Performance of YOLOv7 in Kitchen Safety While Handling Knife

TL;DR

The study addresses detecting unsafe knife-handling hazards in kitchen scenes using YOLOv7. A dataset of 6,004 frames from 1920×1080 video was labeled into six classes, including two hazard types. The model was trained for 40 epochs using AdamW with a learning rate of $0.001$, achieving a peak $mAP_{50-95}=0.7879$, precision $=0.9063$, and recall $=0.7503$ at epoch 31. These results demonstrate potential for real-time hazard alerts to promote safer cooking practices.

Abstract

Safe knife practices in the kitchen significantly reduce the risk of cuts, injuries, and serious accidents during food preparation. Using YOLOv7, an advanced object detection model, this study focuses on identifying safety risks during knife handling, particularly improper finger placement and blade contact with hand. The model's performance was evaluated using metrics such as precision, recall, mAP50, and mAP50-95. The results demonstrate that YOLOv7 achieved its best performance at epoch 31, with a mAP50-95 score of 0.7879, precision of 0.9063, and recall of 0.7503. These findings highlight YOLOv7's potential to accurately detect knife-related hazards, promoting the development of improved kitchen safety.

Figures (10)

• Figure 1: Knife hazards sample.
• Figure 2: Grayscle image
• Figure 3: Precision-confidence value of YOLOv7 for Kitchen dataset.
• Figure 4: Precision of YOLOv7.
• Figure 5: Recall-confidence value of YOLOv7.