Land-Use/Land-Cover Change Detection Using Improved Change-Vector Analysis

Change-vector analysis (CVA) is a valuable technique for land-use/land-cover change detection. This article proposes a new method that can improve CVA. The improved method has two components: Double-Window Flexible Pace Search (DFPS), which aims at determining the threshold of change magnitude; and direction cosines of change vectors for determining change direction (category) that combines single-date image classification with a minimum-distance categorizing technique. The authors report on the use of the improved CVA for the detection of the land-use/land-cover changes in the Haidian District, Beijing, China. The authors conclude that good data quality (similar acquisition dates in different years and cloud-free) and image radiometric normalization have a strong impact on the final change-detection result, because the proposed method is based on an assumption of radiometric similarity among multi-temporal remotely sensed data. The experimental results indicate that the improved CVA has good potential in land-use/land-cover change detection, particularly when ancillary information for classification is only available for one date.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00991112
• Authors:
  • Chen, Jin
  • Gong, Peng
  • He, Chunyang
  • Pu, Ruiliang
  • Shi, Peijun
• Publication Date: 2003-4

Language

• English

Media Info

• Media Type: Print
• Features: Figures; Maps; References; Tables;
• Pagination: pp 369-379
• Serial:
  • Photogrammetric Engineering and Remote Sensing
  • Volume: 69
  • Issue Number: 4
  • Publisher: American Society for Photogrammetry and Remote Sensing
  • ISSN: 0099-1112

Subject/Index Terms

• TRT Terms: Case studies; Land use; Photogrammetry; Photointerpretation; Radiometric analysis
• Uncontrolled Terms: Change detection; Land cover
• Geographic Terms: Beijing (China)
• Subject Areas: Design; Highways; Planning and Forecasting; I21: Planning of Transport Infrastructure;

Filing Info

• Accession Number: 01001832
• Record Type: Publication
• Files: TRIS
• Created Date: Jul 14 2005 10:11AM