Motion detection based on the combining of the background subtraction and spatial color information

To detect the moving objects in a video sequence based on background subtraction approaches, a background model should be generated at the first time before subtract it from each image of the sequence and then segmenting the moving objects. But this detection can be difficult when the environment is influenced by illumination and weather changes. In The goal to solve the problem of environmental illumination changes in the background model and to classify pixels of the current image as foreground or background, a new method of background subtraction is presented in this paper. Firstly, the spatial color information is used to generate the background of each color space (R, G, and B) of the sequence. The absolute difference is computed to subtracting the background before compute the binary image of the moving objects using a threshold. This threshold is also used to update the background at each new image. The experimental results demonstrate that our approach is effective and accurate for moving objects detection and the use of spatial color information was robust to environmental illumination change. The experimental results are also compared with the results of the background estimation algorithm with Sigma-Delta (SD) and Motion detection with pyramid structure of background model (MDPS).