I am working on a project to detect fire in CCTV or any other surveillance cameras. Up till now I have completed the following stages;

  1. Convert the RGB into HSV
  2. Sliced out the Value matrix from HSV
  3. Applied background subtraction model from openCV () to separate the foreground which is area of the fire.
  4. Applied morphological operations on the extracted foreground.
  5. Extracted contours from the foreground.
  6. ANDed the contour mask to original HSV

Now I am getting an HSV image where there are shades of fire color's in the Region of Interest (ROI)

I am getting the following output on the video where there is fire.

output with mask ANDed with RGB original image

output with mask ANDed with HSV image

My problem is I am getting such output on videos where there is no fire but shades of red, yellow and orange are present with high intensity. How can I improve it further with eliminating false positives?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.