SPATIAL COMPOSITION OF SPECTRAL CLASSES - A STRUCTURAL APPROACH FOR IMAGE-ANALYSIS OF HETEROGENEOUS LAND-USE AND LAND-COVER TYPES
Publication in refereed journal

香港中文大學研究人員

全文

引用次數

其它資訊
摘要Spectral classes generated from image classification are conventional output in land-use and land-cover (LU/LC) mapping with digital remotely sensed data. The spatial composition of these spectral classes within a certain spatial range, or window, can be useful information for image analysis. In this study, the concept of spatial composition of spectral classes (SCSC) was developed and examined. It was found that LU/LC types did exhibit different characteristics of SCSC. Ranges of SCSC were used for post-classification labeling to identify different LU/LC types. Results showed that a 7 by 7 window size was suitable for Hong Kong at Level-II classification.
著者FUNG T, CHAN KC
期刊名稱Photogrammetric Engineering and Remote Sensing
出版年份1994
月份2
日期1
卷號60
期次2
出版社AMER SOC PHOTOGRAMMETRY
頁次173 - 180
國際標準期刊號0099-1112
語言英式英語
Web of Science 學科類別Geography, Physical; GEOGRAPHY, PHYSICAL; Geology; Geosciences, Multidisciplinary; GEOSCIENCES, MULTIDISCIPLINARY; Imaging Science & Photographic Technology; IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY; Physical Geography; Remote Sensing; REMOTE SENSING

上次更新時間 2020-28-11 於 01:23