WO2021031173A1 - Traffic state recognition method based on binocular camera - Google Patents

Traffic state recognition method based on binocular camera Download PDF

Info

Publication number
WO2021031173A1
WO2021031173A1 PCT/CN2019/101874 CN2019101874W WO2021031173A1 WO 2021031173 A1 WO2021031173 A1 WO 2021031173A1 CN 2019101874 W CN2019101874 W CN 2019101874W WO 2021031173 A1 WO2021031173 A1 WO 2021031173A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic
vehicle
road
image
gray value
Prior art date
Application number
PCT/CN2019/101874
Other languages
French (fr)
Chinese (zh)
Inventor
丁华平
朱荀
钱文涛
Original Assignee
江苏金晓电子信息股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 江苏金晓电子信息股份有限公司 filed Critical 江苏金晓电子信息股份有限公司
Publication of WO2021031173A1 publication Critical patent/WO2021031173A1/en

Links

Images

Classifications

    • 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
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • 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
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/269—Analysis of motion using gradient-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • 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
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G06T2207/10021—Stereoscopic video; Stereoscopic image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20164—Salient point detection; Corner detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance

Definitions

  • the invention relates to the technical field of intelligent traffic guidance.
  • the technical problem to be solved by the present invention is to provide a method for recognizing traffic status based on binocular cameras.
  • the method utilizes existing traffic system management and control platform hardware, and comprehensively uses technologies such as data processing, computational intelligence, and data communication, which can help travel Provide real-time traffic conditions, help vehicle diversion, improve traffic conditions, reduce travel incidents and traffic congestion, reduce environmental pollution, and promote social and economic development.
  • the technical solutions adopted by the present invention are:
  • a traffic state recognition method based on binocular cameras is based on the support of a traffic system management control platform and includes the following three steps:
  • subscript v normalized vehicle speed
  • subscript q normalized vehicle flow
  • subscript 1 smooth traffic
  • subscript 2 light traffic congestion
  • subscript 3 Traffic congestion
  • subscript 4 severe traffic congestion
  • G C set vehicle gray value
  • N vehicle information image pixel
  • N C vehicle area pixel in the vehicle information image
  • Average gray value of vehicle information image The average gray value of the vehicle area in the vehicle information image, The average gray value of the road area in the vehicle information image, in the above formula, set Is 0;
  • S space occupancy rate; The average gray value of the vehicle in the vehicle information image; The average gray value of the vehicle area in the vehicle information image;
  • the average gray value of the vehicle information image is proportional to the space occupancy rate, and the average gray value of the vehicle information image is used to represent the space occupancy rate S;
  • n number of vehicles
  • L length of road
  • s space occupancy rate
  • the information board uses the two parameters of vehicle flow q and vehicle speed v of each traffic section, and judges that each traffic section belongs to four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion through the clustering center matrix in the database. Which one of them is, and the result is transmitted to the traffic system management and control platform, and the traffic system management and control platform publishes to the information board of the upstream traffic section of the corresponding traffic section.
  • the relevant parameters that determine the road traffic state are calculated, and the binocular camera is controlled by the traffic system management and control platform to collect road traffic state images at 30s intervals.
  • the camera continuously takes two frames of photos during each collection.
  • the traffic status is released in real time after each recognition.
  • This method uses the existing transportation system management and control platform hardware to remotely control the images collected by the binocular camera system through the transportation system management and control platform, and comprehensively uses data processing, computational intelligence, data communication and other technologies to extract and analyze traffic parameters.
  • the traffic system management control platform compares the calculated vehicle flow q and vehicle speed v of each traffic intersection with the traffic state clustering center in the reference database, thereby identifying that each traffic intersection belongs to smooth traffic, light traffic congestion, and traffic. Which of the four traffic conditions is crowded or severely congested, and posted to the information board of the corresponding traffic intersection.
  • This method can provide travelers with real-time traffic conditions and make full and reasonable use of road resources.
  • Real-time judgment of traffic status can help improve route selection, play a role in diversion, improve travel conditions, reduce travel incidents and traffic congestion, and effective traffic guidance can greatly improve traffic conditions, relieve traffic pressure, and help management units to manage and control. Reduce environmental pollution and promote social and economic development.
  • Figure 1 is a flowchart of the method of the present invention.
  • This method is based on the support of the traffic system management control platform and includes the following three steps:
  • subscript v normalized vehicle speed
  • subscript q normalized vehicle flow
  • subscript 1 smooth traffic
  • subscript 2 light traffic congestion
  • subscript 3 Traffic congestion
  • subscript 4 severe traffic congestion
  • G C set vehicle gray value
  • N vehicle information image pixel
  • N C vehicle area pixel in the vehicle information image
  • Average gray value of vehicle information image The average gray value of the vehicle area in the vehicle information image, The average gray value of the road area in the vehicle information image, in the above formula, set Is 0;
  • S space occupancy rate; Average gray value of vehicle information image; The average gray value of the vehicle area in the vehicle information image;
  • the average gray value of the vehicle information image is proportional to the space occupancy rate, and the average gray value of the vehicle information image is used to represent the space occupancy rate S;
  • n number of vehicles
  • L length of road
  • s space occupancy rate
  • the information board uses the two parameters of vehicle flow q and vehicle speed v of each traffic section, and judges that each traffic section belongs to four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion through the clustering center matrix in the database. Which one of them is, and the result is transmitted to the traffic system management and control platform, and the traffic system management and control platform publishes to the information board of the upstream traffic section of the corresponding traffic section.
  • the relevant parameters that determine the road traffic state are calculated, and the binocular camera is controlled by the traffic system management and control platform to collect road traffic state images at 30s intervals.
  • the camera continuously takes two frames of photos during each collection.
  • the traffic status is released in real time after each recognition.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Educational Administration (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Remote Sensing (AREA)
  • Fuzzy Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

