WHU-Stereo: A Challenging Benchmark for Stereo Matching of High-Resolution Satellite Images

Stereo matching of high-resolution satellite images (HRSIs) is still a fundamental but challenging task in the field of photogrammetry and remote sensing. Recently, deep learning (DL) methods have demonstrated the potential for stereo matching on public benchmark datasets. Currently, mainstream stereo matching models depend on quantities of training data with ground truth. However, datasets for stereo matching of satellite images are scarce, which profoundly blocks the application of DL in this field. To facilitate further research, this article publishes a large-scale dataset, termed WHU-Stereo, for stereo matching DL network training and testing. This dataset is created by using airborne light detection and ranging (LiDAR) point clouds and high-resolution stereo imageries taken from the Chinese GaoFen-7 (GF-7) satellite. Occlusions should be seriously considered in the generation of ground-truth disparities. We propose an occlusion removal technique, which can adapt to point clouds with different densities and shows high potential in training data preparation. The WHU-Stereo dataset contains more than 1700 epipolar rectified image pairs, which cover six areas in China and includes various kinds of landscapes. We have assessed the accuracy of ground-truth disparity maps, and it is shown that our dataset achieves comparable precision compared with existing state-of-the-art stereo matching datasets. To verify its feasibility, in experiments, the handcrafted semiglobal matching (SGM) algorithm and recent DL networks have been tested on the dataset. Experimental results show that the WHU-Stereo dataset can serve as a challenging benchmark for stereo matching of HRSIs and performance evaluation of DL models. Our dataset is available at https://github.com/Sheng029/WHU-Stereo.

Automated summary

The article introduces that stereo matching of high-resolution satellite images is still a fundamental but challenging task, and presents a large-scale dataset called WHU-Stereo for training and testing of deep learning networks. The dataset is created using airborne LiDAR point clouds and high-resolution stereo imageries from the Chinese GF-7 satellite, and includes ground-truth disparities considering occlusions. Experimental results demonstrate that the WHU-Stereo dataset can serve as a challenging benchmark for stereo matching and performance evaluation of DL models.