Precision Agriculture University Research

Chonnam National University Builds AI System for Orchard Mapping

Researchers at Chonnam National University published a study describing a framework that fuses drone imagery with ground-based LiDAR data.
Image provided by Chonnam National University

Key Takeaways

  • Researchers at Chonnam National University published a study in Artificial Intelligence in Agriculture describing an AI framework that fuses drone imagery with ground-based LiDAR data.
  • The system reached localization accuracy within a few centimeters across roughly 1.3 kilometers of orchard travel during testing.
  • The framework is designed to cut down long-term drift compared with conventional orchard mapping methods.
  • The resulting digital orchard models are meant to support tasks such as crop inspection, targeted spraying, and harvesting carried out by agricultural robots.
  • The models can also pull out phenotypic traits, including tree height and tree health information.

Chonnam National University Builds AI-Powered Orchard Maps

A team at Chonnam National University has published a study in the journal Artificial Intelligence in Agriculture describing a new AI framework that combines aerial drone imagery with ground-based LiDAR data to build detailed digital models of commercial orchards. The research targets a common problem in orchard robotics: getting reliable localization and mapping in environments with dense tree cover and uneven terrain.

How the Drone-and-LiDAR System Works

The framework uses a deep learning-based cross-modal fusion approach, pairing drone remote sensing imagery with LiDAR-inertial measurements collected by a ground robot. Combining the two data sources lets the system build a more complete and accurate picture of the orchard than either sensor could produce on its own, while also holding up better over long stretches of travel. The work adds to the growing body of precision agriculture research aimed at making field robots more reliable outside of controlled settings.

Chonnam National University's Field Test Results

In tests covering about 1.3 kilometers of orchard travel, the Chonnam National University system reached localization accuracy on the order of a few centimeters, while suppressing the long-term drift that typically affects conventional mapping methods over extended distances. The resulting GIS-based, multi-layer orchard models can also be used to extract phenotypic traits, including tree height and indicators of tree health.

“By integrating what a robot sees on the ground with an aerial map, our system can help agricultural robots work reliably in orchards, supporting practical tasks such as crop inspection, targeted spraying, mowing, transportation, and harvesting,” said Prof. Kyeong-Hwan Lee.

Applications for Precision Agriculture

The researchers say the more accurate orchard models could make it easier to deploy agricultural robots for everyday jobs like inspection, targeted spraying, mowing, transport, and harvesting, while supporting more sustainable food production. More detail on the study is available through Chonnam National University's public release on the research.

Read the entire research here.

administrator
As a dedicated journalist and entrepreneur, I helm iGrow News, a pioneering media platform focused on the evolving landscape of Agriculture Technology. With a deep-seated passion for uncovering the latest developments and trends within the agtech sector, my mission is to deliver insightful, unbiased news and analysis. Through iGrow News, I aim to empower industry professionals, enthusiasts, and the broader public with knowledge and understanding of technological advancements that shape modern agriculture. You can follow me on LinkedIn & Twitter.

Leave a Reply

<!-- ============================================================ iGrow Exit-Intent Popup — drop-in snippet Paste this whole block before in your theme footer (footer.php) or via WPCode / "Insert Headers and Footers" plugin → "Site Wide Footer" location. Behavior: - Desktop only (≥768px wide) — skipped on mobile to avoid Google's mobile interstitial penalty. - Triggers (whichever fires first): 1. Exit-intent (mouse leaves viewport top) 2. 15 seconds on page (TIME_MS variable below) 3. 60% scroll depth (SCROLL_PCT variable below) - Frequency cap: once per 30 days per visitor (cookie) - "Remind me later" option: re-shows after 1 day - Excluded paths: /pricing, /checkout, /billing, /account, /subscribe, /login (edit the EXCLUDE regex to change) - Total weight: ~3 KB ============================================================ -->