A traffic state recognition method based on a binocular camera, belonging to the technical field of intelligent traffic guidance. The method comprises the following three steps: (I) establishing a reference database: a. determining a traffic state clustering center, and sending and storing a traffic state clustering center matrix to and in an information board of each traffic road section by means of a traffic system management control platform; and b. setting a highway background image, and sending, by means of the traffic system management control platform, the highway background image to an information board corresponding to a traffic intersection; (II) calculating relevant parameters that decide a highway traffic state: a. calculating highway space occupancy S; and b. calculating two parameters, i.e. a vehicle flow q and a vehicle velocity v; and (III) recognizing a traffic state: the information board determining, according to the two parameters, i.e. a vehicle flow q and a vehicle velocity v, of each traffic road section, which traffic state each traffic road section belongs to, and releasing same. The method can provide a real-time traffic condition for travelers and fully and rationally utilize road resources.

Description

一种基于双目摄像机的交通状态识别方法A traffic state recognition method based on binocular cameras 技术领域Technical field
本发明涉及智能交通诱导技术领域。The invention relates to the technical field of intelligent traffic guidance.
背景技术Background technique
随着经济和社会的快速发展，交通运输也在高速发展，城市交通的拥堵问题日益严重，这不仅增加了人们的出行时间、提高了出行成本，还造成较大的经济损失。使用道路拓宽解决问题成本高、周期长，且车辆会越来越多，不能有效解决问题。何种采取有力措施，以充分有效地利用现有的道路资源，最大程度地缓解交通压力，以促进社会经济的发展，是目前亟待解决的问题。With the rapid development of economy and society, transportation is also developing at a high speed, and the problem of urban traffic congestion is becoming more and more serious. This not only increases people's travel time, increases travel costs, but also causes greater economic losses. Using road widening to solve problems is costly and long, and there will be more and more vehicles, which cannot effectively solve the problem. How to take effective measures to make full and effective use of existing road resources, relieve traffic pressure to the greatest extent, and promote social and economic development is a problem that needs to be solved urgently.
发明内容Summary of the invention
本发明要解决的技术问题是提供一种基于双目摄像机的交通状态识别方法，该方法利用现有的交通系统管理控制平台硬件，综合运用数据处理、计算智能、数据通信等技术,能够为出行者提供实时的交通状况，有助于车辆分流，改善交通情况,减少出行事件和交通拥堵，降低环境污染，促进社会经济发展。The technical problem to be solved by the present invention is to provide a method for recognizing traffic status based on binocular cameras. The method utilizes existing traffic system management and control platform hardware, and comprehensively uses technologies such as data processing, computational intelligence, and data communication, which can help travel Provide real-time traffic conditions, help vehicle diversion, improve traffic conditions, reduce travel incidents and traffic congestion, reduce environmental pollution, and promote social and economic development.
为解决上述技术问题，本发明所采取的技术方案是：To solve the above technical problems, the technical solutions adopted by the present invention are:
一种基于双目摄像机的交通状态识别方法，该方法基于交通系统管理控制平台支持，包括如下三大步骤：A traffic state recognition method based on binocular cameras. The method is based on the support of a traffic system management control platform and includes the following three steps:
(一)，建立参比数据库：(1) Establish a reference database:
a.确定交通状态聚类中心，基于《城市交通管理评价指标体系》将交通状态划分为交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态，通过车辆流量q和车辆速度v两个参数使用模糊C均值聚类算法将数据进行划分，确定聚类中心矩阵P和模糊度权重m，其中P为：a. Determine the traffic state clustering center, and divide the traffic state into four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion based on the "Urban Traffic Management Evaluation Index System", passing vehicle flow q and vehicle speed v The two parameters use fuzzy C-means clustering algorithm to divide the data to determine the cluster center matrix P and the ambiguity weight m, where P is:
Figure PCTCN2019101874-appb-000001
Figure PCTCN2019101874-appb-000001
(1)式中：下标v：归一化后的车辆速度；下标q：归一化后的车辆流量， 下标1：交通畅通；下标2：交通轻度拥挤；下标3：交通拥挤；下标4：交通严重拥挤；(1) where: subscript v: normalized vehicle speed; subscript q: normalized vehicle flow, subscript 1: smooth traffic; subscript 2: light traffic congestion; subscript 3: Traffic congestion; subscript 4: severe traffic congestion;
将上述交通状态聚类中心矩阵通过交通系统管理控制平台发送并储存至各交通路段的情报板；Send and store the above-mentioned traffic state clustering center matrix through the traffic system management control platform to the information board of each traffic section;
