Land Use Classification using Support Vector Machine and Maximum Likelihood Algorithms by Landsat 5 TM Images

Nowadays, remote sensing images have been identified and exploited as the latest information to study land cover and land uses. These digital images are of significant importance, since they can present timely information, and capable of providing land use maps. The aim of this study is to create land use classification using a support vector machine (SVM) and maximum likelihood classifier (MLC) in Qazvin, Iran, by TM images of the Landsat 5 satellite. In the pre-processing stage, the necessary corrections were applied to the images. In order to evaluate the accuracy of the 2 algorithms, the overall accuracy and kappa coefficient were used. The evaluation results verified that the SVM algorithm with an overall accuracy of 86.67 % and a kappa coefficient of 0.82 has a higher accuracy than the MLC algorithm in land use mapping. Therefore, this algorithm has been suggested to be applied as an optimal classifier for extraction of land use maps due to its higher accuracy and better consistency within the study area. doi: 10.14456/WJST.2015.33

[1]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[3]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[4]  Arzu Erener,et al.  Classification method, spectral diversity, band combination and accuracy assessment evaluation for urban feature detection , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[5]  Patrick Hostert,et al.  Land cover mapping of large areas using chain classification of neighboring Landsat satellite images , 2009 .

[6]  Giles M. Foody,et al.  Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification , 2004 .

[7]  Dawei Han,et al.  Selection of classification techniques for land use - land cover change investigation , 2012 .

[8]  C. Tucker,et al.  NASA’s Global Orthorectified Landsat Data Set , 2004 .

[9]  Federico Girosi,et al.  Support Vector Machines: Training and Applications , 1997 .

[10]  Thomas Blaschke,et al.  Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[11]  D. Lu,et al.  Change detection techniques , 2004 .

[12]  Hamid Reza Moradi,et al.  COMPARISON OF DIFFERENT CLASSIFICATION ALGORITHMS IN SATELLITE IMAGERY TO PRODUCE LAND USE MAPS (CASE STUDY: NOOR CITY) , 2014 .

[13]  K. Balakrishna,et al.  LAND USE AND LAND COVER CHANGE DETECTION AND URBAN SPRAWL ANALYSIS OF VIJAYAWADA CITY USING MULTITEMPORAL LANDSAT DATA , 2012 .

[14]  L. Nykjaer,et al.  Analysis of sea surface temperature time series of the south-eastern North Atlantic , 2004 .

[15]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[16]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[17]  Barnali M. Dixon,et al.  Multispectral landuse classification using neural networks and support vector machines: one or the other, or both? , 2008 .

[18]  Dawei Han,et al.  Identification of Support Vector Machines for Runoff Modelling , 2004 .

[19]  ALIREZA MOGHADDAMNIA,et al.  Performance Evaluation of LLR , SVM , CGNN and BFGSNN Models to Evaporation Estimation , 2010 .

[20]  Dawei Han,et al.  Flood forecasting using support vector machines , 2007 .

[21]  Baharin Bin Ahmad,et al.  Comparison of two Classification methods (MLC and SVM) to extract land use and land cover in Johor Malaysia , 2014 .