Hyperspectral Remote Sensing Data Analysis and Future Challenges
The DOI matches its Crossref record; 183 of the 188 references it cites were found in a registry or an index.
Abstract
Hyperspectral remote sensing technology has advanced significantly in the past two decades. Current sensors onboard airborne and spaceborne platforms cover large areas of the Earth surface with unprecedented spectral, spatial, and temporal resolutions. These characteristics enable a myriad of applications requiring fine identification of materials or estimation of physical parameters. Very often, these applications rely on sophisticated and complex data analysis methods. The sources of difficulties are, namely, the high dimensionality and size of the hyperspectral data, the spectral mixing (linear and nonlinear), and the degradation mechanisms associated to the measurement process such as noise and atmospheric effects. This paper presents a tutorial/overview cross section of some relevant hyperspectral data analysis methods and algorithms, organized in six main topics: data fusion, unmixing, classification, target detection, physical parameter retrieval, and fast computing. In all topics, we describe the state-of-the-art, provide illustrative examples, and point to future challenges and research directions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Schölkopf, B., & Smola, A. J. (2001) · The MIT Press eBooks · doi:10.7551/mitpress/4175.001.0001 · Cited by 11,703
Stable signal recovery from incomplete and inaccurate measurements
Candès, E. J., Romberg, J. K., & Tao, T. (2006) · Communications on Pure and Applied Mathematics · doi:10.1002/cpa.20124 · Cited by 7,036 · cited 1×
“Linear SR is an area of very active research with strong links to compressed sensing [66].”
BackgroundClassification of hyperspectral remote sensing images with support vector machines
Melgani, F., & Bruzzone, L. (2004) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2004.831865 · Cited by 4,411 · cited 1×
“In this context, kernel methods such as the support vector machine (SVM) have been widely used in order to deal effectively with the Hughes phenomenon [85], [86].”
MethodPati, Y. C., Rezaiifar, R., & Krishnaprasad, P. S. (2002) · Proceedings of 27th Asilomar Conference on Signals, Systems and Computers · doi:10.1109/acssc.1993.342465 · Cited by 4,323 · cited 5×
“SPECTRAL UNMIXING IS THE INVERSE PROBLEM OF DETERMINING THE SPECTRALLY PURE COMPONENTS (ENDMEMBERS) PRESENT IN MIXED PIXELS, AS WELL AS THEIR ABUNDANCE FRACTIONS.”
BackgroundMethodInfluentialLearning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Williams, C. K. I. (2003) · Journal of the American Statistical Association · doi:10.1198/jasa.2003.s269 · Cited by 4,281
Morphological Image Analysis: Principles and Applications
(2000) · Sensor Review · doi:10.1108/sr.2000.08720cae.001 · Cited by 3,537
Inverse Methods for Atmospheric Sounding: Theory and Practice
Rodgers, C. D. (2000) · Series on Atmospheric, Oceanic and Planetary Physics · doi:10.1142/3171 · Cited by 3,057 · cited 1×
“The analysis can be done at local or global scales by looking at bio-geo-chemical cycles, atmospheric state and evolution, and vegetation dynamics [155], [156].”
BackgroundHyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches
Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J. (2012) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2012.2194696 · Cited by 2,836 · cited 19×
“6, are the linear model, the bilinear model, and the Hapke model [3], [40].”
BackgroundMethodInfluentialSelf-citationSparse Approximate Solutions to Linear Systems
Natarajan, B. K. (1995) · SIAM Journal on Computing · doi:10.1137/s0097539792240406 · Cited by 2,783 · cited 2×
“The above problem of minimizing the 0, -norm is NP-hard, but its approximate solution can be obtained by greedy algorithms [68].”
Background
Research works printed but not linked: 6
- verrelst, 2011, Retrieval of canopy parameters using Gaussian processes techniques, IEEE Trans Geosci Remote Sensing, 49
- keef, 2008, Optical Sciences Hyper-spectral Sensor Calibration Extrapolated from Multi-spectral Measurements
- schölkopf, 2002, Learning with kernels
- staenz, 2012, Technical committees corner: International spaceborne imaging spectroscopy (ISIS) technical committee, IEEE Geosci Remote Sensing Newslett, 38
- lópez, 0, The promise of reconfigurable computing for hyperspectral imaging on-board systems: Review and trends, Proc IEEE
- 2011, Special Issue on High Performance Computing for Hyperspectral Imaging, Int J High Perform Comput, 4, 528
Cited by
Items 401–500 of 1,002
Cascaded dual-scale crossover network for hyperspectral image classification
Cao, F., & Guo, W. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105122 · Cited by 46
Flexible Gabor-Based Superpixel-Level Unsupervised LDA for Hyperspectral Image Classification
Jia, S., Zhao, Q., Zhuang, J., Tang, D., Long, Y., Xu, M., Zhou, J. W., & Li, Q. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3048994 · Cited by 46
“The relatively small size of labeling samples compared to the high dimension of the data would arise the curse of dimensionality (the so-called “Hughes phenomenon”) [3]–[5].”
