EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on the Recognition and Tracking of Group-Housed Pigs’ Posture Based on Edge Computing

Wenwen Zha, Hualong Li, Guodong Wu, Liping Zhang, Weihao Pan, Lichuan Gu, Jun Jiao, Qiang Zhang

Sensors · 03.11.2023 · 23 (21) · 8952

DOI: 10.3390/s23218952 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.11.2023. Verfasst von Wenwen Zha und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Computer, Anhui Agricultural University, Hefei 230036, China. Hauptthemen laut MEDLINE: Sus scrofa, Algorithms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Provincial Department of Science and Technology, Anhui Provincial Department of Education, Department of Science and Technology of Anhui Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The existing algorithms for identifying and tracking pigs in barns generally have a large number of parameters, relatively complex networks and a high demand for computational resources, which are not suitable for deployment in embedded-edge nodes on farms. A lightweight multi-objective identification and tracking algorithm based on improved YOLOv5s and DeepSort was developed for group-housed pigs in this study. The identification algorithm was optimized by: (i) using a dilated convolution in the YOLOv5s backbone network to reduce the number of model parameters and computational power requirements; (ii) adding a coordinate attention mechanism to improve the model precision; and (iii) pruning the BN layers to reduce the computational requirements. The optimized identification model was combined with DeepSort to form the final Tracking by Detecting algorithm and ported to a Jetson AGX Xavier edge computing node. The algorithm reduced the model size by 65.3% compared to the original YOLOv5s. The algorithm achieved a recognition precision of 96.6%; a tracking time of 46 ms; and a tracking frame rate of 21.7 FPS, and the precision of the tracking statistics was greater than 90%. The model size and performance met the requirements for stable real-time operation in embedded-edge computing nodes for monitoring group-housed pigs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sus scrofaAlgorithmsSwineAnimalsFarmsPostureRecognition, Psychology

Stichwörter der Autor:innen

behavior monitoringedge computingmulti-target trackingtarget detection

Autor:innen und Institutionen

  • School of Information and Computer, Anhui Agricultural University, Hefei 230036, China.
  • Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, China.
  • Institute of Agricultural Economy and Information, Anhui Academy of Agricultural Sciences, Hefei 230031, China.
  • Department of Biosystems Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada.

Förderung

  • Anhui Provincial Department of Science and Technology
  • Anhui Provincial Department of Education
  • Department of Science and Technology of Anhui Province
  • Anhui Province Department of Education

Zitieren

APA

Zha, W., Li, H., Wu, G., Zhang, L., Pan, W., Gu, L., Jiao, J., & Zhang, Q. (2023). Research on the Recognition and Tracking of Group-Housed Pigs’ Posture Based on Edge Computing. Sensors, 23(21), 8952. https://doi.org/10.3390/s23218952

Vancouver

Zha W, Li H, Wu G, Zhang L, Pan W, Gu L, et al. Research on the Recognition and Tracking of Group-Housed Pigs’ Posture Based on Edge Computing. Sensors. 2023;23(21):8952. doi:10.3390/s23218952

BibTeX
@article{Zha2023,
  author = {Zha, Wenwen and Li, Hualong and Wu, Guodong and Zhang, Liping and Pan, Weihao and Gu, Lichuan and Jiao, Jun and Zhang, Qiang},
  title = {Research on the Recognition and Tracking of Group-Housed Pigs’ Posture Based on Edge Computing},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {21},
  pages = {8952},
  doi = {10.3390/s23218952}
}
Kostenlos starten →