All-Sky Cloud Classification Based on Transparency and Texture Features

Abstract:

Article Preview

This paper proposes a new algorithm to classify the cloud of all-sky ground-based based on transparency and texture features. First, we uses the transparency to separate the single sky background and cloud foreground image, which based on the natural matting of perceptual color space method, then analysis the texture features of cloud foreground image with second moment, contrast, correlation and entropy, finally, uses BP neural network to identify the type of the cloud. The experimental results show that the algorithm can separate the sky and cloud effectively, and the cloud classification recognition rate is higher.

Info:

Periodical:

Edited by:

Yuning Zhong

Pages:

3-8

Citation:

X. Y. Chen et al., "All-Sky Cloud Classification Based on Transparency and Texture Features", Applied Mechanics and Materials, Vol. 235, pp. 3-8, 2012

Online since:

November 2012

Export:

Price:

$41.00

[1] Sheng Pei-xuan, Mao Jie-tai, Li Jian-guo, etl. Atmospheric Physics[M]. Beijing: Peking University Press, 2003, 98-101.

[2] Porter T, Duff T. Compositing digital images [C]/Computer Graphics Proceedings, Annual Conference Series , ACM SIGGRAPH , New York , 1984 : 253-259.

DOI: https://doi.org/10.1145/964965.808606

[3] Lin Sheng-you. Alpha Estimation Based on Perceptual Color Space[J]. Computer Engineering, 2007, 33(20): 40-42.

[4] Lv Ju-Jian. The study of natural image matting methods [D]. Guangdong University of Technology, (2009).

[5] Kittler J, Pairman D. Contextual pattern recognition applied to cloud detection and identification[J]. IEEE Trans Geosci Remote Sensing, 1985, 23 (11): 855-863.

DOI: https://doi.org/10.1109/tgrs.1985.289471

[6] Sun Zhong-kang, Shen Zhen-kang. Digital Image Processing and Application[M]. Beijing: National Defence Industry Press, (1985).

[7] Schmid Cordelia, Mohr Roger. Local gray value invariants for image retrieval[J]. IEEE Trans Pattern Anal Mach Intell. 1997, 19(5): 530-535.

DOI: https://doi.org/10.1109/34.589215