Special Section on 2. Oil Palm Fresh Fruit Bunch Detection and Ripeness Classification Using YOLOv5

電子情報通信学会 - IEICE会誌 試し読みサイト
Vol.106 No.10 (2023/10) 目次へ

前の記事へ次の記事へ


Special Section on 2. Oil Palm Fresh Fruit Bunch Detection and Ripeness Classification Using YOLOv5 Mohamed Yasser Mohamed Ahmed Mansour Katrina D. Dambul Kan Yeep Choo

Mohamed Yasser Mohamed Ahmed Mansour, Kan Yeep Choo, Nonmembers (Faculty of Engineering, Multimedia University, Selangor, 63100 Malaysia).

Katrina D. Dambul, Nonmember (Faculty of Engineering, Multimedia University, Selangor, 63100 Malaysia).

THE JOURNAL OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS Vol.106 No.10 pp.886-891 October 2023

Copyright © 2023 The Institute of Electronics, Information and Communication Engineers

Abstract

 In oil palm estates, smart farming technology such as visual-based mobile applications can improve the harvesting process by assisting in the oil palm fresh fruit bunch (FFB) ripeness classification process and allow the monitoring of the harvesting process remotely. In this paper, oil palm FFB detection and ripeness classification is developed using a YOLOv5s model. Augmentation and label smoothing techniques were applied to improve the performance of the model. The results after applying label smoothing techniques showed that the mean average precision of the YOLOv5s model is 87.85%(0.5: 0.95) with a precision of 96.19% and a recall of 95.19%. The results after image augmentation (Mosaic and Cut-Out) showed that the mean average precision of the YOLOv5s model is 86.67%(0.5: 0.95) with a precision of 95.78% and a recall of 98.00%. This model can potentially be implemented in a mobile device to be used in a real time harvesting process.

Keywords:Oil palm fresh fruit bunches, ripeness classification, object detection, YOLO.

1.Introduction

 The oil palm industry plays an important role in Malaysia’s agriculture sector(1). In 2021, the oil palm sector has contributed more than 35% to the agriculture sector and 2.5% to Malaysia’s Gross Domestic Product (GDP)(2). The quality of the oil palm extracted from the oil palm fresh fruit bunches (FFBs) is affected by its maturity level which is determined by a set of standards by Malaysia Palm Oil Board (MPOB)(3). MPOB standards determines the criteria of harvesting by two methods which are colour of the fruits’ surface or the number of loose fruits detached from the bunch on the ground. The current method of harvesting depends on the visual inspection done by workers on the plantations. The condition of the trees such as its height (tall trees) and lighting conditions can affect the accuracy of the visual inspection. In addition, the workers’ lack of experience can also lead to harvesting of bunches which are not in the ideal maturity level, causing the production of low-quality oil palm or fines being imposed. Thus, advanced smart farming technology such as a mobile application implementing a ripeness classification model can potentially assist in the harvesting process of the FFBs. The model can compensate for the workers’ lack of experience in determining suitable FFBs for harvesting and also to ensure accurate ripeness classification despite unfavourable trees and lighting conditions.


続きを読みたい方は、以下のリンクより電子情報通信学会の学会誌の購読もしくは学会に入会登録することで読めるようになります。 また、会員になると豊富な豪華特典が付いてきます。


続きを読む(PDF)   バックナンバーを購入する    入会登録

  

電子情報通信学会 - IEICE会誌はモバイルでお読みいただけます。

電子情報通信学会誌 会誌アプリのお知らせ

電子情報通信学会 - IEICE会誌アプリをダウンロード

  Google Play で手に入れよう

本サイトでは会誌記事の一部を試し読み用として提供しています。