WO2022233099A1 - 基于联网adas调查路域交通违法行为时空特征的方法 - Google Patents
基于联网adas调查路域交通违法行为时空特征的方法 Download PDFInfo
- Publication number
- WO2022233099A1 WO2022233099A1 PCT/CN2021/112101 CN2021112101W WO2022233099A1 WO 2022233099 A1 WO2022233099 A1 WO 2022233099A1 CN 2021112101 W CN2021112101 W CN 2021112101W WO 2022233099 A1 WO2022233099 A1 WO 2022233099A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- road
- traffic
- traffic violations
- violations
- information
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 claims abstract description 48
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 claims abstract description 48
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 claims abstract description 48
- 238000009826 distribution Methods 0.000 claims abstract description 47
- 230000002776 aggregation Effects 0.000 claims abstract description 15
- 238000004220 aggregation Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000007619 statistical method Methods 0.000 claims abstract description 6
- 238000007621 cluster analysis Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 21
- 238000010586 diagram Methods 0.000 abstract description 6
- 230000002265 prevention Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 3
- 238000004806 packaging method and process Methods 0.000 abstract 1
- 238000012544 monitoring process Methods 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
- G08G1/054—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed photographing overspeeding vehicles
Definitions
- the invention relates to the fields of traffic safety and intelligent traffic, in particular to a method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS.
- ADAS with rich functions and strong environmental awareness has been widely used in cars and commercial vehicles, which makes it possible for ADAS to obtain a large amount of traffic violation data.
- the data collected by ADAS is mostly used offline, and effective data has not been uploaded online, so it is impossible to comprehensively collect traffic violations.
- the traffic data collected by a large number of vehicles equipped with ADAS can provide sufficient data sources for the investigation of traffic violations after network integration and analysis. Make full use of existing resources to provide support for the prevention and control of regional traffic accident risks.
- the main purpose of the present invention is to provide a method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS, which can quickly understand the state of the distribution of violations and provide support for road traffic risk prevention and control.
- a method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS including the following steps:
- S2 Encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;
- the information on vehicle traffic violations includes illegal parking, illegal lane change, speeding, illegal U-turn/left turn, driving on the line, wrong-way traffic, pedestrian crossing the road, and driving/vehicle running a red light.
- step S1 the urban road traffic system performs lane line recognition, vehicle feature recognition, vehicle motion trajectory recognition, and signal lights by positioning and image recognition methods according to the forward road traffic video collected by the networked ADAS vehicle through the video capture camera. Recognition, road sign and marking recognition, and then based on the identified basic road information and forward vehicle information, the machine learning algorithm is used to identify the traffic violations of forward vehicles.
- step S3 is:
- the urban area is divided into n sections, and the longitude and latitude information L n , B n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length.
- L n , B n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length.
- number the road segments as 1, 2...n in sequence, where n is a natural number;
- the data points are matched to each target road section in the city map, and the spatiotemporal distribution map of traffic illegal acts is obtained.
- step S4 is:
- the spatial clustering is based on the latitude and longitude location distribution of traffic violations
- the time clustering is based on the distribution of traffic violations on the time axis.
- the resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.
- step S4 the time information recorded in the structured data of traffic violations is integrated, and divided into day, night, or interested time periods of morning peak and evening peak according to the time stamp, and then the latitude and longitude are used.
- the information associates traffic violations with the corresponding road sections in the selected road area, and obtains the distribution and aggregation of traffic violations on the corresponding road sections within a specific time period through statistical and cluster analysis. identify the situation.
- the present invention also provides a system for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS, including:
- the information acquisition module is used to acquire the traffic violation information of forward vehicles sensed by all connected ADAS vehicles in the urban road traffic system;
- the encoding module is used to encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;
- the matching module is used to upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;
- the analysis module is used to perform statistical analysis on the spatiotemporal state of road traffic violations to obtain the frequency of occurrence of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution of road traffic violations to obtain the aggregated road sections and aggregated time periods of traffic violations.
- the matching module is specifically used for:
- the urban area is divided into n sections, and the longitude and latitude information L n , B n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length.
- L n , B n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length.
- number the road segments as 1, 2...n in sequence, where n is a natural number;
- the structured data of one illegal act is taken as a data point, and the data points are matched to each target road section in the city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic illegal acts is obtained.
- the analysis module is specifically used for:
- the spatial clustering is based on the latitude and longitude location distribution of traffic violations
- the time clustering is based on the distribution of traffic violations on the time axis.
- the resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.
- the present invention also provides a computer storage medium, which can be executed by a processor and stores a computer program in the computer program.
- the present invention can measure the required information by using the networked ADAS vehicle, does not need to arrange a detector, and reduces a large number of roadside equipment requirements.
