Video Object Tracking Using Interactive Segmentation and Superpixel Based Gaussian Kernel

A novel non-rigid video object tracking based on interactive segmentation and super pixel Gaussian kernel is proposed in this paper. In the initialization stage, instead of using the traditional bounding box to locate the targeted object, we employed an interactive segmentation with user-defined marker to segment the object accurately in the first frame of the input video to avoid the background influence in the traditional bounding box. During the tracking stage, using a Gaussian kernel as movement constraint, each super pixel is tracked independently to locate the object in the next frame. Experimental results show that the proposed method compared to state of the art methods can achieve better robustness and accuracy for various challenging video clips.