Moving vehicle detection based on fuzzy background subtraction
Xiaofeng Lu, Takashi Izumi, Tomoaki Takahashi, Lei Wang · 2014
Background subtraction is a method typically used to segment moving regions in image sequences taken from a static camera by comparing each new frame with a model of the background scene. This paper proposes a novel fuzzy background subtraction algorithm for moving vehicle detection which achieves the high detection rates, and reduces the influence of illumination changes and shadows in the traffic scene. The proposed method adopts the Choquet integral for fusion the similarity measures of three color components of the YCbCr color space and uniform local binary pattern texture. Otherwise, an adaptive selective method for background maintenance is proposed to address the problem of background pollution. The experimental results of several dataset videos show the robustness and effectiveness of the proposed method.