Background Subtraction Using an Adaptive Local Median Texture Feature in Illumination Changes Urban Traffic Scenes

Background subtraction is commonly employed in foreground object detection in urban traffic scenes. Most of the current color or texture feature-based background subtraction models are easily contaminated by sudden and gradual illumination variations in urban traffic scenes. To resolve this deficiency, an adaptive local median texture feature, which extracts the adaptive distance threshold employing the median information in a predefined local region of a pixel and Weber's law, is introduced. In addition, a sample consensus-based model that evolved from portable visual background extractor is proposed using an adaptive local median texture feature. Then, the foreground is labeled by comparing the input video frames feature with the model. Moreover, to adapt the dynamic background, the random update scheme is used to update the model. Extensive experimental results on the public Change Detection data set of 2014 (CDnet2014) and the real-world urban traffic videos demonstrate that our background subtraction method is superior to the other state-of-the-art texture-feature-based methods. The qualitative and quantitative results show the encouraging efficiency of the proposed technique to deal with sudden and gradual illumination variations in real-world urban traffic scenes.