International Journal on Advanced Science, Engineering and Information Technology, Vol. 8 (2018) No. 3, DOI:10.18517/ijaseit.8.3.2415

Oil-Palm Plantation Identification from Satellite Images by using Google Earth Engine

Supattra Puttinaovarat, Paramate Horkaew

Abstract

Oil-palm plantation is a crucial determinant for land-use planning and agricultural studies. Remote sensing techniques haveelevated limitations of on-site survey as computerized imaging is much efficient and economical. This paper presents a ubiquitous application of Gabor analysis forextracting oil-palm plantation from satellite images. The proposed system was built onthe cloud based Google Earth Engine. Herein, THEOS images were convoluted with Gabor kernels, and their responses were then learned by both K-Means and SVMfor comparison. Experimental results showed that SVM could better identify the plantation areas with precision, recall and accuracy of 92.98%, 88.96% and 94.24%, respectively.

Keywords:

Oil-Palm Plantation; Texture Analysis; Gabor Wavelet; Google Earth Engine (GEE)

Viewed: 99 times (since Sept 4, 2017)

cite this paper