BackgroundLightweight Spectral–Spatial Attention Network for Hyperspectral Image Classification
Cui, Y., Xia, J., Wang, Z., Gao, S., & Wang, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3080394 · Cited by 46
“HSI processing has increasingly become a research hotspot and has been widely used in environmental management, greening detection [3], monitoring [4], crop analysis [5], etc.”
BackgroundJAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images
Chen, W., Ouyang, S., Yang, J., Li, X., Zhou, G., & Wang, L. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3144339 · Cited by 48
Soil Nutrient Estimation and Mapping in Farmland Based on UAV Imaging Spectrometry
Yang, X., Bao, N., Li, W., Liu, S., Fu, Y., & Mao, Y. (2021) · Sensors · doi:10.3390/s21113919 · Cited by 45
“Compared with aerial systems, the UAVs fly at lower altitudes and are not subject to air traffic control [15], and they have more advantages in practical applications because of their lower cost and higher operational flexibility, which is fundamental for precise agriculture monitoring [16].”
BackgroundAsghar, M. Z., Albogamy, F. R., Al-Rakhami, M. S., Asghar, J., Rahmat, M. K., Alam, M. M., Lajis, A., & Nasir, H. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.855254 · Cited by 45
“A point-wise convolution is expressed by Equation (9).”
BackgroundInfluentialRetractedHyperspectral Change Detection Using Semi-Supervised Graph Neural Network and Convex Deep Learning
Lin, T.-H., & Lin, C.-H. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3286440 · Cited by 45
“Due to the ability of HSIs that can identify the material variations through spectral signatures [4], SAM is introduced in this article to better detect the changes by fully utilizing the spectral information.”
BackgroundMethodMahmoodi, J., Abbasi‐Moghadam, D., Sharifi, A., Nezamabadi–pour, H., Esmaeili, M. R., & Vafaeinejad, A. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3439592 · Cited by 50
“spatial distribution and composition of materials within a scene [1].”
BackgroundSparse Graph Regularization for Hyperspectral Remote Sensing Image Classification
Xue, Z., Du, P., Li, J., & Su, H. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2641985 · Cited by 46
HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images
Khan, H. A., Mihoubi, S., Mathon, B., Thomas, J., & Hardeberg, J. Y. (2018) · Sensors · doi:10.3390/s18072045 · Cited by 49
“, remote sensing [14], medical diagnosis [15], cultural heritage [16,17], face recognition [18], food quality control [19], color management and printing [20,21].”
BackgroundSpectral-spatial classification of hyperspectral imagery based on recurrent neural networks
Liu, B., Yu, X., Yu, A., Zhang, P., & Wan, G. (2018) · Remote Sensing Letters · doi:10.1080/2150704x.2018.1511933 · Cited by 45
“It is now commonly accepted that using the spatial and the spectral information simultaneously provides signi fi cant advantages in terms of improving the performance of classi fi cation techniques (Bioucas-Dias et al. 2013).”
Zero-Shot Hyperspectral Image Denoising With Separable Image Prior
Imamura, R., Itasaka, T., & Okuda, M. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00178 · Cited by 50
“Hyperspectral image (HSI) restoration, whereby a degraded image is processed to produce a clear image, is an essential technique in HSI applications [3, 13, 14, 16] given that hyperspectral images are prone to being adversely affected by noise, which prevents the precise extraction of useful information in application…”
BackgroundLiu, B., Guo, W., Chen, X., Gao, K., Zuo, X., Wang, R., & Yu, A. (2020) · IEEE Access · doi:10.1109/access.2020.3004968 · Cited by 47
“Recent researches show that the introduction of spatial information is helpful to improve the classification accuracy of HSI [17], [18].”
