Occlusion boundary detection based on mid-level figure/ground assignment features

Kazuhiko Murasaki, Kyoko Sudo, Yukinobu Taniguchi

Abstract: In this paper, we propose a novel method to detect boundaries and estimate figure/ground assignments simultaneously. The proposed approach is based on the observation that the mid-level feature expression for boundary detection can represent local shape of boundaries with high accuracy and high speed [1]. We use figure/ground information to enhance the mid-level features for occlusion boundaries, and propose an algorithm to integrate these mid-level features efficiently. In our global optimization process, efficient and accurate estimation is achieved by superpixel-based combinatorial optimization. Superpixel segmentation is used to reduce the boundary candidates while integrating neighboring classification responses reduces computation time and improves the accuracy of figure/ground assignment. Experiments show that the proposal can detect occlusion boundaries 10 times faster and conduct figure/ground assignment 7.1% more accurately than the current state-of-the-art alternative.