小波图像融合算法及其在视频车辆检测系统中的应用研究
|
摘要
随着现代经济的高速发展,智能交通系统的研究倍受关注。论文工作研究的视频车辆检测系统是智能交通系统的重要组成部分,它通过对道路现场视频图像序列的分析与处理,实现道路交通信息的自动检测和车辆特征的自动识别。
论文工作结合科研项目的需求,较深入地研究了基于小波变换的图像去噪、配准和融合等多种算法;设计了道路现场视频车辆检测系统,该系统含有基于DSP的视频处理卡和工控机,其中的视频处理卡用于从视频图像中提取各种交通信息,工控机辅助用户查看和管理交通信息;针对小波图像融合运算量大和视频检测系统实时性要求之间的矛盾,论文探索性地把小波图像融合算法应用于视频车辆检测系统的设计,提高了检测系统的检测速度和正确率,基本上满足了视频信息检测的实时性要求。论文做了以下具有创新性的工作:
(1)提出了小波模极大值阈值去噪算法和改进的角点特征的图像配准算法。去噪算法利用信号和噪声的小波模极大值随尺度传播的特性不同,采用特定的阈值区分小波模极大值点是否由噪声产生,达到去噪的目的;改进的图像配准算法利用梯度模值从小波分解后高频分量中提取角点,用特征点灰度信息匹配法剔除误匹配的角点对后,确立仿射变换方程。实验表明,论文提出的去噪算法对噪声的依赖性小,在去噪的同时较好的保留了图像的细节信息;改进的图像配准算法比传统算法的配准精度更高,且具有较低的运算复杂度。
(2)提出了基于局部梯度平均模值的图像融合算法,利用小波变换后两幅图像低频系数的局部梯度平均模值确定低频融合系数;改进了传统的高频系数局部方差融合算法,利用局部方差定义高频系数的区域匹配度,通过区域匹配度确定高频融合系数。实验表明,论文提出的融合算法有效克服了传统融合算法对图像细节表现力不足和容易造成模糊的缺点,融合图像具有良好的视觉效果。
(3)提出了区域化图像融合设计方案,即在设计视频车辆检测系统时,针对小波图像融合算法计算量大、难以实时处理的难点,只对虚拟检测线覆盖的图像区域进行融合,而不处理与车辆检测无关的区域。与对整幅图像进行的融合相比,区域化图像融合只关注感兴趣区域的图像信息,具有运算量小等特点,适用于对实时性要求高的系统。实验表明,将区域化图像融合应用于视频交通信息检测系统,较好地解决了小波图像融合算法计算量大难以进行实时视频处理的难题。
With the development of world economics, intelligent transportation system has become more and more significant. As an important part of intelligent transportation system, vehicle detection system can detect and analyze traffic information automaticly through video processing.
This dissertation researches the wavelet domain image denoising, registration and fusion algorithm; it designs a vehicle detection system which contains DSP based video processing cards and industrial personal computers, video processing cards are used to extract traffic information from video and image, industrial personal computers help users view and manage traffic information. Focusing on the conflict between computational complexity of wavelet domain image fusion algorithm and real-time capability of vehicle detection system, this dissertation has exploringly applied the wavelet domain image fusion algorithm to vehicle detection system, which improves the detection accuracy and meets the time-constraints of system requirements. The innovations involved in the research are as follow:
(1) A wavelet modulus maximum threshold denoising method and an improved image registration algorithm based on corner feature are proposed. Based on the characteristics of random noise on different wavelet transform scales and the relationship between the noise Lipschitz and its wavelet modulus maximum, an image denoising algorithm is presented where the wavelet coefficients of noise signal are filtered by changeable threshold so as to reduce the noise; The improved image registration algorithm extracts the angular point by the gradient modulus, then it eliminates the mismatching points and gets all six raw parameters of the affine transformation equation. Some computer denoising and registration simulation results are given. The results show that the denoising method is effective both in removing the noise and in reserving the detail of image. It also shows that the improved image registration algorithm has high registration precision and low computational complexity.
