SafeLid Vision: A Machine Learning Approach to Automated Helmet Detection

Mrs. K.S.Saraswathi Devi

SafeLid Vision: A Machine Learning Approach to Automated Helmet Detection

Authors: Mrs. K.S.Saraswathi Devi

Unique Paper ID: 167192
Volume: 7
Issue: 9
PageNo: 370-373

Keywords: CNN ORC YOLO3 Machine Learning Helmet Detection

Abstract:
In major Indian cities, a surge in vehicle ownership has created a gridlock – traffic congestion. This, coupled with lax enforcement of helmet use among motorcycle riders, has become a major safety concern. Despite regulations mandating helmets, many riders disregard this rule, leading to a rise in accidents and fatalities. Current enforcement methods heavily rely on reviewing CCTV footage, requiring officers to manually zoom in and identify license plates of riders without helmets. This process is not only time-consuming but also inefficient. This paper proposes a solution that leverages machine learning for automated helmet detection. Helmet detection is a critical but complex task in computer vision, with applications beyond traffic monitoring. The proposed method tackles this challenge in three stages: pre-processing, feature extraction, and classification. The paper also reviews existing technologies and strategies for helmet detection, highlighting the promising results achieved by recent research using features extracted from techniques like Convolutional Neural Networks (CNNs). Our research aims to develop a system that automatically detects riders without helmets and captures their license plate numbers. The core concept revolves around a three-level deep learning object detection approach. First, the YOLOv3 algorithm identifies objects like motorcycles within the video frame. Then, YOLOv5 focuses on these detected motorcycles to determine if the rider is wearing a helmet. Finally, if a helmet violation is identified, YOLOv3 zooms in on the motorcycle to extract the license plate number using Optical Character Recognition (OCR). This extracted license plate number allows authorities to verify the vehicle's registration and potentially identify stolen vehicles within a database. By automating helmet detection and license plate capture, this system empowers traffic police to not only identify helmet violators but also track down stolen vehicles, significantly improving traffic safety and enforcement efficiency.

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 7
Issue: 9
PageNo: 370-373

SafeLid Vision: A Machine Learning Approach to Automated Helmet Detection

Available:https://ijirt.org/Article?manuscript=167192

15 Aug, 2024

SCALABLE IOT DATA MANAGEMENT IN CLOUD ENVIRONMENTS: TECHNIQUES AND CHALLENGES

15 Aug, 2024

OPTIMIZING CLOUD RESOURCE ALLOCATION FOR IOT SYSTEMS USING ML APPROACHES

16 Feb, 2021

Carrier App: Leveraging Machine Learning for Secure Crowdshipping

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry