LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classification

arXiv:2404.03883v1 Announce Type: cross
Abstract: The fusion of hyperspectral and LiDAR data has been an active research topic. Existing fusion methods have ignored the high-dimensionality and redundancy challenges in hyperspectral images, despite that band selection methods have been intensively studied for hyperspectral image (HSI) processing. This paper addresses this significant gap by introducing a cross-attention mechanism from the transformer architecture for the selection of HSI bands guided by LiDAR data. LiDAR provides high-resolution vertical structural information, which can be useful …

abstract arxiv attention challenges classification cs.cv data dimensionality eess.iv fusion image images lidar paper processing redundancy research type