面向场景监控的序列图像清晰化算法研究
|
摘要
近年来,场景监控在各个领域得到了广泛的应用,但由于天气、光照、摄像机运动、信号传输、成像系统自身限制等原因,给图像的清晰程度带来了影响。图像质量不可避免的降低,轻者表现为图像不干净,难于看清细节；重者表现为图像模糊不清,连概貌也看不出来,大大降低了监控系统的可用性。因此,序列图像的清晰化处理算法研究对场景监控系统具有重要意义。
在查阅大量资料和进行多种方法实验的基础上,本文针对序列图像相邻帧中物体重复出现且变化不大及信息可相互弥补的特点,将图像配准方法与超分辨率重建算法相结合,提出了一种针对全局运动的序列图像清晰化处理新方法。通过对序列图像进行处理,可生成较原图像更为清晰的高分辨率图像。
本文从视频监控系统影响图像质量的主要因素入手,分析了成像模型,对序列图像超分辨率重建涉及到的问题进行了深入探讨。针对全局运动的序列图像,引入互信息度作为图像配准的相似测度,结合Powell优化算法的一般思想,讨论了基于两者的图像配准方法。在此基础上,紧接着分析研究了POCS(凸集投影)超分辨率重建算法,并针对凸集投影算法收敛慢、去噪能力弱等特点,在估计初始值方面作了改进,采用中值综合的融合方法综合图像序列相关信息来重新估计初始估计帧,从而加强了图像清晰化和去噪效果。最后运用Matlab编写实验软件平台,进行算法验证,提高了研究效率,并分别对标准图像和真实监控图像进行实验,通过实验结果分析,证明了本文算法可行有效。
In recent years, video scene monitoring system has been widely used in various fields. However, due to some reasons such as weather, lighting, camera movement, signal transmission and restrictions of imaging system itself, the clarity of the images has been decreased, and the quality of images has been inevitably reduced seriously. Images may be not clean and difficult to be seen in the details; More seriously, images are not clear, and they even can't be recognized in general. All these defects decrease the functions of video scene monitoring system greatly. So research of restoration algorithms from sequence images is important for video scene monitoring system.
Based on a lot of information and a variety of experimental methods, this thesis has combined the image registration method and the super-resolution reconstruction algorithm in accordance with the characteristics that the objects in adjacent frames turned up repeatedly, changed little and made up for each other in the sequential images, and provided a new method to clear the image sequence against the global campaign. Through processing the sequence images that are not clean and have noise, it can generate a better high-resolution image than the original images.
This thesis has analyzed the imaging model and the issues that refer to the reconstruction of the image sequence deeply, starting from the main factors that video scene monitoring system affect the image quality in. Against the image sequence of the global campaign, it has introducted the mutual information as the measure of the similar degree of the image registration, combined with the general ideas of Powell optimization, and discussed the registration method based on the two ones. On this basis, it has analysed the super-resolution reconstruction algorithms of the POCS (convex projection), improved the estimation of the initial value against the characteristics that the convex projection algorithm has the slow convergence and the weak capacity to eliminate noise, and adopted an approach of median integration to estimate the initial estimate frame that has related information of the image sequence, and then enhanced the image clarity and the effects of eliminating noise. Finally, the software platform that is programmed by Matlab to verify the algorithm has improved the efficiency of research and tested the standard images and the real monitor images respectively. Through the analysis of the results, the method is proved feasible and effective.
在查阅大量资料和进行多种方法实验的基础上,本文针对序列图像相邻帧中物体重复出现且变化不大及信息可相互弥补的特点,将图像配准方法与超分辨率重建算法相结合,提出了一种针对全局运动的序列图像清晰化处理新方法。通过对序列图像进行处理,可生成较原图像更为清晰的高分辨率图像。
本文从视频监控系统影响图像质量的主要因素入手,分析了成像模型,对序列图像超分辨率重建涉及到的问题进行了深入探讨。针对全局运动的序列图像,引入互信息度作为图像配准的相似测度,结合Powell优化算法的一般思想,讨论了基于两者的图像配准方法。在此基础上,紧接着分析研究了POCS(凸集投影)超分辨率重建算法,并针对凸集投影算法收敛慢、去噪能力弱等特点,在估计初始值方面作了改进,采用中值综合的融合方法综合图像序列相关信息来重新估计初始估计帧,从而加强了图像清晰化和去噪效果。最后运用Matlab编写实验软件平台,进行算法验证,提高了研究效率,并分别对标准图像和真实监控图像进行实验,通过实验结果分析,证明了本文算法可行有效。
In recent years, video scene monitoring system has been widely used in various fields. However, due to some reasons such as weather, lighting, camera movement, signal transmission and restrictions of imaging system itself, the clarity of the images has been decreased, and the quality of images has been inevitably reduced seriously. Images may be not clean and difficult to be seen in the details; More seriously, images are not clear, and they even can't be recognized in general. All these defects decrease the functions of video scene monitoring system greatly. So research of restoration algorithms from sequence images is important for video scene monitoring system.
