EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Serial Multi-Scale Feature Fusion and Enhancement Network for Amur Tiger Re-Identification

Nuo Xu, Zhibin Ma, Yi Xia, Yanqi Dong iD, Jiali Zi, Delong Xu, Fu Xu, Xiaohui Su iD, Haiyan Zhang, Feixiang Chen iD

Animals · 04.04.2024 · 14 (7) · 1106

DOI: 10.3390/ani14071106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 04.04.2024. Verfasst von Nuo Xu und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Outstanding Youth Team Project of Central Universities, National Key R&D Program of China, The Emergency Open Competition Project of National Forestry and Grassland Administration.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Amur tiger is an important endangered species in the world, and its re-identification (re-ID) plays an important role in regional biodiversity assessment and wildlife resource statistics. This paper focuses on the task of Amur tiger re-ID based on visible light images from screenshots of surveillance videos or camera traps, aiming to solve the problem of low accuracy caused by camera perspective, noisy background noise, changes in motion posture, and deformation of Amur tiger body patterns during the re-ID process. To overcome this challenge, we propose a serial multi-scale feature fusion and enhancement re-ID network of Amur tiger for this task, in which global and local branches are constructed. Specifically, we design a global inverted pyramid multi-scale feature fusion method in the global branch to effectively fuse multi-scale global features and achieve high-level, fine-grained, and deep semantic feature preservation. We also design a local dual-domain attention feature enhancement method in the local branch, further enhancing local feature extraction and fusion by dividing local feature blocks. Based on the above model structure, we evaluated the effectiveness and feasibility of the model on the public dataset of the Amur Tiger Re-identification in the Wild (ATRW), and achieved good results on mAP, Rank-1, and Rank-5, demonstrating a certain competitiveness. In addition, since our proposed model does not require the introduction of additional expensive annotation information and does not incorporate other pre-training modules, it has important advantages such as strong transferability and simple training.

Schlagwörter

Stichwörter der Autor:innen

Amur tigerattention mechanismdeep learningdouble branch structurefeature pyramidintelligent recognition

Autor:innen und Institutionen

  • School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China.
  • Engineering Research Center for Forestry-Oriented Intelligent Information Processing, National Forestry and Grassland Administration, Beijing 100083, China.

ORCID-Profile: Yanqi Dong, Xiaohui Su, Feixiang Chen

Förderung

  • Outstanding Youth Team Project of Central Universities
  • National Key R&D Program of China
  • The Emergency Open Competition Project of National Forestry and Grassland Administration
  • National Key R&D Program of China
  • Emergency Open Competition Project of the National Forestry and Grassland Administration

Zitieren

APA

Xu, N., Ma, Z., Xia, Y., Dong, Y., Zi, J., Xu, D., Xu, F., Su, X., Zhang, H., & Chen, F. (2024). A Serial Multi-Scale Feature Fusion and Enhancement Network for Amur Tiger Re-Identification. Animals, 14(7), 1106. https://doi.org/10.3390/ani14071106

Vancouver

Xu N, Ma Z, Xia Y, Dong Y, Zi J, Xu D, et al. A Serial Multi-Scale Feature Fusion and Enhancement Network for Amur Tiger Re-Identification. Animals. 2024;14(7):1106. doi:10.3390/ani14071106

BibTeX
@article{Xu2024,
  author = {Xu, Nuo and Ma, Zhibin and Xia, Yi and Dong, Yanqi and Zi, Jiali and Xu, Delong and Xu, Fu and Su, Xiaohui and Zhang, Haiyan and Chen, Feixiang},
  title = {A Serial Multi-Scale Feature Fusion and Enhancement Network for Amur Tiger Re-Identification},
  journal = {Animals},
  year = {2024},
  volume = {14},
  number = {7},
  pages = {1106},
  doi = {10.3390/ani14071106}
}
Kostenlos starten →