基于纹理显著性的微光图像目标检测

金左轮; 韩静; 张毅; 柏连发

doi:10.7498/aps.63.069501

摘要

微光图像对比度较低，目标显著性不明显，目标自动探测难度大. 针对此问题，本文提出一种噪声鲁棒性较好的图像局部纹理粗糙度算法，并给出一种适用于微光图像显著分析的纹理显著性算法. 首先，提出一种新的局部纹理粗糙度算法，该算法利用最佳尺寸计算局部纹理粗糙度，对纹理图像进行加噪实验，与基于局部分形维的粗糙度方法相比，本文局部纹理粗糙度算法表现出较好的噪声鲁棒性；其次，在提取图像粗糙度特征图的基础上，给出一种针对纹理的显著性度量算法；最后，将纹理显著性算法应用于微光图像目标检测，实验结果证明了该算法的有效性.

关键词:

Abstract

Owing to its low contrast, the target of low light level (LLL) image is not very salient, and it is difficult to detect automatically. Aimed at this problem, this paper proposes a noise robustness algorithm for computing the local texture coarseness (LTC) of textured images, and provides a texture saliency (TS) calculation method that is applicable to saliency analysis of LLL image. Firstly, we present a novel LTC algorithm, by which the LTC around a pixel using the best size of the pixel. Compared with coarseness measure based on local fractal dimension, the LTC algorithm shows much better noise robustness in the experiments of noised textured images. Then, a TS algorithm is given based on the extraction of texture coarseness feature map. Finally, we apply the TS algorithm to LLL image target detection, which is efficient proved by experimental results.

Keywords:

作者及机构信息

1.
南京理工大学, 江苏省光谱成像与智能感知重点实验室, 南京 210094

基金项目: 国家自然科学基金（批准号：61231014，61071147）资助的课题.

Authors and contacts

1.
Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing 210094, China

Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 61231014, 61071147).

参考文献

[1]	Zhang C, Bai L F, Zhang Y 2007 Acta Phys. Sin. 56 3227 (in Chinese) [张闯, 柏连发, 张毅 2007 56 3227]
[2]	Wang L P, Sun S Y, Chen Q, Zhang B M 2000 Infrared Millim. Waves 19 289 (in Chinese) [王利平, 孙韶远, 陈钱, 张保民 2000 红外与毫米波学报 19 289]
[3]	Li Z, Itti L 2011 IEEE Trans. Image Process. 20 2017
[4]	Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese) [许元男, 赵远, 刘丽萍, 张宇, 孙秀冬 2010 59 980]
[5]	Walther D, Koch C 2006 Neural Networks 19 1395
[6]	Zhu Y Q, Qu X H, Zhang F M, Tao H R 2013 Acta Phys. Sin. 62 244201 (in Chinese) [朱元庆, 曲兴华, 张福民, 陶会荣 2013 62 244201]
[7]	Liu F, Liang H X, Zheng L M, Ji X Y 2012 Chin. Phys. B 21 040204
[8]	Wang X Y, Wang Y X, Yun J J 2011 Chin. Phys. B 20 104202
[9]	Haralick R M, Shanmugam K, Dinstein I H 1973 IEEE Trans. Syst. Man Cybern. 6 610
[10]	Ojala T, Pietikainen M, Maenpaa T 2002 IEEE Trans. Pattern Anal. Mach. Intell. 24 971
[11]	Tamura H, Mori S, Yamawaki T 1978 IEEE Trans. Syst. Man Cybern. 8 460
[12]	Fan J, He X, Zhou N, Jain R 2012 IEEE Trans. Multimedia 14 1414
[13]	Chatzichristofis S A, Boutalis Y S 2010 Multimed. Tools. Appl. 46 493
[14]	Shamir L, Wolkow C A, Goldberg I G 2009 Bioinformatics 25 3060
[15]	Novianto S, Suzuki Y, Maeda J 2003 Pattern Recogn. Lett. 24 365
[16]	Julesz B 1981 Nature 290 7
[17]	Zhu S C, Guo C E, Wang Y, Xu Z 2005 Int. J. Comput. Vision 62 121
[18]	Seneta E 1992 Hist. Math. 19 24
[19]	Brodatz P 1966 Textures: A Photographic Album for Artists and Designers (New York: Dover)
[20]	Ma Z M, Tao C K 1999 Acta Phys. Sin. 48 2202 (in Chinese) [马兆勉, 陶纯堪 1999 48 2202]
[21]	Kadir T, Brady M 2001 Int. J. Comput. Vision 45 83
[22]	Palmer S E 1992 Vision Science: Photons to Phenomenology (London: The MIT Press) p254
[23]	Syeda-Mahmood T F 1997 Int. J. Comput. Vision 21 9
[24]	Le Meur O, Le Callet P, Barba D, Thoreau D 2006 IEEE Trans. Pattern Anal. Mach. Intell. 28 802
[25]	Itti L, Koch C, Niebur E 1998 IEEE Trans. Pattern Anal. Mach. Intell. 20 1254
[26]	Hou X D, Zhang L Q 2007 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Minneapolis, USA, June 17–22, 2007 p1

