EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Long-Term Video Tracking Method for Group-Housed Pigs

Qiumei Yang, Xiangyang Hui, Yigui Huang, Miaobin Chen, Senpeng Huang iD, Deqin Xiao

Animals · 19.05.2024 · 14 (10) · 1505

DOI: 10.3390/ani14101505 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 19.05.2024. Verfasst von Qiumei Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Research and Development Project of Guangdong, the National Key Research and Development Program of China, Key Research and Development Project of Guangdong.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pig tracking provides strong support for refined management in pig farms. However, long and continuous multi-pig tracking is still extremely challenging due to occlusion, distortion, and motion blurring in real farming scenarios. This study proposes a long-term video tracking method for group-housed pigs based on improved StrongSORT, which can significantly improve the performance of pig tracking in production scenarios. In addition, this research constructs a 24 h pig tracking video dataset, providing a basis for exploring the effectiveness of long-term tracking algorithms. For object detection, a lightweight pig detection network, YOLO v7-tiny_Pig, improved based on YOLO v7-tiny, is proposed to reduce model parameters and improve detection speed. To address the target association problem, the trajectory management method of StrongSORT is optimized according to the characteristics of the pig tracking task to reduce the tracking identity (ID) switching and improve the stability of the algorithm. The experimental results show that YOLO v7-tiny_Pig ensures detection applicability while reducing parameters by 36.7% compared to YOLO v7-tiny and achieving an average video detection speed of 435 frames per second. In terms of pig tracking, Higher-Order Tracking Accuracy (HOTA), Multi-Object Tracking Accuracy (MOTP), and Identification F1 (IDF1) scores reach 83.16%, 97.6%, and 91.42%, respectively. Compared with the original StrongSORT algorithm, HOTA and IDF1 are improved by 6.19% and 10.89%, respectively, and Identity Switch (IDSW) is reduced by 69%. Our algorithm can achieve the continuous tracking of pigs in real scenarios for up to 24 h. This method provides technical support for non-contact pig automatic monitoring.

Schlagwörter

Stichwörter der Autor:innen

deep learningmulti-object trackingobject detectionpig

Autor:innen und Institutionen

  • College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China.
  • Key Laboratory of Smart Agricultural Technology in Tropical South China, Ministry of Agriculture and Rural Affairs, Guangzhou 510642, China.

ORCID-Profile: Senpeng Huang

Förderung

  • the Key Research and Development Project of Guangdong
  • the National Key Research and Development Program of China
  • Key Research and Development Project of Guangdong
  • National Key Research and Development Program of China

Zitieren

APA

Yang, Q., Hui, X., Huang, Y., Chen, M., Huang, S., & Xiao, D. (2024). A Long-Term Video Tracking Method for Group-Housed Pigs. Animals, 14(10), 1505. https://doi.org/10.3390/ani14101505

Vancouver

Yang Q, Hui X, Huang Y, Chen M, Huang S, Xiao D. A Long-Term Video Tracking Method for Group-Housed Pigs. Animals. 2024;14(10):1505. doi:10.3390/ani14101505

BibTeX
@article{Yang2024,
  author = {Yang, Qiumei and Hui, Xiangyang and Huang, Yigui and Chen, Miaobin and Huang, Senpeng and Xiao, Deqin},
  title = {A Long-Term Video Tracking Method for Group-Housed Pigs},
  journal = {Animals},
  year = {2024},
  volume = {14},
  number = {10},
  pages = {1505},
  doi = {10.3390/ani14101505}
}
Kostenlos starten →