BackgroundCushnahan, T. A., Grafton, M. C. E., Pearson, D. M., & Ramilan, T. (2024) · Remote Sensing · doi:10.3390/rs16173142 · Cited by 44
MMR-HAD: Multiscale Mamba Reconstruction Network for Hyperspectral Anomaly Detection
Fu, X., Zhang, T., Cheng, J., & Jia, S. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3541353 · Cited by 55
DBMLLA: Double-Branch Mamba-Like Linear Attention Network for Hyperspectral Image Classification
Liang, L., Xie, P., Zhang, Y., Li, J., Zhang, Z., Li, J., & Plaza, A. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3605798 · Cited by 51
“H YPERSPECTRAL imaging (HSI) captures information about the light reflected by objects across multiple spectral bands [1].”
Self-citationPerformance measures for classification systems with rejection
Condessa, F., Bioucas‐Dias, J. M., & Kovačević, J. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.10.011 · Cited by 44
Self-citationLocal Spectral Component Decomposition for Multi-Channel Image Denoising
Rizkinia, M., Baba, T., Shirai, K., & Okuda, M. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2561320 · Cited by 44
“Whereas various applications, such as classification, target detection, spectral unmixing, and change detection need detailed and accurate spectral information [2], the noise due to, for example, thermal electronics and dark current, unavoidably contaminates the image acquisition process [3]–[5], which disrupts detail…”
BackgroundLiu, X., Sun, Q., Meng, Y., Fu, M., & Bourennane, S. (2018) · Remote Sensing · doi:10.3390/rs10091425 · Cited by 44
“However, most of the traditional methods extract handcrafted features from HSIs in a shallow manner [14].”
BackgroundSpectral and Spatial Global Context Attention for Hyperspectral Image Classification
Li, Z., Cui, X., Wang, L., Zhang, H., Zhu, X., & Zhang, Y. (2021) · Remote Sensing · doi:10.3390/rs13040771 · Cited by 45
“However, the spectral-based methods infer pixel labels by only using spectral signatures, which in the actual imaging process are easily disturbed by the atmospheric effects, instrument noises, and incident illumination [22,23].”
BackgroundHy-Demosaicing: Hyperspectral Blind Reconstruction From Spectral Subsampling
Zhuang, L., Ng, M. K., Fu, X., & Bioucas‐Dias, J. M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3102136 · Cited by 45
Self-citationMultiscale Adaptive Fusion Network for Hyperspectral Image Denoising
Pan, H., Gao, F., Dong, J., & Du, Q. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3257051 · Cited by 43
“HSIs have been extensively applied in land cover classification [1],”
Hyperspectral Image Classification Using a Superpixel–Pixel–Subpixel Multilevel Network
Tu, B., Ren, Q., Li, Q., He, W., & He, W. P. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3271713 · Cited by 43
“HSIs are rich in spectral information, and therefore, effectively using this information, mining potential data structures, and distinguishing features have become the main challenges of HSI classification tasks [10].”
BackgroundTCCU-Net: Transformer and CNN Collaborative Unmixing Network for Hyperspectral Image
Chen, J., Yang, C., Zhang, L., Yang, L., Bian, L., Luo, Z., & Wang, J. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3352073 · Cited by 43
“However, due to the spatial resolution limitations of HSI instruments [5], pixels in HSIs often consist of mixed spectra [6], [7], representing a combination of various materials, known as mixed pixels.”
BackgroundQuantum Information-Empowered Graph Neural Network for Hyperspectral Change Detection
Lin, C.-H., Lin, T.-H., & Chanussot, J. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3490703 · Cited by 43
“The evolution of hyperspectral imaging (HSI) technology has revolutionized various remote sensing applications [4]–[8].”
BackgroundSelf-citationWu, Z., Wang, Q., Wu, Z., & Shen, Y. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.25.1.013037 · Cited by 43
“EQ-TARGET;temp:intralink-;e002;63;719D 1⁄4 Lþ Sþ N; (2)”
BackgroundMethodInfluentialLazcano, R., Madroñal, D., Salvador, R., Desnos, K., Pelcat, M., Guerra, R., Fabelo, H. A., Ortega, S., López, S., Callicó, G. M., et al. (2017) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2017.05.001 · Cited by 43
“As mentioned in Section 1 , Principal Component Analysis is the ost well-known and widely used technique for data shrinking in I applications, proving to be a powerful tool for hyperspectral imge processing [16] .”
MethodHyperspectral Image Classification With Pre-Activation Residual Attention Network
Gao, H., Yang, Y., Yao, D., & Li, C. (2019) · IEEE Access · doi:10.1109/access.2019.2957163 · Cited by 43
“Therefore, hyperspectral remote sensing technology has been widely used in many fields, including agriculture [2], environmental earth sciences [3], military surveillance [4].”
MethodZhang, M., Gong, M., He, H., & Zhu, S. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3020540 · Cited by 47
“Labels play a very important role in these methods because it can guide the process of FE so that the features extracted from the data with the same label are similar while the differences between features extracted from data with different classes of labels are great [18].”
