Implementation of fire detection system based on video analysis with deep learning

被引:1
|
作者
Son G.-Y. [1 ]
Park J.-S. [1 ]
机构
[1] Dept. of Electronic Eng, Kyungsung University
关键词
Deep learning; Fire detection; Kernel size and stride;
D O I
10.5302/J.ICROS.2019.19.0125
中图分类号
学科分类号
摘要
The performance of convolutional deep learning networks is generally determined according to parameters of target dataset, structure of network, convolution kernel, activation function, and optimization algorithm. In this paper, a proper deep learning model and parameters for video-based fire detection were selected through simulations and applied the learning results to the fire detection solution. We compare and analyze the fire detection performance of AlexNet, GoogLeNet, and VGG-16 to select an effective network for detecting flame and smoke. The learning characteristics and the accuracy for flame and smoke dataset are analyzed according to the sizes and strides of convolution kernel. Dataset for training deep learning models is classified into normal, smoke and flame. Normal class images includes images with clouds and foggy. The kernel size is larger and the smaller the stride in kernel characteristics, the higher accuracy for the image dataset for fire detection. In terms of deep learning network structure, the accuracy of VGG-16 is better than that of other networks. We implement a fire detection solution based on Caffe framework that classifies flames and smoke frame from normal frame for the input video. As experiments of fire detection, it is shown that developed solution can be applied fire detection based on video. © ICROS 2019.
引用
收藏
页码:782 / 788
页数:6
相关论文
共 50 条
  • [31] Design and Research of Video Fire Detection System Based on FPGA
    Li Jinghong
    Lv Riqing
    Zou Xiaohui
    2011 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-6, 2011, : 1677 - 1679
  • [32] Emotion Detection-Based Video Recommendation System Using Machine Learning and Deep Learning Framework
    Bokhare A.
    Kothari T.
    SN Computer Science, 4 (3)
  • [33] Bee2Fire: A Deep Learning Powered Forest Fire Detection System
    Valente de Almeida, Rui
    Crivellaro, Fernando
    Narciso, Maria
    Isabel Sousa, Ana
    Vieira, Pedro
    ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 2, 2020, : 603 - 609
  • [34] Fire Detection in Ship Engine Rooms Based on Deep Learning
    Zhu, Jinting
    Zhang, Jundong
    Wang, Yongkang
    Ge, Yuequn
    Zhang, Ziwei
    Zhang, Shihan
    SENSORS, 2023, 23 (14)
  • [35] Deep Learning Based Fire Risk Detection on Construction Sites
    Ann, Hojune
    Koo, Ki Young
    SENSORS, 2023, 23 (22)
  • [36] Principles for a video fire detection system
    State Key Laboratory of Fire Science, Univ. of Sci. and Technol. of China, Anhui, China
    不详
    Fire Saf J, 1 (57-69):
  • [37] Principles for a video fire detection system
    Cheng, XF
    Wu, JH
    Yuan, X
    Zhou, H
    FIRE SAFETY JOURNAL, 1999, 33 (01) : 57 - 69
  • [38] Deep Learning Algorithm for Fire Detection
    Iqbal, Muhammad
    Setianingsih, Casi
    Irawan, Budhi
    2020 10TH ELECTRICAL POWER, ELECTRONICS, COMMUNICATIONS, CONTROLS AND INFORMATICS SEMINAR (EECCIS), 2020, : 237 - 242
  • [39] The Design and Implementation of Fire Smoke Detection System Based on FPGA
    Li Jinghong
    Zou Xiaohui
    Wang Lu
    PROCEEDINGS OF THE 2012 24TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2012, : 3919 - 3922
  • [40] Implementation of a Photovoltaic Default Detection System using Deep learning
    Gargouri, Amir
    Haddeji, Fahmi
    2024 IEEE INTERNATIONAL CONFERENCE ON ADVANCED SYSTEMS AND EMERGENT TECHNOLOGIES, ICASET 2024, 2024,