Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art
The DOI matches its Crossref record; 329 of the 331 references it cites were found in a registry or an index.
Abstract
Recent advances in airborne and spaceborne hyperspectral imaging technology have provided end users with rich spectral, spatial, and temporal information. They have made a plethora of applications feasible for the analysis of large areas of the Earth?s surface. However, a significant number of factors-such as the high dimensions and size of the hyperspectral data, the lack of training samples, mixed pixels, light-scattering mechanisms in the acquisition process, and different atmospheric and geometric distortions-make such data inherently nonlinear and complex, which poses major challenges for existing methodologies to effectively process and analyze the data sets. Hence, rigorous and innovative methodologies are required for hyperspectral image (HSI) and signal processing and have become a center of attention for researchers worldwide.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Kennedy, J., & Eberhart, R. (2002) · Proceedings of ICNN'95 - International Conference on Neural Networks · doi:10.1109/icnn.1995.488968 · Cited by 58,192
A Threshold Selection Method from Gray-Level Histograms
Otsu, N. (1979) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1979.4310076 · Cited by 43,398
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Peng, H., Long, F., & Ding, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.159 · Cited by 10,544 · cited 1×
“Many extensions of these methods have been proposed in past decades, including modified Fisher’s LDA [41], regularized LDA [42], modified NWFE using spatial and spectral information [43], kernel NWFE [44], extended J–M to multiclass cases [40], J–M distance for spatially invariant features [45], minimal-redundancy/max…”
MethodGoodall, C. (1988) · Technometrics · doi:10.1080/00401706.1988.10488412 · Cited by 8,675
Jolliffe, I. T. (1986) · Springer Series in Statistics · doi:10.1007/978-1-4757-1904-8 · Cited by 8,273
Fukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759 · cited 1×
“, stacked autoencoders [62] and convolutional neural networks (CNNs) [63], are used for spectral-spatial feature extraction for HSI classification [64], [65].”
MethodCombining labeled and unlabeled data with co-training
Blum, A., & Mitchell, T. (1998) · Proceedings of the eleventh annual conference on Computational learning theory · doi:10.1145/279943.279962 · Cited by 5,495
Independent Component Analysis
Hyvärinen, A., Karhunen, J., & Oja, E. (2001) · Wiley eBooks · doi:10.1002/0471221317 · Cited by 5,007
Adapting to Unknown Smoothness via Wavelet Shrinkage
Donoho, D. L., & Johnstone, I. M. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476626 · Cited by 4,630
Research works printed but not linked: 12
- rasti, 2016, FORPDN_SURE
- rasti, 2016, Wavelab_fast
- rasti, 2016, HySURE
- schaum, 0, Long-interval chronochrome target detection, Proc Int Symp Spectral Sensing Research, 1760
- frank, 0, Unsupervised change detection for hyperspectral images, Proc 11th JPL Airborne Earth Science Workshop, 63
- plaza, 2006, Commodity cluster-based parallel processing of hyperspectral imagery, J Parallel and Distributed Comput, 66, 345, 10.1016/j.jpdc.2005.10.001 · DOI · Paper page
- 10.1002/cpe.1720 · DOI · Paper page
- 10.1109/tgrs.2008.918089 · DOI · Paper page
- 10.1109/tgrs.2004.842478 · DOI · Paper page
- 10.1109/tgrs.2010.2075937 · DOI · Paper page
- 10.1109/tgrs.2012.2224874 · DOI
- rasti, 0, A new linear model and sparse regularization, Proc IEEE Int Geoscience and Remote Sensing Symp, 457
Cited by
Deep Learning for Hyperspectral Image Classification: An Overview
Li, S., Song, W., Fang, L., Chen, Y., Ghamisi, P., & Benediktsson, J. A. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2907932 · Cited by 2,007
“Based on the recent studies published in [6], HSI classification (i.”
BackgroundSelf-citationGraph Convolutional Networks for Hyperspectral Image Classification
Hong, D., Gao, L., Yao, J., Zhang, B., Plaza, A., & Chanussot, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3015157 · Cited by 1,691
Self-citationDeep learning classifiers for hyperspectral imaging: A review
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.09.006 · Cited by 1,073
“Also, Ghamisi et al. (2017a) provided a complex taxonomy with eight criteria and twenty categories, although none of them are exclusively dedicated to DL methods.”
