Project - Embeded camera R&D for Real-Time fire detection surveillance in tunnel environment

Embeded camera R&D for Real-Time fire detection surveillance in tunnel environment
- 2008.07.01~2009.06.30
- High Computing Power Embeded Camera R&D, Fire & Smoke Detection(My Job)

The goal of the project is to develop embeded camera for detect fire and smoke.
My job was an algorithm R&D for detection fire & smoke and the s/w programing.
The fire detection algorithm uses the HMM algorithm.
The features of the fire's sequence is learned in the off-line. And then the learned Markov model is used in the oline using viterbi algorithm.

Below Movies are the result of the project.

*** Demo 1, Fire detection Simple situation :

*** Demo 2, Fire detection in the road, There is similar light of the car with fire color:

***Demo 3, Fire detection test in the real fire situation :

***Demo 4, Embeded Camera Test. The camera detects the fire and then zoom in the region of the fire.

***Demo 5, Smoke detection test.


  1. very excellent!
    could you share me source code?
    i need for my project ^^
    thank you very much :)

  2. Sorry, I can' t share the source code. Because the source code is the result of project funded from government. Thank you for visiting my blog.

  3. oh. no problem. thank you ^^ :)

  4. Can you share me detail document to understand your algorithm? I would like to understand your algorithm. Ko-mab-sum-ni-da :)

    1. please refer to this paper

      thank you

    2. Thank you so much. Now, I am also PhD students in Pusan, if possible, we can meet. Thanks :)

    3. Thank you for visiting my blog.

  5. Hi, JH Kim nim.

    Now, I am implementing your algorithm. But I don't know how to do step "Pixel clustering". Because, opencv don't have that function, and I don't also understand that step. How to cluster them? Does it mean you add 40 frames?