Plantation Object Identification and Counting

Khor, Jian Sheng (2023) Plantation Object Identification and Counting. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

Text Full Text - KHOR JIAN SHENG.pdf Restricted to Registered users only Download (18MB)

Abstract

With rising global demand for palm oil, the production of the palm oil needs to be taken seriously. Field maintenance plays an important role in affecting palm oil production. In this research, an approach will be proposed to automatically detect palm oil trees and identify the health condition of palm oil trees as well as label out the unhealthy palm oil tree using AI. In this research, four state-of-the-art object detection models, Faster RCNN Resnet50 with FPN, Faster RCNN Resnet101 with FPN, RetinaNet Resnet50 and YOLOv7, will be built and evaluated accordingly. YOLOv7 score the highest mAP of 93.10%, FRCNN-R50-FPN and FRCNN-R101- FPN models have best overall F1-score. Finally, all the objectives are able to achieve in this project