b.设置公路背景图像，通过交通系统管理控制平台控制双目摄像机拍摄公路无车辆时的图像，将所拍摄图像的公路以外区域部分灰度值置为0，从而提取图像公路部分像素灰度作为公路背景图像；将公路背景图像通过交通系统管理控制平台发送至所对应交通路口的情报板；b. Set the highway background image, control the binocular camera to shoot the image of the highway without vehicles through the traffic system management and control platform, set the gray value of the area outside the highway of the captured image to 0, so as to extract the pixel gray of the highway part of the image as Highway background image; the highway background image is sent to the information board of the corresponding traffic intersection through the traffic system management and control platform;
(二).计算决定公路交通状态的相关参数，通过交通系统管理控制平台控制双目摄像机以一定的时间间隔采集公路交通状态图像：(2). Calculate the relevant parameters that determine the road traffic state, and control the binocular camera through the traffic system management control platform to collect road traffic state images at a certain time interval:
a.计算公路空间占有率S，交通系统管理控制平台将所采集的公路交通状态图像中公路以外区域灰度值置为0，从而提取所述公路交通状态图像中公路及公路上车辆部分像素灰度，从而得到有效公路交通状态图像，将所述有效公路交通状态图像各点灰度值减去背景图像对应点灰度值，得到所述有效公路交通状态图像减去所述背景图像后的车辆信息图像，则：a. Calculate the road space occupancy rate S, and the traffic system management control platform sets the gray value of the area outside the road in the collected road traffic state image to 0, thereby extracting part of the pixel gray of the road and the vehicle on the road in the road traffic state image In order to obtain the effective road traffic state image, the gray value of each point of the effective road traffic state image is subtracted from the gray value of the corresponding point of the background image to obtain the effective road traffic state image after subtracting the background image. Information image, then:
Figure PCTCN2019101874-appb-000002
Figure PCTCN2019101874-appb-000002
(2)式中：G C：设定的车辆灰度值；N：车辆信息图像像素；N C：车辆信息图像中车辆区域像素；
Figure PCTCN2019101874-appb-000003
车辆信息图像平均灰度值；
Figure PCTCN2019101874-appb-000004
车辆信息图像中车辆区域平均灰度值，
Figure PCTCN2019101874-appb-000005
车辆信息图像中道路区域平均灰度值，上式中，设
Figure PCTCN2019101874-appb-000006
为0； (2) In the formula: G C : set vehicle gray value; N: vehicle information image pixel; N C : vehicle area pixel in the vehicle information image;
Figure PCTCN2019101874-appb-000003
Average gray value of vehicle information image;
Figure PCTCN2019101874-appb-000004
The average gray value of the vehicle area in the vehicle information image,
Figure PCTCN2019101874-appb-000005
The average gray value of the road area in the vehicle information image, in the above formula, set
Figure PCTCN2019101874-appb-000006
Is 0;
Figure PCTCN2019101874-appb-000007
Figure PCTCN2019101874-appb-000007
(3)式中：S：空间占有率；
Figure PCTCN2019101874-appb-000008
车辆信息图像中车辆平均灰度值；
Figure PCTCN2019101874-appb-000009
车辆信息图像中车辆区域平均灰度值； (3) where: S: space occupancy rate;
Figure PCTCN2019101874-appb-000008
The average gray value of the vehicle in the vehicle information image;
Figure PCTCN2019101874-appb-000009
The average gray value of the vehicle area in the vehicle information image;
即：所述车辆信息图像的平均灰度值与空间占有率成正比，所述车辆信息图像的平均灰度值用于表征空间占有率S；That is: the average gray value of the vehicle information image is proportional to the space occupancy rate, and the average gray value of the vehicle information image is used to represent the space occupancy rate S;
b.计算车辆流量q和车辆速度v两个参数，将有效公路交通状态图像的Harris角点与公路背景图像的Harris角点相比较，相同部分的为公路的Harris角点，去掉这部分，在有效公路交通状态图像中去掉公路的Harris角点，通过稀疏光流法计算车辆特征点在相邻两帧图像之间通过的像素，计算得出的该像素为车辆像素，车辆像素相对于分道线的像素移动速度，即为车辆的速度V，将双目摄像机提取出的速度的平均值归一化，得到归一化的速度v，则：b. Calculate the two parameters of vehicle flow q and vehicle speed v. Compare the Harris corner of the effective road traffic state image with the Harris corner of the road background image. The same part is the Harris corner of the road. Remove this part, The Harris corner point of the highway is removed from the effective road traffic state image, and the pixel that the vehicle feature point passes between two adjacent frames of image is calculated by the sparse optical flow method. The calculated pixel is the vehicle pixel. The vehicle pixel is relative to the lane The pixel moving speed of the line is the vehicle speed V. Normalize the average value of the speed extracted by the binocular camera to get the normalized speed v, then:
q＝4vs      (4)q=4vs (4)
(4)式中：q：车辆流量；v：车辆速度；S：空间占有率；(4) where: q: vehicle flow; v: vehicle speed; S: space occupancy rate;
n＝Ls      (5)n=Ls (5)
(5)式中：n：车辆数，L：公路长度；s：空间占有率；(5) Where: n: number of vehicles, L: length of road; s: space occupancy rate;
(三).交通状态识别(3) Recognition of traffic status
情报板通过各交通路段的车辆流量q和车辆速度v两个参数，通过数据库中的聚类中心矩阵判断出各交通路段属于交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态的哪一种，并将结果传至交通系统管理控制平台，由交通系统管理控制平台发布至所对应交通路段的上游交通路段的情报板。The information board uses the two parameters of vehicle flow q and vehicle speed v of each traffic section, and judges that each traffic section belongs to four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion through the clustering center matrix in the database. Which one of them is, and the result is transmitted to the traffic system management and control platform, and the traffic system management and control platform publishes to the information board of the upstream traffic section of the corresponding traffic section.
