Robust Vehicle Tracking for Urban Traffic Videos at Intersections

Automatic Vehicle Tracking System

A robust, unsupervised vehicle tracking system for videos of very congested road intersections in urban environments is develpped. Raw tracklets from the standard Kanade- Lucas-Tomasi tracking algorithm are treated as sample points and grouped to form different vehicle candidates. Each tracklet is described by multiple features including position, velocity, and a foreground score derived from robust PCA background subtraction. By considering each tracklet as a node in a graph, we build the adjacency matrix for the graph based on the feature similarity between the tracklets and group these tracklets using spectral embedding and Dirichelet Process Gaussian Mixture Models. The proposed system yields excellent performance for traffic videos captured in urban environments and highways.

Publications:

Chenge Li, An-Ti Chiang, Gregory Dobler, Yao Wang, Kun Xie, Kaan Ozbay, Masoud Ghandehari, Jiaxu Zhou, Di Wang, "Robust Vehicle Tracking for Urban Traffic Videos at Intersections." Advanced Video and Signal Based Surveillance (AVSS), 2016 13th IEEE International Conference on. IEEE, 2016.

Kun Xie, Chenge Li, Kaan Ozbay, Gregory Dobler, HONG YANG, An-Ti Chiang, Masoud Ghandehari, "Development of a Comprehensive Framework for Video-Based Safety Assessment", 2016 IEEE 19th International Conference on Intelligent Transportation Systems. IEEE, 2016.

Credits

PhD students:

Chenge Li, New York University, cl2840@nyu.edu

An-ti Chiang, New York University, dawnandyknight@gmail.com

Supervisors:

Prof. Yao Wang, New York University, yw523@nyu.edu

Dr. Greg Dobler, New York University, greg.dobler@nyu.edu

Information

If you have any questions or need more detailed explanations, please email Chenge Li for further information. :D