Moving object detection algorithm inspired by the sequence detection in the hippocampus and its digital LSI implementation

Abstract

We propose a high-speed moving object detection algorithm based on parallel processing inspired by the mechanism for sequence detection in neural networks such as the hippocampal CA3 region. Computer simulations verified that the present algorithm performs well. A digital LSI architecture for the moving object detection and a modified algorithm suitable for LSI implementation are also proposed. Correct logical operation was verified using a logic simulator and the algorithm was implemented on an FPGA board.