No abstract

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 paper describes a comprehensive approach to localize targeted 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.

No abstract