基于人体视觉特征的实时人像提取及其在虚拟环境照相中的应用
|
摘要
虚拟环境中实时照相系统的研制是为了满足体验经济的发展对数字应用系统的需求。对其中关键技术环节----"实时人像提取"部分的深入研究，不仅能把虚拟现实技术（Virtual Reality Technology，简称VRT）的研究成果引入虚拟照像系统，使系统的性价比大大提高、"人性化"功能加强。同时，也对解决虚拟现实技术应用中所出现的"贵族化"、"计算繁琐"及"数据危机"等三大障碍,开发基于PC的虚拟现实应用系统，有一定的理论与实际的参考意义。
本文从分析人类视觉特征入手，运用系统的观念综合平衡图像质量、实时性、与系统成本等技术指标，在对虚拟实时照相系统具体技术指标深入分析的基础上，提出了基于人类视觉系统（HVS）特性的实时人像提取算法。该算法依据人体视觉特征所决定的数字图象处理指标，参照人体视觉的信息处理机制，经过信息压缩、参数自适应的统计分类、形态学非线性滤波、图像融合、彩色图像增强等紧密配合的模块化处理过程，实现了鲁棒性较强的实时人像提取。算法中24位彩色图与二值特征图之间相互转换的过程,体现了利用变换域处理和信息分层处理的思想。文中对算法的各部分进行了原理与实现方法的深入分析，提供了在Matlab环境下的仿真图片。仿真结果表明，利用二值滤波处理较好地解决了传统的基于区域的图象分类中的边缘不连续的问题；利用边缘渐变方式实现的图像融合简洁有效；由灰度统计直方图均衡所实现的彩色增强处理降低了虚拟照相系统对环境照度的要求。原理分析、量化实验、系统实验、及部分算法在产品中的应用从多方面表明了论文所提方法的正确性。
利用VC所提供的VFW（video for window）功能，在VC6.0的平台下实现了上述内容，应用表明，本文所提算法是可靠的。论文在虚拟环境中实时照相系统的硬件部分对系统结构、单片机操作单元部分进行了论述。
The manufacture of real-time photographing system in virtual environment meets the needs that the development of experience economic towards digital application system. The lucubrating of its key technology part --"real-time portrait pick-up", has introduced the achievement of virtual reality technology into virtual photographing system, made the ratio of performance and price increase greatly, strengthened the "human" function. At the same time, to some extent it also has the practical and academic referenced sense in dealing with the three obstacles ,such as "noble"、"computer overloaded with details" and "data crisis", which appearance when virtual reality technology put into reality.
This article begin with analyzing the character of human vision , making use of the notion of system to balance the several technology targets, such as image quality, real-time capability ,the cost of system and so on, and at the basis of thorough analysis toward the concrete technology target of the virtual real-time photographing system, putting forward the real-time portrait pick-up arithmetic based on human vision system. According as the digital image processing target determined by human vision character , through a series of processes ,such as information condensation, statistics classify base on parameter self-adaptation , morphological non-linearity filtering , image fusion , reinforcing of color picture and so on, this arithmetic realize real-time image pick-up with the development of robust. This arithmetic has also embody the idea of information layered dispose of diversification field dealing, which exist in the mutual transition between 24 bit color picture and two-value characteristic picture. In terms of individually part of this arithmetic, this article has analyzed deeply, and offered the simulation picture in the Matlab environment. The simulation result has indicated that using the method of two-value filter can solve the question perfectly, and the question is the edge discontinuity of traditional image classify base on region; The image fusion which make use of edge gradually change is sententious and efficient; The color image reinforcing which realized by grey statistics histogram equalization method has reduced the need of environment brightness in virtual photographing system. The application of principle analysis, quantum experiment ,system experiment, and some arithmetic in products has proved the exactness of the method we have provided from several aspects.
Through utilizing the VFW(video for window) function which provided by VC system, has realized this arithmetic under the platform of VC6.0, the application has indicated that the scheme which bring forward in this article is exactness and credibility.
In the part of hardware of the virtual environment real-time photographing system, this article has discussed several parts, such as system structure, single chip microcomputer assistant manage unit and so on.
