A Study on a Video-Based Deep Learning Fusion Algorithm for Fire Detection Systems 


Vol. 46,  No. 9, pp. 1487-1496, Sep.  2021
10.7840/kics.2021.46.9.1487


PDF Full-Text
  Abstract

In this paper, we proposed an artificial intelligence system for real-time fire detection using network surveillance cameras. To detect fire, fire candidate areas are recognized using flame characteristics. Therefore, we developed a very fast classifier that distinguishes real fires non-fire regions that resemble fires. The final layer of this model is an image classifier based on a deep learning convolutional neural network (CNN). Also, smoke detection algorithm is proposed because smoke can be a very important clue in detecting fire in the early stage. Similar to fire detection in this algorithm, the hierarchical classification model is used to remove non-smoke moving objects, and finally, the results of the fire and smoke detection algorithms are fused to make a final decision.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. Ryoo and S. Ro, "A Study on a Video-Based Deep Learning Fusion Algorithm for Fire Detection Systems," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 9, pp. 1487-1496, 2021. DOI: 10.7840/kics.2021.46.9.1487.

[ACM Style]

Siyeong Ryoo and Soonghwan Ro. 2021. A Study on a Video-Based Deep Learning Fusion Algorithm for Fire Detection Systems. The Journal of Korean Institute of Communications and Information Sciences, 46, 9, (2021), 1487-1496. DOI: 10.7840/kics.2021.46.9.1487.

[KICS Style]

Siyeong Ryoo and Soonghwan Ro, "A Study on a Video-Based Deep Learning Fusion Algorithm for Fire Detection Systems," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 9, pp. 1487-1496, 9. 2021. (https://doi.org/10.7840/kics.2021.46.9.1487)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880