Časopis Saveza udruženja građana geodetske struke u Bosni i Hercegovini

Journal of the Union of Associations of Geodetic Professionals in Bosnia and Herzegovina

Prvi štampani broj časopisa objavljen je 1967. godine. Elektronsko izdanje časopisa objavljuje se na internetu od 2011. godine.

 

The first printed issue of the journal was published in 1967. Electronic edition of the journal is published on the internet since 2011.

GEODETSKI GLASNIK
UDK 528  /  ISSN: 1512-6102  /  ISSN 2233-1786 Online
POČETNA / HOME

O ČASOPISU / ABOUT THE JOURNAL

AKTUELNI BROJ / CURRENT ISSUE

ARHIVA / ARCHIVE

IMPRESUM / IMPRESSUM

UPUTSTVO ZA AUTORE / GUIDELINES FOR AUTHORS

 

GEODETSKI GLASNIK Volume 51 Issue 48 (December 2017)

 

SADRŽAJ CONTENTS
 

 

 

Author(s):

Mustafa Ustuner

Department of Geomatic Engineering, Yildiz Technical University

Istanbul, Turkey

E-mail adress: mustuner@yildiz.edu.tr

 

Fusun Balik Sanli

Department of Geomatic Engineering, Yildiz Technical University

Istanbul, Turkey

E-mail adress: fbalikr@yildiz.edu.tr

 

 

EVALUATING TRAINING DATA FOR CROP TYPE CLASSIFICATION USING SUPPORT VECTOR MACHINES AND RANDOM FORESTS

 

Mustafa Ustuner, Fusun Balik Sanli

 

 

Abstract:

This study evaluated the effectiveness of three different training datasets for crop type classification using both support vector machines (SVMs) and random forests (RFs). In supervised classification, one of the main facing challanges is to define the training set for the full representation of land use/cover classes. The adaptation of traning data, with the implemented classifier and its characteristics (purity, size and distribution of sample pixels), are of key importance in this context. The experimental results were compared in terms of the classification accuracy with 10-fold cross validation. Results suggest that higher classification accuracies were obtained by less number of training samples. Furthermore, it is highlighted that both methods (SVMs and RFs) are proven to be the effective and powerful classifiers for crop type classification.

 

Keywords:

training data, crop type classification, support vector machines, random forests, machine learning.

 

References:

  1. Blackbridge (2013). Satellite Imagery Product Specifications. [Brochure]. Retrieved from https://resa.blackbridge.com/files/2014-06/RE_Product_Specifications_ENG.pdf  

  2. Foody, G. M., Mathur, A. (2004). Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sensing of Environment, 93(1), 107-117. doi: https://doi.org/10.1016/j.rse.2004.06.017 

  3. Foody, G. M., Mathur, A. (2006). The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM. Remote Sensing of Environment, 103(2), 179-189. doi: http://dx.doi.org/10.1016/j.rse.2006.04.001

  4. Foody, G. M., Mathur, A., Sanchez-Hernandez, C., Boyd, D. S. (2006). Training set size requirements for the classification of a specific class. Remote Sensing of Environment, 104(1), 1-14. doi: https://doi.org/10.1016/j.rse.2006.03.004 

  5. Ghamisi, P., Plaza, J., Chen, Y., Li, J., Plaza, A. J. (2017). Advanced Spectral Classifiers for Hyperspectral Images: A review. IEEE Geoscience and Remote Sensing Magazine, 5(1), 8-32. doi: https://doi.org/10.1109/mgrs.2016.2616418    

  6. Gislason, P. O., Benediktsson, J. A., Sveinsson, J. R. (2006). Random Forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300. doi: https://doi.org/10.1016/j.patrec.2005.08.011 

  7. Huang, C., Davis, L. S., Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4), 725-749. doi: 10.1080/01431160110040323 

  8. Kavzoglu, T. (2009). Increasing the accuracy of neural network classification using refined training data. Environmental Modelling & Software, 24(7), 850-858. doi: http://dx.doi.org/10.1016/j.envsoft.2008.11.012 

  9. Kavzoglu, T., Mather, P. M. (2003). The use of backpropagating artificial neural networks in land cover classification. International Journal of Remote Sensing, 24(23), 4907-4938. doi: 10.1080/0143116031000114851 

  10. Lu, D., Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28(5), 823-870. doi: 10.1080/01431160600746456 

  11. Mather, P. M., Koch, M. (2011). Classification. In Computer Processing of Remotely-Sensed Images (pp. 229-284). Chichester: John Wiley & Sons, Ltd. 

  12. Melgani, F., Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(8), 1778-1790. doi: 10.1109/tgrs.2004.831865 

  13. Pal, M., Mather, P. M. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86(4), 554-565. doi: https://doi.org/10.1016/S0034-4257(03)00132-9 

  14. Papa, J. P., Amorim, W. P., Falcão, A. X., Tavares, J. M. R. S. (2016). Recent Advances On Optimum-Path Forest For Data Classification: Supervised, Semi-Supervised, And Unsupervised Learning. In C. H. Chen (ed.), Handbook of Pattern Recognition and Computer Vision, 5th ed. (pp. 109-123). Singapore: World Scientific. 

  15. Waske, B., Benediktsson, J., Sveinsson, J. (2012). Random Forest Classification of Remote Sensing Data. In C. H. Chen (ed.), Signal and Image Processing for Remote Sensing, Second Edition (pp. 365-374). Boca Raton: CRC Press.

 

UDK 528.8:83:85

 

Article Type:

Professional article

 

pp. 125-133

 

Full text: