Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods

By Gustau Camps-Valls, Devis Tuia, Lorenzo Bruzzone, Jon Atli Benediktsson. IEEE Signal Processing Magazine, 2013

728 citations recorded by the source corpus.

The technological evolution of optical sensors over the last few decades has provided remote sensing analysts with rich spatial, spectral, and temporal information. In particular, the increase in spectral resolution of hyperspectral images (HSIs) and infrared sounders opens the doors to new application domains and poses new methodological challenges in data analysis. HSIs allow the characterization of objects of interest (e.g., land-cover classes) with unprecedented accuracy, and keeps inventories up to date. Improvements in spectral resolution have called for advances in signal processing and exploitation algorithms. This article focuses on the challenging problem of hyperspectral image classification, which has recently gained in popularity and attracted the interest of other scientific disciplines such as machine learning, image processing, and computer vision. In the remote sensing community, the term classification is used to denote the process that assigns single pixels to a set of classes, while the term segmentation is used for methods aggregating pixels into objects and then assigned to a class.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/bd7d537f837cd33f7b5b5d650e4850fabb8492c7

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

Hyperspectral Band Selection: A Review (2019, background): “, biophysical parameter retrieval [3], [4], fine classification of complex environments [5], [6], small target detection [7], [8], and so forth.”
HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification (2019, background): “[2] have surveyed the advances in HSI classification.”
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, neutral): “performance [5]–[7], [11]–[16].”
Spectral–Spatial Graph Convolutional Networks for Semisupervised Hyperspectral Image Classification (2019, methodology): “Many researchers have published their methods to avoid the Hughes phenomenon of HSI, and most traditional techniques classify the HSI only by spectral signatures [13].”
3-D Deep Learning Approach for Remote Sensing Image Classification (2018, methodology): “As a response to this lack of efficient methods, serious efforts have been made, and several approaches have been set up, such as the graphic-based one detailed in [5] or some handcrafted feature tools that can effectively describe the spatial and spectral content of the images [6].”
Spatial-Spectral Transformer for Hyperspectral Image Classification (2021, methodology): “Thus, the obtained abundant information makes HSI useful in many areas including effective measurement of agricultural performance [3], plant diseases detection [4], identification of minerals [5], disease diagnosis and image-guided surgery [6], ecosystem measurement [7], and earth monitoring [8].”
Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification (2019, neutral): “classification [12].”
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, background): “How can we extract valuable information from the various kinds of RS data? How should we deal with the ever-increasing data types and volume? The traditional approaches exploit features from RS images with which information-extraction models can be constructed [11].”
Unsupervised Deep Feature Extraction for Remote Sensing Image Classification (2015, background): “2 Beyond these well-known data characteristics, we should highlight that spatial and spectral redundancy also suggests that the acquired signal may be better described in sparse representation spaces, as recently reported in [4] and [6]–[8].”
Deep learning classifiers for hyperspectral imaging: A review (2019, neutral): “, 2018d) and (vi) data classification (Fauvel et al., 2013; Camps-Valls et al., 2014; Ghamisi et al., 2017a).”
Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review (2019, methodology): “This is the case, for instance, of Scale-Invariant Feature Transform (SIFT) [12], Histogram of Oriented Gradients (HOG) [13] or Local Binary Patterns [14], in conjunction with kernel-based Support Vector Machines (SVM) [15], Random Forests [16] or statistical learning methods [17].”
Multimodal Classification of Remote Sensing Images: A Review and Future Directions (2015, background): “Among all the products that can be obtained from the acquired images, classification maps(1) are perhaps the most relevant ones [4], [5].”