BackgroundMethodInfluentialSelf-citationDeep Learning for Classification of Hyperspectral Data: A Comparative Review
Audebert, N., Le Saux, B., & Lefevre, S. (2019) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2019.2912563 · Cited by 686
“Thus, it is more focused than previous reviews on deep learning [6] while presenting hyperspectral peculiarities from a deep learning point of view, different from [7].”
Ghamisi, P., Gloaguen, R., Atkinson, P. M., Benediktsson, J. A., Rasti, B., Yokoya, N., Wang, Q., Hofle, B., Bruzzone, L., Bovolo, F., et al. (2019) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2018.2890023 · Cited by 629
“(% ) G B FF (% ) [1 36 ] FF c K (% ) [1 39 ] m Lr su b”
BackgroundSelf-citationRasti, B., Hong, D., Hang, R., Ghamisi, P., Kang, X., Chanussot, J., & Benediktsson, J. A. (2020) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2020.2979764 · Cited by 537
“The endmember selection/extraction, subspace identification, and/or rank selection are all refer to this issue [127]–[129].”
BackgroundSelf-citationCascaded Recurrent Neural Networks for Hyperspectral Image Classification
Hang, R., Liu, Q., Hong, D., & Ghamisi, P. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2899129 · Cited by 534
“2899129 one is spectral dimension, which captures the spectral signature (reflective or emissive properties) of each material in different bands along the electromagnetic spectrum [1].”
BackgroundSelf-citationClassification of Hyperspectral and LiDAR Data Using Coupled CNNs
Hang, R., Li, Z., Ghamisi, P., Hong, D., Xia, G., & Liu, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2969024 · Cited by 466
Self-citationSpatial-Spectral Transformer for Hyperspectral Image Classification
He, X., Chen, Y., & Lin, Z. (2021) · Remote Sensing · doi:10.3390/rs13030498 · Cited by 462
“SVM shows its low sensitivity to high dimensionality [13]; therefore, many SVM-based classifiers have been proposed to handle the spectral classification of HSI [14].”
MethodDeep Few-Shot Learning for Hyperspectral Image Classification
Liu, B., Yu, X., Yu, A., Zhang, P., Wan, G., & Wang, R. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2872830 · Cited by 454
“HYPERSPECTRAL image (HSI) analysis can provide end users with abundant spectral and spatial information simultaneously [1].”
BackgroundHyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects
Ahmad, M., Shabbir, S., Roy, S. K., Hong, D., Wu, X., Yao, J., Khan, A. M., Mazzara, M., Distefano, S., & Chanussot, J. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3133021 · Cited by 438
Wang, J., Bretz, M., Dewan, M. A. A., & Delavar, M. A. (2022) · Science of The Total Environment · doi:10.1016/j.scitotenv.2022.153559 · Cited by 430
Stuart, M. B., McGonigle, A. J. S., & Willmott, J. R. (2019) · Sensors · doi:10.3390/s19143071 · Cited by 420
“Currently, hyperspectral imaging is generally performed by satellite or aircraft platforms [20,26,28], with recent advances in airborne and spaceborne technologies providing end users with rich spectral, spatial, and temporal information [1,2].”
BackgroundMethodDeep Learning-Based Change Detection in Remote Sensing Images: A Review
Shafique, A., Cao, G., Khan, Z., Asad, M., & Aslam, M. (2022) · Remote Sensing · doi:10.3390/rs14040871 · Cited by 419
“It is not easy (and sometimes impossible) to characterize a mixed pixel accurately if it is roughly classified as a specific type of substance [83].”
BackgroundLiu, S., Marinelli, D., Bruzzone, L., & Bovolo, F. (2019) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2019.2898520 · Cited by 389
“CD has been one of the most important remote sensing research activities (on methodologies and applications) in recent decades [11].”
BackgroundSelf-citationDeep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review
Signoroni, A., Savardi, M., Baronio, A., & Benini, S. (2019) · Journal of Imaging · doi:10.3390/jimaging5050052 · Cited by 385
“…amount of available data also involves difficulties in comparing different methods that lead to similar results, and this again happens for RS image classification studies on benchmark datasets, where near perfect results have been obtained by several, more or less complex, architectures [27,29].”
ResultNoise Reduction in Hyperspectral Imagery: Overview and Application
Rasti, B., Scheunders, P., Ghamisi, P., Licciardi, G., & Chanussot, J. (2018) · Remote Sensing · doi:10.3390/rs10030482 · Cited by 346
“Remote sensing has been substantially influenced by hyperspectral imaging in the past decades [1].”
BackgroundSelf-citationXu, Y., Du, B., Zhang, L., Cerra, D., Pato, M., Carmona, E., Prasad, S., Yokoya, N., Hansch, R., & Le Saux, B. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2911113 · Cited by 337
“…a great impact for fostering research in data fusion, but also for development of single-sensor processing, since it is the largest freely available HS dataset, with ten times more labeled data than the widely used Salinas or Pavia datasets [46], or the first available multispectral-LiDAR dataset.”
MethodSelf-citationHyperspectral Anomaly Detection: A survey
Su, H., Wu, Z., Zhang, H., & Du, Q. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2021.3105440 · Cited by 310
Deep Cross-Domain Few-Shot Learning for Hyperspectral Image Classification
Li, Z., Liu, M., Chen, Y., Xu, Y., Li, W., & Du, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3057066 · Cited by 302
“And there is a lot of spectral and spatial information in it [1].”
BackgroundZhao, C., Qin, B., Feng, S., Zhu, W., Zhang, L., & Ren, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3230378 · Cited by 294
“HYPERSPECTRAL images (HSIs), delivering advantages stemming from continuous spectrum data and rich spatial information [1], [2], span a broad range of applications [3], such as environmental monitoring [4], ecological science [5], and smart city [6].”
BackgroundGraph and Total Variation Regularized Low-Rank Representation for Hyperspectral Anomaly Detection
Cheng, T., & Wang, B. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2936609 · Cited by 266
“Hyperspectral images, therefore, possess unique advantages in many applications, such as classification and target detection [1]–[4].”
BackgroundLu, Y., Saeys, W., Kim, M., Peng, Y., & Lu, R. (2020) · Postharvest Biology and Technology · doi:10.1016/j.postharvbio.2020.111318 · Cited by 263
Yu, C., Han, R., Song, M., Liu, C., & Chang, C.-I. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2983224 · Cited by 258
Visual Attention-Driven Hyperspectral Image Classification
Haut, J. M., Paoletti, M. E., Plaza, J., Plaza, A., & Li, J. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2918080 · Cited by 251
“HYPERSPECTRAL image (HSI) classification is a very active research field in remote sensing and Earth observation [1], [2].”
BackgroundSelf-citationFascista, A. (2022) · Sensors · doi:10.3390/s22051824 · Cited by 241
Multi-Scale Dense Networks for Hyperspectral Remote Sensing Image Classification
Zhang, C., Li, G., & Du, S. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2925615 · Cited by 202
“Moreover, HSIs lack labeled sample data [4], thereby”
BackgroundRecent advances in plant disease detection: challenges and opportunities
Shafay, M., Hassan, T., Owais, M., Hussain, I., Khawaja, S. G., Seneviratne, L. D., & Werghi, N. (2025) · Plant Methods · doi:10.1186/s13007-025-01450-0 · Cited by 202
Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification
Xi, B., Li, J., Li, Y., Song, R., Hong, D., & Chanussot, J. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3192712 · Cited by 199
“(e-mail: jocelyn@hi.is). etc [1].”
Self-citationZhou, W., Kamata, S., Wang, H., Wong, M. S., & Hou, H. C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128751 · Cited by 192
A Frequency Decoupling Network for Semantic Segmentation of Remote Sensing Images
Li, X., Xu, F., Yu, A., Lyu, X., Gao, H., & Zhou, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3531879 · Cited by 190
“This process is vital for many computer vision tasks and is used in various applications, including natural and medical image parsing [7], [8], [9], [10], autonomous driving [11], [12], [13], [14], road extraction [15], [16], [17], [18], and land-use mapping [19], [20], [21], [22], [23].”
HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model
Wang, D., Hu, M., Jin, Y., Miao, Y., Yang, J., Xu, Y., Qin, X., Ma, J., Sun, L., Li, C., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3557581 · Cited by 189
Self-citationMini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, applications, and prospects
Xiang, T.-Z., Xia, G.-S., & Zhang, L. (2019) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2019.2918840 · Cited by 189
He, X., Chen, Y., & Ghamisi, P. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2951445 · Cited by 184
“In general, there are two types of HSI classification meth-ods: spectral classifiers and spectral–spatial classifiers [5].”