- the present invention uses networked ADAS to identify and count traffic violations in the road area, and can further analyze and obtain the gathering sections and time periods for illegal acts, which can accurately and real-time reflect the characteristics of traffic violations, and has a certain significance for improving the level of road risk prevention and control. .
- FIG. 1 is a flowchart of a method for investigating the spatiotemporal characteristics of road traffic violations based on networked ADAS according to an embodiment of the present invention
- FIG. 2 is a flowchart of a method for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS according to another embodiment of the present invention
- Figure 3a is a schematic diagram of driving on the line with the monitoring record of some illegal behaviors of the vehicle ahead;
- Figure 3b is a schematic diagram of the illegal U-turn in the monitoring record of some illegal behaviors of the vehicle ahead;
- FIG. 4 is a schematic diagram of a method for dividing a road segment
- Figure 5 is a schematic diagram of the spatial distribution characteristics of traffic violations
- FIG. 6 is a schematic structural diagram of a system for investigating spatiotemporal characteristics of road traffic violations based on a networked ADAS according to an embodiment of the present invention.
- the first step is to use the built-in image processing algorithm in ADAS (Advanced Driver Assistant System, ADAS) to extract and analyze the forward video information recorded by the vehicle camera during the driving process of the vehicle, and identify the illegal behavior of the vehicle ahead, And encode the traffic violations collected by ADAS.
- the second step is to package and upload the code of vehicle violations collected by a large number of connected ADAS vehicles, the corresponding time information and the location information obtained by GPS to the traffic data cloud platform, and then use the map matching algorithm to match the collected road traffic violations. to the regional road.
- the third step is to perform preliminary statistics on different road sections, time periods, and illegal acts based on the illegal behavior data in the traffic data cloud platform, and perform cluster analysis on the spatiotemporal distribution of the obtained road traffic violations. Aggregate road segments and aggregate time periods.
- a method for identifying and counting the spatiotemporal characteristics of road traffic violations based on networked ADAS includes the steps:
- S102 Encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the violating vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the violating vehicle into structured data;
- S104 Statistically analyze the spatiotemporal state of road traffic violations to obtain the occurrence frequency of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution state of road traffic violations to obtain aggregated road sections and aggregation periods of traffic violations.
- another embodiment of the present invention is based on a method for identifying and counting the spatiotemporal characteristics of road traffic violations based on networked ADAS, the method comprising:
- the ADAS vehicle records real-time video information of forward traffic operating conditions during driving, and analyzes the recorded video with the help of a recognition processor module integrated in the video camera, and perceives and collects traffic violations of forward vehicles.
- the traffic violation identification and collection system of the present invention includes a video capture camera, a positioning module, an identification processor module, and a video capture camera.
- the video capture camera also has built-in image processing algorithms, which can intelligently identify vehicles ahead, lane lines, roadside signs (such as no parking, no U-turn, etc.), markings (dotted and solid lines, grid lines, etc.) and Traffic lights, etc.
- the positioning module adopts high-precision navigation devices such as GPS and Beidou, which can obtain the accurate latitude and longitude information and accurate time information of the driving recorder. Combined with the shooting range of the camera, it can more accurately judge the location information and accurate time information of the illegal behavior of the vehicle ahead.
- the recognition processor module is built in the video capture camera, and the functions implemented by the camera depend on the algorithms built into the processor.
- the recognition processing module is based on an embedded system and is used to process the information collected by the video camera, and to The location information stored by the location module. Identify the processor module as the core of the system. This module is based on an embedded system and integrates various image recognition algorithms, including lane line recognition, vehicle feature recognition, vehicle motion trajectory recognition, signal light recognition, and road sign marking recognition.
- the processor can detect the relative position of the vehicle ahead and the lane line, and the system will automatically trigger when it finds the vehicle in front of the line pressing behavior to store and capture data; the built-in chip of the processor can intelligently identify each As shown in Figure 3b, the processor recognizes the "No U-turn" sign ahead, and at the same time recognizes that the vehicle has a U-turn motion pattern according to the trajectory of the vehicle ahead. At this time, the system also starts automatically and begins to record the vehicle ahead. illegal behavior.
- the code of each traffic violation is unique. After ADAS recognizes the violation of the vehicle ahead, it can more accurately judge the violation of the vehicle ahead by combining the video capture camera and the high-precision navigation system in the positioning module. location information and accurate time information. The code of traffic violations, the time of occurrence of traffic violations and the location of traffic violations are combined into complete structured data, and the data is transmitted to the traffic data cloud platform using the in-vehicle network.
- the regional roads are selected, and the regional roads are divided into different sections, and the obtained structured data of traffic violations is matched in the map by using the map matching algorithm, and is associated with the sections in the selected regional roads.
