| Paper: | IMDSP-L9.6 | ||
| Session: | Video Segmentation and Tracking | ||
| Time: | Friday, May 19, 15:40 - 16:00 | ||
| Presentation: | Lecture | ||
| Topic: | Image and Multidimensional Signal Processing: Video Segmentation and Tracking | ||
| Title: | FIRE DETECTION IN VIDEO SEQUENCES USING STATISTICAL COLOR MODEL | ||
| Authors: | Turgay Celik, Hasan Demirel, Huseyin Ozkaramanli, Mustafa Uyguroglu, Eastern Mediterranean University, Turkey | ||
| Abstract: | In this paper, we propose a real-time fire-detector which combines foreground information with statistical color information to detect fires. The foreground information which is obtained using adaptive background information is verified by the statistical color information to determine whether the detected foreground object is a candidate for fire or not. The output of the both stages is analyzed in consecutive frames which is the verification process of fire that uses the fact that fire never stays stable in visual appearance. The frame processing rate of the detector is about 30 fps with image size of 176x144 which enables the proposed detector to be applied for real-time applications. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012