(2) This dissertation presents an image fusion algorithm based on local mean gradient modulus. After wavelet decomposition, the fused wavelet coefficients are conbined through the proportion of local mean gradient modulus of coefficients in each low frequency subimage. The improved local deviation fusion rule is used to fuse high frequency subimages, it defines the match measure by the local deviation and finally decides the fusion method for high frequence subimage. Experimental results show that the presented fusion method achieves comparatively high visual effects and performances than the traditional image fusion algorithm.
(3) A design proposal of partition image fusion is brought forward in this dissertation. Focusing on the computational complexity of wavelet domain image fusion algorithm and its low real-time capability, this dissertation proposes a new method that fuses the given partition of images which is covered by the virtual detection line and ignores the the rest partition of this image. Comparing with fusion of the whole image, the partition image fusion has low computational complexity. Experimental results show that partition image fusion method applied in the vehicle detection system not only improves the image quality, but also meets the time-constraints of system requirements.
论文工作结合科研项目的需求,较深入地研究了基于小波变换的图像去噪、配准和融合等多种算法;设计了道路现场视频车辆检测系统,该系统含有基于DSP的视频处理卡和工控机,其中的视频处理卡用于从视频图像中提取各种交通信息,工控机辅助用户查看和管理交通信息;针对小波图像融合运算量大和视频检测系统实时性要求之间的矛盾,论文探索性地把小波图像融合算法应用于视频车辆检测系统的设计,提高了检测系统的检测速度和正确率,基本上满足了视频信息检测的实时性要求。论文做了以下具有创新性的工作:
(1)提出了小波模极大值阈值去噪算法和改进的角点特征的图像配准算法。去噪算法利用信号和噪声的小波模极大值随尺度传播的特性不同,采用特定的阈值区分小波模极大值点是否由噪声产生,达到去噪的目的;改进的图像配准算法利用梯度模值从小波分解后高频分量中提取角点,用特征点灰度信息匹配法剔除误匹配的角点对后,确立仿射变换方程。实验表明,论文提出的去噪算法对噪声的依赖性小,在去噪的同时较好的保留了图像的细节信息;改进的图像配准算法比传统算法的配准精度更高,且具有较低的运算复杂度。
(2)提出了基于局部梯度平均模值的图像融合算法,利用小波变换后两幅图像低频系数的局部梯度平均模值确定低频融合系数;改进了传统的高频系数局部方差融合算法,利用局部方差定义高频系数的区域匹配度,通过区域匹配度确定高频融合系数。实验表明,论文提出的融合算法有效克服了传统融合算法对图像细节表现力不足和容易造成模糊的缺点,融合图像具有良好的视觉效果。
(3)提出了区域化图像融合设计方案,即在设计视频车辆检测系统时,针对小波图像融合算法计算量大、难以实时处理的难点,只对虚拟检测线覆盖的图像区域进行融合,而不处理与车辆检测无关的区域。与对整幅图像进行的融合相比,区域化图像融合只关注感兴趣区域的图像信息,具有运算量小等特点,适用于对实时性要求高的系统。实验表明,将区域化图像融合应用于视频交通信息检测系统,较好地解决了小波图像融合算法计算量大难以进行实时视频处理的难题。
With the development of world economics, intelligent transportation system has become more and more significant. As an important part of intelligent transportation system, vehicle detection system can detect and analyze traffic information automaticly through video processing.
This dissertation researches the wavelet domain image denoising, registration and fusion algorithm; it designs a vehicle detection system which contains DSP based video processing cards and industrial personal computers, video processing cards are used to extract traffic information from video and image, industrial personal computers help users view and manage traffic information. Focusing on the conflict between computational complexity of wavelet domain image fusion algorithm and real-time capability of vehicle detection system, this dissertation has exploringly applied the wavelet domain image fusion algorithm to vehicle detection system, which improves the detection accuracy and meets the time-constraints of system requirements. The innovations involved in the research are as follow:
(1) A wavelet modulus maximum threshold denoising method and an improved image registration algorithm based on corner feature are proposed. Based on the characteristics of random noise on different wavelet transform scales and the relationship between the noise Lipschitz and its wavelet modulus maximum, an image denoising algorithm is presented where the wavelet coefficients of noise signal are filtered by changeable threshold so as to reduce the noise; The improved image registration algorithm extracts the angular point by the gradient modulus, then it eliminates the mismatching points and gets all six raw parameters of the affine transformation equation. Some computer denoising and registration simulation results are given. The results show that the denoising method is effective both in removing the noise and in reserving the detail of image. It also shows that the improved image registration algorithm has high registration precision and low computational complexity.
