PRINCIPAL COMPONENT ANALYSIS OF STACKED MULTITEMPORAL IMAGES FOR THE MONITORING OF RAPID URBAN EXPANSION IN THE PEARL RIVER DELTA

The Pearl River Delta is experiencing very fast urban growth in recent years which has caused rapid loss of the valuable agricultural land i n this fertile region. There is a great need to monitor the rapid urba n expansion using remote sensing for urban planning and management pur poses. 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 sign atures. This paper presents a principal component analysis of stacked multi-temporal images method to reduce such errors. The study demonstr ates that this method can reduce errors in change detection using mult itemporal images and provide a very useful way in monitoring rapid lan d use changes and urban expansion in the Pearl River Delta and other p arts of the world.