Abstract: Large quantity information needs to be dealt during image guidance. In order to compress calculation quantity,a novel method for tracking infrared target based on curves evolving theory and human eye non-uniform sampling characteristic was proposed. First,log-polar coordinate transform model was used to compress calculation quantity and increase calculating speed. And then,levcl sets curves evolving method based on target intensity and edge features was presented to suppress local deformation, thus achieving non-rigid deformed target tracking. Compared with traditional Mean Shift tracking method, this method is stable and efficient. Experimental results show the proposed method is effective for suppress non-rigid deformed.

Key words: Non-uniform sampling, Log-polar transform, Non-rigid deformed, Curve evolving, Particle filtering, Level sets