施引文献

[1]	Zhang C, Bai L F, Zhang Y 2007 Acta Phys. Sin. 56 3227 (in Chinese) [张闯, 柏连发, 张毅 2007 56 3227]
[2]	Wang L P, Sun S Y, Chen Q, Zhang B M 2000 Infrared Millim. Waves 19 289 (in Chinese) [王利平, 孙韶远, 陈钱, 张保民 2000 红外与毫米波学报 19 289]
[3]	Li Z, Itti L 2011 IEEE Trans. Image Process. 20 2017
[4]	Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese) [许元男, 赵远, 刘丽萍, 张宇, 孙秀冬 2010 59 980]
[5]	Walther D, Koch C 2006 Neural Networks 19 1395
[6]	Zhu Y Q, Qu X H, Zhang F M, Tao H R 2013 Acta Phys. Sin. 62 244201 (in Chinese) [朱元庆, 曲兴华, 张福民, 陶会荣 2013 62 244201]
[7]	Liu F, Liang H X, Zheng L M, Ji X Y 2012 Chin. Phys. B 21 040204
[8]	Wang X Y, Wang Y X, Yun J J 2011 Chin. Phys. B 20 104202
[9]	Haralick R M, Shanmugam K, Dinstein I H 1973 IEEE Trans. Syst. Man Cybern. 6 610
[10]	Ojala T, Pietikainen M, Maenpaa T 2002 IEEE Trans. Pattern Anal. Mach. Intell. 24 971
[11]	Tamura H, Mori S, Yamawaki T 1978 IEEE Trans. Syst. Man Cybern. 8 460
[12]	Fan J, He X, Zhou N, Jain R 2012 IEEE Trans. Multimedia 14 1414
[13]	Chatzichristofis S A, Boutalis Y S 2010 Multimed. Tools. Appl. 46 493
[14]	Shamir L, Wolkow C A, Goldberg I G 2009 Bioinformatics 25 3060
[15]	Novianto S, Suzuki Y, Maeda J 2003 Pattern Recogn. Lett. 24 365
[16]	Julesz B 1981 Nature 290 7
[17]	Zhu S C, Guo C E, Wang Y, Xu Z 2005 Int. J. Comput. Vision 62 121
[18]	Seneta E 1992 Hist. Math. 19 24
[19]	Brodatz P 1966 Textures: A Photographic Album for Artists and Designers (New York: Dover)
[20]	Ma Z M, Tao C K 1999 Acta Phys. Sin. 48 2202 (in Chinese) [马兆勉, 陶纯堪 1999 48 2202]
[21]	Kadir T, Brady M 2001 Int. J. Comput. Vision 45 83
[22]	Palmer S E 1992 Vision Science: Photons to Phenomenology (London: The MIT Press) p254
[23]	Syeda-Mahmood T F 1997 Int. J. Comput. Vision 21 9
[24]	Le Meur O, Le Callet P, Barba D, Thoreau D 2006 IEEE Trans. Pattern Anal. Mach. Intell. 28 802
[25]	Itti L, Koch C, Niebur E 1998 IEEE Trans. Pattern Anal. Mach. Intell. 20 1254
[26]	Hou X D, Zhang L Q 2007 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Minneapolis, USA, June 17–22, 2007 p1