- the urban area can be divided into n road sections by adopting the principle that adjacent intersections are one section, and the longitude and latitude information L o and La at the center point O of each intersection are collected, The actual distance between two intersections is the segment length. Then the road segments are numbered as 1, 2...n in sequence, and the four corner points of each road segment represent the range of the road segment; among them:
- Road Loc ⁇ (L o1 ,L a1 ,),(L o2 ,L a2 ),...,(L on ,L an ) ⁇ .
- road segment matching is performed on the structured data of traffic violations uploaded to the data cloud platform to obtain the spatiotemporal distribution characteristics of traffic violations.
- the structured data of an illegal act can also be used as a data point, and the data points are matched to each target road section in the ArcGIS city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic violations can be obtained, as shown in Figure 5.
- the spatial clustering is based on the longitude and latitude location distribution of the traffic violations
- the time clustering is based on the distribution of the traffic violations on the time axis.
- the number of clusters is determined according to the clustering effect.
- the obtained cluster centers are the aggregation points of traffic violations in time and space.
- the embodiment of the present invention is based on a networked ADAS system for investigating the spatiotemporal characteristics of road traffic violations, including:
- the information acquisition module is used to acquire the traffic violation information of forward vehicles sensed by all connected ADAS vehicles in the urban road traffic system;
- the encoding module is used to encode the obtained traffic violation information, determine the time when the traffic violation occurred and the location of the illegal vehicle at that moment, and package the traffic violation code, violation time, and longitude and latitude of the illegal vehicle into structured data;
- the matching module is used to upload the structured data to the traffic data cloud platform, match the traffic violations on the road sections in the selected area according to the time information and latitude and longitude information, and output the time-space distribution map of the traffic violations in each time period;
- the analysis module is used to perform statistical analysis on the spatiotemporal state of road traffic violations to obtain the frequency of occurrence of traffic violations in each road section; perform cluster analysis on the spatiotemporal distribution of road traffic violations to obtain the aggregated road sections and aggregated time periods of traffic violations.
- the matching module is specifically used for:
- the urban area is divided into n sections, and the longitude and latitude information L n , B n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length.
- L n , B n at the center point O of each intersection is collected, and the actual distance between the two intersections is the section length.
