconstruction method and device based on automobile event data recording system
Ameksa et al. Toward flexible data collection of driving behaviour
CN118606163A (en) Computer-implemented method and system for creating a scene library
CN118097626A (en) Driver abnormal behavior identification method, device, equipment and storage medium
CN114244837B (en) Traffic accident liability determination method, blockchain system, vehicle-mounted equipment and client
CN112633163B (en) Detection method for realizing illegal operation vehicle detection based on machine learning algorithm
KR100938549B1 (en) Black box based accident verification system and method
CN114155476B (en) AEB (automatic Emergency bank) accident scene identification method, device, equipment and medium
US20250045491A1 (en) Simulation scenarios in vehicle safety testing
EP4191462A1 (en) Method and system for quantifying vehicle requirement
CN119379745B (en) Vehicle track restoration method, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination