back icon
close icon

Capture phrases in quotes for more specific queries (e.g. "rocket ship" or "Fred Lynn")

Conference Paper  February 1, 2015

Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries



Raza, S. H., Javed, O., Das, A. K., Sawhney, H., Cheng, H., & Essa, I. (2014, September). Depth extraction from videos using geometric context and occlusion boundaries. Paper presented at the British Machine Vision Conference (BVMC'14), Nottingham, United Kingdom.


We present an algorithm to estimate depth in dynamic video scenes.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, 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.

How can we help?

    Once you hit send…

    We’ll match your inquiry to the person who can best help you. Expect a response within 48 hours.

    Our Privacy Policy