An Autoadaptive Edge-Detection Algorithm for Flame and Fire Image Processing

Article English OPEN
Qiu, Tian ; Yan, Yong ; Lu, Gang (2012)

The determination of flame or fire edges is the\ud process of identifying a boundary between the area where there\ud is thermochemical reaction and those without. It is a precursor\ud to image-based flame monitoring, early fire detection, fire evaluation,\ud and the determination of flame and fire parameters. Several\ud traditional edge-detection methods have been tested to identify\ud flame edges, but the results achieved have been disappointing.\ud Some research works related to flame and fire edge detection were\ud reported for different applications; however, the methods do not\ud emphasize the continuity and clarity of the flame and fire edges.\ud A computing algorithm is thus proposed to define flame and fire\ud edges clearly and continuously. The algorithm detects the coarse\ud and superfluous edges in a flame/fire image first and then identifies\ud the edges of the flame/fire and removes the irrelevant artifacts. The\ud autoadaptive feature of the algorithm ensures that the primary\ud symbolic flame/fire edges are identified for different scenarios.\ud Experimental results for different flame images and video frames\ud proved the effectiveness and robustness of the algorithm.
  • References (6)

    [3] China, pp. 1530-1539, September, 2010.

    [4] D. S. Huang, L. Heutte, and M. Lo [8] B. U. Toreyin, Yigithan Dedeoglu, Ugur. Gudukbay, and A. Enis based method for real-

    1 January 2006, pp. 49-58.

    [9] Mario I. Chacon-Murguia and Francisco J. PerezScience, 2011, Volume 6718/2011, pp. 118-126.

    Issue Date: 15-17 June 2010, On page(s): 1 4 [11] B. U. Toreyin, and Onl Conference on Computer Vision and Pattern Recognition, 2007.

    2011), Hefei, China, 12-15 August 2011, pp.182 -186.

  • Metrics
    views in OpenAIRE
    views in local repository
    downloads in local repository

    The information is available from the following content providers:

    From Number Of Views Number Of Downloads
    Kent Academic Repository - IRUS-UK 0 47
Share - Bookmark