Drone and deep learning-based instrumentation for palm fruit detection and yield measurement: a Southeast Asian roadmap

Gunawan, Teddy Surya and Kartiwi, Mira and Jamali, Annisa (2026) Drone and deep learning-based instrumentation for palm fruit detection and yield measurement: a Southeast Asian roadmap. IEEE Instrumentation & Measurement Magazine, 29 (7). pp. 33-46. ISSN 1094-6969 E-ISSN 1941-0123

	PDF - Published Version Restricted to Registered users only Download (1MB) \| Request a copy
	PDF - Supplemental Material Download (216kB)
	PDF - Supplemental Material Download (172kB)

Official URL: https://ieeexplore.ieee.org/document/11595052

Abstract

The palm oil industry, a central component of Southeast Asia’s economy, is facing growing pressure to enhance productivity, sustainability, and labor efficiency amid global environmental and market challenges. Recent advances in instrumentation, unmanned aerial vehicles (UAVs), and deep learning have enabled new opportunities for intelligent measurement and monitoring of palm fruit growth, health, and yield. This Short Review/Roadmap paper presents a regional perspective on the evolution, current state, and future direction of drone- and AI-based instrumentation for palm fruit detection and yield estimation in Malaysia, Indonesia, and Thailand. The review traces the transition from manual inspection and satellite observation to high-resolution UAV imaging integrated with convolutional neural networks (CNNs), YOLO-based object detection, and hyperspectral data analytics. It also highlights hardware and software developments in multispectral imaging, sensor calibration, and edge-AI deployment for real-time plantation monitoring. Despite rapid progress, major challenges remain, including limited labeled datasets, variable lighting and canopy density, and high operational costs for large-scale automation. This paper identifies these gaps and outlines a roadmap toward affordable, data-driven, and sustainable measurement systems through regional collaboration, open datasets, and hybrid sensing architectures. The discussion aims to guide researchers, policymakers, and industry practitioners toward the next generation of precision instrumentation for smart palm agriculture across Southeast Asia.

Item Type:	Article (Review)
Additional Information:	This is collaborative work with Unimas. The article has been indexed in Scopus. The necessary URLs have been updated as well, including Scopus and IEEE Explore. I have updated the PDF file.
Uncontrolled Keywords:	Drone, deep learning, palm fruit detection
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices > TK7885 Computer engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Engineering Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology
Depositing User:	Prof. Dr. Teddy Surya Gunawan
Date Deposited:	06 Oct 2026 09:03
Last Update:	06 Oct 2026 09:03
Queue Number:	2026-09-Q5432
URI:	http://irep.iium.edu.my/id/eprint/131602
Indexed In:	WOS and SCOPUS, Google Scholar

Actions (login required)

View Item