基于视频火灾烟雾检测算法和研究.pdf

Subject :Research on Algorithm of Fire Smoke Detection Based on Video
Specialty :Signal and Information Processing
Name :Wang Nana (Signature)
Instructor:Wu Dongmei (Signature)
ABSTRACT
Traditional sensor-based fire detection system will tend to fail in some large indoor space
and ventilation places, so researching a new fire detection method based puter vision
and video image processing is of great significance. Using video monitoring the fire happens
or not in the scene has some advantages, such as it is not affected by distance space and
environmental constraints, it response fast and detection intuitive to protect the larger area.
The fire occurred early will usually produce large amounts of smoke, by analyzing the video
sequence to detect the scene with fire smoke is the main research work.
Firstly studied monly used methods in moving target detection, contrast and
analyze the respective application occasions, the advantages and disadvantages, and
determined Gaussian mixture model as the method of background modeling and the
extraction of the prospects, which is suitable for smoke detection in this article. The smoke
along with the other moving target was extracted out together, and then analyzed the color
information in the extracted area. After a large number of observations and test statistics
summed up the law of the color of smoke images, which is that the fire smoke is generally
white, blue, gray and black, and their three sub-value of RGB is basically equal, just
distributed in the diagonal of the RGB color cube, and the brightness is also within a certain
range. And according to these, the smoke color decision conditions were designed. The color
analysis for the motion detection area can further rule out the moving object which does not
have smoke color features. Then after the morphological processing and connectivity analysis
in the motion detection and color analysis area, obtained the suspect smoke