Hyperspectral and LiDAR Representation With Spectral–Spatial Graph Network

Abstract

Land cover analysis has received significant attention in remote sensing-related fields. To take advantage of multimodal data, hyperspectral images (HSI) and light detection and ranging (LiDAR) are often combined. However, it is difficult to capture intricate local and global spectral–spatial associations between HSI and LiDAR. To exploit the complementary information of multimodal data, a spectral–spatial graph network is proposed that integrates HSI and LiDAR data into intricate local and global spectral–spatial associations. Specifically, the network consists of a local module and a global module. The local module uses convolution techniques applied over image patches to preserve the local spatial relationships available in multimodal data. The global module constructs a spectral–spatial multimodal graph, which is used to preserve spectral–spatial proximity in multimodal data. Both the local and global modules are utilized to their utmost capacity to generate the final multimodal data representation. Experiments on multimodal remote sensing datasets reveal that the proposed network has attained performance levels comparable to state-of-the-art methods.

Keywords

• Data fusion
• graph neural network
• multimodal data
• remote sensing classification