浏览全部资源
扫码关注微信
收稿：2017-07-11，
修回：2017-9-22，
纸质出版：2018-04-16
移动端阅览
目的
2
图像去雾是计算机视觉的重要研究方向，既获得高质量的去雾图像，又保证较低的时间复杂度一直是图像去雾面临的挑战，为此提出了一种基于雾天图像降质模型的优化去雾方法。
方法
2
根据雾天图像降质模型，暗原色作为先验知识，对模型的两个物理量大气光值和透射率进行优化。传统优化算法中通常都是固定其一，优化另一个物理量，与传统方法不同，考虑到大气光和透射率的相关性，采用多元优化策略，将这两个物理量作为互相影响的整体，利用迭代算法进行优化。为保持去雾图像颜色真实、自然，基于对无雾图像的统计特性，多阈值融合的约束条件作为迭代停止的条件，控制优化去雾程度，复原高质量去雾图像。
结果
2
本文方法与其他去雾方法相比，在视觉效果上，图像结构更加清晰，细节更加丰富，色彩更加真实。在客观数据方面，本文方法获得图像的彩色直方图与有雾图像的彩色直方图在形状上更相似，同时在Cones、Herzeliya、House、Dolls对比图像中，本文方法结果图像的信息熵值都比较高，分别为13.801 270、15.490 912、15.395 014、16.276 838，且时间复杂度较He方法（使用软抠图算法优化透射率）降低了3~5倍。
结论
2
本文去雾方法利用迭代算法对大气光和透射率进行多元优化，同时采用多阈值融合约束条件控制优化去雾程度。本文方法在色彩保真度、细节恢复等方面都优于经典算法，同时获得了较好的客观评价数据。实验结果表明，本文方法能够达到主客观都满意的效果。
Objective
2
Hazy or foggy images have low visibility
contrast
and saturation. These features are undesired in computer vision applications
such as most automatic systems for surveillance
intelligent vehicles
and outdoor object recognition. Thus
image haze removal plays a significant role in computer vision. Many haze removal methods
including image enhancement and restoration methods
have been proposed. Image enhancement methods often suffer from information loss
over-enhancement
distorted colors
and significant halos. Image restoration methods are based on hazy image degradation models and therefore perform better than enhancement methods. On the basis of image degradation models
the use of dark channels prior to obtaining haze-free images is accepted
but the restored images often suffer from the block effect. Some optimization methods are proposed to eliminate the block effect. Visual effects are improved
but the time complexity is high. Thus
maintaining the high quality of haze-free images while ensuring low time complexity has always been a challenge for image defogging. We accordingly propose a multivariate-optimized haze removal method based on hazy image degradation model.
Method
2
Unlike traditional optimization methods that fix other physical quantities while optimizing a physical quantity
the proposed method considers the correlation between the atmospheric light and transmission mentioned in the degradation model. The atmospheric light and transmission are treated as a whole
and we present a multivariate-optimized haze removal method by iteration. The multivariate-optimized haze removal method can optimize atmospheric light and transmission at the same time. Iterated dehazing is an optimization process that can continuously ensure haze-free images. We provide constraint conditions for multi-threshold fusion on the basis of the statistical characteristics of haze-free images to keep the restored image real and natural. The constraint conditions are utilized to control dehazing degree
and haze-free images are then obtained.
Result
2
Haze removal experiments on images show that the performances of the proposed method in terms of visual effect
color histogram
information entropy
and time complexity are better than those of other classical dehazing algorithms. In the subjective aspect
unlike other fog removal methods
the proposed method obtains more natural and real images. The proposed method can keep considerable image details and structure without color distortion. The halo effect and artifacts are considerably reduced in the images by the proposed algorithm. The intensity of restored images is highly preserved. In the objective aspect
the color histogram in hazy images presents a convergent distribution
and the color intensity is high because of fog cover. After removing haze
the color histogram becomes evenly distributed
and the color intensity is enhanced. Thus
the color histogram of dehazed images should be similar to the color histogram of hazy images with a structural shape. The color histograms of our resultant image and the haze image are highly similar in shape. The image information entropy of the result image is relatively high. For images of Cones
Herzeliya
House
and Dolls
the image information entropies are 13.801 270
15.490 912
15.395 014
and 16.276 838
respectively. We also evaluate the time complexity of our algorithm. Our method is three times to five times faster than haze removal methods that optimize transmission via soft matting.
Conclusion
2
This paper presents a multivariate-optimized haze removal method based on the hazy image degradation model. The proposed method not only can optimize multiple variables but also can achieve low time complexity. Constraint conditions for multi-threshold fusion on the basis of the statistical characteristics of haze-free images are developed to control iteration numbers
which contribute to the robustness of the method. Extensive experiments show that the proposed method can obtain satisfactory results in both objective and subjective aspects.
Wu D, Zhu Q S. The Latest research progress of image dehazing[J]. Acta Automatica Sinica, 2015, 41(2):221-239.
