Advanced In-car Video In Police Cars

Dr. Mihran Tuceryan
Dr. Jiang Yu Zheng
Amirali Jazayeri (MS Student)
Hongyuan Cai (PhD Student)

In collaboration with Herbert Blitzer -- Indiana Forensic Institute (IFI)

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. Some examples of critical events are:

• person running out of the stopped car
• package thrown out of the car during pursuit
• door of stopped car opens
• officer down.

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.

Some Videos

• Vehicle localization
• Person running out of vehicle The running person is indicated by a colored vertical line that follows him.
• Officer down detection Fall detection is indicated by the circle tracking the officer chaging color to red.

Publications

1. Amirali Jazayeri, Hongyuan Cai, Jiang Yu Zheng, Mihran Tuceryan, "Vehicle Detection and Tracking in In-Car Video Based on Their Motion," IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 2, pp. 585-595, June 2011. DOI: 10.1109/TITS.2011.2113340
2. A. Jazayeri, H. Cai, J. Y. Zheng, M. Tuceryan, "Car identification in car video using motion model," IEEE Conference on Intelligent Vehicles, San Diego, 1-8, 2010.
3. A. Jazayeri, H. Cai, M. Tuceryan, J. Y. Zhen, "Smart Video Systems in Police Cars," ACM International Conference on Multimedia (MM '10), Firenze, Italy, pp. 807-810, 2010. (pdf)
4. Amirali Jazayeri, Hongyuan Cai, Jiang Yu Zheng, Mihran Tuceryan, Herbert Blitzer, "An Intelligent Video System for Vehicle Localization and Tracking in Police Cars," in Proceedings of the 24th Annual ACM Symposium on Applied Computing (SAC), pp. 939-940, Honolulu, Hawaii, March 2009. (Poster paper) (pdf)

Funding

• US National Institute of Justice grant #2007-DE-BX-K007.