Research Publication: Cost-Effective 3D Reconstruction System for Plant Phenotyping Developed through International Collaboration

Yogyakarta, 4 April 2025 – Smart Agriculture Research Center (SARC) UGM, in international collaboration with the Department of Smart Agricultural Systems and Department of Biosystems Machinery Engineering at Chungnam National University, as well as the Department of Agro-Environmental Sciences at Kyushu University, announces the development of a non-destructive and cost-effective plant growth observation system based on 3D modeling using the Structure from Motion (SfM) method. The results of this research have been published in the prestigious international journal Biosystems Engineering on 10 September 2024 (Volume 49, pages 326–336).

The research, titled "Development and Application of a Low-Cost 3-Dimensional (3D) Reconstruction System Based on the Structure from Motion (SfM) Approach for Plant Phenotyping," is led by Muhammad Akbar Andi Arief, and involves Andri Prima Nugroho, Ardyan Widyanto Putro, Lilik Sutiarso, Byoung-Kwan Cho, and Takashi Okayasu. This international collaboration enabled the integration of expertise and resources from various leading institutions, enriching the research process and producing significant findings.

The system comprises a camera arm, stepper motor, web camera, LED lights, and image processing software to generate 3D models. The system was tested on cabbage plants over a 35-day growth period. Results showed that the system successfully generated 3D models resembling actual plants, with volumetric validation showing R² = 0.9956, RMSE = 13.97 cm³, and MAPE = 71.33%. ANOVA analysis indicated no significant difference between volume measurements using the developed system and conventional systems (ρ-value = 0.946).

Research Outcomes:

This research produced an accurate, efficient, and affordable 3D reconstruction system that can be used for plant phenotyping. The system has potential to improve efficiency and accuracy in measuring plant growth, supporting more precise and sustainable agricultural practices. The system's advantages lie in its ability to generate 3D data non-destructively, enabling continuous monitoring of plant growth without damaging the plants. This is highly beneficial for research and precision agriculture applications.

Further Information:

Publication Title: Development and Application of a Low-Cost 3-Dimensional (3D) Reconstruction System Based on the Structure from Motion (SfM) Approach for Plant Phenotyping
Journal: Biosystems Engineering, Volume 49, pages 326–336, (2024)
DOI: https://doi.org/10.1007/s42853-024-00237-w
Contact: Andri Prima Nugroho (andrew@ugm.ac.id)