Smoke detection for static cameras

Description: This paper describes the smoke detection for static cameras. The background subtraction was used to determine moving objects. Color characteristics were utilized to distinguish smoke regions and other scene members. Separate pixels were united into blobs by morphology operations and connected components labeling methods. The image is then refined by boundary roughness and edge density to decrease amount of false detections. Results of the current frame are compared to the previous one in order to check the behavior of objects in time domain.
This paper describes the smoke detection for static cameras. The background subtraction was used to determine moving objects. Color characteristics were utilized to distinguish smoke regions and other scene members. Separate pixels were united into blobs by morphology operations and connected components labeling methods. The image is then refined by boundary roughness and edge density to decrease amount of false detections. Results of the current frame are compared to the previous one in order to check the behavior of objects in time domain.

Topic: Image color analysis
Cameras,
Image edge detection
Videos
Image resolution
Morphology
Probability
Image color analysis
Cameras,
Image edge detection
Videos
Image resolution
Morphology
Probability

Get full text: https://ieeexplore.ieee.org/abstract/document/7103719/
http://ridda2.utp.ac.pa/handle/123456789/5084