本发明进一步改进在于：The further improvement of the present invention lies in:
第(二)大步骤中，计算决定公路交通状态的相关参数，通过交通系统管理控制平台控制双目摄像机以30s的时间间隔采集公路交通状态图像，每次采集时摄像机连续拍下两帧照片。In the second major step, the relevant parameters that determine the road traffic state are calculated, and the binocular camera is controlled by the traffic system management and control platform to collect road traffic state images at 30s intervals. The camera continuously takes two frames of photos during each collection.
交通状态在每次识别后实时发布。The traffic status is released in real time after each recognition.
采用上述技术方案所产生的有益效果在于：The beneficial effects produced by using the above technical solutions are:
该方法利用现有的交通系统管理控制平台硬件，通过交通系统管理控制平台远程控制双目摄像系统采集的图像，综合运用数据处理、计算智能、数据通 信等技术,进行交通参数的提取与分析，交通系统管理控制平台将计算得出的各交通路口的车辆流量q和车辆速度v与参比数据库中的交通状态聚类中心对比，从而识别出各交通路口属于交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态的哪一种，并发布至所对应交通路口的情报板。This method uses the existing transportation system management and control platform hardware to remotely control the images collected by the binocular camera system through the transportation system management and control platform, and comprehensively uses data processing, computational intelligence, data communication and other technologies to extract and analyze traffic parameters. The traffic system management control platform compares the calculated vehicle flow q and vehicle speed v of each traffic intersection with the traffic state clustering center in the reference database, thereby identifying that each traffic intersection belongs to smooth traffic, light traffic congestion, and traffic. Which of the four traffic conditions is crowded or severely congested, and posted to the information board of the corresponding traffic intersection.
该方法能够为出行者提供实时的交通状况，充分合理利用道路资源。交通状态的实时判断可以帮助改善路径选择，起到分流作用，改善出行情况，减少出行事件和交通拥堵，有效的交通诱导可以大大改善交通状况，缓解交通压力，有助于管理单位做好管控，降低环境污染，促进社会经济发展。This method can provide travelers with real-time traffic conditions and make full and reasonable use of road resources. Real-time judgment of traffic status can help improve route selection, play a role in diversion, improve travel conditions, reduce travel incidents and traffic congestion, and effective traffic guidance can greatly improve traffic conditions, relieve traffic pressure, and help management units to manage and control. Reduce environmental pollution and promote social and economic development.
附图说明Description of the drawings
图1是本发明方法的流程图。Figure 1 is a flowchart of the method of the present invention.
具体实施方式detailed description
下面将结合附图和具体实施例对本发明进行进一步详细说明。The present invention will be further described in detail below with reference to the drawings and specific embodiments.
参见图1，该方法基于交通系统管理控制平台支持，包括如下三大步骤：Refer to Figure 1. This method is based on the support of the traffic system management control platform and includes the following three steps:
(一)，建立参比数据库：(1) Establish a reference database:
a.确定交通状态聚类中心，基于《城市交通管理评价指标体系》将交通状态划分为交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态，通过车辆流量q和车辆速度v两个参数使用模糊C均值聚类算法将数据进行划分，确定聚类中心矩阵P和模糊度权重m，其中P为：a. Determine the traffic state clustering center, and divide the traffic state into four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion based on the "Urban Traffic Management Evaluation Index System", passing vehicle flow q and vehicle speed v The two parameters use fuzzy C-means clustering algorithm to divide the data to determine the cluster center matrix P and the ambiguity weight m, where P is:
Figure PCTCN2019101874-appb-000010
Figure PCTCN2019101874-appb-000010
(1)式中：下标v：归一化后的车辆速度；下标q：归一化后的车辆流量，下标1：交通畅通；下标2：交通轻度拥挤；下标3：交通拥挤；下标4：交通严重拥挤；(1) Where: subscript v: normalized vehicle speed; subscript q: normalized vehicle flow, subscript 1: smooth traffic; subscript 2: light traffic congestion; subscript 3: Traffic congestion; subscript 4: severe traffic congestion;
将上述交通状态聚类中心矩阵通过交通系统管理控制平台发送并储存至各交通路段的情报板；Send and store the above-mentioned traffic state clustering center matrix through the traffic system management control platform to the information board of each traffic section;
b.设置公路背景图像，通过交通系统管理控制平台控制双目摄像机拍摄公路无车辆时的图像，将所拍摄图像的公路以外区域部分灰度值置为0，从而提取图像公路部分像素灰度作为公路背景图像；将公路背景图像通过交通系统管理控制平台发送至所对应交通路口的情报板；b. Set the highway background image, control the binocular camera to shoot the image of the highway without vehicles through the traffic system management and control platform, set the gray value of the area outside the highway of the captured image to 0, so as to extract the pixel gray of the highway part of the image as Highway background image; the highway background image is sent to the information board of the corresponding traffic intersection through the traffic system management and control platform;
(二).计算决定公路交通状态的相关参数，通过交通系统管理控制平台控制双目摄像机以一定的时间间隔采集公路交通状态图像：(2). Calculate the relevant parameters that determine the road traffic state, and control the binocular camera through the traffic system management control platform to collect road traffic state images at a certain time interval:
