Safety Helmet Detection Based On Deep Learning
Author(s):
Disha Sanjay Patil, Swarupa Pankaj Patil, Darshana Kaivalya Patil, Bhagyashri Dilip Patil, Prof. Vinayak Patil
Keywords:
Deep Learning, CNN, YOLOV3.
Abstract
Safety helmet detection is a crucial task in ensuring workplace safety, especially in hazardous environments such as construction sites and industrial facilities. Traditional methods for safety helmet detection often rely on handcrafted features and are limited in their robustness and accuracy. In recent years, deep learning techniques, particularly convolutional neural networks (CNNs), have shown promising results in various computer vision tasks, including object detection. In this paper, we propose a deep learning-based approach for safety helmet detection using CNNs. We present a dataset of annotated images containing individuals wearing safety helmets, which is used to train and evaluate our model. Our approach involves fine-tuning a pre-trained CNN architecture on the safety helmet dataset to leverage its ability to extract high-level features from images. We experiment with different CNN architectures and training strategies to optimize the detection performance. Furthermore, we conduct extensive evaluation experiments on both synthetic and real-world data to demonstrate the effectiveness and robustness of our approach. The experimental results show that our proposed method achieves high accuracy and robustness in safety helmet detection, outperforming traditional methods and demonstrating its potential for practical applications in improving workplace safety.
Article Details
Unique Paper ID: 164851

Publication Volume & Issue: Volume 10, Issue 12

Page(s): 2505 - 2509
Article Preview & Download


Share This Article

Join our RMS



Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Latest Publication

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers