Unsupervised Segmentation of Fire and Smoke From Infra-Red Videos

Unsupervised Segmentation of Fire and Smoke From Infra-Red Videos

This paper proposes a vision-based fire and smoke segmentation system which uses spatial, temporal and motion information to extract the desired regions from the video frames. The fusion of information is done using multiple features such as optical flow, divergence and intensity values. These featu...

Full description

Bibliographic Details
Main Authors: Meenu Ajith, Manel Martinez-Ramon
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Fire detection
gaussian mixture models
iterated conditional modes
k-means clustering
markov random fields
optical flow
Online Access:https://ieeexplore.ieee.org/document/8933369/

Internet

https://ieeexplore.ieee.org/document/8933369/

Similar Items