a.计算公路空间占有率S，交通系统管理控制平台将所采集的公路交通状态图像中公路以外区域灰度值置为0，从而提取所述公路交通状态图像中公路及公路上车辆部分像素灰度，从而得到有效公路交通状态图像，将所述有效公路交通状态图像各点灰度值减去背景图像对应点灰度值，得到所述有效公路交通状态图像减去所述背景图像后的车辆信息图像，则：a. Calculate the road space occupancy rate S, and the traffic system management control platform sets the gray value of the area outside the road in the collected road traffic state image to 0, thereby extracting part of the pixel gray of the road and the vehicle on the road in the road traffic state image In order to obtain the effective road traffic state image, the gray value of each point of the effective road traffic state image is subtracted from the gray value of the corresponding point of the background image to obtain the effective road traffic state image after subtracting the background image. Information image, then:
Figure PCTCN2019101874-appb-000011
Figure PCTCN2019101874-appb-000011
(2)式中：G C：设定的车辆灰度值；N：车辆信息图像像素；N C：车辆信息图像中车辆区域像素；
Figure PCTCN2019101874-appb-000012
车辆信息图像平均灰度值；
Figure PCTCN2019101874-appb-000013
车辆信息图像中车辆区域平均灰度值，
Figure PCTCN2019101874-appb-000014
车辆信息图像中道路区域平均灰度值，上式中，设
Figure PCTCN2019101874-appb-000015
为0； (2) In the formula: G C : set vehicle gray value; N: vehicle information image pixel; N C : vehicle area pixel in the vehicle information image;
Figure PCTCN2019101874-appb-000012
Average gray value of vehicle information image;
Figure PCTCN2019101874-appb-000013
The average gray value of the vehicle area in the vehicle information image,
Figure PCTCN2019101874-appb-000014
The average gray value of the road area in the vehicle information image, in the above formula, set
Figure PCTCN2019101874-appb-000015
Is 0;
Figure PCTCN2019101874-appb-000016
Figure PCTCN2019101874-appb-000016
(3)式中：S：空间占有率；
Figure PCTCN2019101874-appb-000017
车辆信息图像平均灰度值；
Figure PCTCN2019101874-appb-000018
车辆信息图像中车辆区域平均灰度值； (3) where: S: space occupancy rate;
Figure PCTCN2019101874-appb-000017
Average gray value of vehicle information image;
Figure PCTCN2019101874-appb-000018
The average gray value of the vehicle area in the vehicle information image;
即：所述车辆信息图像的平均灰度值与空间占有率成正比，所述车辆信息图像的平均灰度值用于表征空间占有率S；That is: the average gray value of the vehicle information image is proportional to the space occupancy rate, and the average gray value of the vehicle information image is used to represent the space occupancy rate S;
b.计算车辆流量q和车辆速度v两个参数，将有效公路交通状态图像的Harris角点与公路背景图像的Harris角点相比较，相同部分的为公路的Harris 角点，去掉这部分，在有效公路交通状态图像中去掉公路的Harris角点，通过稀疏光流法计算车辆特征点在相邻两帧图像之间通过的像素，计算得出的该像素为车辆像素，车辆像素相对于分道线的像素移动速度，即为车辆的速度V，将双目摄像机提取出的速度的平均值归一化，得到归一化的速度v，则：b. Calculate the two parameters of vehicle flow q and vehicle speed v, compare the Harris corner of the effective highway traffic state image with the Harris corner of the highway background image, the same part is the Harris corner of the highway, remove this part, in The Harris corner point of the highway is removed from the effective road traffic state image, and the pixel that the vehicle feature point passes between two adjacent frames of image is calculated by the sparse optical flow method. The calculated pixel is the vehicle pixel. The vehicle pixel is relative to the lane The pixel moving speed of the line is the vehicle speed V. Normalize the average value of the speed extracted by the binocular camera to get the normalized speed v, then:
q＝4vs     (4)q=4vs (4)
(4)式中：q：车辆流量；v：车辆速度；S：空间占有率；(4) where: q: vehicle flow; v: vehicle speed; S: space occupancy rate;
n＝Ls      (5)n=Ls (5)
(5)式中：n：车辆数，L：公路长度；s：空间占有率；(5) Where: n: number of vehicles, L: length of road; s: space occupancy rate;
(三).交通状态识别(3) Recognition of traffic status
情报板通过各交通路段的车辆流量q和车辆速度v两个参数，通过数据库中的聚类中心矩阵判断出各交通路段属于交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态的哪一种，并将结果传至交通系统管理控制平台，由交通系统管理控制平台发布至所对应交通路段的上游交通路段的情报板。The information board uses the two parameters of vehicle flow q and vehicle speed v of each traffic section, and judges that each traffic section belongs to four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion through the clustering center matrix in the database. Which one of them is, and the result is transmitted to the traffic system management and control platform, and the traffic system management and control platform publishes to the information board of the upstream traffic section of the corresponding traffic section.
第(二)大步骤中，计算决定公路交通状态的相关参数，通过交通系统管理控制平台控制双目摄像机以30s的时间间隔采集公路交通状态图像，每次采集时摄像机连续拍下两帧照片。In the second major step, the relevant parameters that determine the road traffic state are calculated, and the binocular camera is controlled by the traffic system management and control platform to collect road traffic state images at 30s intervals. The camera continuously takes two frames of photos during each collection.
交通状态在每次识别后实时发布。The traffic status is released in real time after each recognition.

