基于天空检测和超像素分割的图像去雾方法
作者:
作者单位:

1.广东省水利水电科学研究院;2.广东省科学院广州地理研究所

基金项目:

广东省重点领域研发计划项目,广东省科学院专项资金项目,广东省水利科技创新项目


Single Image Dehazing Based on Sky Detection and Super Pixel Segmentation
Author:
Affiliation:

1.Guangdong Research Institute of Water Resources and Hydropower;2.Guangdong Academy of Sciences, Guangzhou Institute of Geography

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对经典图像去雾算法在边缘区域易产生光晕效应、天空等明亮区域还原失真、色调偏移等问题,提出一种基于天空检测和超像素分割的改进暗通道图像去雾新方法(Dark Channel Prior based on Sky Detection and Super Pixel, SSPDCP)。该方法首先对雾图采用HSV变换提取亮度分量进行自适应阈值分割,然后应用图像连通分析技术识别天空域;接着利用天空域估计大气光值,针对天空和非天空区域分别建立各自的透射率计算模型,并基于构建的超像素级透射率融合模型获得融合透射率图,以促进边界区域的平滑过渡;采用多尺度引导滤波精化透射率图,最后应用大气散射模型完成图像复原并进行亮度增强处理,实现无雾图像的自然恢复。该方法识别的天空区域较为连续完整,以超像素代替方形窗口有效克服局部块效应的影响,大气光值和透射率图估计更为客观准确,主观定性和客观定量评价方面来看,该方法复原的图像具有整体误差小、信噪比优良、结构相似度高等优势。本文所提出的图像去雾新方法能有效抑制边缘区域的光晕效应,且复原的天空区域明亮自然,图像去雾质量相比现有方法有进一步提升。

    Abstract:

    To solve the halo effect in edge area and color distortion problems in sky area of the classic image dehazing algorithm, a new improved dark channel prior dehazing method based on sky detection and super-pixel segmentation is proposed. The proposed method first applied the HSV color transformation to extract the light component of haze image with an adaptive-threshold segmentation technology. Then sky and non-sky areas were extracted with image connectivity analysis technology. After that, the atmospheric light value was estimated from sky areas, and transmission map of sky and non-sky areas were estimated with luminance model and super-pixels dark channel prior model separately, and a pixel-based fusion model was proposed to obtain a comprehensive transmission map to promote the smooth transition in boundary area. Next, the transmission map was refined by a multi-scale guided filter algorithms. Finally, the dehazed image was restored naturally with atmospheric scattering model and brightness enhancement processing. Experimental results show that the sky area identified from this method is more continuously and completely, and it is effectively to overcome the influence of halo effects when use superpixels instead of square windows to acquire transmission maps. The estimation of atmospheric light values and transmittance maps are more objectively and accurately. From the perspectives of subjective qualitative and objective quantitative evaluation, the proposed method shows more advantage over small overall error, excellent signal-to-noise ratio, and high structural similarity in dehazed images. The proposed method can restore a more natural sky and weaken the halo effect in edge area, the quality of the dehazed image is further improved compared to the state of the art on both qualitative and quantitative analysis.

