Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comparative Analysis of YOLOv5, YOLOv8, and YOLOv10 in Kitchen Safety

Athulya Sundaresan Geetha, Muhammad Hussain

TL;DR

The study benchmarks YOLOv5, YOLOv8, and YOLOv10 for detecting two knife-handling hazards in kitchen scenes using a 6004-frame, six-class dataset derived from smartphone video. It evaluates performance with precision, recall, F1, mAP, and confusion matrices, finding YOLOv5 most balanced overall, YOLOv8 strongest on hazard1, and YOLOv10 comparatively weaker. The work offers architectural insights and practical guidance for deploying real-time kitchen safety surveillance, while highlighting limitations in background discrimination and hazard2 detection. The methodology and augmentation strategies provide a blueprint for robust hazard detection in dynamic, cluttered environments.

Abstract

Knife safety in the kitchen is essential for preventing accidents or injuries with an emphasis on proper handling, maintenance, and storage methods. This research presents a comparative analysis of three YOLO models, YOLOv5, YOLOv8, and YOLOv10, to detect the hazards involved in handling knife, concentrating mainly on ensuring fingers are curled while holding items to be cut and that hands should only be in contact with knife handle avoiding the blade. Precision, recall, F-score, and normalized confusion matrix are used to evaluate the performance of the models. The results indicate that YOLOv5 performed better than the other two models in identifying the hazard of ensuring hands only touch the blade, while YOLOv8 excelled in detecting the hazard of curled fingers while holding items. YOLOv5 and YOLOv8 performed almost identically in recognizing classes such as hand, knife, and vegetable, whereas YOLOv5, YOLOv8, and YOLOv10 accurately identified the cutting board. This paper provides insights into the advantages and shortcomings of these models in real-world settings. Moreover, by detailing the optimization of YOLO architectures for safe knife handling, this study promotes the development of increased accuracy and efficiency in safety surveillance systems.

A Comparative Analysis of YOLOv5, YOLOv8, and YOLOv10 in Kitchen Safety

TL;DR

The study benchmarks YOLOv5, YOLOv8, and YOLOv10 for detecting two knife-handling hazards in kitchen scenes using a 6004-frame, six-class dataset derived from smartphone video. It evaluates performance with precision, recall, F1, mAP, and confusion matrices, finding YOLOv5 most balanced overall, YOLOv8 strongest on hazard1, and YOLOv10 comparatively weaker. The work offers architectural insights and practical guidance for deploying real-time kitchen safety surveillance, while highlighting limitations in background discrimination and hazard2 detection. The methodology and augmentation strategies provide a blueprint for robust hazard detection in dynamic, cluttered environments.

Abstract

Knife safety in the kitchen is essential for preventing accidents or injuries with an emphasis on proper handling, maintenance, and storage methods. This research presents a comparative analysis of three YOLO models, YOLOv5, YOLOv8, and YOLOv10, to detect the hazards involved in handling knife, concentrating mainly on ensuring fingers are curled while holding items to be cut and that hands should only be in contact with knife handle avoiding the blade. Precision, recall, F-score, and normalized confusion matrix are used to evaluate the performance of the models. The results indicate that YOLOv5 performed better than the other two models in identifying the hazard of ensuring hands only touch the blade, while YOLOv8 excelled in detecting the hazard of curled fingers while holding items. YOLOv5 and YOLOv8 performed almost identically in recognizing classes such as hand, knife, and vegetable, whereas YOLOv5, YOLOv8, and YOLOv10 accurately identified the cutting board. This paper provides insights into the advantages and shortcomings of these models in real-world settings. Moreover, by detailing the optimization of YOLO architectures for safe knife handling, this study promotes the development of increased accuracy and efficiency in safety surveillance systems.
Paper Structure (25 sections, 15 equations, 9 figures, 3 tables)

This paper contains 25 sections, 15 equations, 9 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Dataset
  5. Data Augmentation
  6. Random Crop
  7. Random Rotation
  8. Random Shear
  9. Random Grayscale
  10. Hue
  11. Saturation
  12. Brightness
  13. Exposure
  14. Blur
  15. Random Noise
  16. ...and 10 more sections

Figures (9)

  • Figure 1: Sample image of the kitchen dataset.
  • Figure 2: Comparison of precision values across three models.
  • Figure 3: Comparison of recall values across the three models.
  • Figure 4: Comparison of F1 versus confidence across the three models.
  • Figure 5: Comparison of mAP50 values across three models.
  • ...and 4 more figures