Determining land-use information from land cover through an object-oriented classification of IKONOS imagery

The greater availability of remotely sensed high-resolution imagery and advances in object-oriented analysis have created more opportunities for automated urban land-use classifications. To date, few studies have attempted to classify land use from satellite imagery using object-oriented approaches, and those that have tend to rely on manual digitizing or ancillary data to delineate land-use polygon boundaries. This paper explores an object-oriented land-use classification using land-cover information derived from an IKONOS image to automatically delineate and classify the land-use polygons. The study area is in Mississauga (Ontario, Canada), a diverse urban setting. The first step was to classify land cover from the IKONOS image. This then served as the basis for creating a six-class and more detailed ten-class land-use map. The overall accuracies of the six-and ten-class maps were 90% and 86%, respectively. The high accuracies of individual classes suggest that the object-oriented methodology has great potential for efficiently classifying urban land use. The paper concludes with a discussion of the successes and remaining challenges of this type of work.