[M-SD40] Micro-satellite and its constellation for next-generation remote sensing

[MSD40-01] Plant Health Monitoring using Drone-based Hyperspectral Imaging

★Invited Papers

*VOON CHET KOO¹, WEN GUEY CHEAW², YEE KIT CHAN¹ (1.Multimedia University, 2.iRadar Sdn Bhd)

Keywords:Hyperspectral , Plant Health Status, Precision Agriculture

Hyperspectral imaging has gained popularity in precision agriculture because of its rich spectral contents that allow improved analysis of crop stress, crop biophysical and biochemical characteristics. In this project, an experimental study on plant health detection and nutrient extraction has been carried out using a drone based hyperspectral imaging system. There are over 200 bands (500 nm to 900 nm) in a typical hyperspectral camera, as opposed to conventional multispectral cameras which have about 3-10 bands. With wider spectrum of observation, more information can be extracted. An AI-based plant health status monitoring system has been developed. Preliminary testing has been performed in laboratory and at field test sites to validate the proposed system. Initial results show that the hyperspectral data are suitable to be used to monitor the health status of oil palm plantations. In order to estimate the nutrient contents, timely ground-truth data have been collected together with the hyperspectral images using a drone. Data analysis on the obtained ground truth data is carried out to study the correlation properties of the hyperspectral images with various oil palm plantation conditions such as plant growth status, nutrient conditions and disease estimations conditions.