CFPR-YOLO: chili flower pose estimation for robotic pollination in unstructured environments
6 affiliations
- 1College of Electrical and Mechanical Engineering, Hunan Agricultural University
- 2Foshan-Zhongke Innovation Research Institute of Intelligent Agriculture and Robotics
- 3Hunan Provincial Key Laboratory of Intelligent Agricultural Machinery Equipment
- 4College of Horticulture, Hunan Agricultural University
- 5College of Intelligent Science and Engineering, Beijing University of Agriculture
- 6Department of Computer and Electrical Engineering, Mid Sweden University
Abstract
Agricultural engineering informatics is playing an increasingly important role in enabling intelligent perception, decision-making, and automated operations in modern horticultural production systems. Within this context, accurate visual perception of reproductive structures is essential for agricultural informatization tasks such as flowering-stage monitoring, precision pollination, and information-driven fruit-set management in chili cultivation. However, reliable detection and pose-aware recognition of chili flowers remain challenging because of small target size, dense distribution, foliage occlusion, and illumination variability in natural or semi-controlled environments. To address these challenges, this study proposes a lightweight and robust edge vision framework, termed CFPR-YOLO, for chili flower detection and pose-aware perception under complex agricultural conditions. Built upon an improved YOLOv11n architecture, the proposed framework incorporates EfficientFormerV2 to strengthen global-context feature extraction, a C3k2_EMA module to enhance localization of small and occluded targets, and Poly-Scale Convolution (PSConv) to preserve structural details while reducing computational redundancy. In addition, a lightweight attention mechanism is introduced to improve feature discrimination in cluttered backgrounds. Experimental results on both self-constructed and generalization datasets show that the proposed method achieves a precision of 92.6%, a recall of 86.8%, and an mAP50 of 92.1% with only 7.26 M parameters. The framework also demonstrates strong robustness and generalization across different chili varieties. When deployed on an edge computing platform (NVIDIA Jetson AGX Orin), the model achieves real-time inference at 39.5 FPS. Furthermore, validation experiments under controlled indoor conditions show that the proposed framework can effectively support simulated pollination tasks, achieving a success rate of 90.0% for upwardfacing flowers. These results indicate that CFPR-YOLO provides an effective visual perception solution for agricultural engineering informatics-oriented pollination systems and offers practical potential for precision pollination and intelligent fruit-set management in horticultural production.
Related
- Trapped in a hot microcosm: how flower microclimate contributes to pollination syndrome in a thermogenic system
- Generalized pollination of morphologically specialized Vincetoxicum hirundinaria (Apocynaceae, Asclepiadoideae)
- Economic Value of Apple Pollination in the European Union, 2000 to 2024
- Reproductive Biology, Pollination Optimization, and Hybrid Verification of Acacia mangium × A. auriculiformis
- The effectiveness of artificial pollination in various representatives of the genus Pisum L.
BibTeX
@article{kuang2026cfpryolo,
title = {{CFPR-YOLO: chili flower pose estimation for robotic pollination in unstructured environments}},
author = {Minqiu Kuang and Yushi Wang and Xiaojian Li and Dawei Liu and Yang Xiang and Feng Liu and Xiangjun Zou and Fangping XIE and Yuxuan Zhang and Xu Li},
journal = {Frontiers in Plant Science},
year = {2026},
month = jun,
doi = {10.3389/fpls.2026.1861155},
url = {https://doi.org/10.3389/fpls.2026.1861155},
note = {CC BY},
}
RIS
TY - JOUR
TI - CFPR-YOLO: chili flower pose estimation for robotic pollination in unstructured environments
AU - Minqiu Kuang
AU - Yushi Wang
AU - Xiaojian Li
AU - Dawei Liu
AU - Yang Xiang
AU - Feng Liu
AU - Xiangjun Zou
AU - Fangping XIE
AU - Yuxuan Zhang
AU - Xu Li
PY - 2026
DA - 2026/06/05
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1861155
UR - https://doi.org/10.3389/fpls.2026.1861155
AB - Agricultural engineering informatics is playing an increasingly important role in enabling intelligent perception, decision-making, and automated operations in modern horticultural production systems. Within this context, accurate visual perception of reproductive structures is essential for agricultural informatization tasks such as flowering-stage monitoring, precision pollination, and information-driven fruit-set management in chili cultivation. However, reliable detection and pose-aware recognition of chili flowers remain challenging because of small target size, dense distribution, foliage occlusion, and illumination variability in natural or semi-controlled environments. To address these challenges, this study proposes a lightweight and robust edge vision framework, termed CFPR-YOLO, for chili flower detection and pose-aware perception under complex agricultural conditions. Built upon an improved YOLOv11n architecture, the proposed framework incorporates EfficientFormerV2 to strengthen global-context feature extraction, a C3k2_EMA module to enhance localization of small and occluded targets, and Poly-Scale Convolution (PSConv) to preserve structural details while reducing computational redundancy. In addition, a lightweight attention mechanism is introduced to improve feature discrimination in cluttered backgrounds. Experimental results on both self-constructed and generalization datasets show that the proposed method achieves a precision of 92.6%, a recall of 86.8%, and an mAP50 of 92.1% with only 7.26 M parameters. The framework also demonstrates strong robustness and generalization across different chili varieties. When deployed on an edge computing platform (NVIDIA Jetson AGX Orin), the model achieves real-time inference at 39.5 FPS. Furthermore, validation experiments under controlled indoor conditions show that the proposed framework can effectively support simulated pollination tasks, achieving a success rate of 90.0% for upwardfacing flowers. These results indicate that CFPR-YOLO provides an effective visual perception solution for agricultural engineering informatics-oriented pollination systems and offers practical potential for precision pollination and intelligent fruit-set management in horticultural production.
SN - 1664-462X
ER -