Target detection and tracking based on spatially multiplexed and superposition imaging

Abstract

Addressing continuous target detection and tracking over a large field of view in surveillance application, a novel method to detect and track target is presented in a wide field of view based on spatially multiplexed and superposition imaging technique. This system architecture is proposed by using the spherical lens array and confocal plane with the character of wide field and compressive sampling. And the method of moving target detection with superposition imaging is studied emphatically. This method models each pixel as a Gaussian mixture model, while the Gaussian distributions are evaluated to determine which are most likely to result from a background process. Accordingly the background and foreground are separated. Also, the method of moving target decoding and tracking is researched, which means that target location is decoded based on a set resulting from classifying target copies according to position and velocity criteria in the superposition space. Finally, the target detection and decoding algorithm are simulated and the results show that this method can perform target detection and tracking over a wide field of view.