Moving object extraction using multi-tiered pulse-coupled neural network

A novel method for extraction of moving objects in an image sequence using multi-tiered pulse-coupled neural network (PCNN) is presented in this paper. PCNN is a biologically inspired model, which shows highly applicable in various image processing applications, including image segmentation, contour detection, etc. In order to adapt PCNN for moving object extraction, the multi-tiered PCNN model is proposed. This new PCNN model is called E-PCNN, since excitatory term and external linking are its two features. The architecture and algorithm of E-PCNN are presented in detail. It is shown that E-PCNN outweighs the commonly used inter-frame difference algorithm, having three main advantages: utilization of multiple color information, parameter robustness and robustness against noise.