Abstract | ||
---|---|---|
This paper proposes a video-based fire detection system which uses color, spatial and temporal information. The system divides the video into spatio-temporal blocks and uses covariance-based features extracted from these blocks to detect fire. Feature vectors take advantage of both the spatial and the temporal characteristics of flame-colored regions. The extracted features are trained and tested using a support vector machine (SVM) classifier. The system does not use a background subtraction method to segment moving regions and can be used, to some extent, with non-stationary cameras. The computationally efficient method can process 320 × 240 video frames at around 20 frames per second in an ordinary PC with a dual core 2.2 GHz processor. In addition, it is shown to outperform a previous method in terms of detection performance. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/s00138-011-0369-1 | Mach. Vis. Appl. |
Keywords | Field | DocType |
Fire detection,Covariance descriptors,Support vector machines | Background subtraction,Computer vision,Feature vector,Pattern recognition,Computer science,Support vector machine,Flame detection,Frame rate,Artificial intelligence,Covariance matrix,Fire detection,Covariance | Journal |
Volume | Issue | ISSN |
23 | 6 | 0932-8092 |
Citations | PageRank | References |
38 | 1.80 | 15 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yusuf Hakan Habiboglu | 1 | 54 | 3.06 |
Osman Günay | 2 | 78 | 5.26 |
A. Enis Çetin | 3 | 871 | 118.56 |