Hyperspectral Imaging and Applications

© 2022 by the authors; CC BY-NC-ND license

biodiversity; peatland; vegetation type; classification; hyperspectral; in situ measurements; classification; hyperspectral image (HSI); multiscale union regions adaptive sparse representation (MURASR); multiscale spatial information; imaging spectroscopy; airborne laser scanning; minimum noise fraction; class imbalance; Africa; agroforestry; tree species; hyperspectral unmixing; endmember extraction; band selection; spectral variability; prototype space; ensemble learning; hyperspectral; rotation forest; semi-supervised local discriminant analysis; imaging spectroscopy; optical spectral region; thermal infrared spectral region; mineral mapping; data integration; HyMap; AHS; raw material; remote sensing; nonnegative matrix factorization; data-guided constraints; sparseness; evenness; hashing ensemble; hierarchical feature; hyperspectral classification; band expansion process (BEP); constrained energy minimization (CEM); correlation band expansion process (CBEP); iterative CEM (ICEM); nonlinear band expansion (NBE); Otsu’s method; sparse unmixing; hyperspectral; local abundance; nuclear norm; hyperspectral detection; target detection; sprout detection; constrained energy minimization; iterative algorithm; adaptive window; hyperspectral imagery; recursive anomaly detection; local summation RX detector (LS-RXD); sliding window; band selection (BS); band subset selection (BSS); hyperspectral image classification; linearly constrained minimum variance (LCMV); Otsu’s method; successive LCMV-BSS (SC LCMV-BSS); sequential LCMV-BSS (SQ LCMV-BSS); vicarious calibration; reflectance-based method; irradiance-based method; Dunhuang site; 90° yaw imaging; terrestrial hyperspectral imaging; vineyard; water stress; machine learning; tree-based ensemble; band selection (BS); progressive sample processing (PSP); real-time processing; image fusion; hyperspectral image; panchromatic image; structure tensor; image enhancement; weighted fusion; spectral mixture analysis; fire severity; AVIRIS; deep belief networks; deep learning; texture feature enhancement; hyperspectral classification; band grouping; hyperspectral compression; lossy compression; on-board compression; orthogonal projections; Gram–Schmidt orthogonalization; parallel processing; hyperspectral; anomaly detection; sparse coding; KSVD; sliding window; hyperspectral images (HSIs); classification; SVM; composite kernel; algebraic multigrid methods; hyperspectral pansharpening; panchromatic; intrinsic image decomposition; weighted least squares filter; spectral-spatial classification; label propagation; superpixel; semi-supervised learning; rolling guidance filtering (RGF); graph; hyperspectral image; hyperspectral image; deep pipelined background statistics; constrained energy minimization; high-level synthesis; real-time processing; band selection; data fusion; data unmixing; hyperspectral image classification; hyperspectral imaging; spectral variability; target detection