• DocumentCode
    595052
  • Title

    Real-time smoke detection using texture and color features

  • Author

    Yue Wang ; Teck Wee Chua ; Chang, Ronald ; Nam Trung Pham

  • Author_Institution
    Inst. for Infocomm Res., Agency for Sci., Technol. & Res., Singapore, Singapore
  • fYear
    2012
  • fDate
    11-15 Nov. 2012
  • Firstpage
    1727
  • Lastpage
    1730
  • Abstract
    This paper presents a real-time smoke detection algorithm. A modified Center Symmetric Local Ternary Pattern (CS-LTP) is proposed as the smoke texture descriptor. The change in background texture provides a means to differentiate between smoke and non-smoke region. Combined with the color information of smoke, our method is able to achieve real-time performance at minimum of 30 fps. The comparison with the state of art is presented as well. The experiment results show the proposed method can obtain good performance.
  • Keywords
    feature extraction; image colour analysis; image texture; object detection; safety; smoke; CS-LTP; background texture; center symmetric local ternary pattern; color features; nonsmoke region; real-time smoke detection algorithm; smoke color information; smoke texture descriptor; texture features; Detection algorithms; Feature extraction; Hidden Markov models; Histograms; Image color analysis; Real-time systems; Support vector machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2012 21st International Conference on
  • Conference_Location
    Tsukuba
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4673-2216-4
  • Type

    conf

  • Filename
    6460483