A Novel Approach to Unsupervised Change Detection Based on a Semisupervised SVM and a Similarity Measure

By Francesca Bovolo, Lorenzo Bruzzone, Mattia Marconcini. IEEE Transactions on Geoscience and Remote Sensing, 2008

300 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/fea071373863c2f78a268264cfb0ff2e0c4b4f19

How researchers see this paper

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

In Analytical Chemistry

1. Turgay Çelik
2. Liangpei Zhang
3. Bo Du
4. Chen Wu
5. Daifeng Peng
6. Yongjun Zhang
7. Haiyan Guan
8. Le Wang

In Atmospheric Science

1. Lorenzo Bruzzone
2. Bo Du
3. Liangpei Zhang
4. Chen Wu
5. Yongjun Zhang
6. Daifeng Peng
7. Haiyan Guan
8. Le Wang

In Media Technology

1. Lorenzo Bruzzone
2. Bo Du
3. Liangpei Zhang
4. Chen Wu
5. Le Wang
6. Turgay Çelik
7. Yongjun Zhang
8. Daifeng Peng

Citations in the corpus

• Change detection from remotely sensed images: From pixel-based to object-based approaches (2013, methodology): “The algorithm learns from training data and automatically finds a threshold values (Bovolo et al., 2008) from the spectral features for classifying change from no-change.”
• Slow Feature Analysis for Change Detection in Multispectral Imagery (2014, methodology): “the conceptual extension [20]–[22]; 2) image transformation— the original data set is transformed into the feature space to highlight the values of changed pixels [23]; 3) classification— postclassification labels changed pixels by comparing independent multitemporal class maps, and compound classif”
• Monitoring Land-Cover Changes: A Machine-Learning Perspective (2016, unknown): “[23] F.”
• Deep learning for change detection in remote sensing: a review (2022, methodology): “…1981), 2) Post-Classification Change Methods (PCCMs) (Silván-Cárdenas, and Wang 2014; Yuan et al. 2005), 3) Direct Classification Methods (DCMs) (Bovolo, Bruzzone, and Marconcini 2008), 4) Transformation methods (Gong 1993), 5) Change Vector Analysis (CVA) meth-ods (Chen et al. 2003; Johnson,…”
• Deep Learning-Based Change Detection in Remote Sensing Images: A Review (2022, methodology): “In addition, the classification-based CD approaches [16] convert pixels of an image into land cover classes without the need for random noises for change identification [17–19].”
• Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images (2018, methodology): “These methods directly calculate the difference between multi-temporal remote sensing images; 2) Image transformation algorithms extract the effective features of multi-temporal remote sensing images by transforming and combining their feature bands, and mainly include Principle Component Analysis (”
• Support vector machines in remote sensing: A review (2011, unknown): “For example, Bovolo et al. (2008) combined an SVM and a selective Bayesian thresholding approach for unsupervised change detection.”
• CHANGE DETECTION IN REMOTE SENSING IMAGES USING CONDITIONAL ADVERSARIAL NETWORKS (2018, methodology): “The Support Vector Machine (SVM) approach based on (Vapnik, 2000) considers the finding change and no-change regions as a problem of binary classification in a space of spectral features (Huang et al., 2008; Bovolo et al., 2008).”
• SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing Images (2020, methodology): “Bovolo et al. [45] proposed a semisupervised CD for multispectral RS images by utilizing a defined binary semisupervised support vector machine (S 3 VM) classifier, where the unlabeled patterns were gradually considered to define the decision boundary between the changed and unchanged pixels.”
• Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering (2009, methodology): “Several unsupervised change detection techniques have been proposed in the literature falling in these categories [2]–[4] which use complicated data modeling and parameter estimation.”