Improved video vehicle detection algorithm based on virtual line

The video vehicle detection (WD) algorithm based on virtual line is used extensively in intelligent transportation system (ITS). But it only utilizes luminance information of pixels, therefore its false reject rate (FRR) and false accept rate (FAR) are high. In order to solve this problem, an improved algorithm is proposed, which introduces two-level detection and utilizes both luminance and chrominance information. In the first level processing, it performs detection utilizing luminance information. In the second level processing, it does detection and modifies the luminance threshold utilizing chrominance information. Experiment results demonstrate that the improved algorithm can eliminate the influence of shadow and image noise effectively, and it is more accurate and robust. Compared with original algorithm, its average FRR and FAR are obviously lower. Furthermore, it satisfies request of real-time performance.