By a News Reporter-Staff News Editor at Journal of Robotics & Machine Learning -- Researchers detail new data in Pattern Analysis. According to news originating from Canberra, Australia, by VerticalNews correspondents, research stated, “Traditional depth estimation from stereo images is usually formulated as a patch-matching problem, which requires post-processing stages to impose smoothness and handle depth discontinuities and occlusions. While recent deep network approaches directly learn a regressor for the entire disparity map, they still suffer from large errors near the depth discontinuities.”
Funders for this research include China Scholarship Council, National Natural Science Foundation of China, Australian Research Council.
Our news journalists obtained a quote from the research, “In this paper, we propose a novel method to refine the disparity maps generated by deep regression networks. Instead of relying on ad hoc post processing, we learn a unified deep network model that predicts a confidence map and the disparity gradients from the learned feature representation in regression networks. We integrate the initial disparity estimation, the confidence map and the disparity gradients into a continuous Markov Random Field (MRF) for depth refinement, which is capable of representing rich surface structures. Our disparity MRF model can be solved via efficient global optimization in a closed form.”
According to the news editors, the research concluded: “We evaluate our approach on both synthetic and real-world datasets, and the results show it achieves the state-of-art performance and produces more structure-preserving disparity maps with smaller errors in the neighborhood of depth boundaries.”
For more information on this research see: Learning to refine depth for robust stereo estimation. Pattern Recognition , 2018;74():122-133. Pattern Recognition can be contacted at: Elsevier Sci Ltd, The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, Oxon, England. (Elsevier - www.elsevier.com; Pattern Recognition - http://www.journals.elsevier.com/pattern-recognition/)
The news correspondents report that additional information may be obtained from F.Y. Cheng, Natl ICT Australia, Comp Vis Grp, Canberra, ACT 2601, Australia. Additional authors for this research include X.M. He and H. Zhang.
The direct object identifier (DOI) for that additional information is: https://doi.org/10.1016/j.patcog.2017.07.027. This DOI is a link to an online electronic document that is either free or for purchase, and can be your direct source for a journal article and its citation.
Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2018, NewsRx LLC
CITATION: (2018-01-08), Recent Findings from F.Y. Cheng and Co-Authors Yields New Data on Pattern Analysis (Learning to refine depth for robust stereo estimation), Journal of Robotics & Machine Learning, 414, ISSN: 1944-186X, BUTTER® ID: 014943813
From the newsletter Journal of Robotics & Machine Learning.
https://www.newsrx.com/Butter/#!Search:a=14943813
NewsRx® offers 195 weekly newsletters providing comprehensive information on all professional topics, ranging from health, pharma and life science to business, tech, energy, law, and finance. Our newsletters report only the most relevant and authoritative information from qualified sources.