An approach to extract traffic events by integrating the low-level, middle-level, and high-level feature extraction modules is developed in this research. To be more specific, the low-level module extracts features such as motion, size, and location. The middle-level module builds a bridge between the road surface plane in the real world and the captured image plane by geometric analysis. Finally, the high-level module looks for traffic events such as "traffic jam", "lane change", and "traffic rule violation", which require the understanding of the video contents in a specific knowledge domain. In the high-level module, various traffic events are related to motion characteristics obtained from the middle-level module. It is demonstrated by experimental results that the proposed system can achieve robust traffic event extraction. The effectiveness of the proposed technique is analyzed. Conventional traffic event extraction methods demand the knowledge of capturing conditions for camera calibration. This requirement can be greatly relaxed in our proposed scheme.
Robust traffic event extraction from surveillance video
Visual Communications and Image Processing 2004 ; 2004 ; San Jose,California,United States
Proc. SPIE ; 5308
2004-01-18
Conference paper
Electronic Resource
English
Shadow Elimination for Robust Video Surveillance
British Library Conference Proceedings | 2002
|Evidential event inference in transport video surveillance
British Library Online Contents | 2016
|Shadow elimination for robust video surveillance
IEEE | 2002
|