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

@article{elik2009UnsupervisedCD,
  title={Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and \$k\$-Means Clustering},
  author={Turgay Çelik},
  journal={IEEE Geoscience and Remote Sensing Letters},
  year={2009},
  volume={6},
  pages={772-776}
}
In this letter, we propose a novel technique for unsupervised change detection in multitemporal satellite images using principal component analysis (PCA) and k-means clustering. The difference image is partitioned into h times h nonoverlapping blocks. S, S les h2, orthonormal eigenvectors are extracted through PCA of h times h nonoverlapping block set to create an eigenvector space. Each pixel in the difference image is represented with an S-dimensional feature vector which is the projection of… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • The proposed algorithm is fairly robust against the zero-mean Gaussian and speckle noises when PSNR ≥ 20 dB, where the maximum rate of change is 6% for zero-mean Gaussian noise and 8% for speckle noise with respect to nonoise change detection performance.

Citations

Publications citing this paper.
SHOWING 1-10 OF 261 CITATIONS

Unsupervised Change Detection using Thin Cloud-Contaminated Landsat Images

  • 2018 International Conference on Intelligent Systems (IS)
  • 2018
VIEW 12 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Unsupervised saliency-guided SAR image change detection

  • Pattern Recognition
  • 2017
VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Unsupervised Change Detection of Satellite Images Using Local Gradual Descent

  • IEEE Transactions on Geoscience and Remote Sensing
  • 2012
VIEW 19 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Multiscale Change Detection in Multitemporal Satellite Images

  • IEEE Geoscience and Remote Sensing Letters
  • 2009
VIEW 12 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS

FILTER CITATIONS BY YEAR

2005
2019

CITATION STATISTICS

  • 70 Highly Influenced Citations

  • Averaged 41 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-8 OF 8 REFERENCES

Automatic analysis of the difference image for unsupervised change detection

L. Bruzzone, D. Prieto
  • IEEE Trans. Geosci. Remote Sens., vol. 38, no. 3, pp. 1171–1182, May 2000.
  • 2000
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL