OCCLUSION DETECTION AND HANDLING IN IMAGE

Abstract

A major challenge for object tracking system is to detect object due to occlusion. Here we describe method to address partial occlusions for human detection in still images. For that random subspace method (RSM) is chosen for building a classifier ensemble robust against partial occlusions. The component classifiers are chosen on the basis of their individual and combined performance. The main contribution of this work lies in our approach’s capability to improve the detection rate when partial occlusions are present without compromising the detection performance on non-occluded data. In contrast to many recent approaches, a method which does not require manual labeling of body parts, defining any semantic spatial components, or using additional data coming from motion or stereo. Moreover, the method can be easily extended to other object classes. The different approaches are evaluated at the classification and detection levels for both partially occluded and non-occluded data. There are some challenges like to detect human occlusion with skin color background and to detect human occlusion in complex image with existing system and we use different detection technique to detect human occlusion in such conditions.