Tracking Infrared Target with Constructing Multiple Feature Pseudo-Color Image
Ruiming Liu, Qiang Liu · 2010
Mean-shift algorithm is one of the well-known tracking algorithms because of its robust performance. However, Mean-shift algorithm tracks targets only by the color or intensity features. That is to say that, Mean-shift can only tracking the statistical features of pixels. The universal Mean-shift which can track any features of targets has not been developed. We propose a strategy which does not need to improve on the Mean-shift algorithm itself, but it can make Mean-shift track other features. We first map the features into the pixel intensity and create the feature images. Then these feature images are used to construct the multiple feature pseudo-color images (MFPCIs). The Mean-shift algorithm tracking targets in MFPCIs can indirectly track these features.