Robust Vehicle Counting with Severe Shadows and Occlusions
Abstract
We present a robust real-time vision-based system for vehicle tracking and categorization, developed for traffic flow surveillance. We propose a robust segmentation algorithm that detects foreground pixels corresponding to moving vehicles. Experimental results based on four large datasets show that our method can count and classify vehicles with a high level of performance (more than 98%).
Origin : Files produced by the author(s)
Loading...