Claims (3)

  1. 一种基于双目摄像机的交通状态识别方法，其特征在于：所述方法基于交通系统管理控制平台支持，包括如下三大步骤：A traffic state recognition method based on binocular cameras is characterized in that: the method is based on the support of a traffic system management control platform and includes the following three steps:
    (一)，建立参比数据库：(1) Establish a reference database:
    a.确定交通状态聚类中心，基于《城市交通管理评价指标体系》将交通状态划分为交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态，通过车辆流量q和车辆速度v两个参数使用模糊C均值聚类算法将数据进行划分，确定聚类中心矩阵P和模糊度权重m，其中P为：a. Determine the traffic state clustering center, and divide the traffic state into four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion based on the "Urban Traffic Management Evaluation Index System", passing vehicle flow q and vehicle speed v The two parameters use fuzzy C-means clustering algorithm to divide the data to determine the cluster center matrix P and the ambiguity weight m, where P is:
    Figure PCTCN2019101874-appb-100001
    Figure PCTCN2019101874-appb-100001
    (1)式中：下标v：归一化后的车辆速度；下标q：归一化后的车辆流量，下标1：交通畅通；下标2：交通轻度拥挤；下标3：交通拥挤；下标4：交通严重拥挤；(1) Where: subscript v: normalized vehicle speed; subscript q: normalized vehicle flow, subscript 1: smooth traffic; subscript 2: light traffic congestion; subscript 3: Traffic congestion; subscript 4: severe traffic congestion;
    将上述交通状态聚类中心矩阵通过交通系统管理控制平台发送并储存至各交通路段的情报板；Send and store the above-mentioned traffic state clustering center matrix through the traffic system management control platform to the information board of each traffic section;
    b.设置公路背景图像，通过交通系统管理控制平台控制双目摄像机拍摄公路无车辆时的图像，将所拍摄图像的公路以外区域部分灰度值置为0，从而提取所述图像公路部分像素灰度作为公路背景图像；将所述公路背景图像通过交通系统管理控制平台发送至所对应交通路口的情报板；b. Set the highway background image, control the binocular camera to shoot the image of the highway without vehicles through the traffic system management and control platform, and set the gray value of the area outside the highway of the captured image to 0, so as to extract the pixel gray of the highway part of the image As the highway background image; send the highway background image to the information board of the corresponding traffic intersection through the traffic system management control platform;
    (二).计算决定公路交通状态的相关参数，通过交通系统管理控制平台控制双目摄像机以一定的时间间隔采集公路交通状态图像：(2). Calculate the relevant parameters that determine the road traffic state, and control the binocular camera through the traffic system management control platform to collect road traffic state images at a certain time interval:
    a.计算公路空间占有率S，交通系统管理控制平台将所采集的公路交通状态图像中公路以外区域灰度值置为0，从而提取所述公路交通状态图像中公路及公路上车辆部分像素灰度，从而得到有效公路交通状态图像，将所述有效公路交通状态图像各点灰度值减去背景图像对应点灰度值，得到所述有效公路交通状态图像减去所述背景图像后的车辆信息图像，则：a. Calculate the road space occupancy rate S, and the traffic system management control platform sets the gray value of the area outside the road in the collected road traffic state image to 0, thereby extracting part of the pixel gray of the road and the vehicle on the road in the road traffic state image In order to obtain the effective road traffic state image, the gray value of each point of the effective road traffic state image is subtracted from the gray value of the corresponding point of the background image to obtain the effective road traffic state image after subtracting the background image. Information image, then:
    Figure PCTCN2019101874-appb-100002
    Figure PCTCN2019101874-appb-100002
    (2)式中：G C：设定的车辆灰度值；N：车辆信息图像像素；N C：车辆信息图像中车辆区域像素；
    Figure PCTCN2019101874-appb-100003
    车辆信息图像平均灰度值；
    Figure PCTCN2019101874-appb-100004
    车辆信息图像中车辆区域平均灰度值，
    Figure PCTCN2019101874-appb-100005
    车辆信息图像中道路区域平均灰度值，上式中，设
    Figure PCTCN2019101874-appb-100006
    为0；     (2) In the formula: G C : set vehicle gray value; N: vehicle information image pixel; N C : vehicle area pixel in the vehicle information image;
    Figure PCTCN2019101874-appb-100003
    Average gray value of vehicle information image;
    Figure PCTCN2019101874-appb-100004
    The average gray value of the vehicle area in the vehicle information image,
