Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


6806.pdf (6.39 MB)

ETD Abstract Container

Abstract Header

Video and Image Processing for Identification of Fire and Smoke

Garg, Sushil
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1383644990

Abstract Details

2013, MS, University of Cincinnati, Engineering and Applied Science: Mechanical Engineering.
Wildfires exhibit threats of all magnitudes and types to life and property. Past records suggest inevitable need of complete situational awareness and importance of the use of Unmanned Aerial Systems (UAS) to improve the wildland fire management by using onboard digital cameras. This research work focuses on various video and image processing based solutions for improving the situational awareness during wildfire management. A major issue is the presence of smoke that occludes the hot spots in videos taken from such cameras. A novel approach for filtering smoke occlusions in fire image streams using Proper Orthogonal Decomposition (POD) is presented. Images are reconstructed from video of scenes occluded by thick smoke. Assuming that the image of the wildfire is taken from a static camera, the smoke will be moving over a stream of images or a video but the background will be static. Using POD, the smoke is filtered out of the video and clear background with fire can be seen in the output images. Using POD, an infinite-dimensional process can be represented by using only a few number of "modes". Modes represent the energy of different component of the process and combining dominant components while leaving out the rest gives a good approximation of the original process. Effectiveness of technique is demonstrated by applying to a large number of sample videos. Smoke is sufficiently removed from the video with the background information intact. To further improve situational awareness, automated method for fire and smoke detection are presented. In recent years, there has been considerable development in vision-based systems for fire and smoke detection. Forest fire tracking using visual sensors require the ability to identify fire regions in imagery, and a model for fire and smoke identification using Fuzzy Logic based image processing is presented in this research work. The model is tested on a wide range of images containing fire and smoke regions and its effectiveness is demonstrated. The proposed model facilitates the development of a comprehensive fire and smoke detection system and is very attractive for military and civilian applications.
Manish Kumar, Ph.D. (Committee Chair)
Kelly Cohen, Ph.D. (Committee Member)
David Thompson, Ph.D. (Committee Member)
73 p.
Engineering
Smoke Filter; Video Processing

Recommended Citations

Citations

  • Garg, S. (2013). Video and Image Processing for Identification of Fire and Smoke [Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1383644990

    APA Style (7th edition)

  • Garg, Sushil. Video and Image Processing for Identification of Fire and Smoke. 2013. University of Cincinnati, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1383644990.

    MLA Style (8th edition)

  • Garg, Sushil. "Video and Image Processing for Identification of Fire and Smoke." Master's thesis, University of Cincinnati, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1383644990

    Chicago Manual of Style (17th edition)

ucin1383644990
3,442
© 2013, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.