Surface Material Classification Using Landsat-8 OLI Image Acquired in Ulsan by the Different Machine Learning Techniques

Abstract:

Surface material classification is an important task for the preservation of land properties and the management of land development plans. The use of remotely sensed images is efficient for the surface material classification task without human access. This research aims to select the most appropriate machine learning technique for the surface material classification task using the remotely sensed images. In this research, the three different machine learning techniques (MD (Minimum Distance), MLC (Maximum Likelihood Classification), and SVM (Support Vector Machine)) were applied for surface material classification using the Landsat-8 OLI (Operational Land Imager) image acquired in Ulsan, South Korea, in the following steps. First, the training samples for each land cover in the given Landsat images were selected by manual labor. Next, the different machine learning techniques (MD, MLC, and SVM) were applied on the given Landsat images, respectively, for carrying out the surface material classification tasks. The accuracies of the three land cover classification maps generated by the different techniques were assessed using the ground truths. Finally, accuracy comparison was conducted for selecting the most suitable approach for classifying the various surface materials in Ulsan. The statistical results show that the SVM classifier is superior to the MD and MLC classifiers for carrying out surface material classification using the given Landsat-8 OLI image.

• Periodical: Applied Mechanics and Materials (Volume 865)
• Pages: 650-656
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.865.650
• Online since: June 2017
• Authors: Yun Jae Choung, Myung Hee Jo*
• Keywords: Landsat-8 OLI, Machine Learning, Maximum Likelihood, Minimum Distance, Support Vector Machine, Surface Material Classification

References

[1] Y. Choung and M. Jo, Shoreline change assessment for various types of coasts using multi-temporal Landsat imagery of the east coast of South Korea, Remot. Sens. Lett. 7 (2015) 91-100.

DOI: 10.1080/2150704x.2015.1109157

[2] J. F. Mas, Mapping land use/cover in a tropical coastal area using satellite sensor data, GIS and artificial neural networks, Estuarine, Coast. Shelf. Sci. 59 (2004) 219-230.

DOI: 10.1016/j.ecss.2003.08.011

[3] X. Yang and Z. Liu, Using satellite imagery and GIS for land-use and land-cover change mapping in an estuarine watershed, Int. J. Remot. Sens. 26 (2007) 5275-5296.

DOI: 10.1080/01431160500219224

[4] B. W. Szuster, Q. Chen and M. Borger, A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones, Appl. Geograph. 31 (2011) 525-532.

DOI: 10.1016/j.apgeog.2010.11.007

[5] X. Yang, L. Chen, Y. Li, W. Xi and L. Chen, Rule-based land use/land cover classification in coastal areas using seasonal remote sensing imagery: a case study from Lianyungang City, China, Envir. Monit. Assessm. 187 (2015) 449.

DOI: 10.1007/s10661-015-4667-3

[6] T. Acharya, I. Yang and D. Lee, Land Cover Classification Using a KOMPSAT-3A Multi-Spectral Satellite Image, Appl. Sci. 6(11) (2016) 1-11.

DOI: 10.3390/app6110371

[7] J. Jayanth, T. A. Kumar, S. Koliwad and S. Krishnashastry, Identification of land cover changes in the coastal area of Dakshina Kannada district, South India during the year 2004–2008, The Egyptian J. Remot. Sens. Space Sci. 19 (2016) 73-93.

DOI: 10.1016/j.ejrs.2015.09.001

[8] J. S. Park, W. H. Lee and M. H. Jo, Improving Accuracy of Land Cover Classification in River Basins using Landsat-8 OLI Image, Vegetation Index, and Water Index, J. Korean Assoc. Geograph. Inform. Stud. 19 (2016) 98-106.

DOI: 10.11108/kagis.2016.19.2.098

[9] J. R. Jensen, Remote Sensing of the Environment: An Earth Resource Perspective, second ed., Pearson, New Jersey, (2006).

[10] Landsat Missions, Available online: http: /landsat. usgs. gov/best_spectral_bands_to_use. php (Accessed on November 16, 2016).

[11] Classification, Available online: http: /www. harrisgeospatial. com/docs/Classification. html (Accessed on November 16, 2016).

[12] J. R. Jensen, Introductory Digital Image Processing: A Remote Sensing Perspective, fourth ed., Pearson, New Jersey, (2015).