Motion detection via change-point detection for cumulative histograms of ratio images

摘要: Motion detection is widely used as the key module for moving object extraction from image frames. In most of motion methods, backgrounds are subtracted captured images. This called background subtraction. As standard intensity can be expressed multiplication illumination and reflectance, changes will produce a poor difference subtraction affect accuracy detection. this paper, we use ratio images basis For thresholding target images, propose change-point cumulative histograms to prevent difficulties searching peaks valleys in histograms. Experimental results show that performs very well addition, superiority based on also depicted experimentation.