EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLO-Shrimp: A Lightweight Detection Model for Shrimp Feed Residues Fusing Multi-Attention Features

Tianwen Hou, Xinying Miao, Zhenghan Wang, Yi Zhang iD, Zhipeng He, Yifei Sun, Wei Wang iD, Ping Ren

Sensors · 24.01.2026 · 26 (3) · 791

DOI: 10.3390/s26030791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.01.2026. Verfasst von Tianwen Hou und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Dalian Ocean University, Dalian 116023, China. Hauptthemen laut MEDLINE: Aquaculture, Animal Feed. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: General Scientific Research Projects of Liaoning Province Science and Technology Joint Plan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Precise control of feeding rates is critically important in intensive shrimp farming for cost reduction, optimization of farming strategies, and protection of the aquatic environment. However, current assessment of residual feed in feeding trays relies predominantly on manual visual inspection, which is inefficient, highly subjective, and difficult to standardize. The residual feed particles typically exhibit characteristics such as small size, high density, irregular shapes, and mutual occlusion, posing significant challenges for automated visual detection. To address these issues, this study proposes a lightweight detection model named YOLO-Shrimp. To enhance the network’s capability in extracting features from small and dense targets, a novel attention mechanism termed EnSimAM is designed. Building upon the SimAM structure, EnSimAM incorporates local variance and edge response to achieve multi-scale feature perception. Furthermore, to improve localization accuracy for small objects, an enhanced weighted intersection over union loss function, EnWIoU, is introduced. Additionally, the lightweight RepGhost module is adopted as the backbone of the model, significantly reducing both the number of parameters and computational complexity while maintaining detection accuracy. Evaluated on a real-world aquaculture dataset containing 3461 images, YOLO-Shrimp achieves mAP@0.5 and mAP@0.5:0.95 scores of 70.01% and 28.01%, respectively, while reducing the parameter count by 19.7% and GFLOPs by 14.6% compared to the baseline model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AquacultureAnimal FeedAnimalsDetection AlgorithmsAlgorithms

Stichwörter der Autor:innen

YOLOaquaculturedeep learningshrimp farming

Autor:innen und Institutionen

  • College of Information Engineering, Dalian Ocean University, Dalian 116023, China.
  • Liaoning Provincial Key Laboratory Marine Informat Technology, Dalian 116023, China.

ORCID-Profile: Yi Zhang, Wei Wang

Förderung

  • General Scientific Research Projects of Liaoning Province Science and Technology Joint Plan Project

Zitieren

APA

Hou, T., Miao, X., Wang, Z., Zhang, Y., He, Z., Sun, Y., Wang, W., & Ren, P. (2026). YOLO-Shrimp: A Lightweight Detection Model for Shrimp Feed Residues Fusing Multi-Attention Features. Sensors, 26(3), 791. https://doi.org/10.3390/s26030791

Vancouver

Hou T, Miao X, Wang Z, Zhang Y, He Z, Sun Y, et al. YOLO-Shrimp: A Lightweight Detection Model for Shrimp Feed Residues Fusing Multi-Attention Features. Sensors. 2026;26(3):791. doi:10.3390/s26030791

BibTeX
@article{Hou2026,
  author = {Hou, Tianwen and Miao, Xinying and Wang, Zhenghan and Zhang, Yi and He, Zhipeng and Sun, Yifei and Wang, Wei and Ren, Ping},
  title = {YOLO-Shrimp: A Lightweight Detection Model for Shrimp Feed Residues Fusing Multi-Attention Features},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {3},
  pages = {791},
  doi = {10.3390/s26030791}
}
Kostenlos starten →