A fast non-local disparity refinement method for stereo matching

2014 ◽  
Author(s):  
Xiaoming Huang ◽  
Guoqin Cui ◽  
Yundong Zhang
Keyword(s):  
Stereo Matching ◽  
Refinement Method ◽  
Non Local

scholarly journals A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation

2021 ◽  
Vol 13 (10) ◽  
pp. 1903
Author(s):  
Zhihui Li ◽  
Jiaxin Liu ◽  
Yang Yang ◽  
Jing Zhang
Keyword(s):  
Remote Sensing ◽  
Satellite Remote Sensing ◽  
Stereo Matching ◽  
Mean Shift ◽  
Segmentation Method ◽  
Remote Sensing Images ◽  
Edge Matching ◽  
Refinement Method ◽  
Initial Segmentation ◽  
Refinement Algorithm

Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective.

Non-Local Stereo Matching Algorithm Based on Color and Edge Information

2020 ◽  
Vol 57 (10) ◽  
pp. 101020
Author(s):  
马晴晴 Ma Qingqing ◽  
王彩芳 Wang Caifang
Keyword(s):  
Stereo Matching ◽  
Edge Information ◽  
Matching Algorithm ◽  
Non Local

scholarly journals AN OPTIMISED SYSTEM FOR GENERATING MULTI-RESOLUTION DTMS USING NASA MRO DATASETS

2016 ◽  
Vol XLI-B3 ◽  
pp. 115-121
Author(s):  
Y. Tao ◽  
J.-P. Muller ◽  
P. Sidiropoulos ◽  
J. Veitch-Michaelis ◽  
V. Yershov
Keyword(s):  
Open Source ◽  
Cross Correlation ◽  
Stereo Matching ◽  
Uncertainty Estimation ◽  
Confidence Estimation ◽  
Registration Accuracy ◽  
Processing Chain ◽  
Trade Offs ◽  
Refinement Method ◽  
The Eu

Within the EU FP-7 iMars project, a fully automated multi-resolution DTM processing chain, called Co-registration ASP-Gotcha Optimised (CASP-GO) has been developed, based on the open source NASA Ames Stereo Pipeline (ASP). CASP-GO includes tiepoint based multi-resolution image co-registration and an adaptive least squares correlation-based sub-pixel refinement method called Gotcha. The implemented system guarantees global geo-referencing compliance with respect to HRSC (and thence to MOLA), provides refined stereo matching completeness and accuracy based on the ASP normalised cross-correlation. We summarise issues discovered from experimenting with the use of the open-source ASP DTM processing chain and introduce our new working solutions. These issues include global co-registration accuracy, de-noising, dealing with failure in matching, matching confidence estimation, outlier definition and rejection scheme, various DTM artefacts, uncertainty estimation, and quality-efficiency trade-offs.

An O (1) disparity refinement method for stereo matching

2016 ◽  
Vol 55 ◽  
pp. 198-206 ◽  
Author(s):  
Xiaoming Huang ◽  
Yu-Jin Zhang
Keyword(s):  
Stereo Matching ◽  
Refinement Method

scholarly journals DISPARITY REFINEMENT OF BUILDING EDGES USING ROBUSTLY MATCHED STRAIGHT LINES FOR STEREO MATCHING

2018 ◽  
Vol IV-1 ◽  
pp. 77-84
Author(s):  
X. Huang ◽  
R. Qin ◽  
M. Chen
Keyword(s):  
Least Squares ◽  
Stereo Matching ◽  
Low Cost ◽  
Point Clouds ◽  
3D Point Clouds ◽  
Dense Matching ◽  
Non Local ◽  
Epipolar Constraints ◽  
High Flexibility ◽  
Straight Lines

<p><strong>Abstract.</strong> Stereo dense matching has already been one of the dominant tools in 3D reconstruction of urban regions, due to its low cost and high flexibility in generating 3D points. However, the image-derived 3D points are often inaccurate around building edges, which limit its use in several vision tasks (e.g. building modelling). To generate 3D point clouds or digital surface models (DSM) with sharp boundaries, this paper integrates robustly matched lines for improving dense matching, and proposes a non-local disparity refinement of building edges through an iterative least squares plane adjustment approach. In our method, we first extract and match straight lines in images using epipolar constraints, then detect building edges from these straight lines by comparing matching results on both sides of straight lines, and finally we develop a non-local disparity refinement method through an iterative least squares plane adjustment constrained by matched straight lines to yield sharper and more accurate edges. Experiments conducted on both satellite and aerial data demonstrate that our proposed method is able to generate more accurate DSM with sharper object boundaries.</p>

scholarly journals NLCA-Net: a non-local context attention network for stereo matching

2020 ◽  
Vol 9 ◽  
Author(s):  
Zhibo Rao ◽  
Mingyi He ◽  
Yuchao Dai ◽  
Zhidong Zhu ◽  
Bo Li ◽  
...  
Keyword(s):  
Stereo Matching ◽  
Hot Spot ◽  
Contextual Information ◽  
Feature Learning ◽  
Superior Performance ◽  
Local Context ◽  
Disparity Map ◽  
Matching Rule ◽  
Attention Network ◽  
Non Local

Accurate disparity prediction is a hot spot in computer vision, and how to efficiently exploit contextual information is the key to improve the performance. In this paper, we propose a simple yet effective non-local context attention network to exploit the global context information by using attention mechanisms and semantic information for stereo matching. First, we develop a 2D geometry feature learning module to get a more discriminative representation by taking advantage of multi-scale features and form them into the variance-based cost volume. Then, we construct a non-local attention matching module by using the non-local block and hierarchical 3D convolutions, which can effectively regularize the cost volume and capture the global contextual information. Finally, we adopt a geometry refinement module to refine the disparity map to further improve the performance. Moreover, we add the warping loss function to help the model learn the matching rule of the non-occluded region. Our experiments show that (1) our approach achieves competitive results on KITTI and SceneFlow datasets in the end-point error and the fraction of erroneous pixels $({D_1})$ ; (2) our proposed method particularly has superior performance in the reflective regions and occluded areas.

Sign in / Sign up

Export Citation Format

Share Document