Next Article in Journal
UAV-Based Heating Requirement Determination for Frost Management in Apple Orchard
Next Article in Special Issue
Sequence Image Interpolation via Separable Convolution Network
Previous Article in Journal
Integrated Drought Monitoring and Evaluation through Multi-Sensor Satellite-Based Statistical Simulation
Previous Article in Special Issue
A Practical Cross-View Image Matching Method between UAV and Satellite for UAV-Based Geo-Localization
Open AccessArticle

Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network

1
School of Surveying and Geo-Informatics, Shandong Jianzhu University, No. 1000 Fengming Road, Jinan 250101, China
2
Photogrammetric Computer Vision Lab, The Ohio State University, Columbus, OH 43210, USA
3
Chinese Academy of Surveying & Mapping, No. 28 Lianhuachi West Road, Beijing 100830, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2021, 13(2), 274; https://doi.org/10.3390/rs13020274
Received: 28 November 2020 / Revised: 8 January 2021 / Accepted: 11 January 2021 / Published: 14 January 2021
(This article belongs to the Special Issue Computer Vision and Deep Learning for Remote Sensing Applications)
The available stereo matching algorithms produce large number of false positive matches or only produce a few true-positives across oblique stereo images with large baseline. This undesired result happens due to the complex perspective deformation and radiometric distortion across the images. To address this problem, we propose a novel affine invariant feature matching algorithm with subpixel accuracy based on an end-to-end convolutional neural network (CNN). In our method, we adopt and modify a Hessian affine network, which we refer to as IHesAffNet, to obtain affine invariant Hessian regions using deep learning framework. To improve the correlation between corresponding features, we introduce an empirical weighted loss function (EWLF) based on the negative samples using K nearest neighbors, and then generate deep learning-based descriptors with high discrimination that is realized with our multiple hard network structure (MTHardNets). Following this step, the conjugate features are produced by using the Euclidean distance ratio as the matching metric, and the accuracy of matches are optimized through the deep learning transform based least square matching (DLT-LSM). Finally, experiments on Large baseline oblique stereo images acquired by ground close-range and unmanned aerial vehicle (UAV) verify the effectiveness of the proposed approach, and comprehensive comparisons demonstrate that our matching algorithm outperforms the state-of-art methods in terms of accuracy, distribution and correct ratio. The main contributions of this article are: (i) our proposed MTHardNets can generate high quality descriptors; and (ii) the IHesAffNet can produce substantial affine invariant corresponding features with reliable transform parameters. View Full-Text
Keywords: large baseline; oblique stereo images; affine invariant features; convolutional neural network; deep learning; least square matching large baseline; oblique stereo images; affine invariant features; convolutional neural network; deep learning; least square matching
Show Figures

Figure 1

MDPI and ACS Style

Yao, G.; Yilmaz, A.; Zhang, L.; Meng, F.; Ai, H.; Jin, F. Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network. Remote Sens. 2021, 13, 274. https://doi.org/10.3390/rs13020274

AMA Style

Yao G, Yilmaz A, Zhang L, Meng F, Ai H, Jin F. Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network. Remote Sensing. 2021; 13(2):274. https://doi.org/10.3390/rs13020274

Chicago/Turabian Style

Yao, Guobiao; Yilmaz, Alper; Zhang, Li; Meng, Fei; Ai, Haibin; Jin, Fengxiang. 2021. "Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network" Remote Sens. 13, no. 2: 274. https://doi.org/10.3390/rs13020274

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