BackgroundLightweight Tensor Attention-Driven ConvLSTM Neural Network for Hyperspectral Image Classification
Hu, W.-S., Li, H.-C., Deng, Y., Sun, X., Du, Q., & Plaza, A. (2021) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2021.3063805 · Cited by 43
“HYPERSPECTRAL images (HSIs) contain very detailed spatial and spectral information, which can be exploited to analyze the information of the Earth’s surface [1].”
BackgroundSelf-citationLin, Q., Eladawy, A., Sha, J., Li, X., Wang, J., Kurbanov, E. A., & Thomas, A. (2021) · Remote Sensing · doi:10.3390/rs13152865 · Cited by 43
“In the 1980s, the emergence of hyperspectral remote sensing injected new vitality into the field of remote sensing [40].”
BackgroundDeep Generative Model for Spatial–Spectral Unmixing With Multiple Endmember Priors
Shi, S., Zhang, L., Altmann, Y., & Chen, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3168712 · Cited by 53
Liu, J., Wang, T., Skidmore, A. K., Sun, Y., Jia, P., & Zhang, K. F. (2023) · Remote Sensing · doi:10.3390/rs15194797 · Cited by 46
Fast Superpixel Based Subspace Low Rank Learning Method for Hyperspectral Denoising
Sun, L., Jeon, B., Soomro, B. N., Zheng, Y., Wu, Z., & Xiao, L. (2018) · IEEE Access · doi:10.1109/access.2018.2808474 · Cited by 42
“INTRODUCTION As a spectrally sequential data with hundreds of narrow bands ranging from 400 to 2500 nm, hyperspectral imagery (HSI) has a great advantage in discriminating different land covers according to their intrinsic spectra [1].”
BackgroundA New Algorithm for the On-Board Compression of Hyperspectral Images
Guerra, R., Barrios, Y., Díaz, M., Santos, L., López, S., & Sarmiento, R. (2018) · Remote Sensing · doi:10.3390/rs10030428 · Cited by 47
“It is worth to mention here that the PCA transform is used in many hyperspectral applications, such as unmixing or classification, for spectrally decorrelating the information and reducing the number of spectral components of the data set, with the goal of reducing the redundant information, increasing the separabilit…”
MethodZhai, Y., Qu, Z., & Hao, L. (2018) · Remote Sensing · doi:10.3390/rs10030383 · Cited by 42
Dong, Y., Du, B., Zhang, L., & Hu, X. (2018) · Remote Sensing · doi:10.3390/rs10091415 · Cited by 43
“Meanwhile, we use the FAR under TDR = 100% to further evaluate the detection performance [44].”
MethodSurface Defect Detection of Wet-Blue Leather Using Hyperspectral Imaging
Chen, S.-Y., Cheng, Y.-C., Yang, W., & Wang, M. (2021) · IEEE Access · doi:10.1109/access.2021.3112133 · Cited by 46
“The hyperspectral signal has a wider spectrum range and higher spectrum resolution [31]–[33], meaning that the hyperspectral signal has abundant information hidden in each pixel.”
BackgroundLi, N., Ning, Z., Chen, M., Wu, D., Hao, C., Zhang, D., Bai, R., Liu, H., Chen, X., Li, W., et al. (2022) · Remote Sensing · doi:10.3390/rs14215466 · Cited by 48
Nonlocal Structured Sparsity Regularization Modeling for Hyperspectral Image Denoising
Zha, Z., Wen, B., Yuan, X., Zhang, J., Zhou, J., Lu, Y., & Zhu, C. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3269224 · Cited by 43
“…hyperspectral imagery provides a more comprehensive acquisition of spectral data for the same scene, enabling precise differentiation of materials and facilitating its application in various fields, such as geological investigation [1], military monitoring [2], and terrain classification [3].”
BackgroundCross-Channel Dynamic Spatial–Spectral Fusion Transformer for Hyperspectral Image Classification
Qiu, Z., Xu, J., Peng, J., & Sun, W. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3324730 · Cited by 41
“They contain rich spectral and spatial information [3] and are widely used in many fields such as vegetation ecology [4], environmental ecology [5], geological survey [6], urban planning [7], target detection [8], and so on.”
BackgroundHybrid Spectral Denoising Transformer with Guided Attention
Lai, Z., Yan, C. C., & Fu, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01201 · Cited by 58
“Hyperspectral image (HSI) provides substantially more abundant spectral information than the ordinary color image, which makes it especially utilitarian in the field of remote sensing [3, 4], biometric authentication [60], detection [46], and geological science [19, 57].”