    Figure PCTCN2019101874-appb-100005
    The average gray value of the road area in the vehicle information image, in the above formula, set
    Figure PCTCN2019101874-appb-100006
    Is 0;
    Figure PCTCN2019101874-appb-100007
    Figure PCTCN2019101874-appb-100007
    (3)式中：S：空间占有率；
    Figure PCTCN2019101874-appb-100008
    车辆信息图像中车辆平均灰度值；
    Figure PCTCN2019101874-appb-100009
    车辆信息图像中车辆区域平均灰度值；     (3) where: S: space occupancy rate;
    Figure PCTCN2019101874-appb-100008
    The average gray value of the vehicle in the vehicle information image;
    Figure PCTCN2019101874-appb-100009
    The average gray value of the vehicle area in the vehicle information image;
    即：所述车辆信息图像的平均灰度值与空间占有率成正比，所述车辆信息图像的平均灰度值用于表征空间占有率S；That is, the average gray value of the vehicle information image is proportional to the space occupancy rate, and the average gray value of the vehicle information image is used to represent the space occupancy rate S;
    b.计算车辆流量q和车辆速度v两个参数，将有效公路交通状态图像的Harris角点与公路背景图像的Harris角点相比较，相同部分的为公路的Harris角点，去掉这部分，在有效公路交通状态图像中去掉公路的Harris角点，通过稀疏光流法计算车辆特征点在相邻两帧图像之间通过的像素，计算得出的该像素为车辆像素，所述车辆像素相对于所述分道线的像素移动速度，即为车辆的速度V，将双目摄像机提取出的速度的平均值归一化，得到归一化的速度v，则：b. Calculate the two parameters of vehicle flow q and vehicle speed v. Compare the Harris corner of the effective road traffic state image with the Harris corner of the road background image. The same part is the Harris corner of the road. Remove this part, The Harris corner point of the road is removed from the effective road traffic state image, and the pixel that the vehicle feature point passes between two adjacent frames of image is calculated by the sparse optical flow method. The calculated pixel is the vehicle pixel, and the vehicle pixel is relative to The pixel moving speed of the lane dividing line is the vehicle speed V. Normalize the average value of the speed extracted by the binocular camera to obtain the normalized speed v, then:
    q＝4vs      (4)q=4vs (4)
    (4)式中：q：车辆流量；v：车辆速度；S：空间占有率；(4) where: q: vehicle flow; v: vehicle speed; S: space occupancy rate;
    n＝Ls   (5)n=Ls (5)
    (5)式中：n：车辆数，L：公路长度；s：空间占有率；(5) Where: n: number of vehicles, L: length of road; s: space occupancy rate;
    (三).交通状态识别(3) Recognition of traffic status
    情报板通过各交通路段的车辆流量q和车辆速度v两个参数，通过数据库中的聚类中心矩阵判断出各交通路段属于交通畅通、交通轻度拥挤、交通拥挤、交通严重拥挤四种交通状态的哪一种，并将结果传至交通系统管理控制平台，由交通系统管理控制平台发布至所对应交通路段的上游交通路段的情报板。The information board uses the two parameters of vehicle flow q and vehicle speed v of each traffic section, and judges that each traffic section belongs to four traffic states: smooth traffic, light traffic congestion, traffic congestion, and severe traffic congestion through the clustering center matrix in the database. Which one of them, and send the result to the traffic system management and control platform, and the traffic system management and control platform will publish to the information board of the upstream traffic section of the corresponding traffic section.
  2. 根据权利要求1所述的一种基于双目摄像机的交通状态识别方法，其特征在于：所述第(二)大步骤中，计算决定公路交通状态的相关参数，通过交通系统管理控制平台控制双目摄像机以30s的时间间隔采集公路交通状态图像，每次采集时摄像机连续拍下两帧照片。The method for recognizing traffic status based on binocular cameras according to claim 1, characterized in that: in the (second) step, the relevant parameters that determine the road traffic status are calculated, and the traffic system management control platform controls the double The eye camera collects highway traffic state images at 30s intervals, and the camera continuously takes two frames of photos each time.
  3. 根据权利要求1所述的，其特征在于：所述交通状态在每次识别后实时发布。The method according to claim 1, wherein the traffic status is released in real time after each recognition.
PCT/CN2019/101874 2019-08-20 2019-08-22 Traffic state recognition method based on binocular camera WO2021031173A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910766946.1 2019-08-20
CN201910766946.1A CN110610608A (en) 2019-08-20 2019-08-20 Traffic state identification method based on binocular camera

