Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Deep Learning Approach to Detect Complete Safety Equipment For Construction Workers Based On YOLOv7

Md. Shariful Islam, SM Shaqib, Shahriar Sultan Ramit, Shahrun Akter Khushbu, Abdus Sattar, Sheak Rashed Haider Noori

TL;DR

The paper tackles automatic detection of personal protective equipment (PPE) on construction workers using a YOLOv7-based deep learning pipeline. It builds a labeled dataset of helmets, goggles, jackets, gloves, and footwear, trains several YOLO variants, and demonstrates that YOLOv7 achieves the best performance with a mAP@0.5 of 87.7% and strong precision-recall, enabling real-time PPE monitoring. Key contributions include a thorough dataset creation/annotation process, a comprehensive model comparison, and evidence of real-time video applicability (≈70 FPS). The work advances construction safety by providing a scalable, automatic method to identify PPE violations and supports safer site practices through rapid, automated detection.

Abstract

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwears. The recommended approach uses the YOLO v7 (You Only Look Once) object detection algorithm to precisely locate these safety items. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a mAP@0.5 score of 87.7\%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research makes a contribution to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry

A Deep Learning Approach to Detect Complete Safety Equipment For Construction Workers Based On YOLOv7

TL;DR

The paper tackles automatic detection of personal protective equipment (PPE) on construction workers using a YOLOv7-based deep learning pipeline. It builds a labeled dataset of helmets, goggles, jackets, gloves, and footwear, trains several YOLO variants, and demonstrates that YOLOv7 achieves the best performance with a mAP@0.5 of 87.7% and strong precision-recall, enabling real-time PPE monitoring. Key contributions include a thorough dataset creation/annotation process, a comprehensive model comparison, and evidence of real-time video applicability (≈70 FPS). The work advances construction safety by providing a scalable, automatic method to identify PPE violations and supports safer site practices through rapid, automated detection.

Abstract

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwears. The recommended approach uses the YOLO v7 (You Only Look Once) object detection algorithm to precisely locate these safety items. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a mAP@0.5 score of 87.7\%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research makes a contribution to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry
Paper Structure (20 sections, 10 figures, 5 tables)

This paper contains 20 sections, 10 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Methodology
  4. Research Subject and Instrument
  5. Hardware instruments
  6. Data Collection
  7. Data Annotation
  8. Training The Dataset
  9. Training The Model
  10. Network Architecture of YOLOv7
  11. Results and Discussion
  12. Comparison Between All Trained Model
  13. Confusion matrix
  14. Model Performance Based on Video
  15. Comparison of the suggested model with alternative models
  16. ...and 5 more sections

Figures (10)

  • Figure 1: Safety Equipment Detection Workflow Diagram
  • Figure 2: All type of safety equipment’s sample
  • Figure 3: Manual Data Annotation using Labeling Annotator tool
  • Figure 4: text file (.txt) generated after saving the above
  • Figure 5: Data Distribution
  • ...and 5 more figures