.png){kind=icon}
.png){kind=icon}
Return
Personal protective equipment detection method based on knowledge distillation
.png){kind=icon}
PRE
AI
C
R
Y
X
S
DOI：10.1007/s00530-026-02574-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Automatic detection of personal protective equipment (PPE) is critical for ensuring safety in construction sites. However, current methods struggle with two major challenges. One is the limited diversity of training data, which restricts robustness in adverse environments. The other is the accuracy–efficiency trade-off inherent in lightweight models. We propose a detection framework called distillation alignment YOLO (DA-YOLO) for PPE detection. Our method enhances data diversity through controllable augmentation of adverse conditions and introduces a teacher–student distillation framework with consistency constraints across predictions and high-order features extracted from baseline. This joint constraint enables the student model to achieve strong generalization while maintaining low computational cost. Experimental results on public PPE dataset show that DA-YOLO achieves the best performance under the same parameter size with mAP50 reaching 95%, representing an improvement of 4.7% over YOLOv13. By integrating controllable augmentation and a dual-consistency distillation strategy, our method mitigates the critical issues in smart construction site.
Keywords:
Smart construction site
Personal protective equipment
Detection
Knowledge distillation
Journal
IF:
3.1
Papers:
2.7K
Citations:
2.7K
Organization
Cited Papers