本文从分析人类视觉特征入手，运用系统的观念综合平衡图像质量、实时性、与系统成本等技术指标，在对虚拟实时照相系统具体技术指标深入分析的基础上，提出了基于人类视觉系统（HVS）特性的实时人像提取算法。该算法依据人体视觉特征所决定的数字图象处理指标，参照人体视觉的信息处理机制，经过信息压缩、参数自适应的统计分类、形态学非线性滤波、图像融合、彩色图像增强等紧密配合的模块化处理过程，实现了鲁棒性较强的实时人像提取。算法中24位彩色图与二值特征图之间相互转换的过程,体现了利用变换域处理和信息分层处理的思想。文中对算法的各部分进行了原理与实现方法的深入分析，提供了在Matlab环境下的仿真图片。仿真结果表明，利用二值滤波处理较好地解决了传统的基于区域的图象分类中的边缘不连续的问题；利用边缘渐变方式实现的图像融合简洁有效；由灰度统计直方图均衡所实现的彩色增强处理降低了虚拟照相系统对环境照度的要求。原理分析、量化实验、系统实验、及部分算法在产品中的应用从多方面表明了论文所提方法的正确性。
利用VC所提供的VFW（video for window）功能，在VC6.0的平台下实现了上述内容，应用表明，本文所提算法是可靠的。论文在虚拟环境中实时照相系统的硬件部分对系统结构、单片机操作单元部分进行了论述。
The manufacture of real-time photographing system in virtual environment meets the needs that the development of experience economic towards digital application system. The lucubrating of its key technology part --"real-time portrait pick-up", has introduced the achievement of virtual reality technology into virtual photographing system, made the ratio of performance and price increase greatly, strengthened the "human" function. At the same time, to some extent it also has the practical and academic referenced sense in dealing with the three obstacles ,such as "noble"、"computer overloaded with details" and "data crisis", which appearance when virtual reality technology put into reality.
This article begin with analyzing the character of human vision , making use of the notion of system to balance the several technology targets, such as image quality, real-time capability ,the cost of system and so on, and at the basis of thorough analysis toward the concrete technology target of the virtual real-time photographing system, putting forward the real-time portrait pick-up arithmetic based on human vision system. According as the digital image processing target determined by human vision character , through a series of processes ,such as information condensation, statistics classify base on parameter self-adaptation , morphological non-linearity filtering , image fusion , reinforcing of color picture and so on, this arithmetic realize real-time image pick-up with the development of robust. This arithmetic has also embody the idea of information layered dispose of diversification field dealing, which exist in the mutual transition between 24 bit color picture and two-value characteristic picture. In terms of individually part of this arithmetic, this article has analyzed deeply, and offered the simulation picture in the Matlab environment. The simulation result has indicated that using the method of two-value filter can solve the question perfectly, and the question is the edge discontinuity of traditional image classify base on region; The image fusion which make use of edge gradually change is sententious and efficient; The color image reinforcing which realized by grey statistics histogram equalization method has reduced the need of environment brightness in virtual photographing system. The application of principle analysis, quantum experiment ,system experiment, and some arithmetic in products has proved the exactness of the method we have provided from several aspects.
Through utilizing the VFW(video for window) function which provided by VC system, has realized this arithmetic under the platform of VC6.0, the application has indicated that the scheme which bring forward in this article is exactness and credibility.
In the part of hardware of the virtual environment real-time photographing system, this article has discussed several parts, such as system structure, single chip microcomputer assistant manage unit and so on.
