MultiResSAR
收藏资源简介:
MultiResSAR数据集是由武汉大学构建并发布的,包含超过10k对多源、多分辨率、多场景的SAR和光学遥感图像。该数据集旨在为多分辨率SAR与光学遥感图像配准研究提供基准数据,以评估和比较不同配准算法的性能。数据集涵盖了从低分辨率到高分辨率的图像,能够帮助研究者更好地理解和克服高分辨率图像配准中的挑战,如噪声抑制、三维几何信息的融合、跨视角几何变换建模以及深度学习模型的优化等。
The MultiResSAR dataset was constructed and released by Wuhan University, which contains over 10k pairs of multi-source, multi-resolution, multi-scenario SAR and optical remote sensing images. This dataset aims to provide benchmark data for research on multi-resolution SAR and optical remote sensing image registration, so as to evaluate and compare the performance of different registration algorithms. The dataset covers images ranging from low-resolution to high-resolution, which can help researchers better understand and overcome the challenges in high-resolution image registration, such as noise suppression, 3D geometric information fusion, cross-view geometric transformation modeling, and deep learning model optimization.