BackgroundArrigoni, S., Turra, G., & Signoroni, A. (2017) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2017.06.018 · Cited by 46
Spectral–spatial classification of hyperspectral image using three-dimensional convolution network
Liu, B., Yu, X., Zhang, P., Tan, X., Wang, R., & Lu, Z. (2018) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.12.016005 · Cited by 48
“The goal of feature mining and subspace approaches is to reduce the dimensionality of the input space to better exploit the limited training samples available.(10) The support vector machine (SVM) classifier(11,12) using a kernel method was introduced to deal with the problem of small sample sizes, and has long been t…”
MethodMultiresolution Multimodal Sensor Fusion for Remote Sensing Data With Label Uncertainty
Du, X., & Zare, A. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2955320 · Cited by 41
“obtain a better classification result and a more comprehensive understanding of scene [4]–[7].”
BackgroundMartel, E., Lazcano, R., Lopez, J. F., Madroñal, D., Salvador, R., López, S., Juárez, E., Guerra, R., Sanz, C., & Sarmiento, R. (2018) · Remote Sensing · doi:10.3390/rs10060864 · Cited by 47
Residual HSRCNN: Residual Hyper-Spectral Reconstruction CNN from an RGB Image
Han, X., Shi, B., & Zheng, Y. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545634 · Cited by 45
“disease diagnosis in medical imaging [40] and land resource management/planning in remote sensing [7], [3].”
BackgroundCauchy sparse NMF with manifold regularization: A robust method for hyperspectral unmixing
Wang, H., Yang, W., & Guan, N. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.104898 · Cited by 43
Zhang, X., Wang, Y., Zhang, N., Xu, D., Luo, H., Chen, B., & Ben, G. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3046840 · Cited by 41
“In addition, there is a phenomenon that the same ground objects contain different spectral information and different ground objects contain the same spectral information [7].”
BackgroundSpatial Pooling Graph Convolutional Network for Hyperspectral Image Classification
Zhang, X., Chen, S., Zhu, P., Tang, X., Feng, J., & Jiao, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3140353 · Cited by 41
“R ECENT years with the rapid development of remote sensing techniques, it is easier to obtain more and more hyperspectral data [1].”
Zhao, B., Ulfarsson, M. O., Sveinsson, J. R., & Chanussot, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3142988 · Cited by 41
Self-citationA Multiscale Superpixel-Level Group Clustering Framework for Hyperspectral Band Selection
Jia, S., Yuan, Y. H., Li, N., Liao, J., Huang, Q., Jia, X., & Xu, M. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3150361 · Cited by 41
“…information, HSI-oriented processing has become one of the most promising techniques in numerous fields, including geological exploration [1], ecological sciences [2], disaster prediction [3], food industry [4], [5], environmental monitoring [6], [7], astronomy [8], ocean monitoring [9], etc.”
BackgroundBai, J., Shi, W., Xiao, Z. Q., Regan, A., Ali, T. A. A., Zhu, Y., Zhang, R., & Jiao, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3153446 · Cited by 41
Hyperspectral Image Classification via a Novel Spectral–Spatial 3D ConvLSTM-CNN
Farooque, G., Xiao, L., Yang, J., & Sargano, A. B. (2021) · Remote Sensing · doi:10.3390/rs13214348 · Cited by 41
“These include but are not limited to an imbalance between the high dimensionality of the data and the scarcity of training samples, the existence of mixed pixels in the data, and the integration of spectral and spatial information [54].”
BackgroundA Deep Spectral–Spatial Residual Attention Network for Hyperspectral Image Classification
Chhapariya, K., Buddhiraju, K. M., & Kumar, A. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3355071 · Cited by 44
“HSI, with its high spectral resolution, has been widely used in many applications, such as crop monitoring [2], [3], urban development [4], [5], the mining industry [6], [7], environmental and natural resources management [8], [9], surveillance [10], [11], etc.”
BackgroundYang, J.-Y., Li, H.-C., Yang, J.-H., Pan, L., Du, Q., & Plaza, A. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3356510 · Cited by 40
“The HSI classification task, which assigns each pixel to a unique category by using the spatial and spectral information [6], [7], is useful for a variety of applications, i.e., military target detection [8], vegetation monitoring [9], and disaster prevention and control [10].”