Based on a lot of information and a variety of experimental methods, this thesis has combined the image registration method and the super-resolution reconstruction algorithm in accordance with the characteristics that the objects in adjacent frames turned up repeatedly, changed little and made up for each other in the sequential images, and provided a new method to clear the image sequence against the global campaign. Through processing the sequence images that are not clean and have noise, it can generate a better high-resolution image than the original images.
This thesis has analyzed the imaging model and the issues that refer to the reconstruction of the image sequence deeply, starting from the main factors that video scene monitoring system affect the image quality in. Against the image sequence of the global campaign, it has introducted the mutual information as the measure of the similar degree of the image registration, combined with the general ideas of Powell optimization, and discussed the registration method based on the two ones. On this basis, it has analysed the super-resolution reconstruction algorithms of the POCS (convex projection), improved the estimation of the initial value against the characteristics that the convex projection algorithm has the slow convergence and the weak capacity to eliminate noise, and adopted an approach of median integration to estimate the initial estimate frame that has related information of the image sequence, and then enhanced the image clarity and the effects of eliminating noise. Finally, the software platform that is programmed by Matlab to verify the algorithm has improved the efficiency of research and tested the standard images and the real monitor images respectively. Through the analysis of the results, the method is proved feasible and effective.
引文
1.李金伴,王善斌.电视监控系统及其应用[M],北京：化学工业出版社,2008,1-13.
2.黄爱民,安向京,骆力.数字图像处理与分析基础[M],北京：中国水利水电出版社,2005,1-30.
3.冈萨雷斯.数字图像处理(MATLAB版)[M],北京：电子工业出版社,2005,1-49.
4.黄世伟.视频监控系统原理及维护[M],北京：电子工业出版社,2007,1-13.
5.朗锐.数字图像处理学[M],北京：北京希望电子出版社,2003,232-292.
6.许录平.数字图像处理[M],北京：科学出版社,2007,105-136.
7.乔建苹,刘琚.基于支撑向量机的盲超分辨率图像复原算法[J],电子学报,2007,10,1927-1933.
8.付炜,刘志文.高斯型点扩展函数估计及图像复原[J],计算机工程与应用,2007,43(36),80-85.
9.高梅.运动模糊的点扩展函数及图像恢复研究[D],太原：华北工学院,2004.
10.张汗灵.Matlab在图像处理中的应用[M],北京：清华大学出版社,2008,83-185.
11.王爱玲,叶明生,邓秋香.MATLAB R2007图像处理技术与应用[M],北京：电子工业出版社,2008,25-163.
12.罗述谦,李响.基于最大互信息的多模医学图像配准[J],中国图像图形学报,2005,5(7)：551-558.
13.杨虎,马斌荣.基于最大互信息的人脑MR-PET图像配准方法[J],北京生物医学工程,2001,20(4)：246-251.
14. A.Bardera, M.Feixax, I.Boada. Normalized Similarity Measures for Medical Image Registration[D], Spain:Universitat de Girona,2007.
15.张二虎,卞正中.基于最大熵和互信息最大化的特征点配准算法[J],2004,41(7)：1194-1199.
16. P.A.Viola. Alignment by Maximization of Mutual Information[D], USA: Massachusetts(MA),1995.
17.王丽宽.图像配准技术在医学图像处理中的应用[D],北京：北京交通大学,2004.
18.胡顺波,刘常春.基于互信息与边缘互距离的医学图像配准[J],2008,44(6)：36-38.
19.吴成茂.模糊互信息及其在图像分割中的应用[J],计算机工程,2008,34, 218-222.
20.廖勇军,杨丹,张小洪.基于最大特征点对互信息的图像配准[J],2008,25(3)：941-944.
21.Tsao J. Interpolation artifacts in multimodality image registration based on maximization of mutual information[J], IEEE Transactions on Medical Imaging, 2003,22(7):854-864.
