Cooperative project with Mihran Tuceryan and Herb Blitzer

This work aims at real-time in-car video analysis to detect several critical events in order to alarm and assist police action. Particularly, detecting a tracked or stopped vehicle is a crucial task for further examination of suspects, protecting police safety, and remote monitoring from police station. This work employs a comprehensive approach to localize target vehicles in the video under various environments and illumination conditions. The extracted geometry features on the moving objects and background are dynamically projected onto a 1D profile and are constantly tracked. We rely on temporal information of features for vehicle identification, which compensates for the complexity of vehicle shapes, colors and types. We investigated videos of day and night, and different types of roads, proving that our employed approach is robust and effective.

Publications:

Amirali Jazayeri, Hongyuan Cai, Jiang Yu Zheng, Mihran Tuceryan, Herbert Blitzer: An intelligent video system for vehicle localization and tracking in police cars. ACM SAC 2009: 939-940

Amirali Jazayeri, Hongyuan Cai, Jiang Yu Zheng, Mihran Tuceryan: Motion based Vehicle Identification in Car Video. IEEE Intelligent Vehicle, 2010: 939-940 (presentation video and slides here)

A. Jazayeri, H. Cai, M. Tuceryan, J. Y. Zheng, Smart video systems in police car, ACM International Conference on Multimedia, 1-4, 2010

A. Jazayeri, H. Cai, J. Y. Zheng, M. Tuceryan, Vehicle Detection and Tracking in Car Video Based on Motion Model, IEEE Transaction on Intelligent Transportation Systems, 12(2): 583-595 (2011).

Demo video here

Last modified: 10/01/11