BackgroundSelf-citationFeedback Attention-Based Dense CNN for Hyperspectral Image Classification
Yu, C., Han, R., Song, M., Liu, C., & Chang, C. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3058549 · Cited by 180
“H YPERSPECTRAL technology captures beneficial and accurate information of the landform with hundreds of subdivided spectral bands simultaneously, which plays a substantial role in many fields such as geological survey, crop monitoring, and national defense [1]–[3].”
BackgroundGuan, R., Li, Z., Tu, W., Wang, J., Liu, Y., Li, X., Tang, C., & Feng, R. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3370633 · Cited by 180
Global–Local Transformer Network for HSI and LiDAR Data Joint Classification
Ding, K., Lu, T., Fu, W., Li, S., & Ma, F. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3216319 · Cited by 177
“Thus, the application of HSI for land cover classification has an important indicative role in many fields such as geological exploration, urban development planning, forest management, and precision agriculture [5], [6], [7], [8].”
BackgroundHyperspectral Unmixing Using Transformer Network
Ghosh, P., Roy, S. K., Koirala, B., Rasti, B., & Scheunders, P. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3196057 · Cited by 175
“The acquired spectral reflectance is then a mixture of the pure spectra (endmembers) of the materials within the pixel [7], [8].”
BackgroundSelf-citationCai, Y., Zhang, Z., Cai, Z., Liu, X., Jiang, X., & Yan, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3018135 · Cited by 173
“Particularly, deep learning models [1], [8]–[10], such as convolutional neural networks (CNNs) [11], [12], have crucially narrowed the gap between human and machines.”
BackgroundA Single Model CNN for Hyperspectral Image Denoising
Maffei, A., Haut, J. M., Paoletti, M. E., Plaza, J., Bruzzone, L., & Plaza, A. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2952062 · Cited by 171
“However the acquisition process introduces a significant amount of noise in the data, which leads to intraclass variability and interclass similarity [8].”
BackgroundSelf-citationMoharram, M. A., & Sundaram, D. M. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.03.025 · Cited by 168
Hyperspectral Pansharpening Using Deep Prior and Dual Attention Residual Network
Zheng, Y., Li, J., Li, Y., Guo, J., Wu, X., & Chanussot, J. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2986313 · Cited by 165
“This procedure is called as HS pansharpening, which is an extension to HSIs of the conventional pansharpening referring to the fusion of a multispectral image (MSI) and a PAN image [6].”
MethodSelf-citationXu, Y., Du, B., & Zhang, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3118977 · Cited by 162
Ding, Y., Zhao, X., Zhang, Z., Cai, W., Yang, N., & Zhan, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3100578 · Cited by 159
Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement
Tsagkatakis, G., Aidini, A., Fotiadou, K., Giannopoulos, M., Pentari, A., & Tsakalides, P. (2019) · Sensors · doi:10.3390/s19183929 · Cited by 158
“806 Observation denoising is thus a crucial process which has been extensively studied by the remote 807 sensing community [119], while in recent years, several DNN architectures have been proposed for 808 observation denoising.”
BackgroundUnDIP: Hyperspectral Unmixing Using Deep Image Prior
Rasti, B., Koirala, B., Scheunders, P., & Ghamisi, P. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3067802 · Cited by 155
“However, due to the limited spatial resolution and scattering of the light, a pixel spectrum is generally a complex mixture of the pure spectra of its constituent materials, i.e., the endmember spectra [1], [2].”
BackgroundSelf-citationDeep Metric Learning-Based Feature Embedding for Hyperspectral Image Classification
Deng, B., Jia, S., & Shi, D. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2946318 · Cited by 148
“HSI classification, therefore, has been one of the most popular fields in research of the hyperspectral community [2].”
BackgroundTensor Decompositions for Hyperspectral Data Processing in Remote Sensing: A comprehensive review
Wang, M., Hong, D., Han, Z., Li, J., Yao, J. T., Gao, L., Zhang, B., & Chanussot, J. (2023) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3227063 · Cited by 146
“, the identification of military targets) [4], [5], [6].”
