Early Fire Detection of Large Space Combining Thresholding with Edge Detection Techniques

Abstract:

Image segmentation is a crucial step of the early fire detection in large space based on image processing technology. The image edges contain abundant feature information, and the edge detection has been a main topic of image segmentation algorithm. In this paper, several kinds of traditional edge detectors have been used to detect the edge of frame target in the fire video images, and the results have been contrasted and analyzed. Considering the influence of breaks in the edge caused by noise, nonuniform illumination and spurious intensity discontinuities, proposing the method of combining thresholding with edge detection, using Otsu’s method to compute a threshold for segmentation, extracting the flame area from the background, and then using the traditional edge detectors to detect the flame edge. At the same time, the simulation results based on the MATLAB kits indicate that this kind of method has good effectiveness and strong robustness, the detected flame edges have better effect in integrality and definition, and the relevant result can be the basis of the subsequent extraction and analysis of the fire image features as well as the space positioning of the fire.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 2060-2064
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.2060
• Online since: December 2010
• Authors: Guo Liang Hu, Xi Jiang
• Keywords: Early Fire Detection, Edge Detection, Image Segmentation, Thresholding

References

[1] Wang Zhenhua, The Research of Fire Detection Algorithm Based on Video-images, Xian University of Architecture and Technology, Xi An, (2008).

[2] Lu Wei, Study on Fire Intelligent Video Monitoring Recognition Techniques base on Image Processing, Chang'an University, Xi An, (2009).

[3] Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing, Second Edition, Publishing House of Electronics Industry, Beijing, (2002).

[4] Lv Puyi, Li Jin, Wu Liyu and Li Xiang, Research on automatic edge detection of fire video images, Applied Science and technology, Aug. 2003, 30(8): 51-56.

[5] Hu Guoliang, Jiang Xi, Early Fire Detection in Large Space Based on Image Processing Technology, Third International Symposium on Test Automation and Instrumentation, Xiamen, May. 2010, 2(126): 619-623.

[6] Zhao Hongzhong, Zhang Yanchao, Image Retrieval Algorithm Based on Canny Edge Detection Operator, Electronic Design Engineering, Feb. 2010, 18(2): 75-80Dj.M. Maric, P.F. Meier and S.K. Estreicher: Mater. Sci. Forum Vol. 83-87 (1992), p.119.