شماره ركورد كنفرانس :
4001
عنوان مقاله :
COMPARISON OF SVM AND RF ALGORITHMS FOR CROP MAPPING USING MULTI-TIME OPTICAL AND RADAR DATA WITH LIMITED TRAINING SAMPLES
پديدآورندگان :
Khosravi I iman.khosravi@ut.ac.ir University of Tehran , Niazmardi S s.niazmardi@ut.ac.ir University of Tehran , Hamidi M m.hamidi@ut.ac.ir University of Tehran , Safari A asafari@ut.ac.ir University of Tehran , Homayouni S. Department of Geography, Environment, and Geomatics, University of Ottawa, Ottawa, Canada
كليدواژه :
Support Vector Machine , Random Forest , Crop Mapping , Multi , Time , Optical Image , Radar Image
عنوان كنفرانس :
دومين همايش بين المللي پژوهش هاي اطلاعات مكاني و چهارمين همايش بين المللي سنجنده ها و مدل ها در فتوگرامتري و سنجش از دور و ششمين همايش بين المللي مشاهدات زميني در تغييرات محيطي
چكيده فارسي :
This paper aims to compare two state-of-the-art classification algorithms, namely Support Vector Machine (SVM) and Random Forest (RF) algorithms, in terms of accuracy and running time, in order to crop mapping from multi-temporal optical and radar images with limited training samples. The optical data are RapiEye images and the radar data are UAVSAR images. The case study is an agricultural area near Winnipeg, Manitoba, Canada. From each RapidEye image, 38 optical features, and from each UAVSAR image, 49 radar features were extracted. The results indicated RF was more efficient in the classification of radar features, while SVM was more efficient in the classification of optical and stacked features. Furthermore, regarding running time, RF was much faster than SVM in all scenarios.