Publications (1)

Publication Number Publication Date
WO2021031173A1 true WO2021031173A1 (en) 2021-02-25

Family

ID=68890236

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/101874 WO2021031173A1 (en) 2019-08-20 2019-08-22 Traffic state recognition method based on binocular camera

Country Status (2)

Country Link
CN (1) CN110610608A (en)
WO (1) WO2021031173A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116884236A (en) * 2023-06-26 2023-10-13 中关村科学城城市大脑股份有限公司 Traffic flow collection device and traffic flow collection method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3626824A (en) * 1970-02-20 1971-12-14 Harris Intertype Corp Composing method and apparatus
WO2004023091A2 (en) * 2002-09-03 2004-03-18 The Uab Research Foundation Localization of human cytomegalovirus nucleic acids and proteins in human cancer cells
CN101807345A (en) * 2010-03-26 2010-08-18 重庆大学 Traffic jam judging method based on video detection technology
CN104809916A (en) * 2015-04-21 2015-07-29 重庆大学 Mountain road curve vehicle crossing early warning method based on videos
CN106067248A (en) * 2016-05-30 2016-11-02 重庆大学 A kind of traffic status of express way method of estimation considering speed dispersion characteristic
CN107301369A (en) * 2017-09-04 2017-10-27 南京航空航天大学 Road traffic congestion analysis method based on Aerial Images

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102136190B (en) * 2011-05-03 2014-06-18 上海理工大学 Dispatching management system and method for event emergency response of urban bus passenger transport
CN102855759B (en) * 2012-07-05 2014-04-09 中国科学院遥感应用研究所 Automatic collecting method of high-resolution satellite remote sensing traffic flow information
CN104157139B (en) * 2014-08-05 2016-01-13 中山大学 A kind of traffic congestion Forecasting Methodology and method for visualizing
CN104778846B (en) * 2015-03-26 2016-09-28 南京邮电大学 A kind of method for controlling traffic signal lights based on computer vision

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3626824A (en) * 1970-02-20 1971-12-14 Harris Intertype Corp Composing method and apparatus
WO2004023091A2 (en) * 2002-09-03 2004-03-18 The Uab Research Foundation Localization of human cytomegalovirus nucleic acids and proteins in human cancer cells
CN101807345A (en) * 2010-03-26 2010-08-18 重庆大学 Traffic jam judging method based on video detection technology
CN104809916A (en) * 2015-04-21 2015-07-29 重庆大学 Mountain road curve vehicle crossing early warning method based on videos
CN106067248A (en) * 2016-05-30 2016-11-02 重庆大学 A kind of traffic status of express way method of estimation considering speed dispersion characteristic
CN107301369A (en) * 2017-09-04 2017-10-27 南京航空航天大学 Road traffic congestion analysis method based on Aerial Images

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116884236A (en) * 2023-06-26 2023-10-13 中关村科学城城市大脑股份有限公司 Traffic flow collection device and traffic flow collection method
CN116884236B (en) * 2023-06-26 2024-04-16 中关村科学城城市大脑股份有限公司 Traffic flow collection device and traffic flow collection method

Also Published As

Publication number Publication date
CN110610608A (en) 2019-12-24

Similar Documents

Publication Publication Date Title
CN109147331B (en) Road congestion state detection method based on computer vision
CN109191830B (en) Road congestion detection method based on video image processing
CN104778834B (en) Urban road traffic jam judging method based on vehicle GPS data
CN110164152B (en) Traffic signal lamp control system for single-cross intersection
CN105336169B (en) A kind of method and system that traffic congestion is judged based on video
CN111818313B (en) Vehicle real-time tracking method and device based on monitoring video
CN116824859B (en) Intelligent traffic big data analysis system based on Internet of things
CN112885088B (en) Multi-turn road coordination control method based on dynamic traffic flow
CN107545757A (en) Urban road flow rate measuring device and method based on Car license recognition
Odeh Management of an intelligent traffic light system by using genetic algorithm
WO2023035666A1 (en) Urban road network traffic light control method based on expected reward estimation
WO2021031173A1 (en) Traffic state recognition method based on binocular camera
CN102768802A (en) Method for judging road vehicle jam based on finite-state machine (FSM)
CN103927875A (en) Traffic overflowing state recognition method based on video
CN115687709A (en) Traffic dynamic control method based on traffic data dimension reduction reconstruction and multidimensional analysis
Yadav et al. Adaptive traffic management system using IoT and machine learning
CN110536114A (en) A kind of the parking lot CCTV monitoring system and method for Intelligent target tracking
Wang et al. Vision-based highway traffic accident detection
CN104318783A (en) Method for analyzing night traffic flow through car lamp detection
Wang et al. An end-to-end traffic vision and counting system using computer vision and machine learning: the challenges in real-time processing
CN114913447B (en) Police intelligent command room system and method based on scene recognition
CN116580574A (en) Road traffic multidirectional dynamic control method based on traffic flow monitoring
CN112489423B (en) Vision-based urban road traffic police command method
CN107067723B (en) A kind of estimation method of Urban road hourage
CN105702034B (en) Intelligent traffic administration system based on monocular vision and route information method for pushing and system

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: 19942565

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: 19942565

Country of ref document: EP

Kind code of ref document: A1