留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

区域自适应多尺度强光融合的红外图像增强

巫玲 陈念年 廖小华

巫玲, 陈念年, 廖小华. 区域自适应多尺度强光融合的红外图像增强[J]. 红外技术, 2020, 42(11): 1072-1076, 1080.
引用本文: 巫玲, 陈念年, 廖小华. 区域自适应多尺度强光融合的红外图像增强[J]. 红外技术, 2020, 42(11): 1072-1076, 1080.
WU Ling, CHEN Niannian, LIAO Xiaohua. Infrared Image Enhancement Based on Regional Adaptive Multiscale Intense Light Fusion[J]. Infrared Technology , 2020, 42(11): 1072-1076, 1080.
Citation: WU Ling, CHEN Niannian, LIAO Xiaohua. Infrared Image Enhancement Based on Regional Adaptive Multiscale Intense Light Fusion[J]. Infrared Technology , 2020, 42(11): 1072-1076, 1080.

区域自适应多尺度强光融合的红外图像增强

详细信息
    作者简介:

    巫玲(1982-)女,四川遂宁人,讲师,硕士,主要研究方向为光学测量、视觉检测。Email:wuling751@126.com

  • 中图分类号: TP39

Infrared Image Enhancement Based on Regional Adaptive Multiscale Intense Light Fusion

  • 摘要: 图像增强可以分为全局增强和局部增强两种技术,当前基于局部的图像增强技术无法准确地对目标和背景进行分割且难以自适应地对分割区域进行增强。本文提出了一种区域自适应多尺度强光融合算法用于红外图像的增强处理。该算法首先使用语义分割技术完成目标区域和背景区域的划分,然后使用改进后的多尺度强光融合算法分别对各区域进行自适应增强。实验结果表明,所提算法的增强效果均优于当前主流算法,图像增强的视觉效果更真实。
  • 图  1  区域自适应多尺度强光融合算法流程图

    Figure  1.  The flow chart of the regional adaptive multiscale intense light fusion algorithm

    图  2  σ=1对应的高频分量及增强图像

    Figure  2.  High frequency components and enhanced image (σ=1)

    图  3  σ=5对应的高频分量及增强图像

    Figure  3.  High frequency components and enhanced image (σ=5)

    图  4  两种不同图像分割方法的分割结果

    Figure  4.  Segmentation results of two image segmentation methods

    图  5  实验用的部分红外图像

    Figure  5.  Some infrared images for the experiment.

    图  6  算法有效性验证效果展示

    Figure  6.  Demonstration of algorithm validity verification effect

    图  7  不同算法增强效果对比

    Figure  7.  Comparison of enhancement effects of different algorithms

    表  1  算法有效性验证的评价指标对比

    Table  1.   Comparison of evaluation indexes of algorithm validity verification

    Brenner Entropy
    Input image 0.4907 6.3527
    Single scale 0.9100 6.5170
    Multiscale 1.0244 6.5541
    Proposed 1.4699 6.6882
    下载: 导出CSV

