首页 > 论文 > 激光与光电子学进展 > 56卷 > 20期(pp:201003--1)

基于全卷积回归网络的图像去雾算法

Image Dehazing Algorithm Based on Full Convolution Regression Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对当前去雾算法经常出现过度曝光、颜色失真等问题,提出了一种基于全卷积回归网络的去雾算法。该回归网络基于端到端系统,由特征提取和特征融合两部分构成。首先,输入有雾图像,经过特征提取和特征融合,最终回归为粗透射率图;之后使用导向滤波对其进行优化,再利用大气物理散射模型反演出无雾图像;最终采用限制对比度自适应直方图均衡化(CLAHE)对无雾图像进行增强,以得到更符合人类视觉的清晰图像。所提算法不仅可以有效避免去雾后出现的过度曝光和颜色失真等问题,而且能保留图像完整的细节信息,具有较好的去雾效果。

Abstract

Herein, a dehazing algorithm based on a full convolution regression network is proposed to solve the overexposure and color distortions caused by current dehazing algorithms. The regression network is based on an end-to-end system and comprises two parts, feature extraction and feature fusion, to which a foggy image is first subjected, then regressed into a coarse transmittance map and optimized by the guide filter. The atmospheric physical scattering model is used to invert a fog-free image , which is then enhanced via contrast limit adaptive histogram equalization (CLAHE) to obtain a clear image that is more suitable to human vision. The proposed algorithm can avoid problems such as overexposure and color distortion post dehazing, retain complete details, and provide a better dehazing effect.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP56.201003

所属栏目:图像处理

基金项目:广东省省级科技计划项目;

收稿日期:2019-04-09

修改稿日期:2019-04-25

网络出版日期:2019-10-01

作者单位    点击查看

张泽浩:华南师范大学物理与电信工程学院, 广东 广州 510006
周卫星:华南师范大学物理与电信工程学院, 广东 广州 510006

联系人作者:周卫星(940196535@qq.com)

备注:广东省省级科技计划项目;

【1】Liu G, Lü Q B and Liu Y Y. Single image dehazing algorithm based on adaptive dark channel prior. Acta Photonica Sinica. 47(2), (2018).
刘国, 吕群波, 刘扬阳. 基于自适应暗原色的单幅图像去雾算法. 光子学报. 47(2), (2018).

【2】Fattal R. Single image dehazing. ACM Transactions on Graphics. 27(3), 721-728(2008).

【3】Tan R T. Visibility in bad weather from a single image. [C]∥2008 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2008, Anchorage, AK, USA. New York: IEEE. 10139948, (2008).

【4】He K M, Sun J and Tang X O. Single image haze removal using dark channel prior. [C]∥2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE. 1956-1963(2009).

【5】Meng G F, Wang Y, Duan J Y et al. Efficient image dehazing with boundary constraint and contextual regularization. [C]∥2013 IEEE International Conference on Computer Vision, December 1-8, 2013, Sydney, NSW, Australia. New York: IEEE. 14144884, (2013).

【6】Berman D, Treibitz T and Avidan S. Non-local image dehazing. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 1674-1682(2016).

【7】Zhu Q S, Mai J M and Shao L. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing. 24(11), 3522-3533(2015).

【8】Zhang K P, Zhang Z P, Li Z F et al. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters. 23(10), 1499-1503(2016).

【9】Shelhamer E, Long J and Darrell T. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(4), 640-651(2017).

【10】Yu Y H, Lin H F, Meng J N et al. Deep transfer learning for modality classification of medical images. Information. 8(3), (2017).

【11】Cai B L, Xu X M, Jia K et al. DehazeNet: an end-to-end system for single image haze removal. IEEE Transactions on Image Processing. 25(11), 5187-5198(2016).

【12】Zhou F Y, Jin L P and Dong J. Review of convolutional neural network. Chinese Journal of Computers. 40(6), 1229-1251(2017).
周飞燕, 金林鹏, 董军. 卷积神经网络研究综述. 计算机学报. 40(6), 1229-1251(2017).

【13】Li Z W, Tan P, Tan R T et al. Simultaneous video defogging and stereo reconstruction. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 4988-4997(2015).

【14】Narasimhan S G and Nayar S K. Chromatic framework for vision in bad weather. [C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 15, 2000, Hilton Head Island, SC, USA. New York: IEEE. 598-605(2002).

【15】Laina I, Rupprecht C, Belagiannis V et al. Deeper depth prediction with fully convolutional residual networks. [C]∥2016 Fourth International Conference on 3D Vision (3DV), October 25-28, 2016, Stanford, CA, USA. New York: IEEE. 239-248(2016).

【16】He K M, Sun J and Tang X O. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence. 35(6), 1397-1409(2013).

【17】Fei Y J and Shao F. Contrast adjustment based on image retrieval. Laser & Optoelectronics Progress. 55(5), (2018).
费延佳, 邵枫. 基于图像检索的对比度调整. 激光与光电子学进展. 55(5), (2018).

【18】Wang L J, Yang Y Y, Dai M et al. Near infrared spectral pre-processing algorithm based on histogram layering mapping. Laser & Optoelectronics Progress. 54(9), (2017).
王丽杰, 杨羽翼, 代敏 等. 基于直方图分层映射的近红外光谱预处理算法. 激光与光电子学进展. 54(9), (2017).

引用该论文

Zhang Zehao,Zhou Weixing. Image Dehazing Algorithm Based on Full Convolution Regression Network[J]. Laser & Optoelectronics Progress, 2019, 56(20): 201003

张泽浩,周卫星. 基于全卷积回归网络的图像去雾算法[J]. 激光与光电子学进展, 2019, 56(20): 201003

被引情况

【1】刘宇航,吴帅. 基于多尺度融合和对抗训练的图像去雾算法. 激光与光电子学进展, 2020, 57(6): 61015--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF