Multi-view Subspace Graph Convolutional Clustering for Hyperspectral Images
摘要
Recent advances in spectral imaging have established hyperspectral imagery (HSI) as a powerful analytical tool, driving innovation across multiple scientific and operational domains. These high-resolution spectral datasets have demonstrated particular value in environmental monitoring (Camps-Valls et al. in IEEE Signal Process Mag 31:45–54, 2013), security applications (Zhao Y-P, Li H, Chen Y, Wang Z, Li X (2023) Hyperspectral anomaly detection via structured sparsity plus enhanced low-rankness. IEEE Trans Geosci Rem Sens 61:1–15), and geological exploration (Guan et al. in Remote Sensing 14:3216, 2022;Chen Y, Yuan Q, Tang Y, Xiao Y, He J, Zhang L (2023) Spirit: spectral awareness interaction network with dynamic template for hyperspectral object tracking. IEEE Trans Geosci Rem Sens 62:1–16;).