Deep learning (DL) stereo matching methods gained great attention in remote sensing satellite datasets. However, most of these existing studies conclude assessments based only on a few/single stereo images lacking a systematic evaluation on how robust DL methods are on satellite stereo images with varying radiometric and geometric configurations. This paper provides an evaluation of four DL stereo matching methods through hundreds of multi-date multi-site satellite stereo pairs with varying geometric configurations, against the traditional well-practiced Census-SGM (Semi-global matching), to comprehensively understand their accuracy, robustness, generalization capabilities, and their practical potential. The DL methods include a learning-based cost metric through convolutional neural networks (MC-CNN) followed by SGM, and three end-to-end (E2E) learning models using Geometry and Context Network (GCNet), Pyramid Stereo Matching Network (PSMNet), and LEAStereo. Our experiments show that E2E algorithms can achieve upper limits of geometric accuracies, while may not generalize well for unseen data. The learning-based cost metric and Census-SGM are rather robust and can consistently achieve acceptable results. All DL algorithms are robust to geometric configurations of stereo pairs and are less sensitive in comparison to the Census-SGM, while learning-based cost metrics can generalize on satellite images when trained on different datasets (airborne or ground-view).
翻译:深入学习(DL)立体比对方法在遥感卫星数据集中引起了极大注意,然而,大多数现有研究仅以少数/单立体图像为基础进行了评估,没有系统地评价在卫星立体图像上,具有不同辐射度和几何配置的卫星立体图像上如何使用稳健的DL方法;本文通过数百个多日期多站多站卫星立立立体配对,配有不同几何配置的多站立立体配对,对照传统的良好实践的人口普查-SGM(Semi-GM(Semi-GM)(全球匹配),全面理解其准确性、稳健性、概括性能力及其实际潜力。DL方法包括:通过SGM(MC-CNN)等同级神经神经网络(MC-CNN)进行基于学习的衡量成本衡量,以及三个端对端至端(E2E)学习模型,使用地貌和深层次的人口普查网络(Pyrammical-CRational-CVAL),在可接受的地面配置中,所有学习成本和测算法都比得更稳健的,在可接受的GMRML-CS-CS-CS-CL-CRM-CRisal-Cal-CL-CL-CL-CM-C-CM-CM-CM-C-C-CM-CM-CM-C-C-C-CM-C-CAS-CM-C-C-CAS-C-C-C-C-C-C-C-C-C-C-C-CF-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-CF-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-CF-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-