(2) This dissertation presents an image fusion algorithm based on local mean gradient modulus. After wavelet decomposition, the fused wavelet coefficients are conbined through the proportion of local mean gradient modulus of coefficients in each low frequency subimage. The improved local deviation fusion rule is used to fuse high frequency subimages, it defines the match measure by the local deviation and finally decides the fusion method for high frequence subimage. Experimental results show that the presented fusion method achieves comparatively high visual effects and performances than the traditional image fusion algorithm.
(3) A design proposal of partition image fusion is brought forward in this dissertation. Focusing on the computational complexity of wavelet domain image fusion algorithm and its low real-time capability, this dissertation proposes a new method that fuses the given partition of images which is covered by the virtual detection line and ignores the the rest partition of this image. Comparing with fusion of the whole image, the partition image fusion has low computational complexity. Experimental results show that partition image fusion method applied in the vehicle detection system not only improves the image quality, but also meets the time-constraints of system requirements.
引文
[1]朱东辉,智能交通系统的发展,山东交通学院学报,2002,10(4):9~14
[2]黄卫,陈里德,智能运输系统概论,北京:人民交通出版社,2001
[3]翁剑成,翟雅峤,赵晓娟,综合交通信息平台的交通基础数据库设计,中国交通信息产业,2009,135~137
[4]S. Takaba, M.Sakauchi, T. Kaneko. Measurement of Traffic Flow Using Real Time Processing of Moving Pictures. In: 32nd Conference on Vehicular Technology. 1982, 488~494
[5]W. Dichinson, R. C. Waterfall. Video Image Processing for Monitoring Road Traffic. In: IEEE International Conference on Road Traffic Data Collection. 1984, 105~109
[6]何友,王国宏,彭应宁等,多传感器信息融合及应用,北京:电子工业出版社,2007
[7]覃征,鲍复民,李爱国等,数字图像融合,西安:西安交通大学出版社, 2004
[8]Llinas J., Hall D. L. An Introduction to Multisensor Data Fusion. In: Proceedings of the IEEE. 1998, 85(1):6~23
[9]李伟,像素级图像融合方法及应用研究:[博士学位论文],广东:华南理工大学,2006
[10]田杰,复杂背景下图像融合算法及信息融合系统评估研究:[博士学位论文],北京:北京理工大学,2002
[11]Piella G. A General Framewok for Multiresolution Image Fusion: from Pixels to Regions. In: Information Fusion. 2003, 4(4):259~280
[12]俞斯乐,侯正信,冯启明等,电视原理(第五版),北京:国防工业出版社,2001
[13]Texas Instruments. In: TMS320DM642 Video/Imaging Fixed-Point Digital Signal Processor. 21~22
[14]Texas Instruments. In: TMS320DM642 Technical Overview. 13~14
[15]Texas Instruments. In: TMS320C6000 DSP Peripheral Component Interconnect (PCI) Reference Guide. 17~19
[16]李方慧,TMS320C6000系列DSPs原理与应用,北京:电子工业出版社,2003
[17]Texas Instruments. In: TMS320C6000 Code Composer Studio Tutorial, 1-3
[18]李房惠,王飞,何佩琨等,TMS320C6000系列DSPs原理与应用(第二版),北京:电子工业出版社,2003
[71]Y. Sheng, D. Roberge. Optical Wavelet Matched Filters for Shift-invariant Pattern Recognition. In: Optics Letters. 1993, 18(4):299~301
