Auto-Layering Wavelet Transfer to Remove the Circumstance Effect and Noise

Abstract:

The accuracy of visibility measurement from night light sources image is usually affected by the circumstance light and noise. This paper presents an auto-layering wavelet transfer method to remove the circumstance effect and noise simultaneously. Firstly, the light propagation through the fog at night condition is formulized, where the model and features of night image with circumstance effect and noise is given. Secondly, we propose to use multi-scale features of wavelet transfer to decompose the image to remove the circumstance effect and noise, where an auto-layering method is used based on the energy ratio of wavelet coefficients. Experiments show that our method is able to remove the circumstance effect and noise simultaneously and to adjust the decomposed layering number automatically. Our method is not only suitable for many wavelet functions, but also preserves the light sources as well as their glows in the digital images. The relative error of using db4 is 3.16%, and the relative error of using sym2 is 2.02%.

• Periodical: Advanced Materials Research (Volumes 798-799)
• Pages: 624-629
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.798-799.624
• Online since: September 2013
• Authors: Pang Da Dai, Yu Jun Zhang, Chang Hua Lu, Yi Zhou, Wei Zhang, Xue Xiao, Jing Liu, Jing Li Wang
• Keywords: Auto-Layering, Energy Ratio, Night Image, Visibility, Wavelet Transfer

References

[1] Dumont, Cavallo, Extended photometric model of fog effects on road vision, Journal of the TRB, No. 1862, 2004, pp.77-81.

DOI: 10.3141/1862-09

[2] R. Gallen, N. Hautiere, E. Dumont, Static Estimation of the Meteorological Visibility Distance in Night Fog with Imagery, MVA2009 IAPR Conference on Machine Vision Applications, 2009, pp.300-303.

[3] S. G. Narasimhan, S. K. Nayar, Vision and Atmosphere, Int J Compute Vision, Vol. 48, No. 3, 2002, pp.233-254.

[4] S. G. Narasimhan, S. K. Nayar, Shedding light on the weather", Proc. IEEE CVPR, 03, 2003, pp.655-672.

[5] S. Metari, F. Deschenes, A new Convolution Kernel for Atmospheric Point Spread Function Applied to Computer Vision", Proc. IEEE ICCV, 07, 2007, pp.1-8.

DOI: 10.1109/iccv.2007.4408899

[6] G. Nathan, S. Newsam, Using Visibility Cameras to Estimate Atmospheric Light Extinction, Application of Computer Vision, 2011, pp.577-584.

DOI: 10.1109/wacv.2011.5711556

[7] Middleton. Vision through the Atmosphere, University of Toronto Press, (1952).

[8] H. Huang, X.T. Wang, Y.X. Jiang, Application of Dark Area Segmentation in Night Image Enhancing, Laser and Infrared, Vol. 39, No. 4, 2009, pp.443-446.

[9] H. S. Zhu, C. G. Xu, Adaptive image denoising algorithm based on Shearlet transform, Laser and Infrared, Vol. 42, No. 7, 2012, pp.811-814.

[10] S. Q. Liu, S. H. Hu, Y. Xiao, SAR image de-noised based on complex contourlet domain Gaussian scale mixture model, Journal of Beijing Jiaotong University, Vol. 36, No. 2, 2012, pp.24-28.

[11] A. Hilal, B. Daya, P. Beauseroy, Hough Transform and Active Contour for Enhanced Iris Segmentation, International Journal of Computer Science Issue, Vol. 9, No. 2, 2012, pp.1-10.

[12] X. Yang, J. Li, B. Han, Wavelet hierarchical model for aurora images classification, Journal of Xidian University, Vol. 40, No. 2, 2013, pp.24-31.

[13] H. N. Xu, Z. Liu, C. Liu, Remote Sensing Image Denoising by trous Wavelet and Nonsubsampled Directional Filter Bank, Jounal of Shanghai Jiaotong University, Vol. 46, No. 2, 2012, pp.233-238.

[14] S. N. Zhao, F. Zhang, Z. H. Du, The directional diffusion based on discrete wavelet algorithm to achieve side scan sonar image denoising, Journal of Zhejiang University, Vol. 39, No. 5, 2012, pp.593-598.

[15] Y. H. Fang, C. Kong, T. G. Lan, Denoising and baseline correction of spectrum by wavelet transform, Optics and Precision Engineering, Vol. 14, No. 6, 2006, pp.1088-1092.