Support Vector Machine Accuracy Assessment for Extracting Green Urban Areas in Towns

被引：48

作者：

Kranjcic, Nikola ^{[1
]}

Medak, Damir ^{[2
]}

Zupan, Robert ^{[2
]}

Rezo, Milan ^{[1
]}

机构：

[1] Univ Zagreb, Fac Geotech Engn, Hallerova Aleja 7, Varazhdin 42000, Croatia

[2] Univ Zagreb, Fac Geodesy, Kaciceva 26, Zagreb 10000, Croatia

来源：

REMOTE SENSING | 2019年 / 11卷 / 06期

关键词：

machine learning; support vector machine; kernels; green urban areas extraction; satellite images; CLASSIFICATION;

D O I：

10.3390/rs11060655

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

The most commonly used model for analyzing satellite imagery is the Support Vector Machine (SVM). Since there are a large number of possible variables for use in SVM, this paper will provide a combination of parameters that fit best for extracting green urban areas from Copernicus mission satellite images. This paper aims to provide a combination of parameters to extract green urban areas with the highest degree of accuracy, in order to speed up urban planning and ultimately improve town environments. Two different towns in Croatia were investigated, and the results provide an optimal combination of parameters for green urban areas extraction with an overall kappa index of 0.87 and 0.89, which demonstrates a very high classification accuracy.

引用

页数：13

共 35 条

[1]

Agency E.E., 2000, CORINE LAND COVERTEC

[2]

Bird W, 2007, BRIT J GEN PRACT, V57, P69

[3] LIBSVM: A Library for Support Vector Machines [J].

Chang, Chih-Chung ;

Lin, Chih-Jen .

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)

[4]

Cherkassky V, 1997, IEEE Trans Neural Netw, V8, P1564, DOI 10.1109/TNN.1997.641482

[5]

Colin Campbell, 2011, Synth. Lect. Artif. Intell. Mach. Learn., V5, P1

[6]

Congedo L., 2016, SEMIAUTOMATIC CLASSI, DOI [10.13140/RG.2.2.29474.02242/1, DOI 10.13140/RG.2.2.29474.02242/1, 10. 13140/RG.2.2.29474.02242/1]

[7] Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information [J].

Cracknell, Matthew J. ;

Reading, Anya M. .

COMPUTERS & GEOSCIENCES, 2014, 63 :22-33

[8] Hyperspectral image classification using relevance vector machines [J].

Demir, Beguem ;

Erturk, Sarp .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2007, 4 (04) :586-590

[9] Mapping Urban Green Infrastructure: A Novel Landscape-Based Approach to Incorporating Land Use and Land Cover in the Mapping of Human-Dominated Systems [J].

Dennis, Matthew ;

Barlow, David ;

Cavan, Gina ;

Cook, Penny A. ;

Gilchrist, Anna ;

Handley, John ;

James, Philip ;

Thompson, Jessica ;

Tzoulas, Konstantinos ;

Wheater, C. Philip ;

Lindley, Sarah .

LAND, 2018, 7 (01)

[10] Assessing canopy mortality during a mountain pine beetle outbreak using GeoEye-1 high spatial resolution satellite data [J].

Dennison, Philip E. ;

Brunelle, Andrea R. ;

Carter, Vachel A. .

REMOTE SENSING OF ENVIRONMENT, 2010, 114 (11) :2431-2435

← 1 2 3 4 →