- number the road segments as 1, 2...n in sequence, where n is a natural number;
- the structured data of one illegal act is taken as a data point, and the data points are matched to each target road section in the city map according to the collected latitude and longitude coordinates, and the spatiotemporal distribution map of traffic illegal acts is obtained.
- analysis module is specifically used for:
- the spatial clustering is based on the latitude and longitude location distribution of traffic violations
- the time clustering is based on the distribution of traffic violations on the time axis.
- the resulting spatiotemporal clustering centers are the aggregation points of traffic violations in time and space.
- the above-mentioned system for investigating spatiotemporal characteristics of road traffic violations based on networked ADAS is mainly used to realize the method for investigating spatiotemporal characteristics of roadway traffic violations based on networked ADAS in the above embodiment, and the template implementation method has the same functions, which will not be repeated here.
- the present invention also provides a computer storage medium, which can be executed by a processor, and stores a computer program in the computer program.
- the present invention has the following advantages:
- the required information can be measured by using ADAS vehicles, and there is no need to deploy detectors, reducing the demand for a large number of roadside equipment;
- the method proposed by the present invention is suitable for most cities, the detection equipment is not easily affected by the environment, weather, etc., and the measurement accuracy is high;
- ADAS vehicles are the development direction of the future automobile industry, and also cater to the trend of intelligent transportation development.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Remote Sensing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种基于联网ADAS调查路域交通违法行为时空特征的方法,包括:获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;对交通违法行为信息进行编码,并打包为结构化数据;将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。本发明能准确、实时地反应交通违法行为的特征,对于提升道路风险防控水平具有一定意义。
Description
本发明涉及交通安全及智能交通领域,尤其涉及一种基于联网ADAS调查路域交通违法行为时空特征的方法。
我国道路交通事故频发,道路交通事故致死率高居不下。近年来,随着电子产业和IT行业的迅猛发展,基于图像处理的道路交通监控、管理越来越多的应用到了道路交通安全研究中。
据统计,我国70%以上的道路安装有监控摄像头,基于监控摄像头的道路交通车辆违法行为记录与监控,可利用图像处理与模式识别的方法,识别道路交通环境中的车道线、信号灯、标志标线等,根据车辆的轨迹特性、运动状态判断车辆的运动模式,为采集交通违法行为提供有力证据。然而,在一些路侧摄像头无法覆盖或因道路交通形成遮挡导致摄像头无法拍摄的情况下,交通事故肇事者往往会存在投机心理,为事故的侦破带来一定的困难。此外,交管部门安装的电子警察仅能覆盖很小的区域或极少的路段,只能在特定区域实现违法取证,不能覆盖全路网。
目前,具有丰富功能和强大环境感知能力的ADAS已普遍应用于小汽车和营运车辆,这让ADAS获取大量交通违法行为数据成为可能。然而,目前ADAS采集的数据多离线使用,未联网上传有效数据,无法全面采集交通违法行为。 针对目前情况而言,大量装备有ADAS的车辆采集的交通数据经联网整合、分析后能够为调查交通违法行为提供充足的数据源,若能利用联网ADAS数据记录分析前方车辆的违法行为,则能充分利用现有资源,为区域交通事故风险防控提供支撑。
发明内容
本发明主要目的提供一种基于联网ADAS调查路域交通违法行为时空特征的方法,该方法能够快了解违法行为分布的状态,为道路交通风险防控提供支撑。
本发明所采用的技术方案是:
提供一种基于联网ADAS调查路域交通违法行为时空特征的方法,包括以下步骤:
S1、获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;
S2、对获取的交通违法行为信息进行编码,确定交通违法行为发生的时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据;
S3、将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;
