Abstract Today, video cameras are widely used to monitor the state and level of traffic. However, while planning a system for the motorways in the Free State of Saxony (Germany), three major problems became obvious. Most commercial image processing software depends on a particular camera model, and it must be calibrated by a professional. In addition, the diverse and sometimes severe environmental conditions are still a challenge for most algorithms. The research goal of the presented work was to resolve these problems with a novel in-house development. The methods developed for incident detection and parking space surveillance do not disclose vehicle-specific characteristics. Only stochastic and non-specific characteristics are used for image processing. Significant results are a remarkable robustness against weather and lighting conditions as well as minimal requirements regarding camera height and direction. The latter leads to low procurement costs as existing infrastructure can be used for the camera installation.
Experiences with Video-Based Incident Detection and Parking Space Surveillance Systems on Motorways in the Free State of Saxony
2011-01-01
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
video-detection , incident detection , parking space surveillance , stochastic image properties , traffic management Computer Science , Computer Communication Networks , Information Systems Applications (incl. Internet) , Information Storage and Retrieval , Database Management , Algorithm Analysis and Problem Complexity , Management of Computing and Information Systems
British Library Conference Proceedings | 2011
|Wavelet Transforms for Incident Detection on Motorways
British Library Conference Proceedings | 1996
|Incident characteristics on motorways: A contribution of the video technology
British Library Conference Proceedings | 1998
|British Library Conference Proceedings | 1994
|Motion Based Vehicle Detection on Motorways
British Library Conference Proceedings | 1995
|