Capsicum flower identification for robotic pollination in greenhouses

Sunpreet Sharma; Gu Fang; Zhong-Hua Chen; Oliver Obst; David Tissue; Ju Jia Zou; Weiguang Liang

doi:10.1109/ICMLC58545.2023.10327967

Capsicum flower identification for robotic pollination in greenhouses

Sunpreet Sharma, Gu Fang, Zhong-Hua Chen, Oliver Obst, David Tissue, Ju Jia Zou, Weiguang Liang

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

Abstract

Due to restrictions on bees and the lack of wind in the greenhouse, pollination could be a labor-intensive activity. Hence, an automated pollination process is preferred to improve the productivity in greenhouse settings. This paper introduces an image-based pollination method applicable within the greenhouse. A stereo-vision camera and a You Only Look Once (YOLO)-based image processing technique are employed to identify and locate the pollination-ready capsicum flowers in the greenhouse. The detected flower's location is communicated to a robotic system for it to be maneuvered in front of the flower to finish the required pollination. When tested on the test dataset using Precision & Recall Curve (PRC), the proposed detection method achieves an average detection precision of 0.76 for the first class (CapFlower) and 0.61 for the other (Bud).

Original language	English
Title of host publication	Proceedings of 2023 International Conference on Machine Learning and Cybernetics, The University of Adelaide, Adelaide, Australia, 9-11 July, 2023
Publisher	IEEE
Pages	520-527
Number of pages	8
ISBN (Print)	9798350303780
DOIs	https://doi.org/10.1109/ICMLC58545.2023.10327967
Publication status	Published - 2023
Event	International Conference on Machine Learning and Cybernetics - Duration: 9 Jul 2023 → …

Conference

Conference	International Conference on Machine Learning and Cybernetics
Period	9/07/23 → …

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Access to Document

10.1109/ICMLC58545.2023.10327967

Cite this

Sharma, S., Fang, G., Chen, Z.-H., Obst, O., Tissue, D., Zou, J. J., & Liang, W. (2023). Capsicum flower identification for robotic pollination in greenhouses. In Proceedings of 2023 International Conference on Machine Learning and Cybernetics, The University of Adelaide, Adelaide, Australia, 9-11 July, 2023 (pp. 520-527). IEEE. https://doi.org/10.1109/ICMLC58545.2023.10327967

@inproceedings{49a20c804bd14fab8f30a60b1231b7b0,

title = "Capsicum flower identification for robotic pollination in greenhouses",

abstract = "Due to restrictions on bees and the lack of wind in the greenhouse, pollination could be a labor-intensive activity. Hence, an automated pollination process is preferred to improve the productivity in greenhouse settings. This paper introduces an image-based pollination method applicable within the greenhouse. A stereo-vision camera and a You Only Look Once (YOLO)-based image processing technique are employed to identify and locate the pollination-ready capsicum flowers in the greenhouse. The detected flower's location is communicated to a robotic system for it to be maneuvered in front of the flower to finish the required pollination. When tested on the test dataset using Precision & Recall Curve (PRC), the proposed detection method achieves an average detection precision of 0.76 for the first class (CapFlower) and 0.61 for the other (Bud).",

author = "Sunpreet Sharma and Gu Fang and Zhong-Hua Chen and Oliver Obst and David Tissue and Zou, {Ju Jia} and Weiguang Liang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; International Conference on Machine Learning and Cybernetics ; Conference date: 09-07-2023",

year = "2023",

doi = "10.1109/ICMLC58545.2023.10327967",

language = "English",

isbn = "9798350303780",

pages = "520--527",

booktitle = "Proceedings of 2023 International Conference on Machine Learning and Cybernetics, The University of Adelaide, Adelaide, Australia, 9-11 July, 2023",

publisher = "IEEE",

}

Sharma, S, Fang, G , Chen, Z-H , Obst, O , Tissue, D , Zou, JJ & Liang, W 2023, Capsicum flower identification for robotic pollination in greenhouses. in Proceedings of 2023 International Conference on Machine Learning and Cybernetics, The University of Adelaide, Adelaide, Australia, 9-11 July, 2023. IEEE, pp. 520-527, International Conference on Machine Learning and Cybernetics, 9/07/23. https://doi.org/10.1109/ICMLC58545.2023.10327967

Capsicum flower identification for robotic pollination in greenhouses. / Sharma, Sunpreet; Fang, Gu ; Chen, Zhong-Hua et al.
Proceedings of 2023 International Conference on Machine Learning and Cybernetics, The University of Adelaide, Adelaide, Australia, 9-11 July, 2023. IEEE, 2023. p. 520-527.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Capsicum flower identification for robotic pollination in greenhouses

AU - Sharma, Sunpreet

AU - Fang, Gu

AU - Chen, Zhong-Hua

AU - Obst, Oliver

AU - Tissue, David

AU - Zou, Ju Jia

AU - Liang, Weiguang

PY - 2023

Y1 - 2023

N2 - Due to restrictions on bees and the lack of wind in the greenhouse, pollination could be a labor-intensive activity. Hence, an automated pollination process is preferred to improve the productivity in greenhouse settings. This paper introduces an image-based pollination method applicable within the greenhouse. A stereo-vision camera and a You Only Look Once (YOLO)-based image processing technique are employed to identify and locate the pollination-ready capsicum flowers in the greenhouse. The detected flower's location is communicated to a robotic system for it to be maneuvered in front of the flower to finish the required pollination. When tested on the test dataset using Precision & Recall Curve (PRC), the proposed detection method achieves an average detection precision of 0.76 for the first class (CapFlower) and 0.61 for the other (Bud).

AB - Due to restrictions on bees and the lack of wind in the greenhouse, pollination could be a labor-intensive activity. Hence, an automated pollination process is preferred to improve the productivity in greenhouse settings. This paper introduces an image-based pollination method applicable within the greenhouse. A stereo-vision camera and a You Only Look Once (YOLO)-based image processing technique are employed to identify and locate the pollination-ready capsicum flowers in the greenhouse. The detected flower's location is communicated to a robotic system for it to be maneuvered in front of the flower to finish the required pollination. When tested on the test dataset using Precision & Recall Curve (PRC), the proposed detection method achieves an average detection precision of 0.76 for the first class (CapFlower) and 0.61 for the other (Bud).

UR - https://hdl.handle.net/1959.7/uws:74246

U2 - 10.1109/ICMLC58545.2023.10327967

DO - 10.1109/ICMLC58545.2023.10327967

M3 - Conference Paper

SN - 9798350303780

SP - 520

EP - 527

BT - Proceedings of 2023 International Conference on Machine Learning and Cybernetics, The University of Adelaide, Adelaide, Australia, 9-11 July, 2023

PB - IEEE

T2 - International Conference on Machine Learning and Cybernetics

Y2 - 9 July 2023

ER -

Capsicum flower identification for robotic pollination in greenhouses

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this