Transfer Learning of Spatial Features From High-Resolution RGB Images for Large-Scale and Robust Hyperspectral Remote Sensing Target Detection

作者：Yuanfeng Wu, Zijin Li, Boya Zhao, Yuhang Song, Bing Zhang · 发表于：IEEE Transactions on Geoscience and Remote Sensing · 年份：2024 · DOI：10.1109/tgrs.2024.3355184 · 被引用次数：16 · 研究领域：Remote-Sensing Image Classification、Advanced Image and Video Retrieval Techniques、Remote Sensing and Land Use

Target detection is a critical task in interpreting hyperspectral remote sensing images. Small target (such as airplanes) detection is challenging, especially in large-scale complex scenes with high spectral variability of different land cover types. In this paper, we propose a transfer learning-based, large-scale, robust hyperspectral target detector (TLH2TD) to improve the accuracy of hyperspectral target detection (HTD) in large-scale complex scenes. TLH2TD learns the spatial features of hyperspectral targets from high-resolution remote sensing images and achieves high-precision HTD with fused spatial-spectral features. It comprises three parts: (1) The coupled target-background sample expansion (CTBSE) module is designed to expand the labeled hyperspectral target and background samples with sufficient high-resolution, labeled RGB images and a few labeled hyperspectral samples. (2) The hard positive and negative example mining (HPNEM) module trains the hard positive and negative samples to enhance the discriminative ability of the network, addressing the problem of inadequate sample training in large-scale hyperspectral images (HSIs). (3) The spatial-spectral weighted subspace (SSWS) module is designed to fuse the spatial features extracted from the target detection network and the spectral features based on the Mahalanobis distance. The results show that: (1) The TLH2TD achieves average area under the curve (AUC) values of 0.96, 0.96, and 0.93 on small-sized, medium-sized...