A Correlation Tracking Validity Judging Method Based on SAD

Correlation tracking method is accurate when image has low signal-to-noise ratio or target has few feature information, and has simple and little calculation, however it will be invalid under the conditions of occlusion, false target jamming and target deformation. This paper proposes a correlation tracking validity judging method based on sum of absolute difference (SAD), selects the neighborhood region of minimum value in the SAD matrix of sequential images, calculates correlation value to judge tracking validity so as to use further tracking methods to the images tracking wrong, so improves robustness and accuracy of correlation tracking method.