{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:14:49Z","timestamp":1780377289419,"version":"3.54.1"},"reference-count":56,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2017,2,18]],"date-time":"2017-02-18T00:00:00Z","timestamp":1487376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2016M600392"],"award-info":[{"award-number":["2016M600392"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program B for Outstanding PhD Candidate of Nanjing University","award":["201502B008"],"award-info":[{"award-number":["201502B008"]}]},{"name":"Special Research Fund of the Ministry of Land and Resources for NonProfit Sector","award":["201411014-03"],"award-info":[{"award-number":["201411014-03"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41601497"],"award-info":[{"award-number":["41601497"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>The increased feature space available in object-based classification environments (e.g., extended spectral feature sets per object, shape properties, or textural features) has a high potential of improving classifications. However, the availability of a large number of derived features per segmented object can also lead to a time-consuming and subjective process of optimizing the feature subset. The objectives of this study are to evaluate the effect of the advanced feature selection methods of popular supervised classifiers (Support Vector Machines (SVM) and Random Forest (RF)) for the example of object-based mapping of an agricultural area using Unmanned Aerial Vehicle (UAV) imagery, in order to optimize their usage for object-based agriculture pattern recognition tasks. In this study, several advanced feature selection methods were divided into both types of classifiers (SVM and RF) to conduct further evaluations using five feature-importance-evaluation methods and three feature-subset-evaluation methods. A visualization method was used to measure the change pattern of mean classification accuracy with the increase of features used, and a two-tailed t-test was used to determine the difference between two population means for both repeated ten classification accuracies. This study mainly contribute to the uncertainty analysis of feature selection for object-based classification instead of the per-pixel method. The results highlight that the RF classifier is relatively insensitive to the number of input features, even for a small training set size, whereby a negative impact of feature set size on the classification accuracy of the SVM classifier was observed. Overall, the SVM Recursive Feature Elimination (SVM-RFE) seems to be an appropriate method for both groups of classifiers, while the Correlation-based Feature Selection (CFS) is the best feature-subset-evaluation method. Most importantly, this study verified that feature selection for both classifiers is crucial for the evolving field of Object-based Image Analysis (OBIA): It is highly advisable for feature selection to be performed before object-based classification, even though an adverse impact could sometimes be observed from the wrapper methods.<\/jats:p>","DOI":"10.3390\/ijgi6020051","type":"journal-article","created":{"date-parts":[[2017,2,20]],"date-time":"2017-02-20T11:07:24Z","timestamp":1487588844000},"page":"51","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":200,"title":["Evaluation of Feature Selection Methods for Object-Based Land Cover Mapping of Unmanned Aerial Vehicle Imagery Using Random Forest and Support Vector Machine Classifiers"],"prefix":"10.3390","volume":"6","author":[{"given":"Lei","family":"Ma","sequence":"first","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing 210023, China"},{"name":"Department of Geoinformatics\u2014Z_GIS, University of Salzburg, Hellbrunner Str. 34, A-5020 Salzburg, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengyu","family":"Fu","sequence":"additional","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1860-8458","authenticated-orcid":false,"given":"Thomas","family":"Blaschke","sequence":"additional","affiliation":[{"name":"Department of Geoinformatics\u2014Z_GIS, University of Salzburg, Hellbrunner Str. 34, A-5020 Salzburg, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manchun","family":"Li","sequence":"additional","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5473-3344","authenticated-orcid":false,"given":"Dirk","family":"Tiede","sequence":"additional","affiliation":[{"name":"Department of Geoinformatics\u2014Z_GIS, University of Salzburg, Hellbrunner Str. 34, A-5020 Salzburg, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenjin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxue","family":"Ma","sequence":"additional","affiliation":[{"name":"Urban and Resources Environmental College, Nanjing Second Normal University, Nanjing 210013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deliang","family":"Chen","sequence":"additional","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2017,2,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3514","DOI":"10.1109\/TGRS.2012.2224874","article-title":"A novel technique for optimal feature selection in attribute profiles based on genetic algorithms","volume":"51","author":"Pedergnana","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.3390\/rs3102263","article-title":"Machine learning comparison between worldview-2 and quickbird-2-simulated imagery regarding object-based urban land cover classification","volume":"3","author":"Novack","year":"2011","journal-title":"Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.isprsjprs.2012.01.005","article-title":"Oil spill feature selection and classification using decision tree forest on SAR image data","volume":"68","author":"Topouzelis","year":"2012","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1109\/TGRS.2004.831865","article-title":"Classification of hyperspectral remote sensing images with support vector machines","volume":"42","author":"Melgani","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2297","DOI":"10.1109\/TGRS.2009.2039484","article-title":"Feature selection for classification of hyperspectral data by SVM","volume":"48","author":"Pal","year":"2010","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","article-title":"A