BackgroundSelf-citationHyperspectral Image Classification: Potentials, Challenges, and Future Directions
Datta, D., Mallick, P. K., Bhoi, A. K., Ijaz, M. F., Shafi, J., & Choi, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/3854635 · Cited by 146
“-e possible solutions to the above limitations that also represent the possible operations that are performed to analyze and comprehend the HSIs can be (1) technological advancement to make versatile and robust hardware for the spectrometers to capture the scenes more accurately, (2) spectral unmixing and resolution e…”
BackgroundTri-CNN: A Three Branch Model for Hyperspectral Image Classification
Alkhatib, M. Q., Al-Saad, M., Aburaed, N., Mansoori, S. A., Zabalza, J., Marshall, S., & Al-Ahmad, H. (2023) · Remote Sensing · doi:10.3390/rs15020316 · Cited by 142
Hyperspectral Image Classification Based on Deep Attention Graph Convolutional Network
Bai, J., Ding, B., Xiao, Z. Q., Jiao, L., Chen, H., & Regan, A. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3066485 · Cited by 142
“H YPERSPECTRAL images (HSIs) have drawn much attention in recent decades due to their rich data and high spectral resolution [1], [2].”
BackgroundShi, H., Xian, G., Auch, R. F., Gallo, K. P., & Zhou, Q. (2021) · Land · doi:10.3390/land10080867 · Cited by 140
“While much of the methodological variation described here will persist, future methods will evolve and adapt to greater data volumes and processing capabilities [239].”
BackgroundS3Net: Spectral–Spatial Siamese Network for Few-Shot Hyperspectral Image Classification
Xue, Z., Zhou, Y., & Du, P. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3181501 · Cited by 138
Li, M., Liu, Y., Xue, G., Huang, Y., & Yang, G. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3218284 · Cited by 135
“Due to the inherent nonlinearity and spectral-spatial characteristics of HSI [10], spatial information was considered for some spectral-spatial methods for discriminative HSIC [11], [12], [13], [14].”
MethodMiSiCNet: Minimum Simplex Convolutional Network for Deep Hyperspectral Unmixing
Rasti, B., Koirala, B., Scheunders, P., & Chanussot, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3146904 · Cited by 133
“A spectral pixel is generally a mixture of the pure spectra of the materials within the pixel, called endmembers [1], [2].”
BackgroundSelf-citationRoy, S. K., Sukul, A., Jamali, A., Haut, J. M., & Ghamisi, P. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3374324 · Cited by 132
“HS data possess unique high dimensionality, a significant relationship between neighboring bands, and an extensively nonlinear structure of data, enabling them to accurately represent the precise spectra emitted by different substances in an area of interest [1].”
BackgroundSelf-citationConventional to Deep Ensemble Methods for Hyperspectral Image Classification: A Comprehensive Survey
Ullah, F., Ullah, I., Khan, R. U., Khan, S., Khan, K., & Pau, G. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3353551 · Cited by 131
“These techniques are described in numerous in-depth reviews that were published over the past decade [35], [59], [60], [61], [62], [63], [64], [65], [66], [67].”
BackgroundDeep&Dense Convolutional Neural Network for Hyperspectral Image Classification
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2018) · Remote Sensing · doi:10.3390/rs10091454 · Cited by 129
“These kind of methods are known as spectral-based approaches [41], where the HSI X is considered to be a collection of n 1 × n 2 pixel vectors of n bands without a specific spatial arrangement, so that the classification process only takes into account the information comprised by individual pixels x…”
BackgroundSelf-citationAdvances in spaceborne hyperspectral remote sensing in China
Zhong, Y., Wang, X., Wang, S., & Zhang, L. (2021) · Geo-spatial Information Science · doi:10.1080/10095020.2020.1860653 · Cited by 124
“According to the use of the spatial information, the classification methods can be divided into two approaches: (1) spectral classification methods; and (2) spectral-spatial classification methods (Ghamisi et al. 2017b).”
BackgroundMethodDeep Learning in Hyperspectral Unmixing: A Review
Bhatt, J. S., & Joshi, M. V. (2020) · IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss39084.2020.9324546 · Cited by 121
“Over the years, this technology has shown tremendous growth and expansion in the areas of spectral unmixing, classification, denoising, superresolution, land cover, object detection, multitemporal data analysis, and many more [2].”
BackgroundHow to Learn More? Exploring Kolmogorov–Arnold Networks for Hyperspectral Image Classification
Jamali, A., Roy, S. K., Hong, D., Lu, B., & Ghamisi, P. (2024) · Remote Sensing · doi:10.3390/rs16214015 · Cited by 121
Self-citationUnsupervised Recurrent Hyperspectral Imagery Super-Resolution Using Pixel-Aware Refinement
Wei, W., Nie, J., Zhang, L., & Zhang, Y. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3039534 · Cited by 120
“Without loss of generality, we vary α in the range of [1, 3] with an interval of 0.5.”
