Abstract
This study develops a new framework for multi-scale analysis procedures and a new operational wavelet-based algorithm to identify urban classes. For better evaluation of wavelets, traditional classifiers were used: maximum likelihood, Mahalanobis, and minimum distance to identify the same classes. Overall accuracy for maximum likelihood, Mahalanobis, and minimum distance for band-3 and multi-bands were 49%, 43%, 48%, 58%, 56%, and 55%, respectively. However, the wavelet approach with the above measures using Band 3 alone gave much higher accuracies (70%, 80%, and 81 %). It can be concluded that the wavelet-based approaches are far more accurate than the traditional classifiers.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 155-178 |
| Number of pages | 24 |
| Journal | GIScience and Remote Sensing |
| Volume | 43 |
| Issue number | 2 |
| DOIs | |
| State | Published - Apr 2006 |
Fingerprint
ASJC Scopus subject areas
- Geography, Planning and Development
Cite this
A new framework for effective urban land use and land cover classification : A wavelet approach. / Myint, Soe.
In: GIScience and Remote Sensing, Vol. 43, No. 2, 04.2006, p. 155-178.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A new framework for effective urban land use and land cover classification
T2 - A wavelet approach
AU - Myint, Soe
PY - 2006/4
Y1 - 2006/4
N2 - This study develops a new framework for multi-scale analysis procedures and a new operational wavelet-based algorithm to identify urban classes. For better evaluation of wavelets, traditional classifiers were used: maximum likelihood, Mahalanobis, and minimum distance to identify the same classes. Overall accuracy for maximum likelihood, Mahalanobis, and minimum distance for band-3 and multi-bands were 49%, 43%, 48%, 58%, 56%, and 55%, respectively. However, the wavelet approach with the above measures using Band 3 alone gave much higher accuracies (70%, 80%, and 81 %). It can be concluded that the wavelet-based approaches are far more accurate than the traditional classifiers.
AB - This study develops a new framework for multi-scale analysis procedures and a new operational wavelet-based algorithm to identify urban classes. For better evaluation of wavelets, traditional classifiers were used: maximum likelihood, Mahalanobis, and minimum distance to identify the same classes. Overall accuracy for maximum likelihood, Mahalanobis, and minimum distance for band-3 and multi-bands were 49%, 43%, 48%, 58%, 56%, and 55%, respectively. However, the wavelet approach with the above measures using Band 3 alone gave much higher accuracies (70%, 80%, and 81 %). It can be concluded that the wavelet-based approaches are far more accurate than the traditional classifiers.
UR - http://www.scopus.com/inward/record.url?scp=33745798412&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33745798412&partnerID=8YFLogxK
U2 - 10.2747/1548-1603.43.2.155
DO - 10.2747/1548-1603.43.2.155
M3 - Article
AN - SCOPUS:33745798412
VL - 43
SP - 155
EP - 178
JO - GIScience and Remote Sensing
JF - GIScience and Remote Sensing
SN - 1548-1603
IS - 2
ER -