Paper in BMVC (2014): “Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries”

Abstract

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 the 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.

Paper / Citation

  • S. H. Raza, O. Javed, A. Das, H. Sawhney, H. Cheng, and I. Essa (2014), “Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries,” in British Machine Vision Conference (BMVC), Nottingham, UK, 2014. [PDF] [WEBSITE] [arXiv] [BIBTEX]
    @InProceedings{ 2014-Raza-DEFVUGCOB,
    address  = {Nottingham, UK},
    arxiv = {https://arxiv.org/abs/1510.07317},
    author  = {Syed Hussain Raza and Omar Javed and Aveek Das and
    Harpreet Sawhney and Hui Cheng and Irfan Essa},
    booktitle  = {{British Machine Vision Conference (BMVC)}},
    month = {September},
    pdf = {http://www.cc.gatech.edu/~irfan/p/2014-Raza-DEFVUGCOB.pdf},
    title = {Depth Extraction from Videos Using Geometric
    Context and Occlusion Boundaries},
    url = {http://www.cc.gatech.edu/cpl/projects/videodepth/},
    year = {2014}
    }

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.