• Cem Ünsalan
  • Kim L. Boyer
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)


Cities are evolving and districts are changing their characteristics faster than ever before. Although the evolution is slow in the central parts of most cities, it is typically fairly fast in outlying regions. Yesterday’s forested or rural regions around the city become tomorrow’s residential regions (These observations are especially valid in North America). These changes cause many problems for policy makers and government agencies. They affect the public and private utility networks. Maps become less reliable around these regions. As a result, emergency plans based on these maps become unreliable. In this book, we propose an automated multispectral satellite image understanding system on Ikonos images. Our system has modules on land use classification, residential region detection, house and street network extraction. In developing automated methods for each part of the system, we extensively benefit from novel or existing computer vision and pattern recognition techniques. These techniques can also be used in future more advanced automated systems. In the following paragraphs, we provide a brief introduction to each part of our system. Then, we explore each method as well as related concepts in detail in the following chapters.


Normalize Difference Vegetation Index Satellite Image Street Network Vegetation Index Pattern Recognition Technique 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    G. Konecny, J. Schiewe, ISPRS J. Photogramm. Remote Sens.51, 173 (1996) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  1. 1.Electrical and Electronics EngineeringYeditepe UniversityKayisdagiTurkey
  2. 2.Dept. Electrical, Comp. & Systems Eng.Rensselaer Polytechnic InstituteTroyUSA

Personalised recommendations