[72]J. Zhou, X. Fand, B. K. Ghosh. Image Segmentation Based on Multiresolution Filtering. In: IEEE International Conference on Image Processing. 1994, 3:483-487
[73]J. W. Hsieh, H. Y. Mark Liao, M. T. Ko. Wavelet-based Shape From Shading. In: Graphical Models and Image Processing. 1995, 57(4): 343~362
[74]Djamdji J. P., Bijaoui A., Maniere R. Geometrical Registration of Images: The Multiresolution Approach. In: Photogrammetric Engineering and Remote Sensing. 1993, 59(5):645~653
[75]Moigne J. L., Cromp R. F. The Use of Wavelets for Remote Sensing Image Registration and Fusion. In: Proceedings of SPIE, 1996, 535~544
[76]Corvi M., Nicchiotti G. Multiresolution Image Registration, In: Proceedings of International Conference on Image Processing. 1995, 3:224~227
[77]R. Deriche, G. Giraudon. A Computational Approach for Corner and Vertex Detection. In International Journal of Computer Vision. 1993, 2:101~124
[78]K. Rohr. Localization Properties of Direct Corner Detectors. In: Journal of Mathematical Imaging and Vision. 1994, 4:139~150
[79]L. Kitchen, A. Rosenfeld. Gray Level Corner Detection. In: Pattern Recognition Letters. 1982, 1:95~102
[80]O. A. Zuniga, R. Haralick. Corner detection using the facet model. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition. 1983, 30~37
[81]K. Brunnstrom, T. Lindeberg, J. O. Eklundh. Active Detection And Classification of Junctions. In: Proceedings of 2nd European Conference on Computer Vision. 1992, 701~709
[82]ZitováB., Flusser J. Image Registration Methods: A Survey. In: Image and Vision Computing. 2003, 21(11):997~1000
[83]冷晓艳,薛模根,韩裕生等,基于区域特征与灰度交叉相关的序列图像拼接,红外与激光工程, 2005, 34(5):602~605
[84]Krim H., Schick I. C. Minimax Description Length for Signal Denoising and Optimized Representation. In: IEEE Transactions on Information Theory. 1999, 45(3):898~908
[85]Liu Juan, Moulin P. Image Denoising Based on Scale-space Mixture Modeling of Wavelet Coefficients. In: Proceedings of IEEE International Conference on Image Processing. 1999:386~39
[86]邹前进,冯亮,汪亚,红外图像空间噪声分析和预处理方法改进,应用光学, 2007, 28(4):426~430
[87]Burt P. J., Adelson E. H. Merging Images Through Pattern Decomposition. In: Proceedings of SPIE. 1985, (575):173~181
[88]胡旺,图像融合中的关键技术研究:[博士学位论文],四川:四川大学,2006
[89]陶冰洁,王敬儒,采用小波分析的图像融合方法评述,计算机工程与应用,2005,25:16~19
[90]赵有星,李京,基于小波变换的图像融合方法综述,计算机与信息技术,2007,29:413~414
[91]Xydaes C., Petrovo V. Objective Image Fusion Performance Measure. In: Electronic Letters. 2000, 36(4):1939~1949
[92]Leung L. W., King B., Vohora V. Comparison of Image Data Fusion Techniques Using Entropy And INI. In: Proceedings of The 22nd Asian Conference on Remote Sensing. 2001
[93]Y. Chen, R.S. Blum. Experimental Tests of Image Fusion for Night Vision. In: Proceedings of 8th International Conference on Information Fusion. 2005, 1:491~498
[94]胡良梅,高隽,何柯峰,图像融合质量评价方法的研究,电子学报,2004, 32(12A):218~221
[95]G. Qu, D. Zhang, P. Yan. Medical Image Fusion By Wavelet Transform Modulus Maxima. In: Opt. Express. 2001, 9(4):184~190
[96]韩崇昭,朱洪艳,段战胜等,多源信息融合,清华大学出版社,2006