S4、对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
接上述技术方案,车辆交通违法行为信息包括违规停车、违法换道、超速行驶、违法掉头/左转、压线行驶、车辆逆行、行人横穿马路、行车/车辆闯红灯。
接上述技术方案,步骤S1中,城市道路交通***根据联网ADAS车辆通过视频采集摄像头采集的前向道路交通视频,通过定位和图像识别方法进行车道线识别、车辆特征识别、车辆运动轨迹识别、信号灯识别、道路标志标线识别,再基于识别的基本道路信息与前向车辆信息,通过机器学习算法识别前向车辆交通违法行为。
接上述技术方案,步骤S3的具体方法为:
采取相邻交叉口为一路段原则,将城市区域划分为n个的路段,并采集各个交叉口中心点O处的经纬度信息L
n、B
n,两个交叉口之间的实际距离为路段长度,并按照依次顺序将路段编号为1、2……n,n为自然数;
将一次违法行为结构化数据作为一个数据点,根据采集到的经纬度坐标在城市地图中将数据点匹配到各个目标路段,获得交通违法行为时空分布图。
接上述技术方案,步骤S4的具体方法为:
匹配出目标路段的交通违法行为分布情况后,先对路段的交通违法行为进行统计,记录目标时间段内各种违法行为发生的频次;再对匹配在路段上的交通违法行为进行时空聚类,空间聚类基于交通违法行为的经纬度位置分布,时间聚类基于交通违法行为在时间轴上的分布,所得时空聚类中心为交通违法行为在时间和空间上的聚集点。
接上述技术方案,步骤S4中,将交通违法行为的结构化数据中记录的时间信息进行整合,按照时间戳划分为白天、黑夜,或者早高峰、晚高峰的感兴趣时间段,然后再利用经纬度信息将交通违法行为与选定道路区域内的对 应路段进行关联,通过统计和聚类分析获取对应路段在特定时间段内交通违法行为分布情况和聚集情况,对不同时间段不同路段的违法行为发生情况进行辨识。
本发明还提供一种基于联网ADAS调查路域交通违法行为时空特征的***,包括:
信息获取模块,用于获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;
编码模块,用于对获取的交通违法行为信息进行编码,确定交通违法行为发生的时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据;
匹配模块,用于将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;
分析模块,用于对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
接上述技术方案,匹配模块具体用于:
采取相邻交叉口为一路段原则,将城市区域划分为n个的路段,并采集各个交叉口中心点O处的经纬度信息L
n、B
n,两个交叉口之间的实际距离为路段长度,并按照依次顺序将路段编号为1、2……n,n为自然数;
并将一次违法行为结构化数据作为一个数据点,根据采集到的经纬度坐标在城市地图中将数据点匹配到各个目标路段,获得交通违法行为时空分布图。
接上述技术方案,分析模块具体用于:
匹配出目标路段的交通违法行为分布情况后,先对路段的交通违法行为进行统计,记录目标时间段内各种违法行为发生的频次;再对匹配在路段上的交通违法行为进行时空聚类,空间聚类基于交通违法行为的经纬度位置分布,时间聚类基于交通违法行为在时间轴上的分布,所得时空聚类中心为交通违法行为在时间和空间上的聚集点。
本发明还提供了一种计算机存储介质,其可被处理器执行,其内存储有计算机程序,该计算机程序执行上述技术方案所述的基于联网ADAS调查路域交通违法行为时空特征的方法。
本发明产生的有益效果是:本发明利用联网ADAS车辆即可测得所需要的信息,不需要布设检测器,减少了大量路侧设备需求。且本发明利用联网ADAS识别和统计路域交通违法行为,可进一步分析得出违法行为聚集路段和聚集时段,能准确、实时地反应交通违法行为的特征,对于提升道路风险防控水平具有一定意义。
下面将结合附图及实施例对本发明作进一步说明,附图中:
图1是本发明实施例基于联网ADAS调查路域交通违法行为时空特征的方法的流程图;
图2是本发明另一实施例基于联网ADAS调查路域交通违法行为时空特征的方法的流程图;
图3a为前方车辆部分违规行为监控记录压线行驶示意图;
图3b为前方车辆部分违规行为监控记录违规掉头示意图;
图4为划分路段方法示意图;
图5为交通违法行为空间分布特征示意图;
图6是本发明实施例基于联网ADAS调查路域交通违法行为时空特征的***结构示意图。
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。
本发明的主要思路是:第一步是使用ADAS(Advanced Driver Assistant System,ADAS)中内置的图像处理算法提取并分析车辆行驶过程中车载摄像头记录的前向视频信息,识别前方车辆的违法行为,并将ADAS采集的交通违法行为进行编码。第二步是将大量安装有联网ADAS车辆收集的车辆违法行为编码及对应的时间信息和GPS即时获取的位置信息打包上传至交通数据云平台,然后使用地图匹配算法将采集的道路交通违法行为匹配到区域路段。第三步是根据交通数据云平台中违法行为数据,可对不同路段、时间段、违法行为进行初步统计性,对获取的道路交通违法行为时空分布状态进行聚类分析,可得到交通违法行为的聚集路段和聚集时段。
如图1所示,本发明一个实施例基于联网ADAS识别和统计路域交通违法行为时空特征的方法包括步骤:
S101、获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;
S102、对获取的交通违法行为信息进行编码,确定交通违法行为发生的 时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据;
S103、将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;
S104、对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
如图2所示,本发明另一实施例基于联网ADAS识别和统计路域交通违法行为时空特征的方法,该方法包括:
S
1、ADAS车辆在行驶过程中实时记录前向交通运行状况视频信息,借助集成于视频摄像头中的识别处理器模块,对记录的视频进行解析,感知并采集前向车辆交通违法行为。
前向车辆交通违法行为信息,包括违规停车、违法换道、超速行驶、违法掉头/左转、压线行驶、车辆逆行、行人横穿马路、行车/车辆闯红灯等。
需要说明的是,本发明的交通违法行为识别采集***包括视频采集摄像头、定位模块和识别处理器模块,视频采集摄像头。
视频采集摄像头具有常规监控功能外,还内置有图像处理算法,能智能识别前方车辆、车道线、路旁标志(如禁停、严禁掉头等)、标线(虚实线、网格线等)和红绿灯等信息。
定位模块采用GPS、北斗等高精度导航装置,能获取本行车记录仪精确的经纬度信息、准确时间信息,结合摄像头的拍摄范围,可较为准确的判断前方车辆违法行为的位置信息、准确时间信息。
识别处理器模块内置在视频采集摄像头中,摄像头所实现的功能依赖于处理器内置的算法,该识别处理模块基于嵌入式***,用于对视频摄像头采集到的信息进行处理,同时读取违规时的定位模块存储的位置信息。识别处理器模块为本***的核心。该模块基于嵌入式***,集成有各种图像识别算法,包括车道线识别、车辆特征识别、车辆运动轨迹识别、信号灯识别、道路标志标线识别等。
