期刊
IEEE ACCESS
卷 10, 期 -, 页码 95763-95770出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3204762
关键词
Object detection; oil palm; fresh fruit bunch; fruit maturity; YOLO
资金
- Universiti Putra Malaysia Research Grant (Putra Grant) [GP-GPB/2021/9699100]
This paper presents a vision-based ripe FFB detection system as the first step in a robotic FFB harvesting system. The system utilizes a YOLOv4 model and live camera input to detect the presence of ripe FFBs on oil palm trees in real-time, reducing the loss of OER caused by human error.
Fresh Fruit Bunch (FFB) is the main ingredient in palm oil production. Harvesting FFB from oil palm trees at its peak ripeness stage is crucial to maximise the oil extraction rate (OER) and quality. In current harvesting practices, misclassification of FFB ripeness can occur due to human error, resulting in OER loss. Therefore, a vision-based ripe FFB detection system is proposed as the first step in a robotic FFB harvesting system. In this work, live camera input is fed into a Convolutional Neural Network (CNN) model known as YOLOv4 to detect the presence of ripe FFBs on the oil palm trees in real-time. Once a ripe FFB is detected on the tree, a signal is transmitted via ROS to the robotic harvesting mechanism. To train the YOLOv4 model, a large number of ripe FFB images were collected using an Intel Realsense Camera D435 with a resolution of 1920 x 1080. During data acquisition, a subject matter expert assisted in classifying the FFBs in terms of ripe or unripe. During the testing phase, the result of the mean Average Precision (mAP) and recall are 87.9 % and 82 % as the detection fulfilled the Intersect over Union (IoU) with more than 0.5 after 2000 iterations and the system operated at the real-time speed of roughly 21 Frame Per Second (FPS).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据