[97]G. Qu, D. Zhang, P. Yan. Information Measure for Performance of Image Fusion. In: Electronics Letters. 2002, 38(7):313~315
[98]C.S. Xydeas, V. Petrovi?. Objective Image Fusion Performance Measure. In: Electronics Letters. 2000, 36(4):308~309
[99]C.S. Xydeas, V.S. Petrovi?. Objective Pixel-level Image Fusion Performance Measure. In: Proceedings of SPIE. 2000, 4051:89~98
[100]Piella G. New Quality Measures for Image Fusion. In: 7th International Conference on Information Fusion. 2004, 542~546
[101]张流,基于DSP的视频车辆检测系统设计:[硕士学位论文],天津:天津大学,2005
[102]林涛,视觉交通检测技术的研究:[硕士学位论文],天津:天津大学,2005
[103]吴文琪,孙增圻,机器视觉中的计算机定标方法综述,计算机应用研究,2004, 21(2):4~6
[104]全红艳,张田文,基于运动的摄像机定标方法的综述,计算机工程与应用,2003,39(22):113~115
[2]黄卫,陈里德,智能运输系统概论,北京:人民交通出版社,2001
[3]翁剑成,翟雅峤,赵晓娟,综合交通信息平台的交通基础数据库设计,中国交通信息产业,2009,135~137
[4]S. Takaba, M.Sakauchi, T. Kaneko. Measurement of Traffic Flow Using Real Time Processing of Moving Pictures. In: 32nd Conference on Vehicular Technology. 1982, 488~494
[5]W. Dichinson, R. C. Waterfall. Video Image Processing for Monitoring Road Traffic. In: IEEE International Conference on Road Traffic Data Collection. 1984, 105~109
[6]何友,王国宏,彭应宁等,多传感器信息融合及应用,北京:电子工业出版社,2007
[7]覃征,鲍复民,李爱国等,数字图像融合,西安:西安交通大学出版社, 2004
[8]Llinas J., Hall D. L. An Introduction to Multisensor Data Fusion. In: Proceedings of the IEEE. 1998, 85(1):6~23
[9]李伟,像素级图像融合方法及应用研究:[博士学位论文],广东:华南理工大学,2006
[10]田杰,复杂背景下图像融合算法及信息融合系统评估研究:[博士学位论文],北京:北京理工大学,2002
[11]Piella G. A General Framewok for Multiresolution Image Fusion: from Pixels to Regions. In: Information Fusion. 2003, 4(4):259~280
[12]俞斯乐,侯正信,冯启明等,电视原理(第五版),北京:国防工业出版社,2001
[13]Texas Instruments. In: TMS320DM642 Video/Imaging Fixed-Point Digital Signal Processor. 21~22
[14]Texas Instruments. In: TMS320DM642 Technical Overview. 13~14
[15]Texas Instruments. In: TMS320C6000 DSP Peripheral Component Interconnect (PCI) Reference Guide. 17~19
[16]李方慧,TMS320C6000系列DSPs原理与应用,北京:电子工业出版社,2003
[17]Texas Instruments. In: TMS320C6000 Code Composer Studio Tutorial, 1-3
[18]李房惠,王飞,何佩琨等,TMS320C6000系列DSPs原理与应用(第二版),北京:电子工业出版社,2003
[71]Y. Sheng, D. Roberge. Optical Wavelet Matched Filters for Shift-invariant Pattern Recognition. In: Optics Letters. 1993, 18(4):299~301
[72]J. Zhou, X. Fand, B. K. Ghosh. Image Segmentation Based on Multiresolution Filtering. In: IEEE International Conference on Image Processing. 1994, 3:483-487
[73]J. W. Hsieh, H. Y. Mark Liao, M. T. Ko. Wavelet-based Shape From Shading. In: Graphical Models and Image Processing. 1995, 57(4): 343~362
[74]Djamdji J. P., Bijaoui A., Maniere R. Geometrical Registration of Images: The Multiresolution Approach. In: Photogrammetric Engineering and Remote Sensing. 1993, 59(5):645~653
[75]Moigne J. L., Cromp R. F. The Use of Wavelets for Remote Sensing Image Registration and Fusion. In: Proceedings of SPIE, 1996, 535~544
[76]Corvi M., Nicchiotti G. Multiresolution Image Registration, In: Proceedings of International Conference on Image Processing. 1995, 3:224~227
