Development of Virescens Fresh Fruit Bunch Ripeness Prediction using LiDAR for Smart Agriculture

Abstract

Smart Agriculture is a part of Humanitarian Technology. Oil palm fruit is one of the leading agricultural product exports by Malaysia. At present, the general methods used to determine the ripeness of oil palm fresh fruit bunch are using human vision, computer vision and laser-based imaging techniques. This research aims to design and build a scanning system based on a LiDAR sensor and servo motors and obtain point cloud data from oil palm fresh fruit bunch (FFB). The proposed project consists of LiDAR Lite V3, Arduino UNO and two servo motors as its main component. LiDAR sensor is used to collect the intensity value that reflects from the Virescens oil palm FFB, and the data collected are saved in a CSV file for further analysis. The methodology used in this research is the Iterative Waterfall model. This model supports redesign if there are any improvements needed in this project, and the phase can be looped back to the previous iteration if the process faces any errors. The system proposed works successfully to produce point clouds from oil palm fresh fruit bunch, and it is found that ripe oil palm fruit has a lower mean intensity value than unripe oil palm fresh fruit bunch.