JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE B

Accepted manuscript available online (unedited version)

Embedding of ripening topology into one-stage detection for tomato cluster phenotyping

Author(s): Bingquan CHU¹, Ruiyuan WU¹, Haijun ZHANG¹, Haochuan QIN¹, Zishun PENG¹, Fengle ZHU² , Yong HE³
Affiliation(s): ¹School of Biological and Chemical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China ²College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310023, China ³College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
Corresponding email(s): Fengle ZHU, zhufl@zjut.edu.cn Yong HE, yhe@zju.edu.cn
Key Words: Tomato ripeness; Phenotype; Object detection; Topology; YOLO; Spatial sequence

Share this article to： More <<< Previous Paper \|Next Paper >>>

Bingquan CHU¹, Ruiyuan WU¹, Haijun ZHANG¹, Haochuan QIN¹, Zishun PENG¹, Fengle ZHU² , Yong HE³. Embedding of ripening topology into one-stage detection for tomato cluster phenotyping[J]. Journal of Zhejiang University Science B,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.B2500647

@article{title="Embedding of ripening topology into one-stage detection for tomato cluster phenotyping",
author="Bingquan CHU¹, Ruiyuan WU¹, Haijun ZHANG¹, Haochuan QIN¹, Zishun PENG¹, Fengle ZHU² , Yong HE³",
journal="Journal of Zhejiang University Science B",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.B2500647"
}

%0 Journal Article
%T Embedding of ripening topology into one-stage detection for tomato cluster phenotyping
%A Bingquan CHU¹
%A Ruiyuan WU¹
%A Haijun ZHANG¹
%A Haochuan QIN¹
%A Zishun PENG¹
%A Fengle ZHU²
%A Yong HE³
%J Journal of Zhejiang University SCIENCE B
%P
%@ 1673-1581
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.B2500647"

TY - JOUR
T1 - Embedding of ripening topology into one-stage detection for tomato cluster phenotyping
A1 - Bingquan CHU¹
A1 - Ruiyuan WU¹
A1 - Haijun ZHANG¹
A1 - Haochuan QIN¹
A1 - Zishun PENG¹
A1 - Fengle ZHU²
A1 - Yong HE³
J0 - Journal of Zhejiang University Science B
SP -
EP -
%@ 1673-1581
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.B2500647"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: The automated assessment of tomato ripeness is vital for modern greenhouse operations, yet challenges remain due to variable environmental conditions. To provide a solution, we propose Rank-Aware YOLO, a novel detection framework that incorporates the biological prior of top-to-bottom ripening within fruit clusters. This is achieved through two key innovations: an Efficient Position-Aware Head for regressing relative height for fruits, and a Dynamic Margin-Aware Ranking Loss (DM-RankLoss) that enforces the correct spatial sequence. Evaluated on a 3500-image dataset from a solar greenhouse, our plug-and-play module could boost the mAP50 (mean average precision at IoU threshold 0.50) of multiple YOLO architectures by up to 5.66 points. The model effectively learns the cluster topology, achieving a height-MAE (mean absolute error) of 0.107 (normalized) and a pairwise ranking accuracy of 84.59%, while it reduces parameter count by over 10% compared to the baseline for efficient deployment. Visualizations confirm that the model leverages spatial context to resolve color ambiguities. Our work offers a sensor-free, accurate and efficient solution for in situ phenotyping in agricultural robotics.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference