Occlusion boundary detection and figure/ground assignment from optical flow

Abstract

In

Efficient Closed-Form Solution to Generalized Boundary Detection

“…This is in contrast to current approaches [6,7,9] that process low and mid-level layers separately and combine them in different ways to detect different types of boundaries. 4) we only learn a small set of parameters, enabling efficient training with limited data.…”

“…Second, we perform experiments on occlusion boundary detection in short video clips. Multiple frames, closely spaced in time, provide significantly more information about dynamic scenes and make occlusion boundary detection possible, as shown in recent work [6][7][8]24]. Third, we experiment with RGB-D video frames and show that depth can be effectively combined with color and optical flow to detect moving occlusion boundaries.…”

“…State-of-the-art techniques for occlusion boundary detection in video are based on combining, in various ways, the outputs of existing boundary detectors for static color images with optical flow, followed by a global processing phase [6][7][8]24]. Table 3 compares Gb against reported results on the CMU Motion Dataset [6] We use, as one of our layers, the flow computed using Sun et al's public code [27].…”

“…In this paper we propose a general formulation for boundary detection that can be applied, in principle, to the identification of any type of boundaries, such as general edges from low-level static cues ( Figure 6), and occlusion boundaries from motion and depth cues (Figures 1,7,8). We generalize the classical view of boundaries from sudden signal changes on the original low-level image input [1][2][3][4][12][13][14], to a locally linear (planar or step-wise) model on multiple layers of the input, over a relatively large image region.…”

“…The majority of papers on edge detection have focused on using only low-level cues, such as pixel intensity or color [1][2][3][4][5]. Recent work has started exploring the problem of boundary detection based on higher-level representations of the image, such as motion, surface and depth cues [6][7][8], segmentation [9], as well as category specific information [10,11].…”