Login | Register

Automatic Hardhat Wearing Detection to Enhance Construction Site Safety

Title:

Automatic Hardhat Wearing Detection to Enhance Construction Site Safety

Elsafty, Nehad (2015) Automatic Hardhat Wearing Detection to Enhance Construction Site Safety. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
Automatic Hardhat Wearing Detection to Enhance Construction Site Safety.pdf - Accepted Version
1MB

Abstract

ABSTRACT
Automatic Hardhat Wearing Detection to Enhance Construction Site Safety
Nehad Elsafty
Careers in the construction field are involved with risks and engender a wide range of dangers to which workers and professionals are exposed on a daily basis. Numerous injuries and deaths are reported annually. Injuries and deaths have multiple negative financial, emotional, and psychological consequences on the affected persons and their families. In addition, these accidents increase the time and costs of construction projects. Therefore, construction site safety is a critical issue that needs to be monitored and controlled throughout the construction project timeline by both professionals and contractors. Hardhat wearing is one of the basic safety regulations at construction sites, to which all workers and visitors should adhere all of the time. This study proposes a new automated method to determine if workers and others present on construction sites are wearing hardhats (or not). This method could automatically create alarms for those workers who are not wearing hardhats. The method comprises the following steps. First, video frames captured by fixed cameras on the construction site are used for the detection of human bodies and hardhats. Next, the detected human bodies and hardhats are matched using their geometric and spatial relationships. Those human bodies without their matched hardhats are highlighted to bring them to the attention of the onsite safety inspectors. This method has been tested using real site videos. The safety alert’s precision and recall demonstrates its effectiveness and potential to enhance onsite safety monitoring.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Building, Civil and Environmental Engineering
Item Type:Thesis (Masters)
Authors:Elsafty, Nehad
Institution:Concordia University
Degree Name:M.A.
Program:Building Engineering
Date:14 April 2015
Thesis Supervisor(s):zhu, zhenhua
ID Code:981956
Deposited By: NEHAD ELSAFTY
Deposited On:29 Oct 2018 13:58
Last Modified:29 Oct 2018 13:58
Related URLs:
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top