Translational Motion Estimation of Moving Object Based on Windowed Phase Correlation Algorithm with Kernel Regression

Motion estimation is one of the basic problems in digital video processing; it is significant in the applications of video image compression, registration, mosaic, and target detection, and so on. In the base of discussing basic phase correlation algorithm, a method based on kernel regression for constructing two-dimensional circular symmetry window function has been introduced, and the improved scheme based on windowed preprocessing, is proposed for translational motion estimation of moving object. Experimental results show the feasibility of the presented scheme.