Landscape and Ecological Engineering

, Volume 9, Issue 2, pp 239–247

Object-oriented image analysis to extract landscape elements in urban fringes, Central Japan

  • Kazuyuki Takahashi
  • Noritoshi Kamagata
  • Keitarou Hara
Original Paper

DOI: 10.1007/s11355-012-0202-7

Cite this article as:
Takahashi, K., Kamagata, N. & Hara, K. Landscape Ecol Eng (2013) 9: 239. doi:10.1007/s11355-012-0202-7

Abstract

A method enabling the object-oriented image analysis of landscape elements incorporating topographic data was designed and tested on a Japanese countryside target area. IKONOS data (four multispectral bands with a spatial resolution of 4 m and a panchromatic band with a spatial resolution of 1 m) acquired on 23 April 2001 were used. Definiens v.5 software (Definiens AG, München, Germany) was employed for the classification. The initial segmentation was multiresolution and bottom-up, and each segment identified was considered to be one object. Two classifications employing the same landscape elements and ground truth data were implemented. One classification adopted an object-based image analysis classification method based on spectral characteristics; the other utilized an object-oriented image analysis (OOIA) that allows for a suitable scale parameter to be selected independently for each landscape element. In addition, topographic data derived from field surveys (walking surveys) and topographic maps were used to create a topographic database delineating the boundary between valley bottoms and the adjacent slopes (elevation: about 10 m). These data were then integrated into the OOIA analysis. The accuracies of the two classifications were assessed by comparing the results to a master landscape map produced directly from aerial photographs and on-site observations. The object-oriented method using the topographic data resulted in a higher overall kappa coefficients (0.63–0.47) than the object-based method. These results indicate that object-oriented image analysis of very high resolution data used in combination with topographic data can be an effective tool for landscape classification in Japan, where historical land-use patterns have resulted in finely dissected landscapes.

Keywords

Landscape classification Topographic data Japanese countryside IKONOS VHR satellite data 

Copyright information

© International Consortium of Landscape and Ecological Engineering and Springer Japan 2012

Authors and Affiliations

  • Kazuyuki Takahashi
    • 1
  • Noritoshi Kamagata
    • 2
  • Keitarou Hara
    • 3
  1. 1.Graduate School of InformaticsTokyo University of Information SciencesChibaJapan
  2. 2.Kokusai Kogyo Co. LtdFuchuJapan
  3. 3.Department of Environmental InformationTokyo University of Information SciencesChibaJapan

Personalised recommendations