Abstract
We propose a contextual unsupervised classification method of geostatistical data based on combination of Ward clustering method and Markov random fields (MRF). Image is clustered into classes by using not only spectrum of pixels but also spatial information. For the classification of remote sensing data of low spatial resolution, the treatment of mixed pixel is importance. From the knowledge that the most of mixed pixels locate in boundaries of land-covers, we first detect edge pixels and remove them from the image. We here introduce a new measure of spatial adjacency of the classes. Spatial adjacency is used to MRF-based update of the classes. Clustering of edge pixels are processed as final step. It is shown that the proposed method gives higher accuracy than conventional clustering method does.
| Original language | English |
|---|---|
| Title of host publication | Image and Signal Processing for Remote Sensing XII |
| DOIs | |
| Publication status | Published - Dec 1 2006 |
| Event | Image and Signal Processing for Remote Sensing XII - Stockholm, Sweden Duration: Sep 11 2006 → Sep 14 2006 |
Publication series
| Name | Proceedings of SPIE - The International Society for Optical Engineering |
|---|---|
| Volume | 6365 |
| ISSN (Print) | 0277-786X |
Other
| Other | Image and Signal Processing for Remote Sensing XII |
|---|---|
| Country | Sweden |
| City | Stockholm |
| Period | 9/11/06 → 9/14/06 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering
Cite this
Contextual unsupervised classification of remotely sensed imagery with mixels. / Kawaguchi, Shuji; Nishii, Ryuei.
Image and Signal Processing for Remote Sensing XII. 2006. 63650R (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6365).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Contextual unsupervised classification of remotely sensed imagery with mixels
AU - Kawaguchi, Shuji
AU - Nishii, Ryuei
PY - 2006/12/1
Y1 - 2006/12/1
N2 - We propose a contextual unsupervised classification method of geostatistical data based on combination of Ward clustering method and Markov random fields (MRF). Image is clustered into classes by using not only spectrum of pixels but also spatial information. For the classification of remote sensing data of low spatial resolution, the treatment of mixed pixel is importance. From the knowledge that the most of mixed pixels locate in boundaries of land-covers, we first detect edge pixels and remove them from the image. We here introduce a new measure of spatial adjacency of the classes. Spatial adjacency is used to MRF-based update of the classes. Clustering of edge pixels are processed as final step. It is shown that the proposed method gives higher accuracy than conventional clustering method does.
AB - We propose a contextual unsupervised classification method of geostatistical data based on combination of Ward clustering method and Markov random fields (MRF). Image is clustered into classes by using not only spectrum of pixels but also spatial information. For the classification of remote sensing data of low spatial resolution, the treatment of mixed pixel is importance. From the knowledge that the most of mixed pixels locate in boundaries of land-covers, we first detect edge pixels and remove them from the image. We here introduce a new measure of spatial adjacency of the classes. Spatial adjacency is used to MRF-based update of the classes. Clustering of edge pixels are processed as final step. It is shown that the proposed method gives higher accuracy than conventional clustering method does.
UR - http://www.scopus.com/inward/record.url?scp=33751424141&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33751424141&partnerID=8YFLogxK
U2 - 10.1117/12.689566
DO - 10.1117/12.689566
M3 - Conference contribution
AN - SCOPUS:33751424141
SN - 0819464600
SN - 9780819464606
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Image and Signal Processing for Remote Sensing XII
ER -