吴迪, 朱青松.图像去雾的最新研究进展[J].自动化学报, 2015, 41(2):221-239. [DOI:10.16383/j.aas.2015.c131137]
Tan R T. Visibility in bad weather from a single image[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008: 1-8. [ DOI:10.1109/CVPR.2008.4587643 http://dx.doi.org/10.1109/CVPR.2008.4587643 ]
Schechner Y Y, Narasimhan S G, Nayar S K. Instant dehazing of images using polarization[C]//Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, HI, USA: IEEE, 2001: I-325-I-332. [ DOI:10.1109/CVPR.2001.990493 http://dx.doi.org/10.1109/CVPR.2001.990493 ]
Shwartz S, Namer E, Schechner Y Y. Blind haze separation[C]//Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, NY, USA: IEEE, 2006: 1984-1991. [ DOI:10.1109/CVPR.2006.71 http://dx.doi.org/10.1109/CVPR.2006.71 ]
Narasimhan S G, Nayar S K. Chromatic framework for vision in bad weather[C]//Proceedings of 2000 IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, SC, USA: IEEE, 2000: 598-605. [ DOI:10.1109/CVPR.2000.855874 http://dx.doi.org/10.1109/CVPR.2000.855874 ]
Narasimhan S G, Nayar S K. Contrast restoration of weather degraded images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6):713-724.[DOI:10.1109/TPAMI.2003.1201821]
Nayar S K, Narasimhan S G. Vision in bad weather[C]//Proceedings of the 7th IEEE International Conference on Computer Vision. Kerkyra, Greece: IEEE, 1999: 820-827. [ DOI:10.1109/ICCV.1999.790306 http://dx.doi.org/10.1109/ICCV.1999.790306 ]
Kopf J, Neubert B, Chen B, et al. Deep photo: model-based photograph enhancement and viewing[C]//Proceedings of ACM SIGGRAPH Asia. Singapore: ACM, 2008. [ DOI:10.1145/1409060.1409069 http://dx.doi.org/10.1145/1409060.1409069 ]
Narasimhan S G, Nayar S. Interactive deweathering of an image using physical models[C]//Proceedings of 2003 IEEE Workshop on Color and Photometric Methods in Computer Vision. Carnegie Mellon University: ICCV, 2003.
Fattal R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3):72.[DOI:10.1145/1360612.1360671]
He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353.[DOI:10.1109/TPAMI.2010.168]
He K M, Sun J, Tang X O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6):1397-1409.[DOI:10.1109/TPAMI.2012.213]
Xue M G, Zhou P C, Zhang H K. Single foggy image restoration using orientation extended fields of experts[J]. Journal of Computer-Aided Design&Computer Graphics, 2014, 26(5):782-787.
薛模根, 周浦城, 张洪坤.利用方向延伸专家场的单幅雾天图像复原[J].计算机辅助设计与图形学学报, 2014, 26(5):782-787.
Huang L H. Adaptive defogging algorithm of single image in color space[J]. Journal of Computer-Aided Design&Computer Graphics, 2015, 27(8):1506-1511.
黄黎红.色彩空间中的单幅图像自适应去雾算法[J].计算机辅助设计与图形学学报, 2015, 27(8):1506-1511. [DOI:10.3969/j.issn.1003-9775.2015.08.019]
Nair D, Kumar P A, Sankaran P. An effective surround filter for image dehazing[C]//Proceedings of 2014 International Conference on Interdisciplinary Advances in Applied Computing. Amritapuri, India: ACM, 2014: 20. [ DOI:10.1145/2660859.2660926 http://dx.doi.org/10.1145/2660859.2660926 ]
Zhou Y W, Chen Q, Sun Q S, et al. Remote sensing image enhancement based on dark channel prior and bilateral filtering[J]. Journal of Image and Graphics, 2014, 19(2):313-321.
周雨薇, 陈强, 孙权森, 等.结合暗通道原理和双边滤波的遥感图像增强[J].中国图象图形学报, 2014, 19(2):313-321. [DOI:10.11834/jig.20140218]
Liu Y, Li H J, Wang M H. Single image dehazing via large sky region segmentation and multiscale opening dark channel model[J]. IEEE Access, 2017, 5:8890-8903.[DOI:10.1109/ACCESS.2017.2710305]
Zeng L, Dai Y Z. Single image dehazing based on combining dark channel prior and scene radiance constraint[J]. Chinese Journal of Electronics, 2016, 25(6):1114-1120.[DOI:10.1049/cje.2016.08.006]
Meng G F, Wang Y, Duan J Y, et al. Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney, NSW, Australia: IEEE, 2013: 617-624. [ DOI:10.1109/ICCV.2013.82 http://dx.doi.org/10.1109/ICCV.2013.82 ]
Reinhard E, Stark M, Shirley P, et al. Photographic tone reproduction for digital images[C]//Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques. San Antonio, TX, USA: ACM, 2002: 267-276. [ DOI:10.1145/566654.566575 http://dx.doi.org/10.1145/566654.566575 ]
Chambah M, Rizzi A, Gatta C, et al. Perceptual approach for unsupervised digital color restoration of cinematographic archives[C]//Proceedings of SPIE Color Imaging Ⅷ: Processing, Hardcopy, and Applications. Santa Clara, CA, United States: SPIE, 2003: 138-149. [ DOI:10.1117/12.472019 http://dx.doi.org/10.1117/12.472019 ]
Yu J, Xu D B, Liao Q M. Image defogging:a survey[J]. Journal of Image and Graphics, 2011, 16(9):1561-1576.
禹晶, 徐东彬, 廖庆敏.图像去雾技术研究进展[J].中国图像图形学报, 2011, 16(9):1561-1576. [DOI:10.11834/jig.20110920]
相关作者
相关机构
京公网安备11010802024621