survey on object detection in optical remote sensing images","volume":"117","author":"Cheng","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_7","first-page":"70","article-title":"A comparison of three feature selection methods for object-based classification of sub-decimeter resolution ultracam-l imagery","volume":"15","author":"Laliberte","year":"2012","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.isprsjprs.2013.09.014","article-title":"Geographic object-based image analysis\u2014Towards a new paradigm","volume":"87","author":"Blaschke","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.isprsjprs.2014.12.026","article-title":"Training set size, scale, and features in geographic object-based image analysis of very high resolution unmanned aerial vehicle imagery","volume":"102","author":"Ma","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4502","DOI":"10.1080\/01431161.2011.649864","article-title":"Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests","volume":"33","author":"Duro","year":"2012","journal-title":"Int. J. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2564","DOI":"10.1016\/j.rse.2011.05.013","article-title":"Object-oriented mapping of landslides using random forests","volume":"115","author":"Stumpf","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_12","first-page":"235","article-title":"Object-oriented mapping of urban trees using random forest classifiers","volume":"26","author":"Puissant","year":"2014","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_13","unstructured":"Han, J., Pei, J., and Kamber, M. (2011). Data Mining: Concepts and Techniques, Elsevier."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"383","DOI":"10.14358\/PERS.72.4.383","article-title":"Object-based analysis of Ikonos-2 imagery for extraction of forest inventory parameters","volume":"72","author":"Chubey","year":"2006","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1109\/TGRS.2008.2009355","article-title":"Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle (UAV) imagery","volume":"47","author":"Laliberte","year":"2009","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1016\/j.rse.2012.04.011","article-title":"Object based image analysis and data mining applied to a remotely sensed landsat time-series to map sugarcane over large areas","volume":"123","author":"Vieira","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1016\/j.rse.2011.01.009","article-title":"Object-based crop identification using multiple vegetation indices, textural features and crop phenology","volume":"115","author":"Ngugi","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"799","DOI":"10.14358\/PERS.72.7.799","article-title":"Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery","volume":"72","author":"Yu","year":"2006","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_19","first-page":"87","article-title":"A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments","volume":"49","author":"Li","year":"2016","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2895","DOI":"10.1080\/01431160500185227","article-title":"Some issues in the classification of dais hyperspectral data","volume":"27","author":"Pal","year":"2006","journal-title":"Int. J. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1016\/j.rse.2007.03.020","article-title":"Feature selection by genetic algorithms in object-based classification of IKONOS imagery for forest mapping in flanders, Belgium","volume":"110","author":"Verbeke","year":"2007","journal-title":"Remote Sens. Environ."},{"key":"ref_22","first-page":"668","article-title":"Feature selection for SVMS","volume":"13","author":"Weston","year":"2000","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach. Learn."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.rse.2011.11.020","article-title":"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","volume":"118","author":"Duro","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1117\/1.JRS.8.083673","article-title":"Cultivated land information extraction from high-resolution unmanned aerial vehicle imagery data","volume":"8","author":"Ma","year":"2014","journal-title":"J. Appl. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Pe\u00f1a, J.M., Torres-S\u00e1nchez, J., de Castro, A.I., Kelly, M., and L\u00f3pez-Granados, F. (2013). Weed mapping in early-season maize fields using object-based analysis of unmanned aerial vehicle (UAV) images. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0077151"},{"key":"ref_27","unstructured":"Ma, L., Wang, Y., Li, M., Tong, L., and Cheng, L. (2013, January 26\u201328). Using high-resolution imagery acquired with an autonomous unmanned aerial vehicle for urban construction and planning. Proceedings of the International Conference on Remote Sensing, Environment and Transportation Engineering, Najing, China."},{"key":"ref_28","first-page":"12","article-title":"Multiresolution segmentation: An optimization approach for high quality multi-scale image segmentation","volume":"Volume 58","author":"Strobl","year":"2000","journal-title":"Angewandte Geographische Informationsverarbeitung XII"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","article-title":"The weka data mining software: An update","volume":"11","author":"Hall","year":"2009","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_30","unstructured":"Zhao, Z., Morstatter, F., Sharma, S., Alelyani, S., Anand, A., and Liu, H. (2007). Advancing Feature Selection Research: Asu Feature Selection Repository, School of Computing, Informatics, and Decision Systems Engineering, Arizona State University. TR-10-007."},{"key":"ref_31","unstructured":"Liu, H., and Setiono, R. (1995, January 29\u201331). Chi2: Feature selection and discretization of numeric attributes. Proceedings of the Seventh IEEE International Conference on Tools with Artificial Intelligence, Herndon, VA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Gilad-Bachrach, R., Navot, A., and Tishby, N. (2004, January 4\u20138). Margin based feature selection-theory and algorithms. Proceedings of the Twenty-First International Conference on Machine Learning, Banff, AB, Canada.","DOI":"10.1145\/1015330.1015352"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1023\/A:1025667309714","article-title":"Theoretical and empirical analysis of relieff and rrelieff","volume":"53","author":"Kononenko","year":"2003","journal-title":"Mach. Learn."