The Drone Based Hyperspectral Imaging System for Precision Agriculture

Abstract

Precision agriculture using remote sensing can be traced back to 1980’s with various handheld sensors as well as sensors mounted on satellite and airborne platform. Precision agriculture or precision farming is a farming management concept which combines conventional farming method with new technologies such as satellite/radar imaginary and information technology. Unlike conventional farming, precision agriculture integrates a suite of technological tools such as radar images, agriculture monitoring system, and high technology machines into farming practice. The aim is to minimize the crops production costs and maximize the production outputs all in benefiting the farmers. In this project, an experimental study on disease detection and nutrient extraction of plantation such as oil palm n Malaysia will be carried out using a drone based hyperspectral imaging system. In this project, an experimental study on disease detection and nutrient extraction of plantation such as oil palm in Malaysia will be carried out using a drone based hyperspectral imaging system. The major advantages of this hyperspectral sensors are light weight (approximate 250g for sensor) and larger number of band selection (from 600nm to 1000nm) compare to conventional multispectral camera. Therefore, it enables the usage of smaller airborne platform and further reduce the development cost and operation cost. A customised drone has been designed and developed to carry the hyperspectral imaging system. Preliminary testing has been performed in laboratory and oil palm plantation to verify both multirotor drone and hyperspectral imaging system. Initial results show that the hyperspectral data are suitable to be used for differentiation of the healthiness level of the oil palm plantation. In order to achieve the target of disease detection and nutrient extraction, timely ground truth data will be collected together with the field experiment using drone based hyperspectral camera. Data analysis on the obtained ground truth data need to be carried out to study the correlation properties of the hyperspectral images with various oil palm plantation condition. This research is supported by MOSTI International Collaboration Fund, IF0719A1102.