Lightweight SM-YOLOv5 Tomato Fruit Detection Algorithm for Plant Factory
Sensors · 22.03.2023 · 23 (6) · 3336
DOI: 10.3390/s23063336 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.03.2023. Verfasst von Xinfa Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Henan Institute of Science and Technology, Xinxiang 453003, China. Hauptthemen laut MEDLINE: Solanum lycopersicum. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Science and Technology Department of Henan Province, The education department of Henan province, The Science and Technology Bureau of XinXiang City of Henan Province.
Abstract (Originalsprache)
Due to their rapid development and wide application in modern agriculture, robots, mobile terminals, and intelligent devices have become vital technologies and fundamental research topics for the development of intelligent and precision agriculture. Accurate and efficient target detection technology is required for mobile inspection terminals, picking robots, and intelligent sorting equipment in tomato production and management in plant factories. However, due to the limitations of computer power, storage capacity, and the complexity of the plant factory (PF) environment, the precision of small-target detection for tomatoes in real-world applications is inadequate. Therefore, we propose an improved Small MobileNet YOLOv5 (SM-YOLOv5) detection algorithm and model based on YOLOv5 for target detection by tomato-picking robots in plant factories. Firstly, MobileNetV3-Large was used as the backbone network to make the model structure lightweight and improve its running performance. Secondly, a small-target detection layer was added to improve the accuracy of small-target detection for tomatoes. The constructed PF tomato dataset was used for training. Compared with the YOLOv5 baseline model, the mAP of the improved SM-YOLOv5 model was increased by 1.4%, reaching 98.8%. The model size was only 6.33 MB, which was 42.48% that of YOLOv5, and it required only 7.6 GFLOPs, which was half that required by YOLOv5. The experiment showed that the improved SM-YOLOv5 model had a precision of 97.8% and a recall rate of 96.7%. The model is lightweight and has excellent detection performance, and so it can meet the real-time detection requirements of tomato-picking robots in plant factories.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Henan Institute of Science and Technology, Xinxiang 453003, China.
- Faculty of Engineering and Technology, Sumy National Agrarian University, 40000 Sumy, Ukraine.
- College of Mechanical and Electrical Engineering, Xinxiang University, Xinxiang 453003, China.
- Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, China.
ORCID-Profile: Xinfa Wang, Zhenwei Wu, Tao Xu, Mingfu Zhao
Förderung
- The Science and Technology Department of Henan Province
- The education department of Henan province
- The Science and Technology Bureau of XinXiang City of Henan Province
- Key Science and Technology Program of Henan Province
- Colleges and Universities Key Research Project of Henan Province
- Major Science and Technology Projects in Xinxiang City, Henan Province
Zitieren
APA
Wang, X., Wu, Z., Jia, M., Xu, T., Pan, C., Qi, X., & Zhao, M. (2023). Lightweight SM-YOLOv5 Tomato Fruit Detection Algorithm for Plant Factory. Sensors, 23(6), 3336. https://doi.org/10.3390/s23063336
Vancouver
Wang X, Wu Z, Jia M, Xu T, Pan C, Qi X, et al. Lightweight SM-YOLOv5 Tomato Fruit Detection Algorithm for Plant Factory. Sensors. 2023;23(6):3336. doi:10.3390/s23063336
BibTeX
@article{Wang2023,
author = {Wang, Xinfa and Wu, Zhenwei and Jia, Meng and Xu, Tao and Pan, Canlin and Qi, Xuebin and Zhao, Mingfu},
title = {Lightweight SM-YOLOv5 Tomato Fruit Detection Algorithm for Plant Factory},
journal = {Sensors},
year = {2023},
volume = {23},
number = {6},
pages = {3336},
doi = {10.3390/s23063336}
}
EUVIMED