A Deep Learning-Based System to Detect Triple Riding and Helmet Violations Through CCTV Webcam

DOI

10.2991/978-94-6463-700-7_27How to use a DOI?

Keywords

YOLOv8; Traffic violations; Real-time detection; Helmet and Triple Riding Violations; CCTV surveillance

Abstract

The automatic recognition of motorcycle helmets and detection of triple-riding violations in real-time surveillance videos is a growing application in computer science. Deep learning techniques for object detection and classification have gained popularity due to their potential to address surveillance-related challenges. However, existing models face limitations in achieving state-of-the-art results due to low resolution, adverse weather, occlusion, and poor illumination. The critical problem of triple-riding detection remains inadequately addressed. This study proposes a deep learning-based system utilizing the YOLOv8 model for real-time detection of helmet violations and triple-riding infractions using CCTV and webcam footage. While the pre-trained YOLOv8 model is employed for triple riding detection, a custom-trained variant is developed using a dedicated helmet dataset for accurate helmet violation detection. The system processes image and video inputs, generating outputs that visually highlight detected violations. Evaluation metrics such as precision and recall ensure accuracy and reliability. This approach addresses these challenges by leveraging publicly available datasets alongside self-collected data, delivering robust performance. The proposed system represents a significant advancement in automated traffic rule enforcement, contributing to improved road safety and showcasing the potential of deep learning in surveillance applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - T. Gayathri
AU  - M. Kavya
AU  - M. Hema Sri
AU  - L. Harshitha
AU  - K. Sai Venkata Sahithi
AU  - M. Tejaswi
PY  - 2025
DA  - 2025/04/19
TI  - A Deep Learning-Based System to Detect Triple Riding and Helmet Violations Through CCTV Webcam
BT  - Proceedings of the International Conference on Advancements in Computing Technologies and Artificial Intelligence (COMPUTATIA-2025)
PB  - Atlantis Press
SP  - 330
EP  - 343
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-700-7_27
DO  - 10.2991/978-94-6463-700-7_27
ID  - Gayathri2025
ER  -