Occlusion Boundary: A Formal Definition & Its Detection via Deep Exploration of Context

Chaohui Wang (1) , Huan Fu (2) , Dacheng Tao (2) , Michael J Black (3)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 UBTECH Sydney Artificial IntelIigence Centre
3 Perceiving Systems Department

Occlusion boundaries contain rich perceptual information about the underlying scene structure and provide important cues in many visual perception-related tasks such as object recognition, segmentation, motion estimation, scene understanding, and autonomous navigation. However, there is no formal definition of occlusion boundaries in the literature, and state-of-the-art occlusion boundary detection is still suboptimal. With this in mind, in this paper we propose a formal definition of occlusion boundaries for related studies. Further, based on a novel idea, we develop two concrete approaches with different characteristics to detect occlusion boundaries in video sequences via enhanced exploration of contextual information (e.g., local structural boundary patterns, observations from surrounding regions, and temporal context) with deep models and conditional random fields. Experimental evaluations of our methods on two challenging occlusion boundary benchmarks (CMU and VSB100) demonstrate that our detectors significantly outperform the current state-of-the-art. Finally, we empirically assess the roles of several important components of the proposed detectors to validate the rationale behind these approaches.

Mots clés: Occlusion boundaries; convolutional neural networks; fully convolutional networks; conditional random fields

Domaines: Informatique [cs]

Chaohui Wang, Huan Fu, Dacheng Tao, Michael J Black. Occlusion Boundary: A Formal Definition & Its Detection via Deep Exploration of Context. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, ⟨10.1109/TPAMI.2020.3039478⟩. ⟨hal-03132245⟩