Geometric-Spectral Reconstruction Learning for Multi-Source Open-Set Classification With Hyperspectral and LiDAR Data

Dear Editor, This letter presents an open-set classification method of remote sensing images (RSIs) based on geometric-spectral reconstruction learning. More specifically, in order to improve the ability RSI model adapt environment, geometric and spectral feature fusion is proposed. proposes realize features with hyper-spectral light detection ranging (LiDAR) data for first time. In a variety sources sensing, hyperspectral (HSIs) LiDAR can provide rich information target objects. combines both HSIs recognition unknown classes known classes. Experiments show that proposed better than previous state-of-the-art methods.