EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Improved Lightweight Model for Protected Wildlife Detection in Camera Trap Images

Zengjie Du iD, Dasheng Wu iD, Qingqing Wen, Fengya Xu iD, Zhongbin Liu, Cheng Li, Ruikang Luo

Sensors · 02.12.2025 · 25 (23) · 7331

DOI: 10.3390/s25237331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.12.2025. Verfasst von Zengjie Du und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China. Hauptthemen laut MEDLINE: Animals, Wild, Conservation of Natural Resources. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the General Scientific Research Project of Zhejiang Provincial Education Department, the Zhejiang Provincial College Student Science and Technology Activity Plan (Xinmiao Talent Program), Zhejiang Forestry Science and Technology Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effective monitoring of protected wildlife is crucial for biodiversity conservation. While camera traps provide valuable data for ecological observation, existing deep learning models often suffer from low accuracy in detecting rare species and high computational costs, hindering their deployment on edge devices. To address these challenges, this study proposes YOLO11-APS, an improved lightweight model for protected wildlife detection. It enhances the YOLO11n by integrating the self-Attention and Convolution (ACmix) module, the Partial Convolution (PConv) module, and the SlimNeck paradigm. These improvements strengthen feature extraction under complex conditions while reducing computational costs. Experimental results demonstrate that YOLO11-APS achieves superior detection performance compared to the baseline model, attaining a precision of 92.7%, a recall of 87.0%, an mAP@0.5 of 92.6% and an mAP@0.5:0.95 of 62.2%. In terms of model lightweighting, YOLO11-APS reduces the number of parameters, floating-point operations, and model size by 10.1%, 11.1%, and 9.5%, respectively. YOLO11-APS achieves an optimal balance between accuracy and model complexity, outperforming existing mainstream lightweight detection models. Furthermore, tests on unseen wildlife data confirm its strong transferability and robustness. This work provides an efficient deep learning tool for automated wildlife monitoring in protected areas, facilitating the development of intelligent ecological sensing systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Animals, WildConservation of Natural ResourcesAnimalsDeep LearningBiodiversityAlgorithms

Stichwörter der Autor:innen

YOLOcamera trapslightweight deep learningobject detectionprotected wildlife

Autor:innen und Institutionen

  • College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China.
  • Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou 311300, China.
  • Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou 311300, China.
  • Wucheng Nanshan Provincial Nature Reserve Management Center of Zhejiang Province, Jinhua 321000, China.

ORCID-Profile: Zengjie Du, Dasheng Wu, Fengya Xu

Förderung

  • the General Scientific Research Project of Zhejiang Provincial Education Department
  • the Zhejiang Provincial College Student Science and Technology Activity Plan (Xinmiao Talent Program)
  • Zhejiang Forestry Science and Technology Project
  • General Scientific Research Project of Zhejiang Provincial Education Department
  • Zhejiang Provincial College Student Science and Technology Activity Plan

Zitieren

APA

Du, Z., Wu, D., Wen, Q., Xu, F., Liu, Z., Li, C., & Luo, R. (2025). An Improved Lightweight Model for Protected Wildlife Detection in Camera Trap Images. Sensors, 25(23), 7331. https://doi.org/10.3390/s25237331

Vancouver

Du Z, Wu D, Wen Q, Xu F, Liu Z, Li C, et al. An Improved Lightweight Model for Protected Wildlife Detection in Camera Trap Images. Sensors. 2025;25(23):7331. doi:10.3390/s25237331

BibTeX
@article{Du2025,
  author = {Du, Zengjie and Wu, Dasheng and Wen, Qingqing and Xu, Fengya and Liu, Zhongbin and Li, Cheng and Luo, Ruikang},
  title = {An Improved Lightweight Model for Protected Wildlife Detection in Camera Trap Images},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {23},
  pages = {7331},
  doi = {10.3390/s25237331}
}
Kostenlos starten →