Finding Temporally Consistent Occlusion Boundaries in Videos using Geometric Context

TL;DR

This paper introduces an efficient algorithm for detecting temporally consistent occlusion boundaries in videos, leveraging appearance, flow, and geometric features within a probabilistic framework, supported by a new annotated dataset.

Contribution

It proposes a novel framework combining MRF and random forests for occlusion boundary detection, and provides a new dataset for evaluation.

Findings

Scene layout and temporal cues improve occlusion boundary detection.

The method achieves consistent boundary detection across frames.

The dataset enables benchmarking of occlusion reasoning methods.

Abstract

We present an algorithm for finding temporally consistent occlusion boundaries in videos to support segmentation of dynamic scenes. We learn occlusion boundaries in a pairwise Markov random field (MRF) framework. We first estimate the probability of an spatio-temporal edge being an occlusion boundary by using appearance, flow, and geometric features. Next, we enforce occlusion boundary continuity in a MRF model by learning pairwise occlusion probabilities using a random forest. Then, we temporally smooth boundaries to remove temporal inconsistencies in occlusion boundary estimation. Our proposed framework provides an efficient approach for finding temporally consistent occlusion boundaries in video by utilizing causality, redundancy in videos, and semantic layout of the scene. We have developed a dataset with fully annotated ground-truth occlusion boundaries of over 30 videos ($5000 frames). This dataset is used to evaluate temporal occlusion boundaries and provides a much needed baseline for future studies. We perform experiments to demonstrate the role of scene layout, and temporal information for occlusion reasoning in dynamic scenes.