[1]	王建国, 杨松林, 叶永红. 样品表面银膜的粗糙度对钛酸钡微球成像性能的影响. , 2018, 67(21): 214209. doi: 10.7498/aps.67.20180823
[2]	李夏至, 邹德滨, 周泓宇, 张世杰, 赵娜, 余德尧, 卓红斌. 等离子体光栅靶的表面粗糙度对高次谐波产生的影响. , 2017, 66(24): 244209. doi: 10.7498/aps.66.244209
[3]	宋延松, 杨建峰, 李福, 马小龙, 王红. 基于杂散光抑制要求的光学表面粗糙度控制方法研究. , 2017, 66(19): 194201. doi: 10.7498/aps.66.194201
[4]	张永建, 叶芳霞, 戴君, 何斌锋, 臧渡洋. 纳米粗糙度对胶体液滴蒸发图案的影响机制. , 2017, 66(6): 066101. doi: 10.7498/aps.66.066101
[5]	方志明, 崔荣一, 金璟璇. 基于生物视觉特征和视觉心理学的视频显著性检测算法. , 2017, 66(10): 109501. doi: 10.7498/aps.66.109501
[6]	宋永锋, 李雄兵, 史亦韦, 倪培君. 表面粗糙度对固体内部超声背散射的影响. , 2016, 65(21): 214301. doi: 10.7498/aps.65.214301
[7]	陈苏婷, 胡海锋, 张闯. 基于激光散斑成像的零件表面粗糙度建模. , 2015, 64(23): 234203. doi: 10.7498/aps.64.234203
[8]	曹洪, 黄勇, 陈素芬, 张占文, 韦建军. 脉冲敲击技术对PI微球表面粗糙度的影响. , 2013, 62(19): 196801. doi: 10.7498/aps.62.196801
[9]	任卓明, 邵凤, 刘建国, 郭强, 汪秉宏. 基于度与集聚系数的网络节点重要性度量方法研究. , 2013, 62(12): 128901. doi: 10.7498/aps.62.128901
[10]	王萍, 潘跃. 基于显著性特征的大冰雹识别模型. , 2013, 62(6): 069202. doi: 10.7498/aps.62.069202
[11]	许元男, 赵远, 刘丽萍, 张宇, 孙秀冬. 基于伪Wigner-Ville分布和Rényi熵的显著图目标检测. , 2010, 59(2): 980-988. doi: 10.7498/aps.59.980
[12]	谌雄文, 谌宝菊, 施振刚, 宋克慧. 嵌入T型耦合双量子点介观A-B环系统的显著Fano 效应. , 2009, 58(4): 2720-2725. doi: 10.7498/aps.58.2720
[13]	张程宾, 陈永平, 施明恒, 付盼盼, 吴嘉峰. 表面粗糙度的分形特征及其对微通道内层流流动的影响. , 2009, 58(10): 7050-7056. doi: 10.7498/aps.58.7050
[14]	何四华, 杨绍清, 石爱国, 李天伟. 基于图像区域Lyapunov指数的海面舰船目标检测. , 2009, 58(2): 794-801. doi: 10.7498/aps.58.794
[15]	安振连, 赵敏, 汤敏敏, 杨强, 夏钟福. 氟气处理孔洞聚丙烯膜显著改善的电荷存储特性. , 2008, 57(9): 5859-5862. doi: 10.7498/aps.57.5859
[16]	李志华, 王文新, 刘林生, 蒋中伟, 高汉超, 周均铭. As保护下的生长中断时间对AlSb/InAs超晶格界面粗糙度的影响. , 2007, 56(3): 1785-1789. doi: 10.7498/aps.56.1785
[17]	张闯, 柏连发, 张毅. 基于灰度空间相关性的双谱微光图像融合方法. , 2007, 56(6): 3227-3233. doi: 10.7498/aps.56.3227
[18]	侯海虹, 孙喜莲, 申雁鸣, 邵建达, 范正修, 易葵. 电子束蒸发氧化锆薄膜的粗糙度和光散射特性. , 2006, 55(6): 3124-3127. doi: 10.7498/aps.55.3124
[19]	程路, 萧季驹. 非相干光源用于“核-环比”法测量表面粗糙度. , 1990, 39(1): 10-17. doi: 10.7498/aps.39.10
[20]	黄炳忠, 余玉贞, 洪国光. Si-SiO2界面的粗糙度. , 1987, 36(7): 829-837. doi: 10.7498/aps.36.829

计量

文章访问数: 6964
PDF下载量: 802
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

搜索

留言板