如图3a所示,处理器可检测到前方车辆与车道线的相对位置,发现前方车辆的压线行驶行为时本***即自动触发,进行数据存储与抓拍;处理器内置的芯片可智能识别各类标志标线,在图3b所示,处理器识别到前方的“禁止掉头”标志,同时根据前方车辆的轨迹识别出车辆存在掉头的运动模式,此时,***亦自动启动,开始记录前方车辆的违法行为。
S
3、对获取的交通违法行为进行编码,确定交通违法行为发生的时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据。
需要说明的是,每种交通违法行为的编码均是唯一的,ADAS在识别出前方车辆的违法行为后,结合视频采集摄像头和定位模块中的高精度导航***可较为准确的判断前方车辆违法行为的位置信息、准确时间信息。将交通违法行为编码、交通违法行为发生时间和交通违法行为发生位置合并为打包为完整的结构数据,利用车载网络将数据传输至交通数据云平台。
S
3、将所有装配联网ADAS车辆采集的结构化数据上传至交通数据云平台, 根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图。
具体为选定区域道路,将区域道路划分成不同的路段,使用地图匹配算法将获取的交通违法行为结构化数据匹配在地图中,与选定区域道路内的路段进行关联。
需要说明的是,如图4所示,可采取相邻交叉口为一路段原则将该城市区域划分为n个的路段,并采集各个交叉口中心点O处的经纬度信息L
o、L
a,两个交叉口之间的实际距离即为路段长度。然后按照依次顺序将该路段编号为1、2……n,每个路段的4个角点表征路段的范围;其中:
Road
Loc={(L
o1,L
a1,),(L
o2,L
a2),…,(L
on,L
an)}。
在此基础上,对上传至数据云平台的交通违法行为结构化数据进行路段匹配,获得交通违法行为的时空分布特征。
Match:{(lon
i,lat
i)∈Road
Loc,T
i∈T
seg,i=1,…,n}
还可将一次违法行为结构化数据作为一个数据点,根据采集到的经纬度坐标在ArcGIS的城市地图中将数据点匹配到各个目标路段,获得交通违法行为时空分布图,如图5所示。
S
4、对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次,对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
需要说明的是:匹配出目标路段的交通违法行为分布情况后,先对路段的交通违法行为进行统计,记录目标时间段内各种违法行为发生的频次,以早高峰时间段内不同路段的违法行为发生频次为例:
路段 | 1 | 2 | 3 | …… | n |
压线行驶次数 | x 1 | x 2 | x 3 | …… | x n |
违法掉头次数 | y 1 | y 2 | y 3 | …… | y n |
超速行驶次数 | z 1 | z 2 | z 3 | …… | z n |
违规停车次数 | m 1 | m 2 | m 3 | …… | m 4 |
…… | …… | …… | …… | …… | …… |
行车/车辆闯红灯次数 | n 1 | n 2 | n 3 | …… | n 4 |
再对匹配在路段上的交通违法行为进行时空聚类,空间聚类基于交通违法行为的经纬度位置分布,时间聚类基于交通违法行为在时间轴上的分布,根据聚类效果确定聚类数,所得聚类中心即为交通违法行为在时间和空间上的聚集点。
如图6所示,本发明实施例基于联网ADAS调查路域交通违法行为时空特征的***,包括:
信息获取模块,用于获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;
编码模块,用于对获取的交通违法行为信息进行编码,确定交通违法行为发生的时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据;
匹配模块,用于将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;
分析模块,用于对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
进一步地,匹配模块具体用于:
采取相邻交叉口为一路段原则,将城市区域划分为n个的路段,并采集 各个交叉口中心点O处的经纬度信息L
n、B
n,两个交叉口之间的实际距离为路段长度,并按照依次顺序将路段编号为1、2……n,n为自然数;
并将一次违法行为结构化数据作为一个数据点,根据采集到的经纬度坐标在城市地图中将数据点匹配到各个目标路段,获得交通违法行为时空分布图。
进一步地,分析模块具体用于:
匹配出目标路段的交通违法行为分布情况后,先对路段的交通违法行为进行统计,记录目标时间段内各种违法行为发生的频次;再对匹配在路段上的交通违法行为进行时空聚类,空间聚类基于交通违法行为的经纬度位置分布,时间聚类基于交通违法行为在时间轴上的分布,所得时空聚类中心为交通违法行为在时间和空间上的聚集点。
上述基于联网ADAS调查路域交通违法行为时空特征的***主要用于实现上述实施例基于联网ADAS调查路域交通违法行为时空特征的方法,模板实现方法的相同功能,在此不赘述。
本发明还提供了一种计算机存储介质,其可被处理器执行,其内存储有计算机程序,该计算机程序执行上述实施例的基于联网ADAS调查路域交通违法行为时空特征的方法。
综上,本发明有以下优点:
(1)利用ADAS车辆即可测的所需要的信息,不需要布设检测器,减少了大量路侧设备需求;
(2)覆盖范围广,数据精度高,相比现有的违法行为采集技术,利用ADAS车辆识别和统计交通违法行为能够弥补道路设施覆盖范围不足,更客观直接地反应路段交通违法行为的分布状态。
(3)适用性强,本发明提出的方法适合绝大多数的城市,检测设备不易受环境、天气等的影响,且测算精度较高;
(4)符合未来交通领域的发展趋势,ADAS汽车是未来汽车行业发展的方向,也迎合了交通智能化发展的趋势。
应当理解的是,对本领域普通技术人员来说,可以根据上述说明加以改进或变换,而所有这些改进和变换都应属于本发明所附权利要求的保护范围。
Claims (10)
- 一种基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,包括以下步骤:S1、获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;S2、对获取的交通违法行为信息进行编码,确定交通违法行为发生的时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据;S3、将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;S4、对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