BackgroundSelf-citationA New Genetic Method for Subpixel Mapping Using Hyperspectral Images
Tong, X., Xu, X., Plaza, A., Xie, H., Pan, H., Cao, W., & Lv, D. (2016) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2496660 · Cited by 42
Self-citationMultimorphological Superpixel Model for Hyperspectral Image Classification
Liu, T., Gu, Y., Chanussot, J., & Mura, M. D. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2737037 · Cited by 40
“Three kinds of SEs including line, square, and disk with three scales [3], [6], [9] are used.”
MethodSelf-citationHyperspectral Classification Through Unmixing Abundance Maps Addressing Spectral Variability
Ibarrola‐Ulzurrun, E., Drumetz, L., Marcello, J., Gonzalo‐Martín, C., & Chanussot, J. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2892903 · Cited by 42
“In [10] and [43]–[46], to solve this curse of dimensionality problem, data reduction through band selection or feature extraction reduces dimensionality without the need to increase the number of training samples [43], [47], [48].”
BackgroundSelf-citationLiu, T., Zhang, X., & Gu, Y. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2928562 · Cited by 41
“There are six main topics of hyperspectral data analysis, including data fusion, unmixing, classification, target detection, physical parameter retrieval, and fast computing [1].”
BackgroundSu, H., Yao, Y. Q., Wu, Z., & Du, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3029578 · Cited by 40
“However, the fundamental challenges in HSI classification task include insufficient training samples and high dimensionality [1]–[3].”
BackgroundMontes-Herrera, J. C., Cimoli, E., Cummings, V. J., Hill, N. A., Lucieer, A., & Lucieer, V. L. (2021) · Remote Sensing · doi:10.3390/rs13173451 · Cited by 47
“Classification algorithms can be supervised or unsupervised [14].”
BackgroundInfluentialAdaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification
Liu, J., Guan, R., Li, Z., Zhang, J., Hu, Y., & Wang, X. (2023) · Remote Sensing · doi:10.3390/rs15235483 · Cited by 49
Hyperspectral Simultaneous Anomaly Detection and Denoising: Insights From Integrative Perspective
Wang, M., Gao, L., Ren, L., Sun, X., & Chanussot, J. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3437460 · Cited by 40
“In practical HS AD applications, observed images are un-avoidably caused by a variety of noises during data acquisition and transmission [37], [38].”
BackgroundSelf-citationSubpixel Spectral Variability Network for Hyperspectral Image Classification
Han, Z., Yang, J., Gao, L., Zeng, Z., Zhang, B., & Chanussot, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3535749 · Cited by 56
“H YPERSPECTRAL images (HSIs) provide a distinctive advantage over other remote sensing data sources and can precisely depict the spectral characteristics of objects [1], [2].”
Self-citationAltmann, Y., Pereyra, M., & Bioucas‐Dias, J. M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2487862 · Cited by 40
“This dataset has already been studied in [2] and is known to be mainly composed of soil, trees and grass.”
Self-citationSub-Pixel Mapping Based on Conditional Random Fields for Hyperspectral Remote Sensing Imagery
Zhao, J. J., Zhong, Y., Wu, Y., Zhang, L., & Shu, H. (2015) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2015.2416683 · Cited by 43
“in hyperspectral imagery [1], since the sensor's instantaneous”
BackgroundAhmad, M. I., Protasov, S., Khan, A., Hussain, R., Khattak, A. M., & Khan, W. A. (2018) · PLoS ONE · doi:10.1371/journal.pone.0188996 · Cited by 42
DCNR: deep cube CNN with random forest for hyperspectral image classification
Li, T., Leng, J., Kong, L., Guo, S., Bai, G., & Wang, K. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5986-5 · Cited by 39
“Hyperspectral image classification is one of the most key research tasks in remote sensing field [5, 34].”
Dou, Z., Gao, K., Zhang, X., Wang, H., & Wang, J. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2977819 · Cited by 40
“During the last decades, many algorithms have been proposed for the hyperspectral unmixing problem [1], [5].”
BackgroundRotation Equivariant Convolutional Neural Networks for Hyperspectral Image Classification
Paoletti, M. E., Haut, J. M., Roy, S. K., & Hendrix, E. M. T. (2020) · IEEE Access · doi:10.1109/access.2020.3027776 · Cited by 41
“Recent investigation has shown that taking spatial information into account in pixel-wise HSI processing may improve classification performance [45].”
BackgroundMultiview Spatial–Spectral Two-Stream Network for Hyperspectral Image Unmixing
Qi, L., Chen, Z., Gao, F., Dong, J., Gao, X., & Du, Q. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3237556 · Cited by 42
“complex surface and light scattering, mixed pixels, which are comprised of multiple materials spectra, are ubiquitous in a hyperspectral image (HSI) [1].”
