Unsupervised Band Selection Using Fused HSI and LiDAR Attention Integrated with Autoencoder for Enhanced Remote Sensing Analysis

A novel unsupervised band selection framework that integrates hyperspectral imaging (HSI) and light detection and ranging (LiDAR) data through a dual attention mechanism and an Autoencoder to effectively capture essential spatial and spectral features, reduce redundancy, and enhance classification performance in remote sensing applications.