A New Method of Flame Image Segmentation

Shu Xian Zhu; Xue Li Zhu; Yong Jun Zhu

doi:10.4028/www.scientific.net/AMR.562-564.1365

Paper Titles

Testing Instrument for OPS in Hoisting Machinery
p.1344

Paper Moisture Rate Measurement Based on the Spectral Analysis
p.1348

Research and Development of a CNC Machine Tool Dynamic Characteristics Test and Analysis System
p.1352

Simulation of Vector Control for Two Double Y Shift 30° PMSMs Series-Connected System
p.1361

A New Method of Flame Image Segmentation
p.1365

The Numerical Simulation of Full Flow Field of Roto-Jet Pump and Analysis of Energy Losses
p.1369

Numerical Simulation on Spiral Hot Bending Process for End Sheet of Tubular Pile
p.1373

Face Detection Method Using PCNN and Skin Color Model
p.1377

The Construction of Cerebrovascular Model and Numerical Simulation
p.1382

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 562-564A New Method of Flame Image Segmentation

A New Method of Flame Image Segmentation

Abstract:

Separating flame image from background is a precondition and necessary link for identification for recognition algorithm. In current application, the Otsu method is a simple, effective and threshold value selection method suitable for real time processing, but the limitation of this method is it depends too much on the image pattern of “double peak histogram”. To overcome the weakness and shortcoming of Otsu method, this paper puts forward a new method based on grayscale integral projection, for flame image segmentation and positioning. Experiments have proved that this method not only can separate a flame image from background correctly, but also can position the center of a flame image quickly so as to provide the important criterion for dynamic recognition of flame image.

You might also be interested in these eBooks

Materials Engineering and Automatic Control

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 562-564)

Pages:

1365-1368

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.562-564.1365

Citation:

Cite this paper

Online since:

August 2012

Authors:

Shu Xian Zhu, Xue Li Zhu, Yong Jun Zhu

Keywords:

Flame Detection, Grayscale Integral Projection, Image Segmentation, Otsu Method

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] WANG Ya-jun, XU Da-fang, CHEN Xiang-chen, Fier Detectiong Method Based On Dynamic Features[J], Measurement & Control Technology, Vol. 26（2007）p.7(in china).

Google Scholar

[2] FAN Hua-zhong, ZHANG Bo-hu, FENG Yan, A pick-up algorithm of flame object in fire identification system[J], Electronics Optics & Control, Vol. 13(2006),P. 99(in china).

Google Scholar

[3] Chen Thouho, Wu Pinghsueh, Chiou Yungchuen. An early fire detection method based on image processing. Image Processing. ICIP '04. 2004 International Conference on Vol. 3(2004), P. 1707, 24-27 Oct.

DOI: 10.1109/icip.2004.1421401

Google Scholar

[4] CHENG Xin, WANG Da-chuan, YIN Dong-liang, Image type fire detection principle[J]. Fire Safety Science, Vol. 14(2005), P239(in china).

Google Scholar

[5] GAO Na, DONGAi-hua. Study on the method of flame image segmentation in fire detection[J], JOURNAL OF HENAN POLYTECHNIC UNIVERSITY (NATURAL SCIENCE) Vol. 27 (2008),P. 17(in china).

Google Scholar

[6] Otsu N. A threshold selection method from gray-level histogram[J]. IEEE Transactions on SMC(0018-9472), Vol. 9 (1979): P. 652.

Google Scholar

[7] HomgWenbing, Peng J ianwen, Chen Chihyuan. A new image – based real - time flame detection method using color analysis[A ]. Proceeding of Networking, Sensing and Control, 2005.

DOI: 10.1109/icnsc.2005.1461169

Google Scholar