Automated Data Collection and Safety Analysis at Intersections Based on a Novel Video Processing System

Abstract

A novel video-based system is presented which collects trajectories and motion parameters of all objects at intersections. First, a modified ViBe method is used to extract the foreground of moving objects. Then, an object-point-contour matching approach is developed for pairing, tracking, and generating trajectories. Finally, raw trajectories are corrected through post-processing and motion parameters are estimated after object classification. This system demonstrates better performance while tracking tardy and shadowed objects compared with previous studies. The accuracies of 86% and 91% are obtained for traffic counts and velocity validation, respectively. This paper also presents a sample safety analysis using traffic conflict technology to demonstrate the possible implementation for traffic management and safety analysis.

Get full access to this article

View all access options for this article.

References

National Bureau of Statistics of the People’s Republic of China. Annual Data on Traffic Accidents, 2018. http://data.stats.gov.cn/easyquery.htm/. Accessed July 31, 2018.

The Organization for Economic Cooperation and Development. Road Injury Accidents, 2018. http://stats.oecd.org/. Accessed July 31, 2018.

Shirazi

Morris

A Typical Video-based Framework for Counting, Behavior and Safety Analysis at Intersections, IEEE Intelligent Vehicles Symposium, Seoul, South Korea, 2015, pp. 1264–1269.

William

Pedestrian Speed/Flow Relationships for Walking Facilities in Hong Kong. Journal of Transportation Engineering, Vol. 126, 2000, pp. 43–349.

Zheng

Empirical Vehicle Delay Model for Road Segment Based on Pedestrians Crossing Number Distribution. Journal of Chongqing Jiaotong University (Natural Science), 2018. http://kns.cnki.net/kcms/detail/50.1190.U.20170906.1401.010.html, Accessed July 31, 2018.

Zhang

Study on Conflict between Pedestrian and Right-turning Vehicles at Signalized Intersection. Southeast Jiaotong University, 2016.

Tang

Yang

Sun

Zhou

, Prediction of Driver’s Risky Behaviors Based on Vehicle Trajectory Data at Signalized Intersections, Journal of Tongji University (Natural Science), Vol. 45, 2017, pp. 1454–1461.

Wang

Zhang

, Halcon and OpenCV Based Traffic Automatic Conflicting Detecting Method and Data Transaction, Journal of Tongji University (Natural Science), Vol. 38, 2010, pp. 238–244.

Saunier

Sayed

Clustering Vehicle Trajectories with Hidden Markov Models Application to Automated Traffic Safety Analysis, IEEE International Joint Conference on Neural Networks, Vancouver, BC, Canada, 2006, pp. 4132–4138.

10.

Guo

Sayed

Zaki

Liu

Safety Evaluation of Unconventional Outside Left-Turn Lane Using Automated Traffic Conflict Techniques. Canadian Journal of Civil Engineering, Vol. 38, 2016, pp. 238–244.

11.

Barnich

Van Droogenbroeck

ViBe: A Universal Background Subtraction Algorithm for Video Sequences. IEEE Transactions on Image Processing, Vol. 20, 2011, pp. 1709–1724.

12.

Gao

Xiao

Multi Vehicle Detection Based on ViBe and Frame Difference Method. Computer Measurement & Control, Vol. 25, 2017, pp. 35–38.

13.

Lucas

Kanade

An Iterative Image Registration Technique with an Application to Stereo Vision. International Joint Conference on Artificial Intelligence, 1981, pp. 674–679.

14.

Horst

R. V. D.

Time-to-collision as a Cue for Decision Making in Braking. Vision in Vehicles, Vol. 3, 1991, pp. 19–26.

15.

Saunier

Sayed

A Feature-based Tracking Algorithm for Vehicles in Intersections. Conference on Computer & Robot Vision. IEEE Computer Society, Vol. 59, 2006, pp. 59.