EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LKD-YOLOv8: A Lightweight Knowledge Distillation-Based Method for Infrared Object Detection

Xiancheng Cao, Yueli Hu iD, Haikun Zhang

Sensors · 29.06.2025 · 25 (13) · 4054

DOI: 10.3390/s25134054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.06.2025. Verfasst von Xiancheng Cao und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Currently, infrared object detection is utilized in a broad spectrum of fields, including military applications, security, and aerospace. Nonetheless, the limited computational power of edge devices presents a considerable challenge in achieving an optimal balance between accuracy and computational efficiency in infrared object detection. In order to enhance the accuracy of infrared target detection and strengthen the implementation of robust models on edge platforms for rapid real-time inference, this paper presents LKD-YOLOv8, an innovative infrared object detection method that integrates YOLOv8 architecture with masked generative distillation (MGD), further augmented by the lightweight convolution design and attention mechanism for improved feature adaptability. Linear deformable convolution (LDConv) strengthens spatial feature extraction by dynamically adjusting kernel offsets, while coordinate attention (CA) refines feature alignment through channel-wise interaction. We employ a large-scale model (YOLOv8s) as the teacher to imparts knowledge and supervise the training of a compact student model (YOLOv8n). Experiments show that LKD-YOLOv8 achieves a 1.18% mAP@0.5:0.95 improvement over baseline methods while reducing the parameter size by 7.9%. Our approach effectively balances accuracy and efficiency, rendering it applicable for resource-constrained edge devices in infrared scenarios.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismedge computationinfrared object detectionknowledge distillation

Autor:innen und Institutionen

  • School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China.
  • School of Mathematics-Physics and Finance, Anhui Polytechnic University, Wuhu 241000, China.

ORCID-Profile: Yueli Hu

Zitieren

APA

Cao, X., Hu, Y., & Zhang, H. (2025). LKD-YOLOv8: A Lightweight Knowledge Distillation-Based Method for Infrared Object Detection. Sensors, 25(13), 4054. https://doi.org/10.3390/s25134054

Vancouver

Cao X, Hu Y, Zhang H. LKD-YOLOv8: A Lightweight Knowledge Distillation-Based Method for Infrared Object Detection. Sensors. 2025;25(13):4054. doi:10.3390/s25134054

BibTeX
@article{Cao2025,
  author = {Cao, Xiancheng and Hu, Yueli and Zhang, Haikun},
  title = {LKD-YOLOv8: A Lightweight Knowledge Distillation-Based Method for Infrared Object Detection},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4054},
  doi = {10.3390/s25134054}
}
Kostenlos starten →