EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LPCF-YOLO: A YOLO-Based Lightweight Algorithm for Pedestrian Anomaly Detection with Parallel Cross-Fusion

Peiyi Jia, Hu Sheng, Shijie Jia iD

Sensors · 26.04.2025 · 25 (9) · 2752

DOI: 10.3390/s25092752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.04.2025. Verfasst von Peiyi Jia und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Rail Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Project of Liaoning Provincial Department of Education in China, Science and Technology Project of Liaoning Province Transportation Department in China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the issue of high complexity in current pedestrian anomaly detection network models, which hinders real-world deployment, this paper proposes a lightweight anomaly detection network called LPCF-YOLO (Lightweight Parallel Cross-Fusion YOLO) based on the YOLOv8n model. Firstly, the FPC-F (Fast Parallel Cross-Fusion) module, which incorporates PConv, and the S-EMCP (Space-efficient Merging Convolution Pooling) module are designed in the backbone network to replace C2F and SPPF at various scale branches. Additionally, an ADown module is introduced in the third layer to reduce the computational cost. In the neck network, a Lightweight High-level Screening Feature Pyramid Network (L-HSFPN) is designed to replace the PAFPN structure. Furthermore, the Wise-IoU loss function is employed to enhance the model’s localization performance and generalization ability. The experimental results in the UCSD-Ped1 and UCSD-Ped2 datasets show that, compared to YOLOv8n, the proposed approach reduces parameters by 30.33% and FLOPs by 79.01%, achieving 2.09 M parameters and 1.7 G FLOPs; it also results in a 179.62% increase in FPS to 43.9. Meanwhile, the mean average precision (mAP@0.5) is either maintained (in the UCSD-Ped2 dataset) or slightly improved (in the UCSD-Ped1 dataset).

Schlagwörter

Stichwörter der Autor:innen

LPCF-YOLOlightweight feature extractionparallel cross-fusionpedestrian abnormal detection

Autor:innen und Institutionen

  • School of Rail Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, China.

ORCID-Profile: Shijie Jia

Förderung

  • Scientific Research Project of Liaoning Provincial Department of Education in China
  • Science and Technology Project of Liaoning Province Transportation Department in China

Zitieren

APA

Jia, P., Sheng, H., & Jia, S. (2025). LPCF-YOLO: A YOLO-Based Lightweight Algorithm for Pedestrian Anomaly Detection with Parallel Cross-Fusion. Sensors, 25(9), 2752. https://doi.org/10.3390/s25092752

Vancouver

Jia P, Sheng H, Jia S. LPCF-YOLO: A YOLO-Based Lightweight Algorithm for Pedestrian Anomaly Detection with Parallel Cross-Fusion. Sensors. 2025;25(9):2752. doi:10.3390/s25092752

BibTeX
@article{Jia2025,
  author = {Jia, Peiyi and Sheng, Hu and Jia, Shijie},
  title = {LPCF-YOLO: A YOLO-Based Lightweight Algorithm for Pedestrian Anomaly Detection with Parallel Cross-Fusion},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2752},
  doi = {10.3390/s25092752}
}
Kostenlos starten →