Development of 360-degree imaging system for fresh fruit bunch (FFB) identification

Abstract

In every cycle of harvesting operation, farmer does not have any information on how many bunches and which oil palm tree will be harvested. By introducing the 360ᵒ camera imaging system, number of Fresh Fruit Bunch (FFB) can be determined for every tree in a plantation area. Black bunch census was done manually to estimate yield. This was improved by video acquisition using a high resolution 360ᵒ camera integrated with an image processing software for video image processing to calculate number of FFB. Based on the standard planting pattern, it is time consuming process to circle each tree to acquire the 360ᵒ view of each tree. Current technology to approach bunches is destructive and conventional since the process involve physical contact between workers and FFB. Thus, a new method was established by the execution of All-Terrain Vehicle (ATV) between rows in plantation area for video acquisition. Images were extracted and threshold by using MATLAB software. L*, a*, and b* color space was used for the bunch identification throughout 90 samples of images to identify the mean intensity value. Model threshold verification for another 48 samples of images resulted with Coefficient of Determination, R2 of 0.8029 for bunch identification. As a result, a new method for video acquisition was established as well as processing method for bunch identification for large scale plantation area.