Object Tracking Based on Time-varying Saliency

Visual attention has been widely used in image pre-processing, since it can rapidly detect the region of interest in the given scene. This paper presents a novel technique to track the moving object, which is based on the motion saliency model. The salient region is computed by the combination of multi-feature maps and motion saliency map, which vastly reduce the amount of information in further image processing. Next, a single matching method, normalized color histogram, is used to measure the similarity for tracking processing. Experimental results, found in AVSS 07, are reported, which validate our model useful and effective. * Corresponding author. Tao Fang. E-mail: [email protected]; phone:+86-021-34204758