Object tracking: feature selection and confidence propagation

Choosing unique and invariant features is the first important step in object tracking. In this paper, we present a method to find proper-sized and irregularlyshaped trackable features, the use of which can outperform procedures using normal square features. The notion of confidence associated with each feature is introduced as the feature propagates. The use of confidence results in robust tracking even when occlusion is present. Based on the translational displacement of each feature, the affine motion of the object can be accurately estimated. This approach has been tested on a wide variety of video sequences and produces good tracking results.