[77]R. Deriche, G. Giraudon. A Computational Approach for Corner and Vertex Detection. In International Journal of Computer Vision. 1993, 2:101~124
[78]K. Rohr. Localization Properties of Direct Corner Detectors. In: Journal of Mathematical Imaging and Vision. 1994, 4:139~150
[79]L. Kitchen, A. Rosenfeld. Gray Level Corner Detection. In: Pattern Recognition Letters. 1982, 1:95~102
[80]O. A. Zuniga, R. Haralick. Corner detection using the facet model. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition. 1983, 30~37
[81]K. Brunnstrom, T. Lindeberg, J. O. Eklundh. Active Detection And Classification of Junctions. In: Proceedings of 2nd European Conference on Computer Vision. 1992, 701~709
[82]ZitováB., Flusser J. Image Registration Methods: A Survey. In: Image and Vision Computing. 2003, 21(11):997~1000
[83]冷晓艳,薛模根,韩裕生等,基于区域特征与灰度交叉相关的序列图像拼接,红外与激光工程, 2005, 34(5):602~605
[84]Krim H., Schick I. C. Minimax Description Length for Signal Denoising and Optimized Representation. In: IEEE Transactions on Information Theory. 1999, 45(3):898~908
[85]Liu Juan, Moulin P. Image Denoising Based on Scale-space Mixture Modeling of Wavelet Coefficients. In: Proceedings of IEEE International Conference on Image Processing. 1999:386~39
[86]邹前进,冯亮,汪亚,红外图像空间噪声分析和预处理方法改进,应用光学, 2007, 28(4):426~430
[87]Burt P. J., Adelson E. H. Merging Images Through Pattern Decomposition. In: Proceedings of SPIE. 1985, (575):173~181
[88]胡旺,图像融合中的关键技术研究:[博士学位论文],四川:四川大学,2006
[89]陶冰洁,王敬儒,采用小波分析的图像融合方法评述,计算机工程与应用,2005,25:16~19
[90]赵有星,李京,基于小波变换的图像融合方法综述,计算机与信息技术,2007,29:413~414
[91]Xydaes C., Petrovo V. Objective Image Fusion Performance Measure. In: Electronic Letters. 2000, 36(4):1939~1949
[92]Leung L. W., King B., Vohora V. Comparison of Image Data Fusion Techniques Using Entropy And INI. In: Proceedings of The 22nd Asian Conference on Remote Sensing. 2001
[93]Y. Chen, R.S. Blum. Experimental Tests of Image Fusion for Night Vision. In: Proceedings of 8th International Conference on Information Fusion. 2005, 1:491~498
[94]胡良梅,高隽,何柯峰,图像融合质量评价方法的研究,电子学报,2004, 32(12A):218~221
[95]G. Qu, D. Zhang, P. Yan. Medical Image Fusion By Wavelet Transform Modulus Maxima. In: Opt. Express. 2001, 9(4):184~190
[96]韩崇昭,朱洪艳,段战胜等,多源信息融合,清华大学出版社,2006
[97]G. Qu, D. Zhang, P. Yan. Information Measure for Performance of Image Fusion. In: Electronics Letters. 2002, 38(7):313~315
[98]C.S. Xydeas, V. Petrovi?. Objective Image Fusion Performance Measure. In: Electronics Letters. 2000, 36(4):308~309
[99]C.S. Xydeas, V.S. Petrovi?. Objective Pixel-level Image Fusion Performance Measure. In: Proceedings of SPIE. 2000, 4051:89~98
[100]Piella G. New Quality Measures for Image Fusion. In: 7th International Conference on Information Fusion. 2004, 542~546
[101]张流,基于DSP的视频车辆检测系统设计:[硕士学位论文],天津:天津大学,2005
[102]林涛,视觉交通检测技术的研究:[硕士学位论文],天津:天津大学,2005
[103]吴文琪,孙增圻,机器视觉中的计算机定标方法综述,计算机应用研究,2004, 21(2):4~6
[104]全红艳,张田文,基于运动的摄像机定标方法的综述,计算机工程与应用,2003,39(22):113~115