An Improved Occlusion Detection with Constraints Approach for Video Processing

Abstract

The accurate understanding of occlusion region is critical for trustworthy estimation of optical flow to prevent the negative influence of occluded pixels on disocclusion regions. However, occlusion is the result of motion. In contrast, estimating accurate optical flow is necessary to locate reliable occlusions. Hence, one of the key challenges that required further exploration and research is the accuracy at the boundaries of the moving objects. This paper presents the work in process approach that can detect occlusion regions by using some constraints such as pixel-wise coherence, segment-wise confidence and edge-motion coherence. Comparing to the previous methods, our method achieves the same efficiency by solving only one Partial Differential Equation (PDE) problem. The proposed method is faster and provides better coverage rates for occlusion regions than variation techniques in various numbers of benchmark datasets. With these improved results, we can apply and extend our approach to a wider range of applications in computer vision, such as: motion estimation, object detection and tracking, robot navigation, 3D reconstruction, image registration.