EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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, Shinya Watanabe

Sustainability · 12.11.2025 · 17 (22) · 10120

DOI: 10.3390/su172210120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 12.11.2025. Verfasst von Warut Timprae und 11 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Agency, Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 (gmax) 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.

Förderung

  • Japan Science and Technology Agency
  • Japan Society for the Promotion of Science

Zitieren

APA

Timprae, W., Sagawa, T., Baar, S., Kondo, S., Okada, Y., Sato, K., Rumahorbo, P. S., Lyu, Y., Shibuya, K., Gama, Y., Hatanaka, Y., & Watanabe, S. (2025). Tomato Growth Monitoring and Phenological Analysis Using Deep Learning-Based Instance Segmentation and 3D Point Cloud Reconstruction. Sustainability, 17(22), 10120. https://doi.org/10.3390/su172210120

Vancouver

Timprae W, Sagawa T, Baar S, Kondo S, Okada Y, Sato K, et al. Tomato Growth Monitoring and Phenological Analysis Using Deep Learning-Based Instance Segmentation and 3D Point Cloud Reconstruction. Sustainability. 2025;17(22):10120. doi:10.3390/su172210120

BibTeX
@article{Timprae2025,
  author = {Timprae, Warut and Sagawa, Tatsuki and Baar, Stefan and Kondo, Satoshi and Okada, Yoshifumi and Sato, Kazuhiko and Rumahorbo, Poltak Sandro and Lyu, Yan and Shibuya, Kyuki and Gama, Yoshiki and Hatanaka, Yoshiki and Watanabe, Shinya},
  title = {Tomato Growth Monitoring and Phenological Analysis Using Deep Learning-Based Instance Segmentation and 3D Point Cloud Reconstruction},
  journal = {Sustainability},
  year = {2025},
  volume = {17},
  number = {22},
  pages = {10120},
  doi = {10.3390/su172210120}
}
Kostenlos starten →