MethodInfluentialBinary Change Guided Hyperspectral Multiclass Change Detection
Hu, M., Wu, C., Du, B., & Zhang, L. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3233187 · Cited by 119
“ent times [21], [22], and has been widely applied in”
BackgroundLand Use and Land Cover Mapping in the Era of Big Data
Zhang, C., & Li, X. (2022) · Land · doi:10.3390/land11101692 · Cited by 119
“Many satellite sensors produce imagery data with very-high spectral resolutions [32]. produce imagery data with very-high spectral resolutions [32 For example, the Hyperion sensor consists of 220 spectral bands, the AVIRIS system provides 224 spectral bands, the WIS instrument has 812 bands, and…”
BackgroundTarget Detection in Hyperspectral Remote Sensing Image: Current Status and Challenges
Chen, B., Liu, L., Zou, Z., & Shi, Z. (2023) · Remote Sensing · doi:10.3390/rs15133223 · Cited by 119
“Earlier reviews have combed through traditional target detection methods [14–18], but they have not focused on the deep learning-based methods that have emerged in recent years and are becoming mainstream.”
Song, R., Ni, W., Cheng, W., & Wang, X. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3179134 · Cited by 116
Confident Learning-Based Domain Adaptation for Hyperspectral Image Classification
Fang, Z., Yang, Y., Li, Z., Li, W., Chen, Y., Ma, L., & Du, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3166817 · Cited by 115
“The HSIs contain hundreds of spectral bands [5], [6] and, therefore, provide abundant information for accurate classification [7], [8].”
BackgroundXue, Z., Yu, X., Liu, B., Tan, X., & Wei, X. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3065987 · Cited by 114
Adversarial Autoencoder Network for Hyperspectral Unmixing
Jin, Q., Ma, Y., Fan, F., Huang, J., Mei, X., & Ma, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3114203 · Cited by 101
“The information of HSIs can be simplified by the linear mixing model (LMM), which assumes that the physical region corresponding to a pixel contains several pure materials, and the different endmembers do not interfere with each other [13]–[15].”
BackgroundJiang, K., Xie, W., Li, Y., Lei, J., He, G., & Du, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2975295 · Cited by 111
“Abundant spectral, spatial, and temporal information can be obtained via a hyperspectral imaging sensor simultaneously [1], [2].”
BackgroundPredicting air quality via multimodal AI and satellite imagery
Rowley, A., & Karakuş, O. (2023) · Remote Sensing of Environment · doi:10.1016/j.rse.2023.113609 · Cited by 109
“The power of CNNs to handle multi-spectral data and convolve this to identify features [8] is evident in the increase in the body of the academic literature from 3 papers in 2014 to 73 in 2016 [9].”
BackgroundNoise-Robust Hyperspectral Image Classification via Multi-Scale Total Variation
Duan, P., Kang, X., Li, S., & Ghamisi, P. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2915272 · Cited by 108
Self-citationMasked Auto-Encoding Spectral–Spatial Transformer for Hyperspectral Image Classification
Ibañez, D., Fernández-Beltrán, R., Pla, F., & Yokoya, N. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3217892 · Cited by 108
“In the context of HS remote sensing imaging, one of the main intricacies is related to the noise present in the acquired data [32].”
BackgroundSelf-citationHuang, L., Chen, Y., & He, X. Z. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3264235 · Cited by 107
“vibrant topics in the field of remote sensing [2].”
BackgroundSu, H., Wu, Z., Zhu, A., & Du, Q. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.09.008 · Cited by 106
“…visible light, infrared and short wave infrared (even medium and long wave infrared), providing the possibility for diagnosing ground objects (Ghamisi et al., 2017; Goetz et al., 1985, Zheng et al., 2020, Li et al., 2020; Gomez et al., 2018; Pelta and Ben-Dor, 2019; Wietecha et al., 2019).”
