<![CDATA[This paper describes the detection of coconut trees using very-high-resolution optical satelliteimagery. The satellite imagery used in this study was a panchromatic band of Pleiades imagery with aspatial resolution of 0.5 metres. The authors proposed the use of a histogram of oriented gradients(HOG) algorithm as the feature extractor and a support vector machine (SVM) as the classifier for thisdetection. The main objective of this study is to find out the parameter combination for the HOGalgorithm that could provide the best performance for coconut-tree detection. The study shows that thebest parameter combination for the HOG algorithm is a configuration of 3 x 3 blocks, 9 orientation bins,and L2-norm block normalization. These parameters provide overall accuracy, precision and recall ofapproximately 80%, 73% and 87%, respectively.]]>
Copyrights © 2019
