Stereo Matching Method for Remote Sensing Images Based on Attention and Scale Fusion
Open Access
- 18 January 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (2) , 387
Abstract
With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often contain noise, occluded regions, untextured areas, and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and non-negative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder–decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain an accuracy of 1.115 pixels in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (41971363, 2022YFB3903705, 202202AF080004)
- National Key Research and Development Program of China (41971363, 2022YFB3903705, 202202AF080004)
- Major Science and Technology Projects of Yunnan Province (41971363, 2022YFB3903705, 202202AF080004)
This publication has 35 references indexed in Scilit:
- Enhanced disparity maps from multi-view satellite images2016
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation2016
- Fast R-CNN2015
- A Deep Visual Correspondence Embedding Model for Stereo Matching Costs2015
- Computing the stereo matching cost with a convolutional neural network2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Cost Aggregation and Occlusion Handling With WLS in Stereo MatchingIEEE Transactions on Image Processing, 2008
- Stereo matching using belief propagationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Non-parametric local transforms for computing visual correspondence1994
- Stereo by Intra- and Inter-Scanline Search Using Dynamic ProgrammingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1985