Principal component analysis of stacked multi-temporal images for the monitoring of rapid urban expansion in the Pearl River Delta

Abstract

The Pearl River Delta is experiencing very fast urban growth in recent years which has caused rapid loss of the valuable agricultural land in this fertile region. There is a great need to monitor the rapid urban expansion using remote sensing for urban planning and management purposes. However, it has been well recognized that there is significant over-estimation of land use change in using multi-temporal images for change detection because of inadequate creation of classification signatures. This paper presents a principal component analysis of stacked multi-temporal images method to reduce such errors. The study demonstrates that this method can reduce errors in change detection using multitemporal images and provide a very useful way in monitoring rapid land use changes and urban expansion in the Pearl River Delta and other parts of the world.