    表  2  不同算法增强后的评价指标对比

    Table  2.   Comparison of evaluation indexes of different algorithms

    Input image LIME NPE CRM MF BIMEF MSRCR Proposed
    Brenner 0.8259 1.5939 1.3525 0.9502 1.0140 0.8831 0.4191 2.2327
    Entropy 6.1967 6.7101 6.6354 6.4660 6.5497 6.5351 6.1148 6.7776
    下载: 导出CSV
  • [1] Land E H, Mccann J J. Lightness and retinex theory[J]. Journal of the Optical Society of America, 1971, 61(1):1-11. doi:  10.1364/JOSA.61.000001
    [2] Jobson D J, Rahman Z, Woodell G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976. doi:  10.1109/83.597272
    [3] FU X, ZENG D, HUANG Y, et al. A Fusion-based Enhancing Method for Weakly Illuminated Images[J]. Signal Processing, 2016, 12(129):82-96. https://www.sciencedirect.com/science/article/pii/S0165168416300949
    [4] CHEN W, WANG W, YANG W, et al. Deep Retinex Decomposition for Low-Light Enhancement[C]//The British Machine Vision Conference (BMVC), 2018: 61772043. https://arxiv.org/abs/1808.04560
    [5] Debevec P E, Malik J. Recovering high dynamic range radiance maps from photographs[C]//SIGGRAPH 97 Conference Proceedings, 1997: 369-378.
    [6] YING Z, LI G, REN Y, et al. A New Low-Light Image Enhancement Algorithm using Camera Response Model[C]//International Conference on Computer Vision Workshop (ICCV Workshop). IEEE Computer Society, 2017: 3015-3022.
    [7] YING Z, LI G, GAO W. A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement[J]. Journal of Latex Class Files, 2015, 14(8): 1-10. http://export.arxiv.org/abs/1711.00591
    [8] Gharbi M, Chen J, Barron J T, et al. Deep Bilateral Learning for Real-Time Image Enhancement[J]. Acm Transactions on Graphics, 2017, 36(4): 118. https://arxiv.org/pdf/1707.02880
    [9] 徐军, 梁昌洪, 张建奇.一种红外图像增强的新方法[J].西安电子科技大学学报:自然科学版, 2000, 27(5): 14-17. http://www.cnki.com.cn/Article/CJFDTotal-XDKD200005002.htm

    XU J, LIANG C H, ZHANG J Q. A New Approach to IR Image Enhancement[J]. Journal of Xidian University, 2000, 27(5): 14-17. http://www.cnki.com.cn/Article/CJFDTotal-XDKD200005002.htm
    [10] 汪忱, 张宝辉, 王虹, 等.基于视觉显著区域的红外图像增强算法研究[J].红外技术, 2017(9): 835-840. http://www.cnki.com.cn/Article/CJFDTOTAL-HWJS201709010.htm

    WANG C, ZHANG B H, WANG H, etc. Research on Infrared Image Enhancement Algorithm based on Visual Saliency[J]. Infrared Technology, 2017(9): 835-840. http://www.cnki.com.cn/Article/CJFDTOTAL-HWJS201709010.htm
    [11] 关文涛.选择的艺术:Photoshop CS图层通道深度剖析[M].北京:人民邮电出版社, 2006: 459.

    GUAN W T. The art of choice: depth analysis of Photoshop CS layer channel[M]. BeiJing: People's Posts and Telecommunications Press, 2006: 459.
    [12] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing & Computer-assisted Intervention, 2015: 234-241. https://arxiv.org/pdf/1505.04597.pdf
    [13] Itti L. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259. doi:  10.1109/34.730558
    [14] 王竑舒, 徐熙平.广角相机图像的调焦评价函数研究[J].长春理工大学学报:自然科学版, 2019(3): 38-41, 50.

    WANG H S, XU X P. Study on Focusing Evaluation Function of Wide-angle Camera Image[J]. Journal of Changchun University of Science and Technology: Natural Science Edition, 2019(3): 38-41, 50.
    [15] GUO X, LI Y, LING H. LIME: Low-Light Image Enhancement via Illumination Map Estimation[J]. IEEE Transactions on Image Processing, 2017, 26(2): 982-993. http://www.cnki.com.cn/Article/CJFDTotal-CGJM201903009.htm
    [16] WANG S, ZHENG J, HU H M, et al. Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images[J]. IEEE Transactions on Image Processing, 2013, 22(9): 3538-3548. doi:  10.1109/TIP.2013.2261309
    [17] Petro A B, Sbert C, Morel J M. Multiscale Retinex[J]. Image Processing on Line, 2014(4): 71-88. https://www.researchgate.net/publication/272643640_Multiscale_Retinex
  • 加载中
图(7) / 表(2)
计量
  • 文章访问数:  233
  • HTML全文浏览量:  66
  • PDF下载量:  45
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-12-30
  • 修回日期:  2020-11-03
  • 刊出日期:  2020-11-20

目录

    /

    返回文章
    返回