A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery

被引:729
作者
Duro, Dennis C. [1 ]
Franklin, Steven E. [1 ,2 ]
Dube, Monique G. [3 ]
机构
[1] Univ Saskatchewan, Sch Environm & Sustainabil, Saskatoon, SK S7N 5C8, Canada
[2] Trent Univ, Environm & Resource Studies Geog Dept, Peterborough, ON K9J 7B8, Canada
[3] Total E&P Canada Ltd, Sustainabil Div, Calgary, AB T2P 4H4, Canada
关键词
Comparison; Object-based; Decision tree; Random forest; Support vector machine; LAND-COVER CLASSIFICATION; SUPPORT VECTOR MACHINES; RANDOM FOREST; SCALE PARAMETER; IKONOS IMAGERY; DECISION TREES; SEGMENTATION; MULTIRESOLUTION; CLASSIFIERS; AGREEMENT;
D O I
10.1016/j.rse.2011.11.020
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Pixel-based and object-based image analysis approaches for classifying broad land cover classes over agricultural landscapes are compared using three supervised machine learning algorithms: decision tree (DT), random forest (RF), and the support vector machine (SVM). Overall classification accuracies between pixel-based and object-based classifications were not statistically significant (p > 0.05) when the same machine learning algorithms were applied. Using object-based image analysis, there was a statistically significant difference in classification accuracy between maps produced using the DT algorithm compared to maps produced using either RF (p = 0.0116) or SVM algorithms (p = 0.0067). Using pixel-based image analysis. there was no statistically significant difference (p > 0.05) between results produced using different classification algorithms. Classifications based on RF and SVM algorithms provided a more visually adequate depiction of wetland, riparian, and crop land cover types when compared to DT based classifications, using either object-based or pixel-based image analysis. In this study, pixel-based classifications utilized fewer variables (15 vs. 300), achieved similar classification accuracies, and required less time to produce than object-based classifications. Object-based classifications produced a visually appealing generalized appearance of land cover classes. Based exclusively on overall accuracy reports, there was no advantage to preferring one image analysis approach over another for the purposes of mapping broad land cover types in agricultural environments using medium spatial resolution earth observation imagery. (C) 2011 Elsevier Inc. All rights reserved.
引用
收藏
页码:259 / 272
页数:14
相关论文
共 79 条
[51]   Object-based classification of ikonos imagery for mapping large-scale vegetation communities in urban areas [J].
Mathieu, Renaud ;
Aryal, Jagannath ;
Chong, Albert K. .
SENSORS, 2007, 7 (11) :2860-2880
[52]   Comparing correlated kappas by resampling: Is one level of agreement significantly different from another? [J].
McKenzie, DP ;
Mackinnon, AJ ;
Peladeau, N ;
Onghena, P ;
Bruce, PC ;
Clarke, DM ;
Harrigan, S ;
McGorry, PD .
JOURNAL OF PSYCHIATRIC RESEARCH, 1996, 30 (06) :483-492
[53]  
Morissette J. T., 1998, PHOTOGRAMMETRIC ENG, V64
[54]   Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery [J].
Myint, Soe W. ;
Gober, Patricia ;
Brazel, Anthony ;
Grossman-Clarke, Susanne ;
Weng, Qihao .
REMOTE SENSING OF ENVIRONMENT, 2011, 115 (05) :1145-1161
[55]   The ecology of interfaces: Riparian zones [J].
Naiman, RJ ;
Decamps, H .
ANNUAL REVIEW OF ECOLOGY AND SYSTEMATICS, 1997, 28 :621-658
[56]  
Noble B., 2008, Impact Assessment and Project Appraisal, V26, P78, DOI DOI 10.3152/146155108X316405
[57]   Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms [J].
Otukei, J. R. ;
Blaschke, T. .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2010, 12 :S27-S31
[58]   Random forest classifier for remote sensing classification [J].
Pal, M .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2005, 26 (01) :217-222
[59]   Geomorphometry - diversity in quantitative surface analysis [J].
Pike, RJ .
PROGRESS IN PHYSICAL GEOGRAPHY-EARTH AND ENVIRONMENT, 2000, 24 (01) :1-20
[60]   An evaluation of an object-oriented paradigm for land use/land cover classification [J].
Platt, Rutherford V. ;
Rapoza, Lauren .
PROFESSIONAL GEOGRAPHER, 2008, 60 (01) :87-100