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1016\/j.patcog.2010.08.011","article-title":"Mining data with random forests: A survey and results of new tests","volume":"44","author":"Verikas","year":"2011","journal-title":"Pattern Recogn."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1109\/TKDE.2003.1245283","article-title":"Benchmarking attribute selection techniques for discrete class data mining","volume":"15","author":"Hall","year":"2003","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1142\/S0219720006001941","article-title":"Choosing SNPS using feature selection","volume":"4","author":"Phuong","year":"2006","journal-title":"J. Bioinf. Comput. Biol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/S0004-3702(97)00043-X","article-title":"Wrappers for feature subset selection","volume":"97","author":"Kohavi","year":"1997","journal-title":"Artif. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.1016\/j.ins.2009.02.014","article-title":"A wrapper method for feature selection using support vector machines","volume":"179","author":"Maldonado","year":"2009","journal-title":"Inf. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1089\/cmb.2008.0037","article-title":"Use of wrapper algorithms coupled with a random forests classifier for variable selection in large-scale genomic association studies","volume":"16","author":"Rodin","year":"2009","journal-title":"J. Comput. Biol."},{"key":"ref_40","unstructured":"Platt, J.C. (1999). Advances in Kernel Methods: Support Vector Learning, MIT Press."},{"key":"ref_41","first-page":"117","article-title":"Area-based and location-based validation of classified image objects","volume":"28","author":"Whiteside","year":"2014","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"2492","DOI":"10.1109\/JSTARS.2013.2253089","article-title":"Optimization of object-based image analysis with random forests for land cover mapping","volume":"6","author":"Stefanski","year":"2013","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1080\/01431160412331269698","article-title":"Random forest classifier for remote sensing classification","volume":"26","author":"Pal","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.isprsjprs.2011.11.002","article-title":"An assessment of the effectiveness of a random forest classifier for land-cover classification","volume":"67","author":"Ghimire","year":"2012","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.isprsjprs.2014.10.002","article-title":"Multi-class geospatial object detection and geographic image classification based on collection of part detectors","volume":"98","author":"Cheng","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.isprsjprs.2010.11.001","article-title":"Support vector machines in remote sensing: A review","volume":"66","author":"Mountrakis","year":"2011","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_47","first-page":"27","article-title":"LIBSVM: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.isprsjprs.2012.04.001","article-title":"Comparison of support vector machine, neural network, and cart algorithms for the land-cover classification using limited training data points","volume":"70","author":"Shao","year":"2012","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_49","first-page":"298","article-title":"A comparison of selected classification algorithms for mapping bamboo patches in lower gangetic plains using very high resolution worldview 2 imagery","volume":"26","author":"Ghosh","year":"2014","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.rse.2014.07.028","article-title":"Importance of sample size, data type and prediction method for remote sensing-based estimations of aboveground forest biomass","volume":"154","author":"Fassnacht","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"2912","DOI":"10.3390\/rs6042912","article-title":"Performance evaluation of machine learning algorithms for urban pattern recognition from multi-spectral satellite images","volume":"6","author":"Wieland","year":"2014","journal-title":"Remote Sens."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2999","DOI":"10.1016\/j.rse.2008.02.011","article-title":"Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery","volume":"112","author":"Chan","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/TGRS.2012.2202912","article-title":"An svm ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery","volume":"51","author":"Huang","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"4238","DOI":"10.1109\/TGRS.2015.2393857","article-title":"Effective and efficient midlevel visual elements-oriented land-use classification using VHR remote sensing images","volume":"53","author":"Cheng","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"13440","DOI":"10.3390\/rs71013440","article-title":"Response to johnson ba scale issues related to the accuracy assessment of land use\/land cover maps produced using multi-resolution data: Comments on \u201cthe improvement of land cover classification by thermal remote sensing\u201d","volume":"7","author":"Sun","year":"2015","journal-title":"Remote Sens."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"13436","DOI":"10.3390\/rs71013436","article-title":"Scale issues related to the accuracy assessment of land use\/land cover maps produced using multi-resolution data: Comments on \u201cthe improvement of land cover classification by thermal remote sensing\u201d","volume":"7","author":"Johnson","year":"2015","journal-title":"Remote Sens."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/6\/2\/51\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:28:34Z","timestamp":1760207314000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/6\/2\/51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,18]]},"references-count":56,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2017,2]]}},"alternative-id":["ijgi6020051"],"URL":"https:\/\/doi.org\/10.3390\/ijgi6020051","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,18]]}}}