CCTV cameras are becoming a common fixture at the roadside. Their use varies from traffic monitoring to security surveillance. In this paper an advanced two-stage framework for estimating vehicular traffic density on a road segment is presented. The proposed approach is computationally efficient and robust to varying illumination. The method is novel because it combines state-of-the-art image processing techniques with a simple traffic model in order to increase robustness. Experimental results have shown that the proposed framework can achieve higher performance than existing state-of-the-art techniques under conditions of varying illumination.
Advanced framework for illumination invariant traffic density estimation
01.10.2009
603302 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Illumination Invariant Background Extraction
British Library Conference Proceedings | 1999
|