A Deep Learning-Based CCTV System for Automatic Smoking Detection in Fire Exit Zones

TL;DR

This paper presents a deep learning CCTV system for automatic smoking detection in fire exit zones, utilizing a custom YOLO-based model that performs efficiently across various environments and edge devices.

Contribution

The authors developed a novel YOLOv8-based model tailored for challenging surveillance scenarios, achieving high accuracy and real-time performance on edge devices.

Findings

The custom model achieved 78.90% recall and 83.70% mAP at 50.

The system operates in real-time with inference times of 52-97 ms on Jetson Xavier NX.

The dataset includes 8,124 images from 20 scenarios, including low-light conditions.

Abstract

A deep learning real-time smoking detection system for CCTV surveillance of fire exit areas is proposed due to critical safety requirements. The dataset contains 8,124 images from 20 different scenarios along with 2,708 raw samples demonstrating low-light areas. We evaluated three advanced object detection models: YOLOv8, YOLOv11, and YOLOv12, followed by development of a custom model derived from YOLOv8 with added structures for challenging surveillance contexts. The proposed model outperformed the others, achieving a recall of 78.90 percent and mAP at 50 of 83.70 percent, delivering optimal object detection across varied environments. Performance evaluation on multiple edge devices using multithreaded operations showed the Jetson Xavier NX processed data at 52 to 97 milliseconds per inference, establishing its suitability for time-sensitive operations. This system offers a robust and adaptable platform for monitoring public safety and enabling automatic regulatory compliance.