Next Article in Journal
Land Use/Land Cover Changes and Their Driving Factors in the Northeastern Tibetan Plateau Based on Geographical Detectors and Google Earth Engine: A Case Study in Gannan Prefecture
Previous Article in Journal
A High-Performance Spectral-Spatial Residual Network for Hyperspectral Image Classification with Small Training Data
Open AccessArticle

Stereo Dense Image Matching by Adaptive Fusion of Multiple-Window Matching Results

by 1, 2, 2, 1,* and 2,3,4
1
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
2
Department of Civil, Environmental and Geodetic Engineering, The Ohio State University, Columbus, OH 43221, USA
3
Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43221, USA
4
Translational Data Analytics, The Ohio State University, Columbus, OH 43221, USA
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(19), 3138; https://doi.org/10.3390/rs12193138
Received: 24 August 2020 / Revised: 16 September 2020 / Accepted: 22 September 2020 / Published: 24 September 2020
Traditional stereo dense image matching (DIM) methods normally predefine a fixed window to compute matching cost, while their performances are limited by the matching window sizes. A large matching window usually achieves robust matching results in weak-textured regions, while it may cause over-smoothness problems in disparity jumps and fine structures. A small window can recover sharp boundaries and fine structures, while it contains high matching uncertainties in weak-textured regions. To address the issue above, we respectively compute matching results with different matching window sizes and then proposes an adaptive fusion method of these matching results so that a better matching result can be generated. The core algorithm designs a Convolutional Neural Network (CNN) to predict the probabilities of large and small windows for each pixel and then refines these probabilities by imposing a global energy function. A compromised solution of the global energy function is utilized by breaking the optimization into sub-optimizations of each pixel in one-dimensional (1D) paths. Finally, the matching results of large and small windows are fused by taking the refined probabilities as weights for more accurate matching. We test our method on aerial image datasets, satellite image datasets, and Middlebury benchmark with different matching cost metrics. Experiments show that our proposed adaptive fusion of multiple-window matching results method has a good transferability across different datasets and outperforms the small windows, the median windows, the large windows, and some state-of-the-art matching window selection methods. View Full-Text
Keywords: dense image matching (DIM); convolutional neural network (CNN); matching window fusion; matching cost fusion; indoor image; aerial image; satellite image dense image matching (DIM); convolutional neural network (CNN); matching window fusion; matching cost fusion; indoor image; aerial image; satellite image
Show Figures

Graphical abstract

MDPI and ACS Style

Han, Y.; Liu, W.; Huang, X.; Wang, S.; Qin, R. Stereo Dense Image Matching by Adaptive Fusion of Multiple-Window Matching Results. Remote Sens. 2020, 12, 3138. https://doi.org/10.3390/rs12193138

AMA Style

Han Y, Liu W, Huang X, Wang S, Qin R. Stereo Dense Image Matching by Adaptive Fusion of Multiple-Window Matching Results. Remote Sensing. 2020; 12(19):3138. https://doi.org/10.3390/rs12193138

Chicago/Turabian Style

Han, Yilong; Liu, Wei; Huang, Xu; Wang, Shugen; Qin, Rongjun. 2020. "Stereo Dense Image Matching by Adaptive Fusion of Multiple-Window Matching Results" Remote Sens. 12, no. 19: 3138. https://doi.org/10.3390/rs12193138

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop