基于能量估计的局部运动模糊检测

doi:10.11772/j.issn.1001-9081.2016.10.2859

计算机应用 ›› 2016, Vol. 36 ›› Issue (10): 2859-2862.DOI: 10.11772/j.issn.1001-9081.2016.10.2859

基于能量估计的局部运动模糊检测

赵森祥^1,2, 李少波^1,2, 陈斌^1,2, 赵雪专^1,2

1. 中国科学院成都计算机应用研究所, 成都 610041;
2. 中国科学院大学, 北京 100049

收稿日期:2016-03-16 修回日期:2016-06-17 发布日期:2016-10-10
通讯作者: 赵森祥,E-mail:mynameiziji@163.com
作者简介:赵森祥(1987—),男,四川绵阳人,硕士研究生,主要研究方向:图像处理、机器视觉;李少波(1973—),男,湖南岳阳人,教授,博士生导师,博士,主要研究方向:制造信息系统、计算智能;陈斌(1970—),男,四川广汉人,研究员,博士生导师,博士,主要研究方向:图像分析、机器视觉;赵雪专(1986—),男,河南濮阳人,博士研究生,主要研究方向:图像分析、机器视觉。
基金资助:
四川省科技成果转换项目（2014CC0043）。

Local motion blur detection based on energy estimation

ZHAO Senxiang^1,2, LI Shaobo^1,2, CHEN Bin^1,2, ZHAO Xuezhuan^1,2

1. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
2. University of Chinese Academy Sciences, Beijing 100049, China

Received:2016-03-16 Revised:2016-06-17 Published:2016-10-10
Supported by:
BackgroundThis work is partially supported by the Science and Technology Achievement Transformation Foundation of Sichuan Province (2014CC0043).

摘要/Abstract

摘要： 为了解决日常拍摄的图像或视频中普遍存在局部运动模糊导致信息丢失的问题，提出一种基于能量估计的局部运动模糊检测算法。该算法首先计算图像的Harris特征点，根据每个区域内的特征点分布筛选出备选区域；然后根据近单色区域梯度分布平滑的特点，通过计算备选区域的梯度分布并参照平均幅值阈值过滤掉大部分容易被误判的部分；最后根据运动模糊对图像能量衰减的特征对备选区域进行模糊方向估计，并计算模糊方向和与其垂直方向的能量，根据两个方向上能量的比值进一步去掉单色区域和散焦模糊区域。在图像库上的实验结果表明，所提算法能较好从存在近单色区域和散焦区域干扰的图像中检测出运动模糊区域，有效提高局部运动模糊检测的鲁棒性以及适应性。

关键词: 运动模糊, 散焦模糊, 去模糊, 点扩散函数, 图像梯度

Abstract: In order to solve the problem of information loss caused by local motion blur in daily captured images or videos, a local motion detection algorithm based on region energy estimation was proposed. Firstly, the Harris feature points of the image were calculated, and alternative areas were screened out according to the distribution of feature points of each area. Secondly, according to the characteristic of smooth gradient distribution in monochromatic areas, the gradient distribution of the alternative areas was calculated and the average amplitude threshold was used to filter out most of areas which can be easily misjudged. At last, the blur direction of the alternative areas was estimated according to the energy degeneration feature of motion blur images, and the energy of the blur direction and its perpendicular direction were calculated, thus the monochrome region and defocus blur areas were further removed according to the energy ratio in both above directions. Experimental results on image data sets show that the proposed method can detect the motion blur areas from images with monochromatic areas and defocus blur areas, and effectively improve the robustness and adaptability of local motion blur detection.

Key words: motion blur, defocus blur, deblurring, point spread function, image gradient

中图分类号:

TP391.4

赵森祥, 李少波, 陈斌, 赵雪专. 基于能量估计的局部运动模糊检测[J]. 计算机应用, 2016, 36(10): 2859-2862.

ZHAO Senxiang, LI Shaobo, CHEN Bin, ZHAO Xuezhuan. Local motion blur detection based on energy estimation[J]. Journal of Computer Applications, 2016, 36(10): 2859-2862.

参考文献

[1] DAI S Y, YANG M, WU Y, et al. Tracking motion-blurred targets in video[C]//Proceedings of the 2006 IEEE International Conference on Image Processing. Piscataway, NJ: IEEE, 2010: 2389-2392.
[2] LIN H Y, LI K J. Motion blur removal and its application to vehicle speed detection[C]//Proceedings of the 2004 IEEE International Conference on Image Processing. Piscataway, NJ: IEEE, 2004, 5: 3407-3410.
[3] FAVARO P, SOATTO S. A variational approach to scene reconstruction and image segmentation from motion-blur cues[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2004, 1: 631-6371.
[4] DERPANIS K G, LECCE M, DANIILIDIS K, WILDES R P. Dynamic scene understanding: the role of orientation features in space and time in scene classification[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2012: 1306-1313.
[5] LIU R T, LI Z R, JIA J Y. Image partial blur detection and classification[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2008:1-8.
[6] LIN H T, TAI Y W, BROWN M S. Motion regularization for matting motion blurred objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11):2329-2336.
[7] LEVIN A. Blind motion deblurring using image statistics[M]. Cambridge: MIT Press, 2006:841-848.
[8] CHAKRABARTI A, ZICKLER T, FREEMAN W T. Analyzing spatially-varying blur[C]//Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2010:2512-2519.
[9] DAI S Y, WU Y. Removing partial blur in a single image[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2009:2544-2551.
[10] ZHENG S C, XU L, JIA J Y. Forward motion deblurring[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ: IEEE, 2013:1465-1472.
[11] YARON O, SIDI M. A combined corner and edge detector[C]//Proceedings of the Fourth Alvey Vision Conference, Piscataway, NJ: IEEE, 1988:147-151.
[12] 王宇庆. 局部方差在图像质量评价中的应用[J]. 中国光学, 2011, 4(5):531-536.(WANG Y Q. Application of local variance in image quality assessment[J]. Chinese Optics and Applied Optics Abstracts, 2011, 4(5):531-536.)
[13] CHO S, LEE S. Fast motion deblurring[J]. ACM Transactions on Graphics, 2009, 28(5):89-97.
[14] 廖永忠, 蔡自兴, 何湘华. 基于Radon变换的运动模糊图像恢复[J]. 计算机应用, 2014, 34(7):2005-2009.(LIAO Y Z, CAI Z X, HE X H. Motion blurred image blind restoration based Radon transform[J]. Journal of Computer Applications, 2014, 34(7):2005-2009.)
[15] 廖宇, 郭黎. 一种运动模糊图像的模糊参数估计方法[J]. 计算机工程与科学, 2014,36(10):2002-2008.(LIAO Y, GUO L. A novel blur parameter estimation method for blurred images[J]. Computer Engineering & Science, 2014, 36(10):2002-2008.)
[16] CHEN X G, YANG J, WU Q, et al. Motion blur detection based on lowest directional high-frequency energy[C]//Proceedings of the 2010 IEEE International Conference on Image Processing. Piscataway, NJ: IEEE, 2010:2533-2536.

基于能量估计的局部运动模糊检测

Local motion blur detection based on energy estimation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李福海, 蒋慕蓉, 杨磊, 谌俊毅. 基于生成对抗网络的梯度引导太阳斑点图像去模糊方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3345-3352.
[2]	陈赛健, 朱远平. 基于生成对抗网络的文本图像联合超分辨率与去模糊方法[J]. 计算机应用, 2020, 40(3): 859-864.
[3]	林传健, 邓炜, 童同, 高钦泉. 基于深度体素流的模糊视频插帧方法[J]. 计算机应用, 2020, 40(3): 819-824.
[4]	贾瑞明, 邱桢芝, 崔家礼, 王一丁. 盲去模糊的多尺度编解码深度卷积网络[J]. 计算机应用, 2019, 39(9): 2552-2557.
[5]	葛成伟程浩刘国庆. 噪声条件下的运动模糊参数同步辨识的新算法[J]. 计算机应用, 2012, 32(12): 3381-3384.
[6]	李宇成余海桃王目树. 车辆运动模糊图像分块恢复的新方法[J]. 计算机应用, 2012, 32(04): 1108-1112.
[7]	郭红伟. 基于频谱边缘检测的运动模糊方向精确估计[J]. 计算机应用, 2012, 32(03): 770-772.
[8]	梁敏朱虹欧阳光振刘薇. 模糊图像点扩散函数的亚像素精度离散化方法[J]. 计算机应用, 2012, 32(02): 496-498.
[9]	范海菊张爱丽冯乃勤. 基于局部标准差和方向微分的模糊方向识别[J]. 计算机应用, 2011, 31(09): 2506-2508.
[10]	王蕾冯晓毅万小娜. 基于改进卡尔曼滤波的盲图像恢复[J]. 计算机应用, 2011, 31(03): 711-714.
[11]	刘瑞华黎芳苏理云. 基于双侧滤波的多幅灰色图像修复[J]. 计算机应用, 2010, 30(4): 902-904.
[12]	吴振宇. 运动模糊参数的空域鉴别方法[J]. 计算机应用, 2009, 29(12): 3378-3380.
[13]	刘瑞华鲍政. 基于Gibbs分布的盲图像修复[J]. 计算机应用, 2008, 28(9): 2281-2284.
[14]	陈波. 一种新的运动模糊图像恢复方法[J]. 计算机应用, 2008, 28(8): 2024-2026.
[15]	黄琦张国基唐向京. 基于霍夫变换的图像运动模糊角度识别法的改进[J]. 计算机应用, 2008, 28(1): 211-213.