A Sensor Image Dehazing Algorithm Based on Feature Learning

Sensors - Tập 18 Số 8 - Trang 2606
Kun Liu1, Linyuan He1, Shiping Ma1, Shan Gao1, BI Du-yan1
1College of Aeronautics Engineering, Air Force Engineering University, Xi’an 710038, China

Tóm tắt

To solve the problems of color distortion and structure blurring in images acquired by sensors during bad weather, an image dehazing algorithm based on feature learning is put forward to improve the quality of sensor images. First, we extracted the multiscale structure features of the haze images by sparse coding and the various haze-related color features simultaneously. Then, the generative adversarial network (GAN) was used for sample training to explore the mapping relationship between different features and the scene transmission. Finally, the final haze-free image was obtained according to the degradation model. Experimental results show that the method has obvious advantages in its detail recovery and color retention. In addition, it effectively improves the quality of sensor images.

Từ khóa


Tài liệu tham khảo

Helmers, 2003, CMOS vs. CCD sensors in speckle interferometry, Opt. Laser Technol., 35, 587, 10.1016/S0030-3992(03)00078-1

Pizer, 1987, Adaptive histogram equalization and its variations, Comput. Vis. Graph. Image Process., 39, 355, 10.1016/S0734-189X(87)80186-X

Voicu, 1997, Practical considerations on color image enhancement using homomorphic filtering, J. Electron. Imaging, 6, 108, 10.1117/12.251157

Farge, 1992, Wavelet transform and their application to turbulence, Annu. Rev. Fluid Mech., 24, 395, 10.1146/annurev.fl.24.010192.002143

Xie, B., Guo, F., and Cai, Z. (2010, January 13–14). Improved Single Image Dehazing Using Dark Channel Prior and Multi-scale Retinex. Proceedings of the International Conference on Intelligent System Design and Engineering, Changsha, China.

He, K., Sun, J., and Tang, X. (2009, January 22–24). Single image haze removal using dark channel prior. Proceedings of the CVPR 2009 Computer Vision and Pattern Recognition, Miami Beach, FL, USA.

Tan, R.T. (2008, January 23–28). Visibility in bad weather from a single image. Proceedings of the CVPR 2008 Computer Vision and Pattern Recognition, Anchorage, AK, USA.

Zhu, Q., Mai, J., and Shao, L. (2014). Single image dehazing using color attenuation prior. Chin. J. New Clin. Med.

Berman, D., Treibitz, T., and Avidan, S. (2016, January 27–30). Non-local Image Dehazing. In Proceeding of the Computer Vision and Pattern Recognition, Las Vegas, NV, USA.

Tang, K., Yang, J., and Wang, J. (2014, January 23–28). Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing. Proceedings of the Computer Vision and Pattern Recognition, Columbus, OH, USA.

Mccartney, 1977, Optics of the Atmosphere: Scattering by Molecules and Particles, Opt. Acta. Int. J. Opt., 14, 698

Silberman, N., Hoiem, D., Kohli, P., and Fergus, R. (2012). Indoor Segmentation and Support Inference from RGBD Images. European Conference on Computer Vision, Springer.

Fattal, 2008, Single image dehazing, ACM Trans. Graph., 27, 1, 10.1145/1360612.1360671

Ko, H. (2012, January 13–16). Fog-degraded image restoration using characteristics of RGB channel in single monocular image. Proceedings of the 2012 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA.

Platt, 2007, Efficient sparse coding algorithms, Proc. Nips, 19, 801

Vogl, 1988, Accelerating the convergence of the back-propagation method, Biol. Cybern., 59, 257, 10.1007/BF00332914

Cai, 2016, DehazeNet: An End-to-End System for Single Image Haze Removal, IEEE Trans. Image Process., 25, 5187, 10.1109/TIP.2016.2598681

Chen, C., Do, M.N., and Wang, J. (2016). Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization. Computer Vision—ECCV 2016, Springer International Publishing.

Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., and Yang, M.M. (2016). Single Image Dehazing via Multi-scale Convolutional Neural Networks. European Conference on Computer Vision, Springer.

Tarel, J.P., and Bigorgne, E. (2009, January 3–5). Long-range road detection for off-line scene analysis. Proceedings of the IEEE Intelligent Vehicle Symposium (IV’2009), Xian, China.

Tarel, J.P., and Hautière, N. (October, January 29). Fast visibility restoration from a single color or gray level image. Proceedings of the International Conference on Computer Vision, Kyoto, Japan.

Tan, 2003, The laws of the information entropy values of land use composition, J. Nat. Resour., 1, 017

Cincotta, 1996, Information entropy, Celest. Mech. Dyn. Astron., 64, 43, 10.1007/BF00051604

Poor, 1997, Probability of error in MMSE multiuser detection, IEEE Trans Inf. Theory, 43, 858, 10.1109/18.568697

Wang, L.T., Hoover, N.E., Porter, E.H., and Zasio, J.J. (July, January 28). SSIM: A software levelized compiled-code simulator. Proceedings of the 24th ACM/IEEE Design Automation Conference, Miami Beach, FL, USA.