夜视图像局部颜色传递算法

薛模根; 周浦城; 刘存超

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

夜视图像局部颜色传递算法

薛模根, 周浦城, 刘存超

文章导航 > 红外与激光工程 > 2015 > 44(2): 781-785

薛模根, 周浦城, 刘存超. 夜视图像局部颜色传递算法[J]. 红外与激光工程, 2015, 44(2): 781-785.

引用本文:

薛模根, 周浦城, 刘存超. 夜视图像局部颜色传递算法[J]. 红外与激光工程, 2015, 44(2): 781-785.

Xue Mogen, Zhou Pucheng, Liu Cunchao. A novel local color transfer method for night vision image[J]. Infrared and Laser Engineering, 2015, 44(2): 781-785.

Citation:

Xue Mogen, Zhou Pucheng, Liu Cunchao. A novel local color transfer method for night vision image[J]. Infrared and Laser Engineering, 2015, 44(2): 781-785.

夜视图像局部颜色传递算法

薛模根^1,2,
周浦城^1,2,
刘存超^1,2

1.
陆军军官学院军用光电技术与系统实验室,安徽合肥230031;
2.
偏振光成像探测技术安徽省重点实验室,安徽合肥230031

基金项目:

安徽省自然科学基金(1208085QF115)

详细信息

作者简介:
薛模根(1964-),男,教授,博士生导师,博士,主要从事信息融合、光电对抗方面的研究工作。Email:zhoupc2004@163.com

中图分类号: TP391

A novel local color transfer method for night vision image

1.
Laboratory of Military Electro-Optical Technology and System,Army Officer Academy of PLA,Hefei 230031,China;
2.
Anhui Provincial Key Laboratory of Polarized Light Imaging Detection Technology,Hefei 230031,China

摘要: 针对基于全局统计信息颜色传递过程中存在的染色效果不能很好保持图像色彩的自然性,局部区域颜色与真实场景的颜色不符、目标变淡的问题,提出一种夜视图像局部颜色传递算法。首先,采用稀疏表示的方法对红外与微光图像融合;其次,对得到的融合图像进行非线性扩散,扩散结果采用核模糊均值聚类算法进行图像分割;然后,在YCbCr颜色空间对红外与微光图像块进行颜色传递;最后,把得到的彩色图像块组合成一幅图像,随后用得到的灰度融合图像来表征YCbCr空间的Y通道。实验结果表明,文中算法得到的彩色图像更加自然、真实。
- 彩色夜视 /
- 颜色传递 /
- 图像分割 /
- 非线性扩散
Abstract: A natural global color mapping method matches the statistical properties of night vision imagery to those of a daylight color image. Thus the rendered night vision image appears to resemble the natural target image in terms of color appearance and the reference image is not automatically selected. However, the colored night vision image may appear unnatural if the target image's global color statistics are different from that of the night vision scene. And then target is not easy to be detected because the color of target and background is similarity. Consequently, a new local color transfer method was presented. Firstly, the infrared (IR) and low-level-light (LL) images were fused by using sparse representation. Secondly, a nonlinear diffusion filter was applied to the gray fused image. The diffused image segmented by Kernel fuzzy C-mean algorithm. Finally, the IR and LL images block were color fused by using color transfer technology in the YCbCr color space, where the Y component of the color image was replaced with the fused image, which is a gray scale image made with multi-band night vision images. Experimental result shows that the obtained image has more natural and realistic coloration compared with global coloring method.
- coloring night-vision /
- color transfer /
- image segmentation /
- nonlinear diffusion

