Improved RT-DETR and its application to fruit ripeness detection
Frontiers in Plant Science · 27.02.2025 · 16
DOI: 10.3389/fpls.2025.1423682 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 27.02.2025. Verfasst von Mengyang Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics and Electronic Engineering, Jiangsu Normal University, Xuzhou, China. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Crop maturity status recognition is a key component of automated harvesting. Traditional manual detection methods are inefficient and costly, presenting a significant challenge for the agricultural industry.
Methods
To improve crop maturity detection, we propose enhancements to the Real-Time DEtection TRansformer (RT-DETR) method. The original model's Backbone structure is refined by: HG Block Enhancement: Replacing conventional convolution with the Rep Block during feature extraction, incorporating multiple branches to improve model accuracy. Partial Convolution (PConv): Replacing traditional convolution in the Rep Block with PConv, which applies convolution to only a portion of the input channels, reducing computational redundancy. Efficient Multi-Scale Attention (EMA): Introducing EMA to ensure a uniform distribution of spatial semantic features within feature groups, improving model performance and efficiency.
Results
The refined model significantly enhances detection accuracy. Compared to the original model, the average accuracy (mAP@0.5) improves by 2.9%, while model size is reduced by 5.5% and computational complexity decreases by 9.6%. Further experiments comparing the RT-DETR model, YOLOv8, and our improved model on plant pest detection datasets show that our model outperforms others in general scenarios.
Discussion
The experimental results validate the efficacy of the enhanced RT-DETR model in crop maturity detection. The improvements not only enhance detection accuracy but also reduce model size and computational complexity, making it a promising solution for automated crop maturity detection.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Physics and Electronic Engineering, Jiangsu Normal University, Xuzhou, China.
- School of Electrical Engineering and Automation, Jiangsu Normal University, Xuzhou, China.
- School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, Hubei, China.
- College of International Studies, National University of Defense Technology, Nanjing, China.
Zitieren
APA
Wu, M., Qiu, Y., Wang, W., Su, X., Cao, Y., & Bai, Y. (2025). Improved RT-DETR and its application to fruit ripeness detection. Frontiers in Plant Science, 16. https://doi.org/10.3389/fpls.2025.1423682
Vancouver
Wu M, Qiu Y, Wang W, Su X, Cao Y, Bai Y. Improved RT-DETR and its application to fruit ripeness detection. Frontiers in Plant Science. 2025;16. doi:10.3389/fpls.2025.1423682
BibTeX
@article{Wu2025,
author = {Wu, Mengyang and Qiu, Ya and Wang, Wenying and Su, Xun and Cao, Yuhao and Bai, Yun},
title = {Improved RT-DETR and its application to fruit ripeness detection},
journal = {Frontiers in Plant Science},
year = {2025},
volume = {16},
doi = {10.3389/fpls.2025.1423682}
}
EUVIMED