BackgroundMethodZhao, R., Yang, Z., Meng, X., & Shao, F. (2024) · Remote Sensing · doi:10.3390/rs16040717 · Cited by 39
Brook, A., & Dor, E. B. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2489207 · Cited by 39
“Merging the spectral domain with the spatial/temporal one makes the HSI technology highly demanded and enables new frontiers in the fields of earth observation applications and environmental monitoring [2], [4], [13], [19], [20], [24], [33]–[35], [44], [49], [52].”
BackgroundHyperspectral Target Detection With Macro-Micro Feature Extracted by 3-D Residual Autoencoder
Shi, Y., Li, J., Yin, Y., Xi, B., & Li, Y. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2939833 · Cited by 41
“Thus, it is difficult to gain satisfying detection accuracy only based on spectral information [6], [7].”
BackgroundFusion of hyperspectral imaging and LiDAR for forest monitoring
Tusa, E., Laybros, A., Monnet, J., Mura, M. D., Barré, J.-B., Vincent, G., Dalponte, M., Féret, J., & Chanussot, J. (2019) · Data handling in science and technology · doi:10.1016/b978-0-444-63977-6.00013-4 · Cited by 42
Self-citationAdaptive Residual Convolutional Neural Network for Hyperspectral Image Classification
Huang, H. B., Pu, C., Li, Y., & Duan, Y. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2995445 · Cited by 38
“Feature extraction (FE) is considered as a key step to address this issue in HSI classification [9].”
BackgroundHuang, K.-K., Ren, C.-X., Liu, H., Lai, Z., Yu, Y., & Dai, D. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107744 · Cited by 43
Object detection in hyperspectral images
Lone, Z. A., & Pais, A. R. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103752 · Cited by 41
Gao, H., Zhang, Y., Chen, Z., Xu, F., Hong, D., & Zhang, B. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3288739 · Cited by 38
“Although the abovementioned classic detectors are generic and excellent, the characteristics of real HSI, such as spectral variability and subpixel interference may result in degraded performances [27], [28].”
BackgroundMa, X., Zhang, X., Tang, X., Zhou, H., & Jiao, L. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2990457 · Cited by 40
“mation but also the high-resolution spectral information for discriminating ground objects [1].”
BackgroundDetection of Single Burials Using Multispectral Drone Data: Three Case Studies
Rocke, B., & RUFFELL, A. H. (2022) · Forensic Sciences · doi:10.3390/forensicsci2010006 · Cited by 37
“While the potential of hyperspectral data to detect anomalies in soil and vegetation is considerably greater than multispectral imaging, hyperspectral data often requires complex computation and algorithms, which is outside the remit of many scientists, humanitarian organisations and law enforcement [14].”
BackgroundBai, J., Shi, W., Xiao, Z. Q., Ali, T. A. A., Ye, F., & Jiao, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3235711 · Cited by 38
“The pixel-level HSI classification (HSIC) with promised accuracy facilitates emerging applications in various fields, such as resource exploration, disaster prevention and rescue, and urban planning [3], [4], [5], [6], [7].”
BackgroundHyperspectral Unmixing Using Higher-Order Graph Regularized NMF With Adaptive Feature Selection
Qu, K., Li, Z., Wang, C., Luo, F., & Bao, W. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3275740 · Cited by 37
“Hyperspectral images (HSIs) are widely used in the fields of agricultural yield estimation, mineral exploration, and environmental monitoring [1].”
BackgroundJi, R., Tan, K., Wang, X., Chen, P., & Xin, L. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3322422 · Cited by 37
“I N RECENT years, with the rapid development of remote sensing technology, hyperspectral sensors are considered a revolution, with their unprecedented spectral, spatial, and temporal resolutions [1], [2].”
BackgroundBao, R., Xia, J., Mura, M. D., Du, P., Chanussot, J., & Ren, J. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2513002 · Cited by 37
“, shape, texture, and spatial relationships) is beneficial for improving the classification result [3].”
BackgroundSelf-citationShapelet-Based Sparse Representation for Landcover Classification of Hyperspectral Images
Roscher, R., & Waske, B. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2015.2484619 · Cited by 37
“, [1] and [2]).”
Hyperspectral Image Super-Resolution via Local Low-Rank and Sparse Representations
Dian, R., Shutao Li, A., Fang, L., & Bioucas‐Dias, J. M. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8519213 · Cited by 37
“HSIs have been used in many Earth remote sensing applications [1], due to its high spectral resolution.”
