UAV remote sensing atmospheric degradation image restoration based on multiple scattering APSF estimation

Abstract

Unmanned aerial vehicle (UAV) remote imaging is affected by the bad weather, and the obtained images have the disadvantages of low contrast, complex texture and blurring. In this paper, we propose a blind deconvolution model based on multiple scattering atmosphere point spread function (APSF) estimation to recovery the remote sensing image. According to Narasimhan analytical theory, a new multiple scattering restoration model is established based on the improved dichromatic model. Then using the L0 norm sparse priors of gradient and dark channel to estimate APSF blur kernel, the fast Fourier transform is used to recover the original clear image by Wiener filtering. By comparing with other state-of-the-art methods, the proposed method can correctly estimate blur kernel, effectively remove the atmospheric degradation phenomena, preserve image detail information and increase the quality evaluation indexes.

References

[1] HeK M, SunJ, TangX O. Single Image Haze Removal Using Dark Channel Prior, IEEE Conference on Computer Vision and Pattern Recognition, 2009, 1956

[2] WangW-x, XiaoX, ChenL-q. Optics and Precision Engineering, 2015, 23: 2100

[3] LiuH-b, YangJ, WuY-p. Journal of Electronics and Information Technology, 2016, 33: 381

[4] LiuY, ZhangH-y, WuY-d. Journal of Graphics, 2015, 36: 68

[5] NayarS, NarasimhanS. International Journal of Computer Vision, 2002, 48: 233

[6] WeiP, LiuY, WangSDehazing Model Based on Multiple ScatteringInternational Congress on Image and Signal Processing, 2010, 249

[7] PanJ S, SunD Q, PfisterH, YangM H. Blind Image Deblurring Using Dark Channel Prior, IEEE Conference on Computer Vision and Pattern Recognition, 2016, 1628

[8] LiaoY-z, CaiZ-X, HeX-h. Optics and Precision Engineering, 2015, 23: 2086

[9] XuL, ZhengH, JiaJ. Unnatural L0 Sparse Representation for Natural Image Deblurring, IEEE Conference on Computer Vision and Pattern Recognition, 2013, 1107

[10] ChoS, ParisS, HornB K P, FreemanW TBlur Kernel Estimation Using the Radon TransformIEEE Conference on Computer Vision and Pattern Recognition, 2011, 241

[11] KrishnanD, TayT, FergusR. Blind Deconvolution Using a Normalized Sparsity Measure, IEEE Conference on Computer Vision and Pattern Recognition, 2011, 233

[12] PerroneD, FavaroP. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 10: 8162

[13] YuY-B, PengN, GanJ-Y. Acta Electronica Sinica, 2016, 44: 1168

[14] PanJ S, HuZ, SunZ X, YangM H. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 10: 255

[15] HuZ, ChoS, WangJ, YangM-H. Deblurring Low-Light Images with Light Streaks, IEEE Conference on Computer Vision and Pattern Recognition, 2014, 3382

[16] WangN, DingJ, ChenL, ChangR. Efficient Image Deblurring via Blockwise Non-Blind Deconvolution Algorithm, International Conference on Information Communications and Signal Processing, 2015, 1