22. Shingo Iwano, Tatsuya Nakamura, Yuko Kamioka, et al. Computer-aided Diagnosis: A shape classification of pulmonary nodules imaged by High-resolution CT[J], Computerized Medical Imaging and Graphics,2006,29(565-570):1-4.
23.郑亚琴.放射治疗中射野图像与参考图像的互信息配准[D],天津：天津医科大学,2006.
24.栾红霞.基于定量定性互信息的医学图像配准[D],上海：上海交通大学,2007.
25. Silva L, Bellon O R P, Boyer K L. Precision range image registration using a robust surface interpenetration measure and enhanced genetic algorithms[J], IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(5):762-776.
26. C.Studholme. Measures of 3D Medical Image Alignment[D], London:University of London,1997.
27.张鄂.机械与工程与工程优化设计[M],北京：科学出版社,2008,48-52.
28.赵文蕾.基于互有位移序列图像的超分辨率复原技术研究[D],秦皇岛：燕山大学,2006.
29.周智浩.基于序列图像的二维超分辨率重构技术研究[D],杭州：浙江大学,2006.
30. Shechtman E, Caspi Y, Irani M. Space-time super-resolution[J], IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(4):531-545.
31.袁建华.超分辨率重建中若干问题的研究[D],北京：中国科学院研究生院,2006.
32. Farsiu S, Robinson D, Elad M, et al. Advances and challenges in super-resolution[J], International Journal of Imaging Systems and Technology,2004,14(2):47-57.
33.李淑静.超分辨率图像重建算法的研究与实现[D],青岛：青岛大学,2007.
34.邵肖伟.数字图像修复技术研究[D],北京：中国科学技术大学,2006.
35. Michael K.Ng, N.K.Bose. Analysis of Displacement Errors in High-Resolution Image Reconstruction With Multisensors[J], IEEE Transactions on Circuits and Systems,2002,49(6):806-813.
36.倚海伦.基于序列图像的超分辨率重建算法研究[D],西安：西北工业大学，2007.
37. R.Chan, S.D.Riemenschneider, L.shen, et al. Tight frame:an efficient way from high-resolution image reconstruction[J], Applied and Computational Harmonic Analysis,2004,17:91-115.
38. Sung Cheol Park, Min Kyu Park, Moon Gi Kang. Super-Resolution Image
Reconstruction:A Technical Overview[J], IEEE Signal Processing Magazine,2003, 21,1053-5888.
39.张艳.空间域超分辨率图像重建技术研究[D],郑州：解放军信息工程大学,2007.
40.孙雷.视频图像的超分辨率复原技术研究[D],郑州：解放军信息工程大学,2007.
41.罗俊.运动模糊图像成像与超分辨率重构研究[D],武汉：华中科技大学,2006.
42.韩玉兵.图像及视频序列的超分辨率重建[D],南京：东南大学,2005.
43.禹晶.序列图像超分辨率重建方法的研究[D],北京：北京工业大学,2007.
44.许录平,姚静.一种图像快速超分辨率复原方法[J],2007,34,382-385.
45.覃征,鲍复民,李爱国等.数字图像融合[M],西安：西安交通大学出版社,2004,7-25.
2.黄爱民,安向京,骆力.数字图像处理与分析基础[M],北京：中国水利水电出版社,2005,1-30.
3.冈萨雷斯.数字图像处理(MATLAB版)[M],北京：电子工业出版社,2005,1-49.
4.黄世伟.视频监控系统原理及维护[M],北京：电子工业出版社,2007,1-13.
5.朗锐.数字图像处理学[M],北京：北京希望电子出版社,2003,232-292.
6.许录平.数字图像处理[M],北京：科学出版社,2007,105-136.
7.乔建苹,刘琚.基于支撑向量机的盲超分辨率图像复原算法[J],电子学报,2007,10,1927-1933.
8.付炜,刘志文.高斯型点扩展函数估计及图像复原[J],计算机工程与应用,2007,43(36),80-85.
9.高梅.运动模糊的点扩展函数及图像恢复研究[D],太原：华北工学院,2004.
10.张汗灵.Matlab在图像处理中的应用[M],北京：清华大学出版社,2008,83-185.
11.王爱玲,叶明生,邓秋香.MATLAB R2007图像处理技术与应用[M],北京：电子工业出版社,2008,25-163.
