科研之友
微信
新浪微博
Facebook
分享链接
摘要
We devised a semiautomatic approach for extracting lake features based on a customized set of normalized difference water index (NDWI) information which was obtained by incorporating high resolution, 8-band World View-2 data. An extensive accuracy assessment was carried out for three semiautomatic feature extraction approaches for extracting 36 lake features on Larsemann Hills, Antarctica. The method was tested on five existing PAN-sharpening algorithms, which suggest that the customized NDWI approach renders intermediate performance (root mean square error varies from similar to 227 to similar to 235 m(2)) and highest stability when compared with existing feature extraction techniques. In general, the customized NDWI rendered a least misclassification (approximate to 11 percent), followed by target detection (approximate to 16 percent) and spectral processing (7,4 7 percent) methods for extraction of 36 lakes. We also found that customized NDWI caused consistently least misclassification (approximate to 21 percent) than the target detection (approximate to 23 percent) and spectral processing (approximate to 30 percent) methods for extraction of partially snow or ice-covered 11 lakes. Our results indicate that the use of the customized NDWI approach and appropriate PAN-sharpening algorithm can greatly improve the semiautomatic extraction of lake features in cryospheric environment.
- 出版日期2014-10
