Dimensionality Reduction techniques: An operational comparison on multispectral satellite images using unsupervised clustering

被引：0

作者：

Journaux, Ludovic ^{[1
]}

Tizon, Xavier ^{[1
]}

Foucherot, Irene ^{[1
]}

Gouton, Pierre ^{[1
]}

机构：

[1] Univ Bourgogne, CNRS, UMR 5158, LE2I, BP 47870, F-21078 Dijon, France

来源：

2006 7TH NORDIC SIGNAL PROCESSING SYMPOSIUM | 2006年

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Multispectral satellite imagery provides us with useful but redundant datasets. Using Dimensionality Reduction (DR) algorithms, these datasets can be made easier to explore and to use. We present in this study an objective comparison of five DR methods, by evaluating their capacity to provide a usable input to the K-means clustering algorithm. We also suggest a method to automatically find a suitable number of classes K, using objective "cluster validity indexes" over a range of values for K Ten Landsat images have been processed, yielding a classification rate in the 70-80% range. Our results also show that classical linear methods, though slightly outperformed by more recent nonlinear algorithms, still offer a reasonable trade-off.

引用

页码：242 / +

页数：2

共 50 条

[21] Unsupervised Change Detection in Multitemporal Multispectral Satellite Images Using Parallel Particle Swarm Optimization
Kusetogullari, Huseyin
Yavariabdi, Amir
Celik, Turgay
[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (05) : 2151 - 2164
[22] Recurrent neural networks for automatic clustering of multispectral satellite images
Koprinkova-Hristova, P.
Alexiev, K.
Borisova, D.
Jelev, G.
Atanassov, V.
[J]. IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XIX, 2013, 8892
[23] Active and Reactive Power Load Profiling Using Dimensionality Reduction Techniques and Clustering
Yetkin, E. Fatih
Ceylan, Oguzhan
Papadopoulos, Theofilos A.
Kazaki, Anastasia G.
Barzegkar-Ntovom, Georgios A.
[J]. 2019 54TH INTERNATIONAL UNIVERSITIES POWER ENGINEERING CONFERENCE (UPEC), 2019,
[24] Quantification of multispectral photoacoustic images: unsupervised unmixing methods comparison
Dolet, Aneline
Ammanouil, Rita
Grenier, Thomas
Richard, Cedric
Tortoli, Piero
Vray, Didier
Varray, Francois
[J]. 2018 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IUS), 2018,
[25] Spatial clustering using neighborhood for multispectral images
Raj, Aditya
Minz, Sonajharia
[J]. JOURNAL OF APPLIED REMOTE SENSING, 2020, 14 (03)
[26] A new methodology for efficient classification of multispectral satellite images using neural network techniques
Vassilas, N
Charou, E
[J]. NEURAL PROCESSING LETTERS, 1999, 9 (01) : 35 - 43
[27] New methodology for efficient classification of multispectral satellite images using neural network techniques
Natl Research Cent `Demokritos', Attiki, Greece
[J]. Neural Process Letters, 1 (35-43):
[28] A New Methodology for Efficient Classification of Multispectral Satellite Images Using Neural Network Techniques
Nikolaos Vassilas
Eleni Charou
[J]. Neural Processing Letters, 1999, 9 : 35 - 43
[29] A comparison of dimensionality reduction techniques for text retrieval
Vinay, V
Cox, IJ
Wood, K
Milic-Frayling, N
[J]. ICMLA 2005: FOURTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, PROCEEDINGS, 2005, : 293 - 298
[30] A Comparison of Dimensionality Reduction Techniques for Hyperspectral Imagery
Race, Benjamin
Wittman, Todd
[J]. ALGORITHMS, TECHNOLOGIES, AND APPLICATIONS FOR MULTISPECTRAL AND HYPERSPECTRAL IMAGING XXVIII, 2022, 12094

← 1 2 3 4 5 →