A smoke image segmentation algorithm based on rough set and region growing

Haitao Wang; Yanli Chen

doi:10.17221/34/2019-JFS

A smoke image segmentation algorithm based on rough set and region growing

Haitao Wang, Yanli Chen

https://doi.org/10.17221/34/2019-JFSCitation:Wang H., Chen Y. (2019): A smoke image segmentation algorithm based on rough set and region growing. J. For. Sci., 65: 321-329.

download PDF

Because the image fire smoke segmentation algorithm can not extract white, gray and black smoke at the same time, a smoke image segmentation algorithm is proposed by combining rough set and region growth method. The R component of the image is extracted in the RGB colour space, the roughness histogram is constructed according to the statistical histogram of the R component, and the appropriate valley value in the roughness histogram is selected as the segmentation threshold, the image is roughly segmented. Relative to the background image, the smoke belongs to the motion information, and the motion region is extracted by the interframe difference method to eliminate static interference. Smoke has a unique colour feature, a smoke colour model is created in the RGB colour space, the motion disturbances of similar colour are removed and the suspected smoke areas are obtained. The seed point is selected in the region, and the region is grown on the result of rough segmentation, the smoke region is extracted. The experimental results show that the algorithm can segment white, gray and black smoke at the same time, and the irregular information of smoke edges is relatively complete. Compared with the existing algorithms, the average segmentation accuracy, recall rate and F-value are increased by 19%, 21.5% and 20%, respectively.

Keywords:

forest fire prevention; roughness histogram

References:

Cai S.D., Yang F. (2011): Colour image segmentation based on HSV space and rough-set theory. Optoelectronic Technology, 31: 5–9.

Ho C.C. (2009): Machine vision–based real–time early flame and smoke detection. Measurement Science and Technology, 20: 495–502.

Jia Yang, Yuan Jie, Wang Jinjun, Fang Jun, Zhang Qixing, Zhang Yongming (2016): A Saliency-Based Method for Early Smoke Detection in Video Sequences. Fire Technology, 52, 1271-1292 https://doi.org/10.1007/s10694-014-0453-y

Lin H., Liu Z.G, Zhao T L., Zhang Y. (2013): Improved algorithm for smoking identification of the forest fire based on the video survey. Journal of Safety and Environment, 13: 210–214.

Lizarraga-Morales Rocio A., Sanchez-Yanez Raul E., Ayala-Ramirez Victor, Correa-Tome Fernando E. (2014): Integration of color and texture cues in a rough set–based segmentation method. Journal of Electronic Imaging, 23, 023003- https://doi.org/10.1117/1.JEI.23.2.023003

Otsu Nobuyuki (1979): A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9, 62-66 https://doi.org/10.1109/TSMC.1979.4310076

Ouiem Bchir, Mohamed Maher Ben Ismail, Norah Asiri. (2019): Image Based Smoke Detection Using Source Separation. Spectroscopy and Spectral Analysis, 29: 982–989.

Ren Z X, Gao S H, Chia LT, Ivor Wai–Hung Tsang. (2014): Region-based saliency detection and its application in object recognition. IEEE Transactions on Circuits & Systems for Video Technology, 24: 769–779.

Shi Y.K, Zhong Z., Zhang D.X, Yang J.J. (2015): A study on smoke detection based on multi–feature. Journal of Signal Processing, 31: 1336–1341.

Wu A.G., Du C.Y., Li M. (2008): Smoke detection method based on mixed Gaussian model and wavelet transformation. Chinese Journal of Scientific Instrument, 29: 1622–1626.

Wu J., Ye F., Ma J.L. (2008): The segmentation and visualization of human organs based on adaptive photo growing method. Proceedings of the 8th International Conference on Computer and Information Technology Workshops, Sydney, Australia, Jul 8–11, 2008. Washington: IEEE Computer Society: 439–443.

Xie Q. (2011): Research on Image Segmentation Based on Rough Set Theory. Changsha, Central South University.

Yu Chunyu, Mei Zhibin, Zhang Xi (2013): A Real-time Video Fire Flame and Smoke Detection Algorithm. Procedia Engineering, 62, 891-898 https://doi.org/10.1016/j.proeng.2013.08.140

Zhang W.C., Li P., Gao C.Q. (2016): Smoke detection based on adaptive region growing method in forest background. Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, 28: 100–106.

Zhao Yaqin (2015): Candidate Smoke Region Segmentation of Fire Video Based on Rough Set Theory. Journal of Electrical and Computer Engineering, 2015, 1-8 https://doi.org/10.1155/2015/280415

Zhao Yaqin, Li Qiujie, Gu Zhou (2015): Early smoke detection of forest fire video using CS Adaboost algorithm. Optik - International Journal for Light and Electron Optics, 126, 2121-2124 https://doi.org/10.1016/j.ijleo.2015.05.082

Zen Revaldo I.M., Widyanto M. Rahmat, Kiswanto Gandjar, Dharsono Guruh, Nugroho Yulianto S. (2013): Dangerous Smoke Classification Using Mathematical Model of Meaning. Procedia Engineering, 62, 963-971 https://doi.org/10.1016/j.proeng.2013.08.149

download PDF

Czech Academy of Agricultural Sciences

A smoke image segmentation algorithm based on rough set and region growing

Haitao Wang, Yanli Chen

Web of Science

SCImago Journal Rank (SCOPUS)

New Issue Alert

Publish with JFS!

Similarity Check

Referred to in

Licence terms

Open Access Policy

Contact

Address