12.罗述谦,李响.基于最大互信息的多模医学图像配准[J],中国图像图形学报,2005,5(7)：551-558.
13.杨虎,马斌荣.基于最大互信息的人脑MR-PET图像配准方法[J],北京生物医学工程,2001,20(4)：246-251.
14. A.Bardera, M.Feixax, I.Boada. Normalized Similarity Measures for Medical Image Registration[D], Spain:Universitat de Girona,2007.
15.张二虎,卞正中.基于最大熵和互信息最大化的特征点配准算法[J],2004,41(7)：1194-1199.
16. P.A.Viola. Alignment by Maximization of Mutual Information[D], USA: Massachusetts(MA),1995.
17.王丽宽.图像配准技术在医学图像处理中的应用[D],北京：北京交通大学,2004.
18.胡顺波,刘常春.基于互信息与边缘互距离的医学图像配准[J],2008,44(6)：36-38.
19.吴成茂.模糊互信息及其在图像分割中的应用[J],计算机工程,2008,34, 218-222.
20.廖勇军,杨丹,张小洪.基于最大特征点对互信息的图像配准[J],2008,25(3)：941-944.
21.Tsao J. Interpolation artifacts in multimodality image registration based on maximization of mutual information[J], IEEE Transactions on Medical Imaging, 2003,22(7):854-864.
22. Shingo Iwano, Tatsuya Nakamura, Yuko Kamioka, et al. Computer-aided Diagnosis: A shape classification of pulmonary nodules imaged by High-resolution CT[J], Computerized Medical Imaging and Graphics,2006,29(565-570):1-4.
23.郑亚琴.放射治疗中射野图像与参考图像的互信息配准[D],天津：天津医科大学,2006.
24.栾红霞.基于定量定性互信息的医学图像配准[D],上海：上海交通大学,2007.
25. Silva L, Bellon O R P, Boyer K L. Precision range image registration using a robust surface interpenetration measure and enhanced genetic algorithms[J], IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(5):762-776.
26. C.Studholme. Measures of 3D Medical Image Alignment[D], London:University of London,1997.
27.张鄂.机械与工程与工程优化设计[M],北京：科学出版社,2008,48-52.
28.赵文蕾.基于互有位移序列图像的超分辨率复原技术研究[D],秦皇岛：燕山大学,2006.
29.周智浩.基于序列图像的二维超分辨率重构技术研究[D],杭州：浙江大学,2006.
30. Shechtman E, Caspi Y, Irani M. Space-time super-resolution[J], IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(4):531-545.
31.袁建华.超分辨率重建中若干问题的研究[D],北京：中国科学院研究生院,2006.
32. Farsiu S, Robinson D, Elad M, et al. Advances and challenges in super-resolution[J], International Journal of Imaging Systems and Technology,2004,14(2):47-57.
33.李淑静.超分辨率图像重建算法的研究与实现[D],青岛：青岛大学,2007.
34.邵肖伟.数字图像修复技术研究[D],北京：中国科学技术大学,2006.
35. Michael K.Ng, N.K.Bose. Analysis of Displacement Errors in High-Resolution Image Reconstruction With Multisensors[J], IEEE Transactions on Circuits and Systems,2002,49(6):806-813.
36.倚海伦.基于序列图像的超分辨率重建算法研究[D],西安：西北工业大学，2007.
37. R.Chan, S.D.Riemenschneider, L.shen, et al. Tight frame:an efficient way from high-resolution image reconstruction[J], Applied and Computational Harmonic Analysis,2004,17:91-115.
38. Sung Cheol Park, Min Kyu Park, Moon Gi Kang. Super-Resolution Image
Reconstruction:A Technical Overview[J], IEEE Signal Processing Magazine,2003, 21,1053-5888.
39.张艳.空间域超分辨率图像重建技术研究[D],郑州：解放军信息工程大学,2007.
40.孙雷.视频图像的超分辨率复原技术研究[D],郑州：解放军信息工程大学,2007.
41.罗俊.运动模糊图像成像与超分辨率重构研究[D],武汉：华中科技大学,2006.
42.韩玉兵.图像及视频序列的超分辨率重建[D],南京：东南大学,2005.
43.禹晶.序列图像超分辨率重建方法的研究[D],北京：北京工业大学,2007.
44.许录平,姚静.一种图像快速超分辨率复原方法[J],2007,34,382-385.
45.覃征,鲍复民,李爱国等.数字图像融合[M],西安：西安交通大学出版社,2004,7-25.