Kernel-Based Framework for Multitemporal and Multisource Remote Sensing Data Classification and Change Detection

By Gustau Camps-Valls, Luis Gómez-Chova, Jordi Muñoz-Marí, José Luis Rojo-Álvarez, M. Martínez‐Ramón. IEEE Transactions on Geoscience and Remote Sensing, 2008

380 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/d83e1b7e694f0ef150bc1d80256d2ba66c22c38e

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. Jon Atli Benediktsson
2. Lorenzo Bruzzone
3. Liangpei Zhang
4. Xin Huang
5. Gustau Camps-Valls
6. Francesca Bovolo
7. Devis Tuia
8. Shutao Li

In Ecology

1. Liangpei Zhang
2. Lorenzo Bruzzone
3. Xin Huang
4. Francesca Bovolo
5. Gustau Camps-Valls
6. Maoguo Gong
7. Luis Gómez-Chova
8. Silvia Marchesi

In Media Technology

1. Lorenzo Bruzzone
2. Jon Atli Benediktsson
3. Liangpei Zhang
4. Gustau Camps-Valls
5. Xin Huang
6. Devis Tuia
7. Antonio J. Plaza
8. Francesca Bovolo

Citations in the corpus

• An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery (2013, methodology): “has been proved to be effective for classification of multisource data than the single or simple kernel classifier [21], [22], [52].”
• Semisupervised Neural Networks for Efficient Hyperspectral Image Classification (2010, background): “In recent years, supervised kernel classifiers, such as support vector machines (SVMs) [2], have demonstrated very good performance in multispectral, hyperspectral, and multisource image classification [3]–[5].”
• A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images (2018, methodology): “The problem of change detection based on heterogeneous images can be addressed by using classification-based methods [30], [31].”
• Support vector machines in remote sensing: A review (2011, neutral): “Camps-Valls et al. (2008) proposed a methodological framework using composite kernels for multi-temporal classification of remote sensing data from different sources.”
• Mean Map Kernel Methods for Semisupervised Cloud Classification (2010, methodology): “However, this is suboptimal as illustrated elsewhere [21], [54], [55], and intuition is lost.”
• Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data (2010, methodology): “Recent studies discuss the use of SVM for spectral–spatial classification of urban hyperspectral data [10]–[12] and multisource classification [13]–[15] and extend the supervised SVM techniques by semisupervised concepts [16], [17].”
• A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images (2012, methodology): “, the detection of different kinds of change) has been usually treated as a problem of explicitly detecting landcover transitions according to (semi- and partially) supervised methods [1], [2].”
• Multimodal Classification of Remote Sensing Images: A Review and Future Directions (2015, background): “An alternative presented in [76] and [81] considers first mapping the vectors x ðtÞ i and x ðtÞ j and then stacking them in Hilbert spaces.”