Hyperspectral image data analysis

By David A. Landgrebe. IEEE Signal Processing Magazine, 2002

1,179 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/8df1d4600c9bb71eb96f85a2b928e0591db3778d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

Deep Learning-Based Classification of Hyperspectral Data (2014, methodology): “Hyperspectral data are becoming a valuable tool for monitoring the Earth’s surface [1], [2], and are used in a wide array of applications.”
A Low-Rank and Sparse Matrix Decomposition-Based Mahalanobis Distance Method for Hyperspectral Anomaly Detection (2016, background): “In recent years, hyperspectral anomaly detection has become a booming research topic and has been successfully applied in many application fields, such as mineral reconnaissance, border monitoring, and search and rescue [1], [2], [4], [5].”
Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network (2015, neutral): “To deal with the Hughes effect [1], many feature reduction methods were proposed including the recent work on sparse representation [6], [8].”
Constrained Nonnegative Matrix Factorization for Hyperspectral Unmixing (2009, background): “is a necessary preprocessing step for hyperspectral applications [1]–[4].”
Hyperspectral Band Selection: A Review (2019, methodology): “Therefore, it is necessary to develop new dimensionality reduction methods and protocols for hyperspectral image processing [10]–[12].”
Medical hyperspectral imaging: a review (2014, background): “In particular, it is complex in many aspects: (1) high data redundancy due to high correlation in the adjacent bands, (2) variability of hyperspectral signatures, and (3) curse of dimensionality.(125) With abundant spatial and spectral information available, advanced image classification methods for”
Hyperspectral Imaging Applications in Agriculture and Agro-Food Product Quality and Safety Control: A Review (2013, background): “, leaf size and leaf area index; wavelengths ranged between 400 and 2,400 nm) (43).”
Deep learning classifiers for hyperspectral imaging: A review (2019, methodology): “In particular, HSI data are characterized by their two spatial components: ×n n1 2, and by their large spectral domain, nband, allowing the exploitation of both types of features (Landgrebe, 2002).”
Tensor Discriminative Locality Alignment for Hyperspectral Image Spectral–Spatial Feature Extraction (2013, background): “The first data set is an urban site of the airborne HYDICE from the mall in Washington, DC, which has an original size of 1280 × 307 pixels.”
Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation (2015, background): “Typical examples of multi-band images include hyperspectral (HS) images [1], multi-spectral (MS) images [2], integral ﬁeld spectrographs [3], magnetic resonance spectroscopy images etc.”
Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding (2015, methodology): “In this paper, we select three benchmark data sets for performance evaluation of our EMR-SLRAalgorithm: the Wiki Text-Image data set(1) [34], the NUS-WIDE-LITE data set(2) [35], and the HYDICE hyperspectral data set(3) [36].”
A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data (2004, background): “difficult and expensive [8], a fact that has traditionally prevented”
Segmentation and classification of hyperspectral images using watershed transformation (2010, background): “The first attempts to classify hyperspectral images were designed to assign each pixel to one of the classes based on its spectrum only [4].”
A support vector method for anomaly detection in hyperspectral imagery (2006, background): “Among the reasons for the difference are: 1) the Gaussian assumption of the RX may be less valid for higher dimensional data, as explained in [14] and 2) robust estimation of the covariance matrix is more difficult as the number of bands increases.”
Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches (2012, positive): “This data set is generated with a mixing matrix sampled from the USGS library and with endmembers, spectral vectors, and fractional abundances given by mixtures of two Dirichlet modes with parameters [6, 25, 9] and [7, 8, 23] and mode weights of 0.”