BackgroundJaiswal, G., Rani, R., Mangotra, H., & Sharma, A. (2023) · Computer Science Review · doi:10.1016/j.cosrev.2023.100584 · Cited by 106
Hyperspectral and LiDAR Fusion Using Deep Three-Stream Convolutional Neural Networks
Li, H., Ghamisi, P., Soergel, U., & Zhu, X. X. (2018) · Remote Sensing · doi:10.3390/rs10101649 · Cited by 104
“, multispectral and hyperspectral images) [1,2], or elevation and shape information obtained by light detection and ranging (LiDAR)”
BackgroundSelf-citationDemarchi, L., Kania, A., Ciężkowski, W., Piórkowski, H., Oświecimska-Piasko, Z., & Chormański, J. (2020) · Remote Sensing · doi:10.3390/rs12111842 · Cited by 104
“Characterized by both high spatial and spectral resolution, they typically record the reflected object’s light across hundreds of narrow spectral bands, within the visible, near infrared (NIR), mid infrared (MIR), and short-wave infrared (SWIR) parts of the electromagnetic spectrum [33,34], resulting in a 3-dimensiona…”
BackgroundMultiscale and Cross-Level Attention Learning for Hyperspectral Image Classification
Xu, F., Zhang, G., Song, C., Wang, H., & Mei, S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3235819 · Cited by 104
“Compared with ordinary RGB images, hyperspectral images (HSIs) own higher spectral resolution, more bands, and thus each pixel has an independent spectral curve, which helps HSI to detect the physical features of materials [1], [2], [3], [4].”
BackgroundHyperspectral Anomaly Detection Using Reconstruction Fusion of Quaternion Frequency Domain Analysis
Tu, B., Yang, X., He, W. P., Li, J., & Plaza, A. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3227167 · Cited by 101
“D data cube, combining imaging technology with spectral detection technology [1], [2], [3].”
MethodSelf-citationCurrent advances in imaging spectroscopy and its state-of-the-art applications
Zahra, A., Qureshi, R., Sajjad, M., Sadak, F., Nawaz, M., Khan, H. A., & Uzair, M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122172 · Cited by 99
Machine learning assisted Raman spectroscopy: A viable approach for the detection of microplastics
Sunil, M., Pallikkavaliyaveetil, N., Mithun, N., Gopinath, A., Chidangil, S., Kumar, K. S., & Lukose, J. (2024) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2024.105150 · Cited by 99
A Spectral and Spatial Attention Network for Change Detection in Hyperspectral Images
Gong, M., Jiang, F., Qin, A. K., Liu, T., Zhan, T., Lu, D., Zheng, H., & Zhang, M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3139077 · Cited by 97
“Unlike multispectral and synthetic aperture radar images, HSIs typically consist of hundreds of spectral bands, including the whole visible, the near-infrared, the short infrared, and the thermal infrared spectra, which can capture richer and finer details about ground objects [9].”
BackgroundHu, M., Wu, C., & Zhang, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3218795 · Cited by 97
“Hyperspectral image (HSI) provides unique spectral curve for every kind of ground object, showing great potential for object discrimination and classification [6], [7].”
BackgroundAdvances in Earth observation and machine learning for quantifying blue carbon
Pham, T. D., Ha, N. T., Saintilan, N., Skidmore, A. K., Phan, D. C., Le, N. N., Luu, V. H., Takeuchi, W., & Friess, D. A. (2023) · Earth-Science Reviews · doi:10.1016/j.earscirev.2023.104501 · Cited by 96
“…of fast computing techniques for satellite image analysis, particularly in the context of real-time monitoring is the cost for purchasing a HPC and its Data fusion, Machine Learning on GEE high energy consumption required for running and maintaining HPC architectures (Ghamisi et al., 2017).”
MethodEl-Omairi, M. A., & Garouani, A. E. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e20168 · Cited by 95
“This technology enables the detection of unique spectral signatures of materials, facilitating accurate identification and in-depth chemical analysis [39].”
BackgroundRetractedAttention-Based Second-Order Pooling Network for Hyperspectral Image Classification
Xue, Z., Zhang, M., Liu, Y., & Du, P. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3048128 · Cited by 93
Yue, J., Fang, L., Ghamisi, P., Xie, W., Li, J., Chanussot, J., & Plaza, A. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3161377 · Cited by 93
“ability to extract abstract features without requiring the manual design of features [3], [4], [5], [6], [7].”
BackgroundSelf-citationChen, N., Fang, L., Xia, Y., Xia, S., Liu, H., & Yue, J. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3361652 · Cited by 93
“However, due to the potential nonlinear structure in hyper-spectral data, researchers have proposed several nonlinear transformation methods aimed at better capturing nonlinear features within the data [18].”