    参考文献
    [1] .L., T.T., et al. Single Image Dehazing Based on Adaptive Histogram Equalization and Linearization of Gamma Correction[C]. 2019 25th Asia-Pacific Conference on Communications (APCC). 2019:36-40.
    [2] .Z., X., L. X. and C. X. Fog Removal from Video Sequences Using Contrast Limited Adaptive Histogram Equalization[C]. 2009 International Conference on Computational Intelligence and Software Engineering. 2009:1-4.
    [3] .I., E. and M. R. A Fast Algorithm for Contrast Restoration of Weather Degraded Images[C]. 2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems. 2012:636-641.
    [4] .Zotin, A., Fast Algorithm of Image Enhancement based on Multi-Scale Retinex[J].Procedia Computer Science, 2018. 131:6-14.
    [5] .Yong, D., G. B. and C. J., Haze detection and removal in high resolution satellite image with wavelet analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002. 40(1):210-217.
    [6] .刘佳敏与何宁, 基于改进同态滤波的低对比度图像增强. 计算机应用与软件[J], 2020. 37(03): 220-224.
    Liu Jiamin, He Ning. Low Contrast Image Enhancement Based on Improved Homomorphic Filtering[J]. Computer Applications and Software, 2020. 37(03): 220-224.
    [8] [7].He, K., J. Sun and X. Tang, Single Image Haze Removal Using Dark Channel Prior[J]. IEEE Trans Pattern Anal Mach Intell, 2011. 33(12):2341-53.
    [9] [8].D., B., T. T. and A. S. Non-local Image Dehazing[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:1674-1682.
    [10] [9].Zhu, Q., J. Mai and L. Shao, A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior[J]. IEEE Trans Image Process, 2015. 24(11):3522-33.
    [11] [10].He, K., J. Sun and X. Tang, Guided image filtering[J]. IEEE Trans Pattern Anal Mach Intell, 2013. 35(6):1397-409.
    [12] [11].代书博, 徐伟, 朴永杰, 陈彦彤. 基于暗原色先验的遥感图像去雾方法[J]. 光学学报, 2017, 37(3): 0328002.
    Dai Shubo, Xu Wei, Piao Yongjie, Chen Yantong. Remote Sensing Image Defogging Based on Dark Channel Prior[J]. Acta Optica Sinica, 2017, 37(3): 0328002.
    [14] [12].谭伟, 曹世翔, 齐文雯, 何红艳. 一种高分辨率遥感图像去雾霾方法[J]. 光学学报, 2019, 39(3): 0301005.
    Wei Tan, Shixiang Cao, Wenwen Qi, Hongyan He. A Haze Removal Method for High-Resolution Remote Sensing Images[J]. Acta Optica Sinica, 2019, 39(3): 0301005.
    [16] [13].廖章回与姜闯, 高分辨率遥感影像快速去雾[J]. 测绘学报, 2022. 51(03): 446-456.
    LIAO Zhanghui, JIANG Chuang. Fast dehaze of high resolution remote sensing images[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(3): 446-456.
    [18] [14].Bolun, C., et al., DehazeNet: An End-to-End System for Single Image Haze Removal[J]. IEEE Trans Image Process, 2016. 25(11):5187-5198.
    [19] [15].J, M.E., Optics of the atmosphere: Scattering by molecules and particles[M]// 1976, New York: John Wiley and Sons. 23-32.
    [20] [16].杨燕,张浩文,张金龙.结合天空分割和透射率映射的图像去雾[J].光学精密工程,2021,29(02):400-410.
    Yang Yan, Zhang Haowen, Zhang Jinlong.Single Image Dehazing Combining Sky Segmentation and Transmission Mapping[J]. Optics and Precision Engineering, 2021,29(02):400-410.
    [22] [17].金天虎 , 陶砚蕴 , 李佐勇. 基于超像素图像分割的暗通道先验去雾改进算法[J]. 电子学报, 2023, 51(1): 146-159 .
    JIN Tian-hu , TAO Yan-yun , LI Zuo-yong. An Improved Dark Channel Prior Dehazing Algorithm Based on Superpixel Image Segmentation[J]. ACTA ELECTONICA SINICA, 2023, 51(1): 146-159.
    [24] [18].Geraets, W.G., A.N. van Daatselaar and J.G. Verheij, An efficient filling algorithm for counting regions[J]. Comput Methods Programs Biomed, 2004. 76(1):1-11.
    [25] [19].Zhu, Y., et al., Haze removal method for natural restoration of images with sky[J]. Neurocomputing, 2017. 275(JAN.31):499-510.
    [26] [20].Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2012,34(11):2274?2282.
    [27] [21].刘海波, 杨杰, 吴正平, 张庆年, 邓勇. 基于区间估计的单幅图像快速去雾[J]. 电子与信息学报, 2016, 38(2): 381-388. doi: 10.11999/JEIT150403.
    Liu Haibo,Yang Jie,Wu Zhengping, et al.Fast Single Image Dehazing Based on Interval Estimation[J]. Journal of Electronics & Information Technology,2016, 38(2): 381-388. doi: 10.11999/JEIT150403.
    [29] [22].A., H. and Z. D. Image Quality Metrics: PSNR vs. SSIM[C].The 20th International Conference on Pattern Recognition. 2010:2366-2369.
    相似文献
    引证文献
    引证文献 [0]
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

高仁强,陈亮雄,孙秀峰,王欢欢,高真.基于天空检测和超像素分割的图像去雾方法[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:76
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2024-01-09
  • 最后修改日期:2024-03-10
  • 录用日期:2024-03-11

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司