Advances in Spectral-Spatial Classification of Hyperspectral Images

By Mathieu Fauvel, Yuliya Tarabalka, Jon Atli Benediktsson, Jocelyn Chanussot, James C. Tilton. Proceedings of the IEEE, 2013

1,259 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/b5c3adb715117cacfceaccb3bdef8a6b57b9b5d1

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 Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, background): “As indicated in many spectral–spatial classification studies, the use of the spatial feature can significantly improve the classification accuracy [81]–[83].”
Hyperspectral Remote Sensing Data Analysis and Future Challenges (2013, background): “A detailed overview of recent advances in spatial-spectral classification of hyperspectral data is available at [102].”
Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking (2016, background): “For example, morphological filters [36], segmentation [37], Markov random”
Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods (2013, methodology): “Overall accuracies and the kappa statistic for each method are reported in parentheses [21].”
Automatic Feature Learning for Spatio-Spectral Image Classification With Sparse SVM (2014, methodology): “For all these reasons, classifiers exploiting spatial information extracted from HS data, but also applying dimension reduction, tend to achieve better results than a purely spectral classifier applied in high-dimensional feature space [10], [15].”
Unsupervised Spectral–Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery Classification (2015, background): “a lot of information, further work [5] has demonstrated that combining spectral and spatial information can achieve further”
Classification of Hyperspectral Images by Exploiting Spectral–Spatial Information of Superpixel via Multiple Kernels (2015, background): “informative spectral information of the HSI pixels has many applications, such as classification [1], target detection [2], anomaly detection [3], spectral unmixing [4], and others [5].”
Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks (2016, background): “As a result, detailed spatial information has become available [18].”
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “For spectral-spatial classification of HSIs using segmentation approaches, there are usually two methods to consider: 1) segmentation and classification maps can be integrated using majority voting within each object by assigning the whole object to the most frequent classification label within that”
Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network (2017, background): “, noise removal [48,49], classification [50,51], and SR [52].”
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, methodology): “A detailed overview of other techniques in this field is available in [6].”
A Survey on Spectral–Spatial Classification Techniques Based on Attribute Profiles (2015, methodology): “In order to model the spatial information of a scene, two common strategies are available: a crisp neighborhood system and an adaptive neighborhood system [1].”
Bayesian sparse representation for hyperspectral image super resolution (2015, background): “Spectral characteristics of hyperspectral imaging have recently been reported to enhance performance in many computer vision tasks, including tracking [22], recognition and classification [14], [32], [28], segmentation [25] and document analysis [20].”
Pixel-level image fusion: A survey of the state of the art (2017, background): “P More recently, hyperspectral (HS) imaging which acquires a scene with several hundreds of contiguous spectral bands has demonstrated to be very useful for land-cover classiﬁcation[119] integration of spectral and elevation information [124].”
Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models (2018, background): “These features consider the neighborhood around a pixel as part of its own characteristics, and allow to place spectral signatures in context and solve ambiguities at the pixel level (Fauvel et al., 2013).”