Full Text:
<1>
CLC number:
On-line Access: 2026-03-23
Received: 2025-10-14
Revision Accepted: 2026-03-12
Crosschecked: 0000-00-00
Cited: 0
Clicked: 2
Embedding of ripening topology into one-stage detection for tomato cluster phenotyping
| |||||||||||||
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, 1998, -1(-1): .
@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",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="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
%V -1
%N -1
%P
%@ 1673-1581
%D 1998
%I Zhejiang University Press & Springer
%DOI 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
VL - -1
IS - -1
SP -
EP -
%@ 1673-1581
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.B2500647
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.
Open peer comments: Debate/Discuss/Question/Opinion
<1>