A Video-based Framework for Automated Trajectory Collection at Intersections

doi:10.11908/j.issn.0253-374x.2019.03.010

Home > Archive>Volume 47, Issue 03, 2019 >0369-0377. DOI:10.11908/j.issn.0253-374x.2019.03.010

A Video-based Framework for Automated Trajectory Collection at Intersections
DOI:
                        10.11908/j.issn.0253-374x.2019.03.010
                    
CSTR:
                        [cstr]
                    
Author:
                        YANG ZhenYANG Zhen
Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
ZHANG QiuchenZHANG Qiuchen
Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:
Clc Number:U495
Fund Project:

Article

Figures

Metrics

Reference [17]

Related [20]

Cited by

Materials

Comments

Abstract:

A video-based framework was presented to collect trajectories of objects at intersections. Firstly, a modified ViBe algorithm was used to extract the foreground of moving objects. Then, an OPC(ObjectPointContour) matching approach was developed for paring, tracking and generating image trajectories. Finally, real world trajectories were obtained through perspective transformation so that velocity and acceleration could be estimated. The framework was stable to occlusion and stagnation. The accuracy of 88.89%, 86.00%, and 83.33% were obtained for vehicles, bicycles and pedestrians counts and 91.71% for velocity estimation. This automatic system provides a solution for data collection and video analysis for intersection safety management and research.

Key words:trajectory; video tracking; video analysis; optical flow

Reference

[1] 中华人民共和国国家统计局交通事故年度数据[DB/OL]. [2017-12-15]http://data.stats.gov.cn/easyquery.htm/.National Bureau of Statistics of the People’s Republic of China Annual data on traffic accidents[DB/OL]. [2017-12-15]http://data.stats.gov.cn/easyquery.htm/.

[2] The Organization for Economic Cooperation and Development. Road injury accidents[DB/OL]. [2016-7-28]. http://stats.oecd.org/.

[3] 慈玉生,郑淑妮,赵韩涛. 基于过街人数分布的路段机动车延误经验模型[J/OL]. 重庆交通大学学报(自然科学版),:1-5(2017-09-06).http://kns.cnki.net/kcms/detail/50.1190.U.20170906.1401.010.html.CI Y S, ZHENG S N, XU Y Q. Empirical Vehicle Delay Model for Road Segment Based on Pedestrians Crossing Number Distribution[J/OL]. Journal of Chongqing Jiaotong University(Natural Science), :1-5(2017-09-06).http://kns.cnki.net/kcms/detail/50.1190.U.20170906.1401.010.html.

[4] LAM, W H K. Pedestrian Speed/Flow Relationships for Walking Facilities in Hong Kong[J]. Journal of Transportation Engineering, 2000, 126(4):343-349.

[5] SU Y, YAO D, ZHANG Y, et al. Vehicle/pedestrian conflict analysis and exclusive right-turn phase setting study[J]. 1931, 26(7):733-738.

[6] 张晓玮. 信号控制交叉口行人与右转车辆的冲突研究[D]. 西南交通大学, 2016.ZHANG X W, Study on Conflict between Pedestrian and Right-turning Vehicles at Signalized Intersection[D]. Southeast Jiaotong University, 2016

[7] 唐克双, 杨博文, 许凯等. 基于车辆轨迹数据的交叉口危险驾驶行为预测[J]. 同济大学学报:自然科学版, 2017, 45(10):1454-1461.TANG K S, YANG B W, XU K, et al. Prediction of Driver''s Risky Behaviors Based on Vehicle Trajectory Data at Signalized Intersections[J]. Journal of Tongji University (Natural Science), 2017, 45(10): 1454-1461.

[8] SHIRAZI M S, Morris B. A typical video-based framework for counting, behavior and safety analysis at intersections[C]// Intelligent Vehicles Symposium. IEEE, 2015:1264-1269.

[9] SAUNIER N, SAYED T. Clustering Vehicle Trajectories with Hidden Markov Models Application to Automated Traffic Safety Analysis[C]// International Joint Conference on Neural Networks. IEEE, 2006:4132-4138.

[10] 王俊骅, 张方方, 张兰芳. 基于OpenCV和Halcon的交通冲突视频自动检测及数据处理[J]. 同济大学学报(自然科学版), 2010, 38(2):238-244.WANG J H, ZHANG F F, ZHANG L F. Halcon and OpenCV Based Traffic Automatic Conflicting Detecting Method and Data Transaction[J]. Journal of Tongji University (Natural Science),

[11] GUO Y, SAYED T T, ZAKI M, et al. Safety Evaluation of Unconventional Outside Left-Turn Lane Using Autom. [J]. Canadian Journal of Civil Engineering, 2016. 2010, 38(2):238-244.

[12] CHEN C, ZHANG X. Moving Vehicle Detection Based on Union of Three-Frame Difference[M]// Advances in Electronic Engineering, Communication and Management Vol.2. Springer Berlin Heidelberg, 2012:459-464.

[13] 高飞,高炎,徐云静等. 融合ViBe与帧差法的交叉路口多车辆检测方法[J]. 计算机测量与控制,2017,25(10):35-38.GAO F, GAO Y, XU Y J, et al Multi Vehicle Detection Based on ViBe and Frame Difference Method[J]. Computer Measurement Control, 2017,25(10):35-38.

[14] BARNICH O, VAN Droogenbroeck M. ViBe: a universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011, 20(6):1709-1724.

[15] LUCAS B D, KANADE T. An iterative image registration technique with an application to stereo vision[C]// International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc. 1981:674-679.

[16] EAMONN Keogh, CHOTIRAT Ann Ratanamahatana. Exact indexing of dynamic time warping[J]. Knowledge and Information Systems, 2005, 7(3):358-386.

[17] MOHAMED H. Zaki. SAYED T. A framework for automated road-users classification using movement trajectories[J]. Transportation Research Part C Emerging Technologies, 2013, 33(4):50-73.

Get Citation

YANG Zhen, ZHANG Qiuchen. A Video-based Framework for Automated Trajectory Collection at Intersections[J].同济大学学报(自然科学版),2019,47(03):0369~0377

Copy

Article Metrics

Abstract:1366
PDF: 959
HTML: 1324
Cited by: 0

History

Received:January 26,2018
Revised:January 03,2019
Adopted:December 05,2018
Online: April 03,2019
Published:

Get Citation

Share

Article Metrics

History

Article QR Code