Universitas Gadjah Mada Develops Automated Oil Palm Tree Counting System Using Deep Learning
Development of an Automated Oil Palm Tree Counting System Based on Remote Sensing Using Deep Learning
Yogyakarta – A research team from Universitas Gadjah Mada (UGM), led by Andri Prima Nugroho, STP., M.Sc., Ph.D., IPU, ASEAN Eng., APEC Eng., from the Department of Agricultural Technology, has successfully developed an automated system for counting oil palm trees. This innovative system utilizes remote sensing imagery with Deep Learning methods, completed in 2022, aiming to improve efficiency, reduce manual errors, and accelerate the inventory process in oil palm plantations.
This research addresses the challenges of manual inventory processes that are time-consuming and prone to errors in large-scale oil palm plantations. “By using aerial imagery from remote sensing, we can detect and identify each oil palm tree accurately through Deep Learning algorithms,” explained Andri Prima Nugroho. This approach significantly speeds up the counting process and provides more reliable data for plantation management.
The developed system is the result of collaboration with external partners (national/international) and is internally funded. This innovation is not only relevant to AI for Industry and Business but also represents a significant breakthrough in the field of Computer Vision (CV) for precision agriculture applications. The system’s accuracy and speed are expected to assist plantation managers in making strategic decisions, from planting planning to production estimation.
The development of this automated counting system reinforces Universitas Gadjah Mada’s commitment to delivering advanced technology-based solutions to support efficiency and sustainability in Indonesia’s oil palm industry.