BackgroundChen, J., Zhao, M., Wang, X., Richard, C., & Rahardja, S. (2023) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3208987 · Cited by 90
Fang, J., Yang, J., Khader, A., & Xiao, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3361553 · Cited by 90
“narrow bands in the visible to infrared spectrum [1], [2].”
BackgroundFeng, Y., Song, L., Wang, L., & Wang, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3311535 · Cited by 88
Remote sensing image classification using subspace sensor fusion
Rasti, B., & Ghamisi, P. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.07.002 · Cited by 87
Self-citationHyperspectral Image Classification Based on Deep Deconvolution Network With Skip Architecture
Ma, X., Fu, A., Wang, J., Wang, H., & Yin, B. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2837142 · Cited by 86
“2837142 in the spectral domain [2].”
Research Progress on the Early Monitoring of Pine Wilt Disease Using Hyperspectral Techniques
Wu, W., Zhang, Z., Zheng, L., Han, C., Wang, X., Xu, J., & Wang, X. (2020) · Sensors · doi:10.3390/s20133729 · Cited by 86
Transformer-Based Autoencoder Framework for Nonlinear Hyperspectral Anomaly Detection
Wu, Z., & Wang, B. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3361469 · Cited by 86
“Owing to the high spectral resolution of HSIs, each pixel can be viewed as a consecutive spectral curve [1], and each material has its own unique spectral curve, which develops many practical applications in HSIs, such as classification [2], [3] and target detection [4], [5].”
BackgroundFeng, S., Zhang, H., Xi, B., Zhao, C., Li, Y., & Chanussot, J. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3476116 · Cited by 86
“D data cube with abundant spatial and spectral information, containing unique characteristics of various land covers [1], [2], [3].”
BackgroundA Multi-Scale Wavelet 3D-CNN for Hyperspectral Image Super-Resolution
Yang, J., Zhao, Y., Chan, J. C.-W., & Xiao, L. (2019) · Remote Sensing · doi:10.3390/rs11131557 · Cited by 85
“Single-frame HSI super-resolution (SR) tries to reconstruct HR HSI using only one LR HSI [25].”
MethodHyperspectral Image Denoising via Subspace-Based Nonlocal Low-Rank and Sparse Factorization
Cao, C., Jie, Y., Zhou, C., Hu, K., Xiao, F., & Gao, X. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2896031 · Cited by 84
“The bandwise normalization method is adopted to transfer pixels in the each band of HSI into [0, 1] before denoising.”
BackgroundMethodModified Tensor Locality Preserving Projection for Dimensionality Reduction of Hyperspectral Images
Deng, Y., Li, H.-C., Pan, L., Shao, L., Du, Q., & Emery, W. J. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2786223 · Cited by 84
Metadata
- Authors
- Ghamisi, P., Yokoya, N., Li, J., Liao, W., Liu, S., Plaza, J., Rasti, B., & Plaza, A.
- Affiliations
- Technical University of Munich (DE)
- The University of Tokyo (JP)
- Sun Yat-sen University (CN)
- Ghent University (BE)
- Tongji University (CN)
- Universidad de Extremadura (ES)
- University of Iceland (IS)
- ORCID
- Venue
- IEEE Geoscience and Remote Sensing Magazine
- Published
- 2017-12
- Volume
- 5
- Issue
- 4
- Pages
- 37-78
- ISSN
- 2168-6831 (ISSN-L)
- 2473-2397
- OpenAlex
- W2782517596
- Cited by
- 909
- References
- 331
- Citations by year
- 2026: 100 · 2025: 130 · 2024: 129 · 2023: 143 · 2022: 112 · 2021: 117 · 2020: 73 · 2019: 76 · 2018: 29
- FWCI
- 40.36
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Geoscience and Remote Sensing Magazine (publishedVersion)
- elib (German Aerospace Center) (acceptedVersion)
- Ghent University Academic Bibliography (Ghent University) (submittedVersion)
- Funders
- Purdue University
- University of Houston
- Università degli Studi di Pavia
- Japan Society for the Promotion of Science (15K20955)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Satellite Image Processing and Photogrammetry
- Keywords
- hyperspectral image analysis, airborne hyperspectral imaging, mixed pixels, light scattering, atmospheric distortion, geometric distortion, high-dimensional data, training sample scarcity, nonlinear data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.