Brandao, P, Mazomenos, E orcid.org/0000-0003-0357-5996 and Stoyanov, D (2019) Widening siamese architectures for stereo matching. Pattern Recognition Letters, 120. pp. 75-81. ISSN 0167-8655
Abstract
Computational stereo is one of the classical problems in computer vision. Numerous algorithms and solutions have been reported in recent years focusing on developing methods for computing similarity, aggregating it to obtain spatial support and finally optimizing an energy function to find the final disparity. In this paper, we focus on the feature extraction component of stereo matching architecture and we show standard CNNs operation can be used to improve the quality of the features used to find point correspondences. Furthermore, we use a simple space aggregation that hugely simplifies the correlation learning problem, allowing us to better evaluate the quality of the features extracted. Our results on benchmark data are compelling and show promising potential even without refining the solution.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2018 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license. (http://creativecommons.org/licenses/by/4.0/) |
Keywords: | Stereo matching; Convolutional neural network; Disparity; Computer vision |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Electronic & Electrical Engineering (Leeds) > Robotics, Autonomous Systems & Sensing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 05 Mar 2020 14:17 |
Last Modified: | 05 Mar 2020 14:17 |
Status: | Published |
Publisher: | Elsevier |
Identification Number: | 10.1016/j.patrec.2018.12.002 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:158065 |