A Video Smoke Detection Algorithm Based on Cascade Classification and Deep Learning

Fires are a common cause of catastrophic personal injuries and devastating property damage. Every year, many fires occur and threaten human lives and property around the world. Providing early important sign for early fire detection, and therefore the detection of smoke is always the first step in fire-alarm systems. In this paper we propose an automatic smoke detection system built on camera surveillance and image processing technologies. The key features used in our algorithm are to detect and track smoke as moving objects and distinguish smoke from non-smoke objects using a convolutional neural network (CNN) model for cascade classification. The results of our experiment, in comparison with those of some earlier studies, show that the proposed algorithm is very effective not only in detecting smoke, but also in reducing false positives.

• Publication year

  2018

• Venue

  KSII Transactions on Internet and Information Systems

• Publication date

  2018-12-30

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.3837/tiis.2018.12.022
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Fine-tuning Deep Convolutional Networks for Plant Recognition

  2015cited by this paper
• Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks

  2014cited by this paper
• Wildfire smoke detection using temporospatial features and random forest classifiers

  2012influential reference
• SMOKE DETECTION USING SPATIAL AND TEMPORAL ANALYSES

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012influential reference
• Deep Learning of Representations for Unsupervised and Transfer Learning

  2011cited by this paper
• Wildfire smoke detection using computational intelligence techniques

  2011cited by this paper
• An effective four-stage smoke-detection algorithm using video images for early fire-alarm systems

  2011influential reference
• Target-Tracking Based Early Fire Smoke Detection in Video

  2009cited by this paper
• Image Classification using Random Forests and Ferns

  2007cited by this paper
• Contour based smoke detection in video using wavelets

  2006cited by this paper
• Adaptive background mixture models for real-time tracking

  1999influential reference

• Digital Technologies and Machine Learning in Environmental Hazard Monitoring: A Synthesis of Evidence for Floods, Air Pollution, Earthquakes, and Fires

  2026cites this paper
• Human detection with smoke occlusion based on AI-generated images

  2025cites this paper
• Machine Learning for Fire Safety in the Built Environment: A Bibliometric Insight into Research Trends and Key Methods

  2025cites this paper
• Optimizing Fire Scene Analysis: Hybrid Convolutional Neural Network Model Leveraging Multiscale Feature and Attention Mechanisms

  2024cites this paper
• A novel smoke detection algorithm based on improved mixed Gaussian and YOLOv5 for textile workshop environments

  2023cites this paper
• Research on smoke flame detection based on improved YOLOv3

  2023cites this paper
• CENet: A Channel-Enhanced Spatiotemporal Network With Sufficient Supervision Information for Recognizing Industrial Smoke Emissions

  2022cites this paper
• A survey on vision-based outdoor smoke detection techniques for environmental safety

  2022cites this paper
• Fire Detection and Warning Application from Images and Videos using Deep Learning

  2022cites this paper
• AOSVSSNet: Attention-Guided Optical Satellite Video Smoke Segmentation Network

  2022cites this paper
• Controllable smoke image generation network based on smoke imaging principle

  2022influential citation
• Development and optimization of image fire detection on deep learning algorithms

  2022cites this paper
• Video Face Recognition of Virtual Currency Trading System Based on Deep Learning Algorithms

  2021cites this paper
• Early Wildfire Smoke Detection in Videos

  2021cites this paper
• An efficient fire detection algorithm based on multi‐scale convolutional neural network

  2021cites this paper
• Automated Censorable Content Identification In Videos Using Deep Learning

  2020cites this paper
• Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association

  2020cites this paper
• Sign Language Translation Using Deep Convolutional Neural Networks

  2020cites this paper
• Reconstruction of Convolutional Neural Network for Sign Language Recognition

  2020cites this paper
• Image fire detection algorithms based on convolutional neural networks

  2020cites this paper
• Decoupled Deep Neural Network for Smoke Detection

  year unknowncites this paper