Quantitative Performance of Spectral Indices in Large Scale Plant Health Analysis

Abstract

Problem statement: Oil palm trees are planted in large scale areas. The detection and mapping of diseases are considered as important for oil palm industry and need a timely detection to control the disease spread. Approach: Vegetation analysis of airborne hyperspectral imagery could be an ideal method to deal with this problem since this data could be acquired on user demand. Airborne hyperspectral dataset was preprocessed in order to prepare it for the vegetation analysis processing for the purpose of detection and mapping Ganoderma disease in oil palm trees. Many vegetation indices were tested and analyzed to classify oil palm trees into healthy and unhealthy trees, in both individual analysis of vegetation indices and forest health composites that are available in ENVI software. Accuracy assessment was calculated by using ground truth data. Results: The results showed that all vegetation indices tested in this study provide a good accuracy which ranges from 68.57-82.86 and 60-80% for both vegetation indices and forest health composites respectively. With regard to the vegetation indices the highest accuracy was achieved by using Red Edge Normalized Difference Vegetation Index (NDVI 705) with 82.86% of overall accuracy and as for the forest health composites the highest accuracy was achieved by using the composite that include Vogelmann Red Edge Index 1 (VOG1) with 80% of overall accuracy. Conclusion/Recommendations: Vegetation indices based on the red edge provide better results than other indices based on other techniques.