Object-Oriented Image Analysis

Creating land-cover and land-use maps for urban areas has always been challenging due to the complexity of an urban landscape. The greater availability of remotely sensed high-resolution imagery and recent advances in object-oriented analysis allow for more detail than ever before in urban image classification. This book explores object-oriented land-cover and land-use classifications with one-meter resolution Ikonos imagery. First, three different ways of classifying land cover, with varying inclusion of ancillary building and road data, are examined. Second, the spatial relations of the land-cover information are examined to derive land use. Accuracy assessments, as well as statistical and visual evaluations, for the classifications show that the object-oriented approach works well for classifying an urban area. The results confirm the observed trend in the literature to move away from traditional pixel-based techniques for urban image classification in exchange for object-oriented methods. This book will be useful to those who want to develop new ways of efficiently classifying complex urban areas, using object-oriented image classification techniques.

Autorentext

Mike Lackner, MSc.: Studied Geography with emphasis on remote sensing and GIS at the University of Toronto, Ontario, and before at Portland State University, Portland, Oregon. Worked as a remote-sensing/GIS technician for Space Imaging (now Sanborn) in Portland, Oregon. Currently works on several projects at the University of Toronto.