- 根据权利要求1所述的基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,车辆交通违法行为信息包括违规停车、违法换道、超速行驶、违法掉头/左转、压线行驶、车辆逆行、行人横穿马路、行车/车辆闯红灯。
- 根据权利要求1所述的基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,步骤S1中,城市道路交通***根据联网ADAS车辆通过视频采集摄像头采集的前向道路交通视频,通过定位和图像识别方法进行车道线识别、车辆特征识别、车辆运动轨迹识别、信号灯识别、道路标志 标线识别,再基于识别的基本道路信息与前向车辆信息,通过机器学习算法识别前向车辆交通违法行为。
- 根据权利要求1所述的基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,步骤S3的具体方法为:采取相邻交叉口为一路段原则,将城市区域划分为n个的路段,并采集各个交叉口中心点O处的经纬度信息L n、B n,两个交叉口之间的实际距离为路段长度,并按照依次顺序将路段编号为1、2……n,n为自然数;将一次违法行为结构化数据作为一个数据点,根据采集到的经纬度坐标在城市地图中将数据点匹配到各个目标路段,获得交通违法行为时空分布图。
- 根据权利要求1所述的基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,步骤S4的具体方法为:匹配出目标路段的交通违法行为分布情况后,先对路段的交通违法行为进行统计,记录目标时间段内各种违法行为发生的频次;再对匹配在路段上的交通违法行为进行时空聚类,空间聚类基于交通违法行为的经纬度位置分布,时间聚类基于交通违法行为在时间轴上的分布,所得时空聚类中心为交通违法行为在时间和空间上的聚集点。
- 根据权利要求1所述的基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,步骤S4中,将交通违法行为的结构化数据中记录的时间信息进行整合,按照时间戳划分为白天、黑夜,或者早高峰、晚高峰的感兴趣时间段,然后再利用经纬度信息将交通违法行为与选定道路区域内的对应路段进行关联,通过统计和聚类分析获取对应路段在特定时间段内交通违法行为分布情况和聚集情况,对不同时间段不同路段的违法行为发生情况进行辨识。
- 一种基于联网ADAS调查路域交通违法行为时空特征的***,其特征在于,包括:信息获取模块,用于获取城市道路交通***内所有联网ADAS车辆在行驶过程中感知到的前向车辆交通违法行为信息;编码模块,用于对获取的交通违法行为信息进行编码,确定交通违法行为发生的时刻和该时刻下违规车辆所处的位置,将交通违规编码、违规时间和违规车辆经纬度打包为结构化数据;匹配模块,用于将结构化数据上传至交通数据云平台,根据时间信息和经纬度信息将交通违法行为在选定区域道路内的路段上进行匹配,输出各时间段内交通违法行为时空分布图;分析模块,用于对道路交通违法行为时空状态进行统计分析,获取各路段交通违法行为发生频次;并对道路交通违法行为时空分布状态进行聚类分析,得到交通违法行为的聚集路段和聚集时段。
- 根据权利要求7所述的基于联网ADAS调查路域交通违法行为时空特征的***,其特征在于,匹配模块具体用于:采取相邻交叉口为一路段原则,将城市区域划分为n个的路段,并采集各个交叉口中心点O处的经纬度信息L n、B n,两个交叉口之间的实际距离为路段长度,并按照依次顺序将路段编号为1、2……n,n为自然数;并将一次违法行为结构化数据作为一个数据点,根据采集到的经纬度坐标在城市地图中将数据点匹配到各个目标路段,获得交通违法行为时空分布图。
- 根据权利要求7所述的基于联网ADAS调查路域交通违法行为时空特征的方法,其特征在于,分析模块具体用于:匹配出目标路段的交通违法行为分布情况后,先对路段的交通违法行为进行统计,记录目标时间段内各种违法行为发生的频次;再对匹配在路段上的交通违法行为进行时空聚类,空间聚类基于交通违法行为的经纬度位置分布,时间聚类基于交通违法行为在时间轴上的分布,所得时空聚类中心为交通违法行为在时间和空间上的聚集点。
- 一种计算机存储介质,其特征在于,其内存储有可被处理器执行的计算机程序,该计算机程序执行权利要求1-6中任一项所述的基于联网ADAS调查路域交通违法行为时空特征的方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110493304.6 | 2021-05-07 | ||
CN202110493304.6A CN113362590A (zh) | 2021-05-07 | 2021-05-07 | 基于联网adas调查路域交通违法行为时空特征的方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022233099A1 true WO2022233099A1 (zh) | 2022-11-10 |
Family
ID=77526051
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/112101 WO2022233099A1 (zh) | 2021-05-07 | 2021-08-11 | 基于联网adas调查路域交通违法行为时空特征的方法 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113362590A (zh) |
WO (1) | WO2022233099A1 (zh) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105096594A (zh) * | 2015-06-30 | 2015-11-25 | 北京奇虎科技有限公司 | 基于行车记录仪的信息关联方法、装置及*** |
CN105551110A (zh) * | 2016-02-05 | 2016-05-04 | 北京奇虎科技有限公司 | 一种行车数据记录方法、装置和*** |
CN107766401A (zh) * | 2017-05-26 | 2018-03-06 | 温州市勘察测绘研究院 | 基于大数据的人行道违停分析方法及*** |
CN209281615U (zh) * | 2018-11-28 | 2019-08-20 | 北京万集科技股份有限公司 | 一种基于行车记录仪违章抓拍*** |
CN110459057A (zh) * | 2019-07-29 | 2019-11-15 | 湖南湖芯信息科技有限公司 | 基于大众监督的车载抓拍交通违规事件处理*** |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130265423A1 (en) * | 2012-04-06 | 2013-10-10 | Xerox Corporation | Video-based detector and notifier for short-term parking violation enforcement |
CN104899198A (zh) * | 2014-03-04 | 2015-09-09 | 苏州工业园区格网信息科技有限公司 | 基于gis地图的事件时空数据分析方法 |
