Browse > Article

A Rule-Based Image Classification Method for Analysis of Urban Development in the Capital Area  

Lee, Jin-A (과학기술연합대학원대학교 지리정보시스템공학)
Lee, Sung-Soon (한국지질자원연구원 국토지질연구본부)
Publication Information
Abstract
This study proposes a rule-based image classification method for the time-series analysis of changes in the land surface of the Seongnam-Yongin area using satellite-image data from 2000 to 2009. In order to identify the change patterns during each period, 11 classes were employed in accordance with statistical/mathematic rules. A generalized algorithm was used so that the rules could be applied to the unsupervised-classification method that does not establish any training sites. The results showed that the urban area of the object increased by 145% due to housing-site development. The image data from 2009 had a classification accuracy of 98%. For method verification, the results were compared to land-cover changes through Post-classification comparison. The maximum utilization of the available data within multiple images and the optimized classification allowed for an improvement in the classification accuracy. The proposed rule-based image-classification method is expected to be widely employed for the time-series analysis of images to produce a thematic map for urban development and to monitor urban development and environmental change.
Keywords
Remote Sensing; Rule-Based Classification; Unsupervised-Classification; Time Series Analysis; Landsat;
Citations & Related Records
연도 인용수 순위
  • Reference