Tomato Growth Monitoring and Phenological Analysis Using Deep Learning-Based Instance Segmentation and 3D Point Cloud Reconstruction

Warut Timprae, Tatsuki Sagawa, Stefan Baar, Satoshi Kondo, Yoshifumi Okada, Kazuhiko Sato, Poltak Sandro Rumahorbo, Yan Lyu, Kyuki Shibuya, Yoshiki Gama, Yoshiki Hatanaka and Shinya Watanabe ()
Additional contact information
Warut Timprae: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Tatsuki Sagawa: Hitachi Solutions, Co., Ltd., 4-12-7 Higashishinagawa, Shinagawa-ku, Tokyo 140-0002, Japan
Stefan Baar: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Satoshi Kondo: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Yoshifumi Okada: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Kazuhiko Sato: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Poltak Sandro Rumahorbo: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Yan Lyu: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan
Kyuki Shibuya: Asai Nursery, Inc., Tsu 514-2221, Japan
Yoshiki Gama: Asai Nursery, Inc., Tsu 514-2221, Japan
Yoshiki Hatanaka: Asai Nursery, Inc., Tsu 514-2221, Japan
Shinya Watanabe: Graduate School of Engineering, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan

Sustainability, 2025, vol. 17, issue 22, 1-22

Abstract: Accurate and nondestructive monitoring of tomato growth is essential for large-scale greenhouse production; however, it remains challenging for small-fruited cultivars such as cherry tomatoes. Traditional 2D image analysis often fails to capture precise morphological traits, limiting its usefulness in growth modeling and yield estimation. This study proposes an automated phenotyping framework that integrates deep learning-based instance segmentation with high-resolution 3D point cloud reconstruction and ellipsoid fitting to estimate fruit size and ripeness from daily video recordings. These techniques enable accurate camera pose estimation and dense geometric reconstruction (via SfM and MVS), while Nerfacto enhances surface continuity and photorealistic fidelity, resulting in highly precise and visually consistent 3D representations. The reconstructed models are followed by CIELAB color analysis and logistic curve fitting to characterize the growth dynamics. When applied to real greenhouse conditions, the method achieved an average size estimation error of 8.01% compared to manual caliper measurements. During summer, the maximum growth rate (g max ) of size and ripeness were 24.14%, and 95.24% higher than in winter, respectively. Seasonal analysis revealed that winter-grown tomatoes matured approximately 10 days later than summer-grown fruits, highlighting environmental influences on phenological development. By enabling precise, noninvasive tracking of size and ripeness progression, this approach is a novel tool for smart and sustainable agriculture.

Keywords: tomato growth estimation; instance segmentation; ellipsoid fitting; photogrammetry (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/22/10120/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/22/10120/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:22:p:10120-:d:1793182

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().