testing multivariate adaptive regression splines (mars) as a method of land cover classification of terra-aster satellite images测试多元自适应回归样条函数(火星)作为terra-aster卫星图像的土地覆盖分类的方法.pdfVIP

Sensors 2009, 9, 9011-9028; doi:10.3390/ OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Testing Multivariate Adaptive Regression Splines (MARS) as a Method of Land Cover Classification of TERRA-ASTER Satellite Images Elia Quirós, Ángel M. Felicísimo and Aurora Cuartero * Polytechnic School, University of Extremadura, 10071 Cáceres, Spain; E-Mails: equiros@unex.es (E.Q.); amfeli@unex.es (A.M.F.) * Author to whom correspondence should be addressed; E-Mail: acuartero@unex.es; Tel.: +34-927257195; Fax: +34-927257324. Received: 24 September 2009; in revised form: 1 November 2009 / Accepted: 2 November 2009 / Published: 13 November 2009 Abstract: This work proposes a new method to classify multi-spectral satellite images based on multivariate adaptive regression splines (MARS) and compares this classification system with the more common parallelepiped and maximum likelihood (ML) methods. We apply the classification methods to the land cover classification of a test zone located in southwestern Spain. The basis of the MARS method and its associated procedures are explained in detail, and the area under the ROC curve (AUC) is compared for the three methods. The results show that the MARS method provides better results than the parallelepiped method in all cases, and it provides better results than the maximum likelihood method in 13 cases out of 17. These results demonstr