A Multi-Task Detection Approach with Multi-Scale Attention Aggregation and Feature Enhancement
Agronomy · 09.02.2026 · 16 (4) · 419
DOI: 10.3390/agronomy16040419 ↗Kurz gefasst
Fachartikel in der Zeitschrift Agronomy, online erschienen am 09.02.2026. Verfasst von Xibao Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Project of Scientific and Technological Innovation 2030, National Natural Science Foundation of China, Major Research Plan of the National Natural Science Foundation of China.
Abstract (Originalsprache)
This research presents an advanced YOLOv8-MMD framework specifically designed for intelligent white radish harvesting systems, addressing the critical need for simultaneous species recognition and quality evaluation. The proposed architecture is built upon a dual-branch detection system (YOLOv8-Dual) with a shared Backbone network, and is further enhanced by two novel components: the Multi-Scale Attention Aggregation (MSAA) module that strategically combines channel-wise and spatial attention mechanisms to refine feature representation, and the Multi-scale Feature Enhancement (MAFE) module that facilitates effective information fusion across different hierarchical levels of the network. Extensive experimental validation reveals that the YOLOv8-MMD model achieves remarkable performance metrics, including a species detection precision of 0.945 and a quality assessment precision of 0.812, representing improvements of 1.4% and 4%, respectively, over the baseline YOLOv8-Dual model. Under the comprehensive mAP@50 evaluation standard, the model reaches 0.949 for species identification and 0.859 for quality classification, while maintaining impressive recall rates of 0.924 and 0.836 for the respective tasks. The system demonstrates exceptional robustness when deployed in challenging field conditions, consistently performing well under varying lighting intensities, different growth stages, and partial occlusion scenarios. Computational analysis confirms the model’s practical viability, achieving a processing throughput of 112 frames per second with 8.1 GFLOPs of computational overhead, thereby meeting stringent real-time operational requirements for agricultural robotic applications. Comparative studies with existing methods further substantiate the superiority of the proposed approach in balancing detection accuracy with computational efficiency. The integration of multi-scale attention mechanisms and hierarchical feature enhancement strategies provides a comprehensive solution for automated agricultural harvesting in complex, unstructured environments, offering significant potential for practical implementation in precision agriculture systems.
Förderung
- Major Project of Scientific and Technological Innovation 2030
- National Natural Science Foundation of China
- Major Research Plan of the National Natural Science Foundation of China
Zitieren
APA
Wu, X., Yang, K., Zhao, W., Wang, Y., Chen, W., & Zhao, C. (2026). A Multi-Task Detection Approach with Multi-Scale Attention Aggregation and Feature Enhancement. Agronomy, 16(4), 419. https://doi.org/10.3390/agronomy16040419
Vancouver
Wu X, Yang K, Zhao W, Wang Y, Chen W, Zhao C. A Multi-Task Detection Approach with Multi-Scale Attention Aggregation and Feature Enhancement. Agronomy. 2026;16(4):419. doi:10.3390/agronomy16040419
BibTeX
@article{Wu2026,
author = {Wu, Xibao and Yang, Kexin and Zhao, Wei and Wang, Yiqun and Chen, Wenbai and Zhao, Chunjiang},
title = {A Multi-Task Detection Approach with Multi-Scale Attention Aggregation and Feature Enhancement},
journal = {Agronomy},
year = {2026},
volume = {16},
number = {4},
pages = {419},
doi = {10.3390/agronomy16040419}
}
EUVIMED