MethodSelf-citationHyperspectral Band Selection Using Weighted Kernel Regularization
Sun, W., Yang, G., Peng, J., & Du, Q. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2922201 · Cited by 37
“U SING tens to hundreds of narrow spectral channels (i.e., bands), hyperspectral sensors collect reflection signals of ground objects on the earth surface [1], [2].”
BackgroundSubpixel-Pixel-Superpixel-Based Multiview Active Learning for Hyperspectral Images Classification
Li, Y., Lu, T., & Li, S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2971081 · Cited by 38
“H YPERSPECTRAL image (HSI) classification is an active research field in remote sensing community, which is very important in different civil and military applications [1].”
BackgroundAnalysis of PCA Based Feature Extraction Methods for Classification of Hyperspectral Image
Ali, U. A. M. E., Hossain, M. A., & Islam, M. R. (2019) · doi:10.1109/iciet48527.2019.9290629 · Cited by 37
Liu, H., Lu, Y., Wu, Z., Du, Q., Chanussot, J., & Wei, Z. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3064708 · Cited by 40
“HYPERSPECTRAL (HS) image has received an increasing interest due to its high spectral resolution [1]–[5].”
BackgroundSelf-citationGuo, Q., Zhang, J., Zhong, C., & Zhang, Y. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3074538 · Cited by 37
“Mixed pixels are one of the typical characteristics in HSIs, which makes CD particularly complex due to their widespread presence [20].”
BackgroundZhu, D., Du, B., Dong, Y., & Zhang, L. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3210389 · Cited by 37
Learning Single Spectral Abundance for Hyperspectral Subpixel Target Detection
Zhu, D., Du, B., & Zhang, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3239061 · Cited by 37
“B Y MEANS of airborne or spaceborne sensors, hyperspectral spectrometers can capture electromagnetic spectrum covering ultraviolet, visible, near-infrared, and short-wave infrared regions as hundreds of narrow contiguous bands into hyperspectral imagery (HSI) [1], [2], [3], [4].”
BackgroundLiu, R., Zhang, L., & Du, B. (2017) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2016.2640274 · Cited by 38
Dynamical Hyperspectral Unmixing With Variational Recurrent Neural Networks
Borsoi, R. A., Imbiriba, T., & Closas, P. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3266660 · Cited by 41
“of different materials in a scene [1].”
Nonparametric Detection of Nonlinearly Mixed Pixels and Endmember Estimation in Hyperspectral Images
Imbiriba, T., Bermudez, J. C. M., Richard, C., & Tourneret, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2509258 · Cited by 36
ANSGA-III: A Multiobjective Endmember Extraction Algorithm for Hyperspectral Images
Cheng, Q., Du, B., Zhang, L., & Liu, R. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2893621 · Cited by 36
“2893621 nels for each pixel in a scene that make it easy to identify and interpret the different types of ground objects [9]–[11].”
BackgroundSemisupervised Band Selection With Graph Optimization for Hyperspectral Image Classification
He, F., Nie, F., Wang, R., Jia, W., Zhang, F., & Li, X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3037746 · Cited by 36
Metadata
- Authors
- Bioucas-Dias, J. M., Plaza, A., Camps-Valls, G., Scheunders, P., Nasrabadi, N., & Chanussot, J.
- Affiliations
- Universidad de Extremadura (ES)
- University of Antwerp (BE)
- DEVCOM Army Research Laboratory (US)
- Institut polytechnique de Grenoble (FR)
- Venue
- IEEE Geoscience and Remote Sensing Magazine
- Published
- 2013-06
- Volume
- 1
- Issue
- 2
- Pages
- 6-36
- ISSN
- 2168-6831 (ISSN-L)
- OpenAlex
- W2087263574
- Cited by
- 2,223
- References
- 188
- Citations by year
- 2026: 204 · 2025: 228 · 2024: 201 · 2023: 209 · 2022: 215 · 2021: 219 · 2020: 178 · 2019: 183 · 2018: 155 · 2017: 131 · 2016: 129 · 2015: 105 · 2014: 62 · 2013: 4
- FWCI
- 196.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Geoscience and Remote Sensing Magazine (publishedVersion)
- Funders
- Ministerio de Economía y Competitividad (TIN2012-38102-C03-01)
- Fundação para a Ciência e a Tecnologia
- 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 › Chemistry › Analytical Chemistry › Spectroscopy and Chemometric Analyses
- Keywords
- hyperspectral remote sensing, hyperspectral data processing, spectral unmixing, spectral mixing, data fusion, hyperspectral image classification, target detection, high dimensionality
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.