Loose Fruitlet and Fresh Fruit Bunch Detection for Palm Oil Harvest Management
2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)(2022)
Abstract
The palm oil industry can be considered one of the crucial industries, especially in Asian countries like Malaysia and Indonesia. The production flow is depending on the efficiency of the palm oil harvest management. The management during harvest time includes collecting and counting the fresh fruit bunch (FFB) and loose fruitlet (LF) production. Thus, in this paper, we proposed a method that able to detect and count the FFB and LF production automatically. The as-proposed method consisted of two parts: (a) fruitlet detection using an image processing prior to harvest and (b) palm oil tree, FFB, and grabber detection using the Faster R-CNN algorithm during harvest time. During the pre-harvest, the number of fruitlets can be determined through the status of the tree either by ready-to-harvest (RTH) or not ready-to-harvest (NRTH). If the status was RTH, the system performed tree detection for tagging purposes. When they started to harvest, the detection system would detect the FFB and grabber. It would then track the grabber until overlaps with the FFB location. Then, the system would add the FFB to the count module. It means the FFB had been taken to the truck. The as-proposed system achieved the detection accuracy of 96.5% for FFB, 99.2% for grabber, and 97.2% for tree.
MoreTranslated text
Key words
fresh fruit bunch,fruitlet,deep learning,image processing,harvest management
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined