Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries

Syed Raza, Omar Javed, Aveek Das, Harpreet Sawhney, Hui Cheng and Irfan Essa

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.10

Abstract

We present an algorithm to estimate depth in dynamic video scenes. We propose to learn and infer depth in videos from appearance, motion, occlusion boundaries, and geometric context of the scene. Using our method, depth can be estimated from unconstrained videos with no requirement of camera pose estimation, and with significant background/foreground motions. We start by decomposing a video into spatio-temporal regions. For each spatio-temporal region, we learn the relationship of depth to visual appearance, motion, and geometric classes. Then we infer the depth information of new scenes using piecewise planar parametrization estimated within a Markov random field (MRF) framework by combining appearance to depth learned mappings and occlusion boundary guided smoothness constraints. Subsequently, we perform temporal smoothing to obtain temporally consistent depth maps. To evaluate our depth estimation algorithm and facilitate future research, we provide a novel dataset with ground truth depth for outdoor video scenes. We present a thorough evaluation of our algorithm on our new dataset and the publicly available Make3d static image dataset.

Session

Video and Structure From Motion

Files

Extended Abstract (PDF, 1 page, 118K)
Paper (PDF, 12 pages, 332K)
Bibtex File

Presentation

Citation

Syed Raza, Omar Javed, Aveek Das, Harpreet Sawhney, Hui Cheng, and Irfan Essa. Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.10
	title = {Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries},
	author = {Raza, Syed and Javed, Omar and Das, Aveek and Sawhney, Harpreet and Cheng, Hui and Essa, Irfan},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.10 }
}