[1]
[2]	Yang Shaokui, Liu Wen. Color fusion method for low-level light and infrared images[J]. Infrared and Laser Engineering, 2014, 43(5): 1654-1659. (in Chinese)
[3]	Su Yu, Gao Shaoshu, Jin Weiqi, et al. Color-quality subjective evaluation for color fusion images of typical scenes based on color harmony [J]. Infrared and Laser Engineering, 2014, 43(11): 3767-3774. (in Chinese)
[4]
[5]
[6]	Toet A. Natural colour mapping for multiband night vision imagery[J]. Information Fusion, 2003, 4(1): 155-166.
[7]	Zheng Y, Essock E A. A local-coloring method for night-vision colorization utilizing image analysis and fusion [J]. Information Fusion, 2008, 9(2): 186-199.
[8]
[9]
[10]	Qian Xiaoyan, Zhang Tianchi, Wang Bangfeng, et al. Color night vision algorithm based on local color mapping [J]. Journal of Image and Graphics, 2012, 17(5): 689-693. (in Chinese)
[11]	Aharon M, Elad M, Bruckstein A. The K-SVD: an algorithm for designing of overcomplete dictionaries for sparse representation [J]. IEEE Trans on Signal Processing, 2006, 54(11): 4311-4322.
[12]
[13]	Candes E J, Romberg J, Tao T. Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information [J]. IEEE Trans on Information Theory, 2011, 52(2): 489-509.
[14]
[15]
[16]	Cao Junfeng, Shi Jiacheng, Luo Haibo, et al. Image enhancement using clustering and histogram equalization [J]. Infrared and Laser Engineering, 2012, 41(12): 3436-3441. (in Chinese)
[17]	Weickert J, ter Haar Romeny B M, Viergever M A. Efficient and reliable schemes for nonlinear diffusion filtering [J]. IEEE Trans on Image Processing, 1998, 7(3): 398-401.
[18]
[19]	Li Yunfeng, Feng Xiaoyun, Xu Mingwei, et al. Night vision dual-band images coloration using fast fusion and color transfer [J]. Journal of Image and Graphics, 2012,17(10): 1213-1221. (in Chinese)

[1]	黄宜帆, 贺岩, 胡善江, 侯春鹤, 朱小磊, 李凯鹏, 刘芳华, 陈勇强, 郭守川. 海洋激光雷达图像处理提取海水深度的方法 . 红外与激光工程, 2021, 50(6): 20211034-1-20211034-8. doi: 10.3788/IRLA20211034
[2]	甘士忠, 肖志涛, 陈雷, 南瑞杰. 基于高阶非线性模型的多目标高光谱图像解混算法 . 红外与激光工程, 2019, 48(10): 1026002-1026002(7). doi: 10.3788/IRLA201948.1026002
[3]	黄林生, 张庆, 张东彦, 林芬芳, 徐超, 赵晋陵. Relief-F筛选波段的小麦白粉病早期诊断研究 . 红外与激光工程, 2018, 47(5): 523001-0523001(8). doi: 10.3788/IRLA201847.0523001
[4]	崔光茫, 张克奇, 徐之海, 冯华君, 赵巨峰. 基于仿射重建和噪声散点直方图的图像噪声水平估计 . 红外与激光工程, 2018, 47(S1): 182-188. doi: 10.3788/IRLA201847.S126002
[5]	仲红玉, 尹丽菊, 高明亮, 邹国锋, 申晋, 王炫. 多参数亮度值重映射的颜色传递方法 . 红外与激光工程, 2018, 47(5): 526002-0526002(8). doi: 10.3788/IRLA201847.0526002
[6]	陈雷, 甘士忠, 孙茜. 基于回溯优化的非线性高光谱图像解混 . 红外与激光工程, 2017, 46(6): 638001-0638001(8). doi: 10.3788/IRLA201746.0638001
[7]	鲍雪晶, 戴仕杰, 郭澄, 吕寿丹, 沈成, 刘正君. 基于插值的共焦显微镜非线性畸变失真图像校正 . 红外与激光工程, 2017, 46(11): 1103006-1103006(7). doi: 10.3788/IRLA201746.1103006
[8]	刘乾, 袁道成, 何华彬, 吉方. 白光干涉仪传递函数的成因分析及其非线性研究 . 红外与激光工程, 2017, 46(6): 634002-0634002(6). doi: 10.3788/IRLA201746.0634002
[9]	鲁佳颖, 谷小婧, 顾幸生. 面向微光/红外融合彩色夜视的场景解析方法 . 红外与激光工程, 2017, 46(8): 804002-0804002(6). doi: 10.3788/IRLA201746.0804002
[10]	陈一超, 胡文刚, 武东生, 何永强, 李晓明. 三波段真彩色夜视光谱匹配技术 . 红外与激光工程, 2015, 44(12): 3837-3842.
[11]	苏宇, 高绍姝, 金伟其, 贾晓婷, 潘定平, 刘佳妮, 金凯佳. 典型场景彩色融合图像颜色协调性的主观评价 . 红外与激光工程, 2014, 43(11): 3767-3774.
[12]	祁敏, 曹剑中, 周祚峰, 高博, 郭惠楠, 杨磊. 基于Tao 立体匹配框架的全局优化算法 . 红外与激光工程, 2014, 43(9): 3122-3127.
[13]	王金玲, 贺小军, 宋克非. 采用区域互信息的多光谱与全色图像融合算法 . 红外与激光工程, 2014, 43(8): 2757-2764.
[14]	王冬冬, 张炜, 金国锋, 杨正伟, 田干. 尖点突变理论在红外热波检测图像分割中的应用 . 红外与激光工程, 2014, 43(3): 1009-1015.
[15]	高陈强, 阎兵早, 李强. 基于非线性映射模型的红外弱小目标图像仿真 . 红外与激光工程, 2013, 42(11): 2919-2924.
[16]	张勇, 金伟其. 夜视融合图像质量客观评价方法 . 红外与激光工程, 2013, 42(5): 1360-1365.
[17]	张勇, 金伟其. 夜视融合图像质量主观评价方法 . 红外与激光工程, 2013, 42(2): 528-532.
[18]	徐正平, 沈宏海, 黄厚田, 姚园, 孙超, 许永森. 单DMD彩色视频显示系统的颜色控制 . 红外与激光工程, 2013, 42(7): 1848-1852.
[19]	曹忆南, 王新伟, 周燕. 距离选通激光成像空间定位模糊C均值聚类分割法 . 红外与激光工程, 2013, 42(10): 2682-2686,2696.
[20]	闵超波, 张俊举, 常本康, 孙斌, 李英杰. 采用边界评价的红外视频运动目标时空域分割方法 . 红外与激光工程, 2013, 42(10): 2636-2641.

