ABSTRACT
This chapter provides an object tracking algorithm in the low-rank representation has been proposed to cope with the occlusion. It describes the observation sequence into a low-rank matrix, which is composed of the moving object, and a sparse support matrix, which is composed of the occlusion. The chapter discusses the variation between several adjacent frames to locate the moving object in the sequence, and the sparse support matrix to cope with the occlusion. Since the wide use of image processing, moving object tracking has become an important direction in the field of computer vision. However, due to the occlusion, feature points in moving object may disappear, enter and leave the view field. The occlusion is defined as any objects that move differently from the moving object or block the moving object in the view. The chapter presents several experiments to compare our moving object tracking algorithm with the KLT tracking method.
