Abstract

We address the problem of detecting occlusion boundaries from motion sequences, which is important for motion segmentation, estimating depth order, and related tasks. Previous work by Stein and Hebert has addressed this problem and obtained good results on a bench- marked dataset using two-dimensional image cues, motion estimation, and a global boundary model [1]. In this paper we describe a method for detecting occlusion boundaries which uses depth cues and local seg- mentation cues. More specifically, we show that crude scaled estimates of depth, which we call pseudo-depth, can be extracted from motion se- quences containing a small number of image frames using standard SVD factorization methods followed by weak smoothing using a Markov Ran- dom Field defined over super-pixels. We then train a classifier for oc- clusion boundaries using pseudo-depth and local static boundary cues (adding motion cues only gives slightly better results). We evaluate per- formance on Stein and Hebert’s dataset and obtain results of similar average quality which are better in the low recall/high precision range. Note that our cues and methods are different from [1] – in particular we did not use their sophisticated global boundary model – and so we conjecture that a unified approach would yield even better results.