点击查看大图

计量

文章访问数: 341
HTML全文浏览量: 65
PDF下载量: 242
被引次数: 0

夜视图像局部颜色传递算法

1. 陆军军官学院军用光电技术与系统实验室,安徽合肥230031;

2. 偏振光成像探测技术安徽省重点实验室,安徽合肥230031

作者简介:
薛模根(1964-),男,教授,博士生导师,博士,主要从事信息融合、光电对抗方面的研究工作。Email:zhoupc2004@163.com

收稿日期: 2014-06-15
修回日期: 2014-07-20
刊出日期: 2015-02-25

基金项目:

安徽省自然科学基金(1208085QF115)

中图分类号: TP391

关键词:

摘要: 针对基于全局统计信息颜色传递过程中存在的染色效果不能很好保持图像色彩的自然性,局部区域颜色与真实场景的颜色不符、目标变淡的问题,提出一种夜视图像局部颜色传递算法。首先,采用稀疏表示的方法对红外与微光图像融合;其次,对得到的融合图像进行非线性扩散,扩散结果采用核模糊均值聚类算法进行图像分割;然后,在YCbCr颜色空间对红外与微光图像块进行颜色传递;最后,把得到的彩色图像块组合成一幅图像,随后用得到的灰度融合图像来表征YCbCr空间的Y通道。实验结果表明,文中算法得到的彩色图像更加自然、真实。

English Abstract

A novel local color transfer method for night vision image

1. Laboratory of Military Electro-Optical Technology and System,Army Officer Academy of PLA,Hefei 230031,China;

2. Anhui Provincial Key Laboratory of Polarized Light Imaging Detection Technology,Hefei 230031,China

Received Date: 2014-06-15
Rev Recd Date: 2014-07-20
Publish Date: 2015-02-25

Keywords:

Abstract: A natural global color mapping method matches the statistical properties of night vision imagery to those of a daylight color image. Thus the rendered night vision image appears to resemble the natural target image in terms of color appearance and the reference image is not automatically selected. However, the colored night vision image may appear unnatural if the target image's global color statistics are different from that of the night vision scene. And then target is not easy to be detected because the color of target and background is similarity. Consequently, a new local color transfer method was presented. Firstly, the infrared (IR) and low-level-light (LL) images were fused by using sparse representation. Secondly, a nonlinear diffusion filter was applied to the gray fused image. The diffused image segmented by Kernel fuzzy C-mean algorithm. Finally, the IR and LL images block were color fused by using color transfer technology in the YCbCr color space, where the Y component of the color image was replaced with the fused image, which is a gray scale image made with multi-band night vision images. Experimental result shows that the obtained image has more natural and realistic coloration compared with global coloring method.