Survey of the Various Techniques Used for Smoke Detection Using Image Processing

  • Shirley SelvanEmail author
  • David Anthony Durand
  • V. Gowtham
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 35)


The concept of smoke detection was put forth by the development of sensors. These sensors relayed the parameters they sensed to a processor which made decisions. The presence of smoke is often an indicator of fire. Hence, given the ability to detect smoke in the early stages of fire, major fire accidents can be prevented. All though this method of smoke detection using sensors was a great success it was not very usefully in extreme conditions (weather, range, location) and sometimes even produced false alarms. Image processing paved way for more accurate detection of smoke since it uses digital data rather than analog inputs. With image processing both, fire and smoke could be detected easily. This method of detection involves various processes like extracting features, comparing with references, classification etc. This survey paper briefly explains the various techniques proposed/used to detect smoke.


Stationary wavelet transform Change detection Multi-layer perceptron Support Vector Machine Feret’s region Covariance descriptors Dual dictionary modelling Sparse representation 


  1. 1.
    Gonzalez-Gonzalez, R., Alarcon-Aquino, V., Rosas-Romero, R., Starostenko, O., Rodriquez-Asomoza, J.: Wavelet-based smoke detection in outdoor video sequence. 978-1-4244773-9/10/$26.00 ©2010. IEEE (2010)Google Scholar
  2. 2.
    Morerio, P., Marcenaro, L., Regazzoni, C.S., Gera, G.: Early fire and smoke detection based on color features and motion Analysis. 978-1-4673-2533-2/12/$26.00 ©2012. IEEE (2012)Google Scholar
  3. 3.
    Luo, F.-L., Unbehauen, R.: Applied Neural Networks for Signal Processing. Cambridge University Press, New York (1999)Google Scholar
  4. 4.
    Maruta, H., Nakamura, A., Knrokawa, F.: A novel detection method using support vector machine. 978-1-4244-6890-4/10/$26.00 ©2010. IEEE (2010)Google Scholar
  5. 5.
    Habiboglu, Y., Gunay, O., Cetin, A.: Flame detection method in video using covariance descriptors. In: IEEE International Conference on Speech and Signal Processing, pp. 1817–1820 (2011)Google Scholar
  6. 6.
    Chen, T.-H., Wu, P.-H., Chiou, Y.-C.: An early fire-detection method based on image processing. In: ICIP 2004, 24–27 October 2004 , vol. 3, pp. 1707–1710. IEEE (2004)Google Scholar
  7. 7.
    Tuzel, O., Poriki, F., Meer, P.: Region covariance: a fast descriptor for detection and classification. In: Computer Vision-ECCV 2006, pp. 589–600 (2006)CrossRefGoogle Scholar
  8. 8.
    Tian, H., Li, W., Ogunbona, P.O., Wang, L.: Detection and separation of smoke from single image frame. 1057-7149 ©2017. IEEE (2017)Google Scholar
  9. 9.
    Surya, T.S., Suchithra, M.S.: Survey on different smoke detection techniques using image processing. IJRCCT 3(11), 16–19 (2014)Google Scholar
  10. 10.
    Keys, R.: Cubic convolution interpolation for digital image processing. IEEE Trans. Signal Process. Acoust. Speech Signal Process. 29, 1153 (1981)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Otsu, N.: A threshold selection method from gray–level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)CrossRefGoogle Scholar
  12. 12.
    Umbaugh, S.: Computer Imaging: Digital Image Analysis and Processing. CRC Press (2005)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Shirley Selvan
    • 1
    Email author
  • David Anthony Durand
    • 1
  • V. Gowtham
    • 1
  1. 1.Department of Electronics and CommunicationSt. Joseph’s College of EngineeringChennaiIndia

Personalised recommendations