Correlation Rules and Ontologies Acquisition in Knowledge Extraction of Image

摘要

After quantization and classification of the deviations between TM and ETM+ images based on approved thresholds, a correlation analysis method for the compared calibration is suggested in this paper. Four time points of raster data for 15 years of the highest group of land surface temperature and the lowest group of vegetation of the Kunsan city, are observed and analyzed their correlations for the change detection of urban land cover. This experiment detected strong and proportional correlation relationship between the highest group of land surface temperature and the lowest group of vegetation index which exceeded R=(+)0.9478, so the proposed correlation analysis model between land surface temperature and vegetation will be able to give proof an effective suitability to the land cover change detection and monitoring.