Image moments-based structuring and tracking of objects

Abstract

This paper presents a new method for structuring and tracking of objects in video sequences. Our approach is based on image moments and the BSP-tree data structure. We use invariant properties of these moments to construct a BSP-tree and determine an ellipsis that approximates the object's shape. Then, we employ this information to track objects frame by frame through the image sequence. The method works well for segmented images with a single object and we assume that the motion will not change abruptly.