Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering

By Turgay Çelik. IEEE Geoscience and Remote Sensing Letters, 2009

1,093 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/d3fda1e44c8ba36c58b800c9b7a0e9fe7ddb6242

How researchers see this paper

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

In Artificial Intelligence

In Atmospheric Science

In Media Technology

Citations in the corpus

A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images (2012, methodology): “analysis would imply the application of clustering algorithms to BD vectors [17], [21].”
Optical Remote Sensing Image Change Detection Based on Attention Mechanism and Image Difference (2021, methodology): “…analysis [11]), image transformation (e.g., vegetation index [5], change vector analysis (CVA) [12], [13], principal component analysis (PCA) [14], [15], independent component analysis (ICA) [16]), image classiﬁcation [17], [18], and other advanced algorithms, such as slow feature analysis…”
Multitask learning for large-scale semantic change detection (2018, methodology): “Other methods use unsupervised learning approaches such as iterative training (Liu et al., 2016), au-toencoders (Zhao et al., 2014), and principal component analysis with k -means clustering (Celik, 2009) to separate changed pixels from unchanged ones.”
End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++ (2019, methodology): “Numerous PBCD approaches have been proposed to exploit the spectral and textual features of pixels, such as image algebra-based methods [7], image transformation-based methods [8,9], image classification-based methods [10], and machine learning-based methods [11–13].”
Self-Supervised Representation Learning for Remote Sensing Image Change Detection Based on Temporal Prediction (2020, methodology): “In some cases, the FCM algorithm has the advantages of retaining more image information than hard clustering such as k-means clustering algorithm [15].”
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “In this case, classical techniques in multispectral imaging such as thresholding [292] or clustering [293] can still be considered, based on the computed magnitude of the SCVs.”
A Novel Framework for the Design of Change-Detection Systems for Very-High-Resolution Remote Sensing Images (2013, neutral): “The approaches to change detection can be essentially divided into two groups: i) supervised [3], [5], [14], [15], [17], [18], [19], [20], [21], [22], [23], [24], [25], [26]; and ii) unsupervised approaches [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37].”
Change Detection in Multisource VHR Images via Deep Siamese Convolutional Multiple-Layers Recurrent Neural Network (2020, methodology): “To validate the effectiveness of the proposed SiamCRNN, nine of the most widely used CD methods are used for comparison, namely CVA [9], MAD [14], IRMAD [15], SFA [16], iterative slow feature analysis (ISFA) [16], PCAK-means [13], support vector machine (SVM), DSCN [25], and RNN-CD [27].”
Deep Learning-Based Change Detection in Remote Sensing Images: A Review (2022, background): “Many traditional techniques of change detection, such as image algebra [11] and transformation [12], are relatively limited in their applications and are affected by the inﬂuences of atmospheric conditions, changing seasons, satellite sensors, and solar elevations, reducing the accuracy of change…”
Change Detection on Remote Sensing Images Using Dual-Branch Multilevel Intertemporal Network (2023, methodology): “In contrast, image transformation methods, such as principal component analysis (PCA) [7], change vector analysis [8], and tasseled cap transformation [9], resort the spatial mapping to highlight the changed information.”
GETNET: A General End-to-End 2-D CNN Framework for Hyperspectral Image Change Detection (2019, methodology): “As a linear transformation technique, principal component analysis (PCA) [15] decorrelates images [16].”
SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing Images (2020, methodology): “Furthermore, to overcome the effect of “salt and pepper” noise, spatial-context information was introduced by using neighboring windows [11], and probability graph models (PGMs) [12], [13].”
SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images (2021, methodology): “Therefore, many traditional change detection methods, such as Image Difference, change vector analysis (CVA) [2] and PCA & Kmeans [3], etc., which can achieve effective results in some simple scenarios, often perform poorly in these complex scenarios.”