运动图像序列中的斑点检测算法

doi:10.3969/j.issn.1000-3428.2013.08.049

计算机工程 ›› 2013, Vol. 39 ›› Issue (8): 227-230.doi: 10.3969/j.issn.1000-3428.2013.08.049

运动图像序列中的斑点检测算法

张然然^1a，庞海波²，张怡^1b

(1. 天津大学 a. 计算机科学与技术学院；b. 软件学院，天津 300072；2. 上海大学计算机工程与科学学院，上海 200072)

收稿日期:2012-02-29 出版日期:2013-08-15 发布日期:2013-08-13
作者简介:张然然(1980－)，女，博士研究生，主研方向：图像与视频处理；庞海波、张怡，博士研究生
基金项目:
上海市教委重点学科建设基金资助项目“可视媒体修复与检索关键技术研究”（J050103）

Blotch Detection Algorithm in Motion Image Sequence

ZHANG Ran-ran ^1a, PANG Hai-bo ², ZHANG Yi ^1b

(1a. School of Computer Science and Technology; 1b. School of Software, Tianjin University, Tianjin 300072, China; 2. School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China)

Received:2012-02-29 Online:2013-08-15 Published:2013-08-13

摘要/Abstract

摘要： 传统运动图像斑点检测算法通过降低阈值来提高正确检测率，但较高的错误检测率直接影响其后的斑点修复结果。为最大化正确检测率与错误检测率之间的比值，在SROD检测算法的基础上提出改进的斑点检测算法。引入自适应多阈值的概念，对同一帧图像中的不同斑点进行自动收敛，找到合适的阈值，采用纹理匹配方法减小斑点区域中由于运动矢量估计导致的偏差。对实际破损以及人工添加斑点的图像序列进行性能评估，结果表明，改进算法能在得到较高正确检测率的同时降低错误检测率。

关键词: 斑点检测, 自适应多阈值, 纹理匹配, 迭代算法, 视频修复, 运动矢量估计

Abstract: Traditional blotch detection algorithms obtain higher correct detection rates by reducing the value of threshold. However, the corresponding higher number of false alarms affects the following correction results directly. To maximize the ratio between correct detections and false alarms, this paper proposes an improved blotch detector based on simplified rank-ordered difference. The improved detector can achieve the most appropriate threshold to the different blotch in a certain frame by introducing dual-steps adaptive multi-threshold. It uses employment of texture matching to avoid the possible deviation caused by motion vector estimation in the regions with blotches. Performance evaluation is taken to the image sequences with both real blotches and artificially corrupted ones separately. Experimental results indicate higher correct detection rates and fewer false alarms simultaneously.

Key words: blotch detection, adaptive multi-threshold, texture matching, iterative algorithm, video restoration, motion vector estimation

中图分类号:

TP18

张然然, 庞海波, 张怡. 运动图像序列中的斑点检测算法[J]. 计算机工程, 2013, 39(8): 227-230.

ZHANG Ran-Ran, LONG Hai-Bei, ZHANG Yi. Blotch Detection Algorithm in Motion Image Sequence[J]. Computer Engineering, 2013, 39(8): 227-230.

