Real Time Smoke (Cigarette) Detection Using Deep Learning
Kushagra Singh, Nishant Anand, Devesh Dwivedi, Hari Om Jaiswal, Dhruv Parmar, Harsh Choudhary
Attention Deep Learning Real-Time Detection Smoking Detection Yolo
Absolutely, cigarette smoking poses serious health risks, contributing to chronic diseases and fatalities globally. Detecting smoking behaviour in real-time holds promise for mitigating these harmful effects. In our research paper, we introduce a novel project: real-time cigarette detection using deep learning models. The primary objective is to identify instances of cigarette smoking in real-time using live camera feeds and promptly alert authorities to intervene as necessary. The proposed system the YOLOv3 (You Only Look Once) object detection algorithm, a state-of-the-art deep learning model for object detection. The system's foundation lies in a meticulously curated dataset comprising images featuring cigarettes and non-cigarette objects. To enhance its versatility, the dataset undergoes augmentation, incorporating varied lighting conditions, angles, and backgrounds. This diversification fortifies the model's ability to discern smoking behaviour across a spectrum of real-world scenarios. Operating seamlessly, the system employs a camera to capture live video feeds in real-time. Through continuous analysis of these feeds, the model swiftly identifies instances of cigarette smoking, prompting immediate intervention when necessary. The frames are then processed by the YOLOv3 algorithm to detect cigarettes. The system was evaluated on a dataset of real-world smoking scenarios, achieving an accuracy of 92.5% in detecting cigarettes. Testing under various lighting conditions, distances, and angles suggests a comprehensive evaluation aimed at ensuring its reliability and consistency. In assessing the system's real-time capabilities, we observed an impressive performance, with an average processing time of merely 0.3 seconds per frame. This swift analysis ensures timely detection of smoking instances, enabling prompt intervention to mitigate potential health risks.
Article Details
Unique Paper ID: 164354

Publication Volume & Issue: Volume 10, Issue 12

Page(s): 2841 - 2845
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

Call For Paper

Volume 11 Issue 1

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

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews