Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos

TL;DR

This paper introduces a novel interactively constrained encoding (ICE) scheme that integrates motion and appearance cues for improved foreground object segmentation in unconstrained videos, emphasizing their mutual assistance and structural correlation.

Contribution

The paper proposes a new ICE scheme for collaborative encoding of motion and appearance cues, applied in a two-stage framework with superpixel processing and bipartite graph matching for multi-object localization.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively captures structural patterns of objects throughout segmentation

Reduces computational complexity by using superpixels

Abstract

We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos. Unlike conventional methods encoding motion and appearance patterns individually, our method puts particular emphasis on their mutual assistance. Specifically, we propose using an interactively constrained encoding (ICE) scheme to incorporate motion and appearance patterns into a graph that leads to a spatiotemporal energy optimization. The reason of utilizing ICE is that both motion and appearance cues for the same target share underlying correlative structure, thus can be exploited in a deeply collaborative manner. We perform ICE not only in the initialization but also in the refinement stage of a two-layer framework for object segmentation. This scheme allows our method to consistently capture structural patterns about object perceptions throughout the whole framework. Our method can be operated on superpixels instead of raw pixels to reduce the number of graph nodes by two orders of magnitude. Moreover, we propose to partially explore the multi-object localization problem with inter-occlusion by weighted bipartite graph matching. Comprehensive experiments on three benchmark datasets (i.e., SegTrack, MOViCS, and GaTech) demonstrate the effectiveness of our approach compared with extensive state-of-the-art methods.