Research and Implementation of YOLOv8+Transformer in Human Fall Detection Image Recognition

Authors

  • Qinqin Li School of Big Data and Artificial Intelligence, Anhui Xinhua University, Hefei 230088, China
  • Nvshenglan Ren School of Big Data and Artificial Intelligence, Anhui Xinhua University, Hefei 230088, China
  • Xinyu Wang School of Big Data and Artificial Intelligence, Anhui Xinhua University, Hefei 230088, China
  • Mengqing Hu School of Big Data and Artificial Intelligence, Anhui Xinhua University, Hefei 230088, China
  • Rui Guo West Campus of Beijing No.8 High School, Beijing 102308, China

DOI:

https://doi.org/10.54691/w0v9vp33

Keywords:

Fall Detection; YOLOv8; Transformer; Attention Mechanism; Image Enhancement.

Abstract

Human fall detection is a crucial research direction in the fields of intelligent security and elderly care monitoring. Traditional detection methods suffer from issues such as low accuracy, poor real-time performance, and privacy leakage. To address these problems, this paper proposes a human fall image recognition method that integrates YOLOv8 and Transformer. First, to tackle the limited sample size in public fall datasets, various data augmentation strategies like image rotation and flipping are employed to expand the dataset and enhance the model's generalization capability. Second, the Swin Transformer module is introduced into the YOLOv8 backbone network, leveraging its sliding window self-attention mechanism to improve the model's ability to capture global contextual information. Finally, multi-scale feature fusion is achieved through a feature pyramid network, thereby enhancing the detection accuracy for fall targets of varying scales.

Downloads

Download data is not yet available.

References

[1] Chen, N. H. (2025). Research on nighttime pedestrian detection based on low-light image enhancement and YOLOv8 model optimization [Doctoral dissertation]. Wuhan Textile University.

[2] Zhang, Y. T., Huang, D. Q., Wang, D. W., et al. (2023). A review of deep learning-based object detection algorithms and their applications. Computer Engineering and Applications, 59(18), 1–13.

[3] Fu, M. M., Deng, M. L., & Zhang, D. X. (2023). Object detection algorithm based on deep learning and Transformer. Computer Engineering and Applications, 59(1), 37–48.

[4] Yang, L. (2023). Research on automatic escalator pedestrian fall detection based on deep learning [Doctoral dissertation]. Xi'an University of Science and Technology.

[5] Luo, Y. W., Huo, G. Y., & Cheng, Z. (2026). Sonar image object detection combining sample generation with Swin Transformer-YOLO network. Acta Acustica, 51(1), 201–215.

[6] Yang, L. Y. (2025). Research on an improved YOLOv8 fire image detection algorithm integrating Transformer [Doctoral dissertation]. Shenyang University.

Downloads

Published

2026-06-23

Issue

Section

Articles