参考文献

[1] 林成春. 视频修复问题研究[D]. 杭州: 浙江大学, 2008.
[2] Bovik A. 图像与视频处理手册(影印版)[M]. 2版. 北京: 电子工业出版社, 2006.
[3] 谌安军, 滕升华, 邹谋炎. 一种用于图像序列斑点去除的运动估计修正方法[J]. 中国科学院研究生院学报, 2006, 23(3): 396-402.
[4] Storey R. Electronic Detection and Concealment of Film Dirt: UK, 2139039[P]. 1984-05-04.
[5] Storey R. Electronic Detection and Concealment of Film
Dirt[J]. SMPTE Journal, 1985, 94(5): 642-647.
[6] Kokaram A C, Rayner P J W. A System for the Removal of Impulsive Noise in Image Sequences[C]//Proceedings of International Conference on SPIE Visual Communications in Image Processing. Boston, USA: [s. n.], 1992: 322-331.
[7] Kokaram A C. Motion Picture Restoration: Digital Algorithms for Artifact Suppression in Degraded Motion Picture Film and Video[M]. [S. l.]: Springer-Verlag, 1998.
[8] Geman S, Geman D. Stochastic Relaxation, Gibbs Distribu- tion, and Beyesian Restoration of Images[J]. IEEE Trans- actions on Pattern Analysis Machine Intelligence, 1984, 6(6): 721-741.
[9] Kokaram A C, Morris R D, Fitzgerald W J, et al. Detection of Missing Data in Image Sequences[J]. IEEE Transactions on Image Processing, 1995, 4(11): 1496-1508.
[10] Bornard R. Probabilistic Approaches for the Digital Restora- tion of Television Archives[D]. Paris, France: Ecole Centrale Paris, 2002.
[11] Chong M N, Liu P, Goh W, et al. A New Spatio-temporal MRF Model for the Detection of Missing Data in Image Sequences[C]//Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Munich, Germany: [s. n.], 1997: 2977-2980.
[12] Nadenau M J, Mitra S K. Blotch and Scratch Detection in Image Sequences Based on Rank Ordered Differences[C]// Proceedings of the 5th International Workshop on Time- varying Image Processing and Moving Object Recognition. Florence, Italy: Elsevier, 1996: 1-7.
[13] van Roosmalen P M B. Restoration of Archived Film and Video[D]. Delft, Holland: Delft University of Technology, 1999.
编辑金胡考

[1]	冯刚,覃锡忠,贾振红,牛红梅,王哲辉. 认知无线电环境下无线能量通信网能效研究[J]. 计算机工程, 2019, 45(3): 142-147.
[2]	牛小宁,刘宏哲,袁家政,宣寒宇. 基于Inliers跟踪统计的RGB-D室内定位与地图构建[J]. 计算机工程, 2018, 44(9): 15-21,27.
[3]	刘欣,陈智斌,文有为. 基于交替迭代的均匀噪声消除算法[J]. 计算机工程, 2018, 44(7): 316-320.
[4]	翟永,李宁,王晓飞. 基于带宽利用率的指数函数调制路由算法[J]. 计算机工程, 2018, 44(6): 93-99,103.
[5]	楚万顺,张起贵. 基于全双工中继网络的功率分配优化策略[J]. 计算机工程, 2018, 44(1): 149-153.
[6]	陈宇,李洪宇,夏宗基. 基于修正隐式Landweber方法的ECT图像重建算法 [J]. 计算机工程, 2018, 44(1): 268-273.
[7]	赵小宝，张华平. 基于迭代算法的新词识别[J]. 计算机工程, 2014, 40(7): 154-158,164.
[8]	段世芳, 马社祥. 图像压缩感知的双收缩快速迭代算法[J]. 计算机工程, 2012, 38(19): 226-228,232.
[9]	王小俊, 刘旭敏, 关永. 基于改进Canny算子的图像边缘检测算法[J]. 计算机工程, 2012, 38(14): 196-198.
[10]	张青. 基于MD5的迭代散列算法[J]. 计算机工程, 2011, 37(18): 124-126.
[11]	谢涛, 李志华, 黄轶伦. H.264高清视频解码实时错误掩盖算法[J]. 计算机工程, 2011, 37(14): 9-11,17.
[12]	赵建蕾;王汇源;方颖. 偏暗或泛白背景的车牌图像二值化方法[J]. 计算机工程, 2008, 34(6): 210-211.
[13]	贾庆忠;刘永善;刘藻珍. 基于dsPIC30F控制器的高精度实时控制算法[J]. 计算机工程, 2007, 33(16): 223-225,.
[14]	田新梅;吴秀清;刘莉. 大样本情况下的一种新的SVM迭代算法[J]. 计算机工程, 2007, 33(08): 205-207.
[15]	应伟;王正欧;安金龙. 一种基于改进的支持向量机的多类文本分类方法[J]. 计算机工程, 2006, 32(16): 74-76.

运动图像序列中的斑点检测算法

Blotch Detection Algorithm in Motion Image Sequence

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10