Foreground soft segmentation for the search space reduction
Eunji Cho, Daijin Kim · 2014
This paper proposes the foreground soft segmentation to reduce the search space. Our contributions are twofold: (i) using a quad-tree structure to efficiently obtain a binary label image for foreground; and (ii) search space reduction by limiting the locations within the only area based on segmented foreground. We show that the proposed method achieved segmentation of foreground in the various environments and poses.