A comparison between different pixel-based classification methods over urban area using very high resolution data

• Published in: American Society for Photogrammetry and Remote Sensing Annual Conference 2012, ASPRS 2012
• Main Author: Taherzadeh E.; Shafri H.Z.M.; Soltani S.H.K.; Mansor S.; Ashurov R.
• Format: Conference paper
• Language: English
• Published: 2012
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84873500391&partnerID=40&md5=86d83791f43d30afe141f07d41e01270

Cities are centers of human activity and more than half of the world's population live in metropolitan areas. Urban areas are characterized by a large variety of artificial and natural surface materials influencing ecological, climatic and energetic conditions. With advent of new sensors in remote sensing fields that capture the data in high spatial and spectral resolution we are able to classify the urban area accurately. The main goal of this study is, comparison between different pixels based classification methods such as Maximum likelihood, Minimum distance, spectral angel mapper and Support Vector Machine (SVM).Thus to apply these methods we use pansharpening image of worldview 2 from Kuala Lumpur, Malaysia with 0.6 meter spatial resolution and 8 spectral bands. The results show that SVM method more accurate than other methods in classify the urban area with 72% overall accuracy with Kappa coefficient 0.65.However the very high resolution data shows the good potential for classify the urban area but still some limitations exist such as, misclassification between some urban classes such as road and some roof materials, exist of shadows that leads to misclassification of some classes, displacement of high rise building and dense trees and their shadow overlapping the nearby urban features make the mapping more difficult. Presently, we do not have effective and reliable solution to this problem without using additional data. However using pixel based classification method such as SVM is very useful for classify the urban area especially for detection the impervious surface but to avoid the limitations that mentioned above we should use also some spatial and texture information to improve the classification accuracy.