SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images

By Yuliya Tarabalka, Mathieu Fauvel, Jocelyn Chanussot, Jon Atli Benediktsson. IEEE Geoscience and Remote Sensing Letters, 2010

730 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/4db744cf8c986b57838727fe4368fbaae052ad2b

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

1. Shutao Li
2. Jon Atli Benediktsson
3. Pedram Ghamisi
4. Antonio J. Plaza
5. Jun Yu Li
6. Qian Du
7. Yushi Chen
8. Xudong Kang

In Ecology

1. Qian Du
2. Antonio J. Plaza
3. Jon Atli Benediktsson
4. Shutao Li
5. Pedram Ghamisi
6. José M. Bioucas-Dias
7. Jocelyn Chanussot
8. Yushi Chen

In Media Technology

1. Shutao Li
2. Antonio J. Plaza
3. Jon Atli Benediktsson
4. Pedram Ghamisi
5. Jun Yu Li
6. Qian Du
7. Jocelyn Chanussot
8. Yushi Chen

Citations in the corpus

• Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification (2015, methodology): “From the results, SVM-MRF is superior to Spec-SVM but inferior to LBP-SVM.”
• Hyperspectral Remote Sensing Data Analysis and Future Challenges (2013, background): “MRFs exploit the continuity, in probability sense, of neighboring labels [99].”
• Parsing the Hand in Depth Images (2014, methodology): “The Markov Random Fields [16] can be used to refine the classification results, which can well model the constraints from the neighboring states and the image observations [17].”
• Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, methodology): “and [57] alternatively used probabilistic SVM and a Gaussian mixture classifier to model the spectral information, respec-”
• Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering (2014, methodology): “The morphological and kernel-based methods have given good results in terms of accuracies for classifying hyperspectral images [20]–[25].”
• Spectral–spatial classification of hyperspectral images using deep convolutional neural networks (2015, background): “Markov random fields models (Tarabalka et al. 2010; Li, Bioucas-Dias, and Plaza 2012) have been introduced for hyperspectral data classification by merging spatial and spectral features.”
• Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks (2016, background): “It has been found that spectral–spatial FE methods provide good improvement in terms of classification performance [19].”
• A deep learning framework for hyperspectral image classification using spatial pyramid pooling (2016, background): “Markov random fi elds (MRFs)-based models, which merges spatial and spectral features, have been proposed for hyperspectral image classi fi cation (Tarabalka et al. 2010; Li, Bioucas-Dias, and Plaza 2012).”
• Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification (2017, neutral): “In remote sensing image analysis it is a common practice to train classifiers on the spectrum of a small number (a couple of hundreds) of isolated sample pixels [36].”
• Deep Few-Shot Learning for Hyperspectral Image Classification (2019, methodology): “…a large number of spectral–spatial feature extraction methods have been developed for HSI classification, such as extended morphological profiles [11], Markov random field [12], local binary pattern [13], Gabor wavelet filters [14], discriminant analysis [15], [16], and segmentation approaches [17].”