CN108257383A (zh) * | 2018-01-16 | 2018-07-06 | 河南魏来网络科技有限公司 | 一种车载终端和交通通行行为的监控*** |
CN108986474A (zh) * | 2018-08-01 | 2018-12-11 | 平安科技(深圳)有限公司 | 交通事故的定责方法、装置、计算机设备及计算机存储介质 |
JP7218535B2 (ja) * | 2018-10-12 | 2023-02-07 | トヨタ自動車株式会社 | 交通違反車両識別システム及びサーバ |
-
2021
- 2021-05-07 CN CN202110493304.6A patent/CN113362590A/zh active Pending
- 2021-08-11 WO PCT/CN2021/112101 patent/WO2022233099A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105096594A (zh) * | 2015-06-30 | 2015-11-25 | 北京奇虎科技有限公司 | 基于行车记录仪的信息关联方法、装置及*** |
CN105551110A (zh) * | 2016-02-05 | 2016-05-04 | 北京奇虎科技有限公司 | 一种行车数据记录方法、装置和*** |
CN107766401A (zh) * | 2017-05-26 | 2018-03-06 | 温州市勘察测绘研究院 | 基于大数据的人行道违停分析方法及*** |
CN209281615U (zh) * | 2018-11-28 | 2019-08-20 | 北京万集科技股份有限公司 | 一种基于行车记录仪违章抓拍*** |
CN110459057A (zh) * | 2019-07-29 | 2019-11-15 | 湖南湖芯信息科技有限公司 | 基于大众监督的车载抓拍交通违规事件处理*** |
Also Published As
Publication number | Publication date |
---|---|
CN113362590A (zh) | 2021-09-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kan et al. | Traffic congestion analysis at the turn level using Taxis' GPS trajectory data | |
US9459626B2 (en) | Learning signs from vehicle probes | |
US9564048B2 (en) | Origin destination estimation based on vehicle trajectory data | |
CN110717433A (zh) | 一种基于深度学习的交通违规分析方法及装置 | |
EP4239614A2 (en) | Systems and methods for image-based location determination and parking monitoring | |
CN107885795B (zh) | 一种卡口数据的数据校验方法、***和装置 | |
CN102013159A (zh) | 基于高清视频检测数据的区域动态od矩阵获取方法 | |
CN107590999B (zh) | 一种基于卡口数据的交通状态判别方法 | |
Tak et al. | Development of AI‐Based Vehicle Detection and Tracking System for C‐ITS Application | |
CN114771548A (zh) | 用于高级驾驶辅助***测试和验证的数据记录 | |
Singh et al. | Intelligent traffic management system | |
JP2004101504A (ja) | 走行リンク確定システム及びリンク旅行時間計測システム | |
Yao et al. | Developing operating mode distribution inputs for MOVES with a computer vision–based vehicle data collector | |
CN110610118A (zh) | 交通参数采集方法及装置 | |
WO2022233099A1 (zh) | 基于联网adas调查路域交通违法行为时空特征的方法 | |
RU2770145C1 (ru) | Устройство и система регистрации объектов в области автодороги | |
CN116434525A (zh) | 一种高速公路智能管理预警*** | |
Zaki et al. | Comprehensive safety diagnosis using automated video analysis: Applications to an urban intersection in Edmonton, Alberta, Canada | |
EP3922947A2 (en) | Traffic analytics system for defining road networks | |
CN114241373A (zh) | 一种端到端的车辆行为检测方法、***、设备及存储介质 | |
Sayed et al. | A novel approach for diagnosing road safety issues using automated computer vision techniques | |
Jomrich et al. | Lane Accurate Detection of Map Changes based on Low Cost Smartphone Data. | |
Gokasar et al. | Real-time prediction of traffic density with deep learning using computer vision and traffic event information | |
Рубель et al. | Problems with effective traffic management | |
Bareiss | A Dataset of Vehicle and Pedestrian Trajectories from Normal Driving and Crash Events in One Year of Virginia Traffic Camera Data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21939744 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21939744 Country of ref document: EP Kind code of ref document: A1 |