EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LFIR-YOLO: Lightweight Model for Infrared Vehicle and Pedestrian Detection

Quan Wang, Fengyuan Liu, Yi Cao, Farhan Ullah iD, Muxiong Zhou

Sensors · 14.10.2024 · 24 (20) · 6609

DOI: 10.3390/s24206609 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.10.2024. Verfasst von Quan Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Internet of Things Engineering, Wuxi University, Wuxi 214105, China. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Project of Key Laboratory of Ministry of Public Security for Road Traffic Safety;Jiangsu Universities' General Project for Philosophy and Social Science R…, Open Project of Key Laboratory of Ministry of Public Security for Road Traffic Safety, 2023 Excellent Science and Technology Innovation Team of Jiangsu Province Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The complexity of urban road scenes at night and the inadequacy of visible light imaging in such conditions pose significant challenges. To address the issues of insufficient color information, texture detail, and low spatial resolution in infrared imagery, we propose an enhanced infrared detection model called LFIR-YOLO, which is built upon the YOLOv8 architecture. The primary goal is to improve the accuracy of infrared target detection in nighttime traffic scenarios while meeting practical deployment requirements. First, to address challenges such as limited contrast and occlusion noise in infrared images, the C2f module in the high-level backbone network is augmented with a Dilation-wise Residual (DWR) module, incorporating multi-scale infrared contextual information to enhance feature extraction capabilities. Secondly, at the neck of the network, a Content-guided Attention (CGA) mechanism is applied to fuse features and re-modulate both initial and advanced features, catering to the low signal-to-noise ratio and sparse detail features characteristic of infrared images. Third, a shared convolution strategy is employed in the detection head, replacing the decoupled head strategy and utilizing shared Detail Enhancement Convolution (DEConv) and Group Norm (GN) operations to achieve lightweight yet precise improvements. Finally, loss functions, PIoU v2 and Adaptive Threshold Focal Loss (ATFL), are integrated into the model to better decouple infrared targets from the background and to enhance convergence speed. The experimental results on the FLIR and multispectral datasets show that the proposed LFIR-YOLO model achieves an improvement in detection accuracy of 4.3% and 2.6%, respectively, compared to the YOLOv8 model. Furthermore, the model demonstrates a reduction in parameters and computational complexity by 15.5% and 34%, respectively, enhancing its suitability for real-time deployment on resource-constrained edge devices.

Schlagwörter

Stichwörter der Autor:innen

C2f DWRCGA Fusioninfrared imaging detectionlightweight headloss optimizationtraffic scenes

Autor:innen und Institutionen

  • School of Internet of Things Engineering, Wuxi University, Wuxi 214105, China.
  • School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 210044, China.
  • Key Laboratory of Ministry of Public Security for Road Traffic Safety, Traffic Management Research Institute of the Ministry of Public Security, Wuxi 214151, China.

ORCID-Profile: Farhan Ullah

Förderung

  • Open Project of Key Laboratory of Ministry of Public Security for Road Traffic Safety;Jiangsu Universities' General Project for Philosophy and Social Science R…
  • Open Project of Key Laboratory of Ministry of Public Security for Road Traffic Safety
  • 2023 Excellent Science and Technology Innovation Team of Jiangsu Province Universities
  • Jiangsu Universities’ General Project for Philosophy and Social Science Research
  • Open Project of National Engineering Technology Research Center For Sensor Network
  • Wuxi University Research Start-up Fund for Introduced Talents
  • National Natural Science Foundation of China

Zitieren

APA

Wang, Q., Liu, F., Cao, Y., Ullah, F., & Zhou, M. (2024). LFIR-YOLO: Lightweight Model for Infrared Vehicle and Pedestrian Detection. Sensors, 24(20), 6609. https://doi.org/10.3390/s24206609

Vancouver

Wang Q, Liu F, Cao Y, Ullah F, Zhou M. LFIR-YOLO: Lightweight Model for Infrared Vehicle and Pedestrian Detection. Sensors. 2024;24(20):6609. doi:10.3390/s24206609

BibTeX
@article{Wang2024,
  author = {Wang, Quan and Liu, Fengyuan and Cao, Yi and Ullah, Farhan and Zhou, Muxiong},
  title = {LFIR-YOLO: Lightweight Model for Infrared Vehicle and Pedestrian Detection},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {20},
  pages = {6609},
  doi = {10.3390/s24206609}
}
Kostenlos starten →