Effective Moving Objects Detection Based on Clustering Background Model for Video Surveillance

Dynamic background modeling is an essential task for numerous visual surveillance applications such as incident detection and traffic management. Adaptive mixture models and nonparametric models are two popular methods for background modeling at present. However, it is usually too costly to perform for the both methods in real time, since they are both memory and computationally inefficient. To overcome this problem, this paper presents a new method for modeling dynamic background based on clustering theory. For a dynamic background, the histogram of each pixel value over time is usually in the form of multimodal. Therefore, regarding each peak as a cluster, we employ clustering technique to construct and update the model of a dynamic background. By using the established background model, the moving objects are segmented from the background quickly and accurately. Experimental results show that the proposed background modeling method can effectively capture and adapt to the changes in background. In addition, this method outperforms the current background modeling methods in terms of computational time and memory requirement, thus being easy to implement for DSP or FPGA based hardware.