• Aliya Bi Can

Image processing is used for detecting smoke in outdoor videos. The technique of background subtraction using Gaussian Mixture Model(GMM) is used to obtain the moving regions in video images. Foreground detection is done using GMM. Improved Fuzzy C-Means (FCM) clustering algorithm along with Color-Based Decision Rule is used for detecting the smoke regions. The basic idea is finding the foreground using mask. Improved FCM works on each frame so that every pixel in the frame is checked if it is a smoke pixel based on Color-Based Decision Rule. During each iteration of improved FCM, pixels assignment of each frame is carried out for forming clusters. According to Color-Based Decision Rule, the pixels in cluster will be checked for smoke and non-smoke pixels. Finally the smoke region will be shown with pink area for highlighting the region of interest.

Background Subtraction Method, Color-Based Decision Rule, Fuzzy C-Means, Optical Flow, Video Frame.

"Characteristic measurement and smoke detection using image processing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.870-875, June 2019, Available :http://www.jetir.org/papers/JETIR1906R18.pdf

"Characteristic measurement and smoke detection using image processing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp870-875, June 2019, Available at : http://www.jetir.org/papers/JETIR1906R18.pdf