Abstract

Boundary detection is essential for a variety of computer vi- sion tasks such as segmentation and recognition. We propose a unified formulation for boundary detection, with closed-form solution, which is applicable to the localization of different types of boundaries, such as in- tensity edges and occlusion boundaries from video and RGB-D cameras. Our algorithm simultaneously combines low- and mid-level image repre- sentations, in a single eigenvalue problem, and we solve over an infinite set of putative boundary orientations. Moreover, our method achieves state of the art results at a significantly lower computational cost than current methods. We also propose a novel method for soft-segmentation that can be used in conjunction with our boundary detection algorithm and improve its accuracy at a negligible extra computational cost.