Moving Object Detection Algorithm Based on Background Subtraction and Frame Differencing

With the aim of overcoming the disadvantage of rapid lighting changes, a moving object detection algorithm based on background and consecutive frames difference is presented. At first, background model is obtained by statistical properties of pixels block-based. Then, the moving object is extracted with background subtraction and multi-frame-differencing, which is insensitivity to the target object's speed and environmental disturbance. Furthermore, rapid lighting changes are discovered through quantity change of consecutive frames' foreground pixels. And, the normalized cross-correlation coefficient is used to suppress false positives. Finally, morphologic operation is applied to remove the influence of outside noise. Experimental results show that the proposed algorithm with simple model can prevent a large quantity of false detection which is produced by rapid lighting changes and the moving object is obtained integrally and correctly.