Object- and pixel-based analysis for mapping crops and their agro-environmental associated measures using QuickBird imagery

被引:207
作者
Luisa Castillejo-Gonzalez, Isabel [1 ]
Lopez-Granados, Francisca [2 ]
Garcia-Ferrer, Alfonso [1 ]
Manuel Pena-Barragan, Jose [2 ]
Jurado-Exposito, Montserrat [2 ]
Sanchez de la Orden, Manuel [1 ]
Gonzalez-Audicana, Maria [3 ]
机构
[1] Univ Cordoba, Dept Cartog Engn Geodesy & Photogrammetry, E-14071 Cordoba, Spain
[2] CSIC, Inst Sustainable Agr, Cordoba 14080, Spain
[3] Univ Publ Navarra, Dept Projects & Rural Engn, Pamplona 31006, Spain
关键词
Agro-environmental measures; Conservation agriculture; Crop inventory; Multispectral and pan-sharpened imagery; Remote sensing; CLASSIFICATION; FUSION; SEGMENTATION; EXTRACTION; ACCURACY;
D O I
10.1016/j.compag.2009.06.004
中图分类号
S [农业科学];
学科分类号
09 ;
摘要
Currently, monitoring of agrarian policy actions usually requires ground visits to sample targeted farms, a time-consuming and very expensive procedure. To improve this, we have undertaken a study of the accuracy of five supervised classification methods (Parallelepiped, Minimum Distance, Mahalanobis Classifier Distance, Spectral Angle Mapper and Maximum Likelihood) using multispectral and pan-sharpened QuickBird imagery. We sought to verify whether remote sensing offers the ability to efficiently identify crops and agro-environmental measures in a typical agricultural Mediterranean area characterized by dry conditions. A segmentation of the satellite data was also used to evaluate pixel, object and pixel + object as minimum information units for classification. The results indicated that object- and pixel + object-based analyses clearly outperformed pixel-based analyses, yielding overall accuracies higher than 85% in most of the classifications and exhibiting the Maximum Likelihood of being the most accurate classifier. The accuracy for pan-sharpened image and object-based analysis indicated a 4% improvement in performance relative to multispectral data. (C) 2009 Elsevier B.V. All rights reserved.
引用
收藏
页码:207 / 215
页数:9
相关论文
共 34 条
[1]  
[Anonymous], 2002, DATA FUSION DEFINITI
[2]  
[Anonymous], BIOMETRICS
[3]  
Baatz M., 2000, ANGEW GEOGRAPHISCHE, P12
[4]   Predicting tillage practices and agricultural soil disturbance in north central Montana with Landsat imagery [J].
Bricklemyer, RS ;
Lawrence, RL ;
Miller, PR ;
Battogtokh, N .
AGRICULTURE ECOSYSTEMS & ENVIRONMENT, 2006, 114 (2-4) :210-216
[5]   Fusion of multispectral and panchromatic satellite images using the curvelet transform [J].
Choi, M ;
Kim, RY ;
Nam, MR ;
Kim, HO .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2005, 2 (02) :136-140
[6]   Object-based analysis of Ikonos-2 imagery for extraction of forest inventory parameters [J].
Chubey, MS ;
Franklin, SE ;
Wulder, MA .
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2006, 72 (04) :383-394
[7]   A REVIEW OF ASSESSING THE ACCURACY OF CLASSIFICATIONS OF REMOTELY SENSED DATA [J].
CONGALTON, RG .
REMOTE SENSING OF ENVIRONMENT, 1991, 37 (01) :35-46
[8]  
DAVIS CH, 2002, P 2002 IEEE INT GEOS, P2980
[9]  
*DEF AG, 2007, DEF PROF 5 0 ESS TRA
[10]  
DEFINENS AG, 2007, DEF DEV 7 REF BOOK