Article: Learning stereo disparity with feature consistency and confidence Journal: International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC) 2022 Vol.39 No.1/2 pp.83 - 92 Abstract: Most of the existing stereo matching methods have been formulated into four regular parts: feature extraction (FE), cost calculation (CC), cost aggregation (CA), and disparity refinement (DF). They can obtain high precision results in most regions through modifying parts of the four methods, but still have problems in some ill-posed regions. This paper focuses on feature consistency and confidence (FCC), discovers the new attributes of the feature, and proposes a novel neural network structure for stereo matching by measuring the consistency and confidence of features. Base on this method, the paper fuses the cost volume and calculates the pixel confidence map for cost calculation and cost aggregation. The experimental results show the proposed method outperforms most of the state-of-the-art methods on both SceneFlow and Kitti benchmarks and lowers the estimation error of stereo matching down to 1.82% ranking at the 7th position in the Kitti 2015 scoreboard six months ago (http://www.cvlibs.net/datasets/kitti/). Inderscience Publishers - linking academia, business and industry through research

Title: Learning stereo disparity with feature consistency and confidence

Authors: Liaoying Zhao; Jiaming Li; Jianjun Li; Yong Wu; Shichao Cheng; Zheng Tang; Guobao Hui; Chin-Chen Chang

Addresses: School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China ' School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China ' School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China ' School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China ' School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China ' CETC Key Laboratory of Data Link Technology, No. 20 Institute of CETC Xi'an 710129, China ' CETC Key Laboratory of Data Link Technology, No. 20 Institute of CETC Xi'an 710129, China ' Department of Information Engineering and Computer Science, Feng Chia University, Taichung City, Taiwan

Abstract: Most of the existing stereo matching methods have been formulated into four regular parts: feature extraction (FE), cost calculation (CC), cost aggregation (CA), and disparity refinement (DF). They can obtain high precision results in most regions through modifying parts of the four methods, but still have problems in some ill-posed regions. This paper focuses on feature consistency and confidence (FCC), discovers the new attributes of the feature, and proposes a novel neural network structure for stereo matching by measuring the consistency and confidence of features. Base on this method, the paper fuses the cost volume and calculates the pixel confidence map for cost calculation and cost aggregation. The experimental results show the proposed method outperforms most of the state-of-the-art methods on both SceneFlow and Kitti benchmarks and lowers the estimation error of stereo matching down to 1.82% ranking at the 7th position in the Kitti 2015 scoreboard six months ago (http://www.cvlibs.net/datasets/kitti/).

Keywords: depth estimation; stereo matching; confidence measure; feature consistency; multi-distance metrics.

DOI: 10.1504/IJAHUC.2022.120948

International Journal of Ad Hoc and Ubiquitous Computing, 2022 Vol.39 No.1/2, pp.83 - 92

Received: 26 Nov 2020
Accepted: 07 Jan 2021
Published online: 18 Feb 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Learning stereo disparity with feature consistency and confidence

Keep up-to-date