引文
【1】B. Joseph Pine II,James H. Gilmore. Welcome to the Experience Economy . Harvard Business Review.July - August 1998. P.97
【2】 汪成为,高文,王行仁著.《灵境(虚拟现实)技术的理论、实现及应用》,清华大学出版社,1996.9, P.1-P.7
【3】 张茂军.《虚拟现实系统》.科学出版社.2001.9. P.308-P.313
【4】 李祖枢.《网上照相吧及操作方法》.中国发明专利.IPC.01107322.2001.9.12.P.30
【5】邵景莅.虚拟环境下实时照相技术研究及其系统实现.重庆大学硕士学位论文.2000. P.1-P.8
【6】叶庭芳. 一拍即合独领风骚"大头帖"放送流行新魅力.台湾电玩杂志.2000.No.116. P.90-P.92
【7】 戴汝为,王珏,田捷. 《智能自动化丛书 智能系统的综合集成》.1995.P.165-P.232
【8】Misawa, Z., Nakashima, K., Iwamoto, T., Shimoda, S.. Proposed computer-controlled digital HDTV chroma-key system . SMPTE Journal 104. 3 Mar 1995 . P.134-P.138
【9】Ben-Ezra, Moshe.Segmentation with invisible keying signal. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Jun 2000. P.32-P.37
【10】 齐 越,胡晓峰,张茂军.虚拟演播室：结构及关键技术.中国图象图形学报.2000.6 vol6. P.457-P.461
【11】 苏光大.《微机图象处理系统》. 清华大学出版社.2000.7. P.1-P.17
【12】刘健勤,盛津芳,魏敏洁.《面向智能体的视觉信息处理》.科学出版社.2000.4. P.61-P.100
【13】贾云得.《机器视觉》,科学出版社，2000.4,P.48-P.60,P.20-P.22,P.22-P.25
【14】章毓晋.《图象工程（上册）-图象处理和分析》．清华大学出版社．1999.3． P.179-P.215,P.16,P.3,P.96
【15】 罗 涛.头肩视频图像的运动物体自动提取.北京大学学报(自然科学版).2000.9 vol36 NO.5. P.509-P.605
【16】YangG,Huang T. Human Full Detection a Complex Background. Pattern Rcognition.1994. vol27 NO.1.P.53-P.63
【17】Yuille A,Cohen D,Halliana P. Feature Extraction From Face Using Deformable Templates.IEEE Copmputer Spciety Conference on Computer Vision and Pattern Recognition.1989.P.104-P.109
【18】 Kostas Haris, Efstratiadis S N, Maglaveras N． Watershedbased image segm on with fast region merging．In:Proceedings of IEEE International conference on
Image Prccessing．Chicago，IL,USA, 1998,3．P.338-P.342.
【19】 杜啸晓，杨新，施鹏飞．一种新的基于区域和边界的图象分割方法．2001 Vol.6 No.8 P.755-P.759
【20】 Kunt M. Benard M Leonardi R，Recent Results in High Compression Image Coding， IEEE Trans.Circuits and Systems,1987,CAS-34(4):1306～13362
【21】 Willmin P.Reed T.Kunt Image Squence Coding by Split and Merge, IEEE Trans.
Communication,1991,39(12):1845～1855
【22】 庄越挺,刘小明,潘云鹤.一种基于视频的人体动画骨架提取.计算机研究与发展. vol 37 .2000.4.P.498-P.507
【23】 Zhang Y J,Yao Y R, He Y.Automatic Face Segmenation Using Color Cues for Codeing Typical Videophone Scenes. SPIE-VCIP'97.San Jose 1997.P.468-P.479
【24】 Matsui, Toshikazu． New objective performance evaluation criteria for imaging systems based on a human vision model and their fundamental characteristics．Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers v 52 Apr 1998 Ｐ.583-Ｐ.593
【25】 罗晓晖.双高斯差模型的低层次视觉尺度要素检测研究.重庆大学博士论文.2002.
【26】 陈众.在虚拟影像环境中实时人像提取及应用.重庆大学硕士学位论文.2000.P.47-P.67
【27】寿天德.《视觉信息处理的脑机制》.上海科技教育出版社.1997.P.3-P.4,P.25- P.40,P.75-93
【28】[日]福岛邦彦著;马万禄等译.《视觉生理与仿生学》.科学出版社.1980. P.28-P.37,58-P.137
【29】马颂德,张正友著. 《计算机视觉:计算理论与算法基础》.科学出版社.1998.P.2
【30】[美]卡洛琳·M·布鲁墨.《视觉原理》. 北京大学出版社.1987.P.1-P.80
【31】容观澳编著.《计算机图象处理》.清华大学出版社.2000.2 P.24-P.37
【32】[日]应用物理学会光学讨论会编辑 杨雄里译.《生理光学 眼的光学与视觉》.科学出版社.1980.P.295-P.310,P.40-P.78
【33】高文,陈熙霖.《计算机视觉--算法与系统原理》.清华大学出版社.1999.P.1-P.17
【34】李祖枢.仿人智能控制研究20年.中国智能自动化学术会议论文集.重庆.1999.北京. 清华大学出版社.1999.P.20-P.32
【35】Kenneth R.Castleman .《DIGITAL IMAGE PROCESSING》，清华大学出版社,2000.2 P.1-P.35
【36】Rogowitz, B.E., Pappas, T.N., Allebach, J.P..Human vision and electronic imaging .Journal of Electronic Imaging. January 2001. P.10-P.19
【37】A M Van Dijk, J-B Martens. Subjective quality assessment of compressed images. Signal Processing. 1997.vol58.P.235-P.252.
【38】Lee S U, Chung S Y..A comparative performance study of several global thresholding
techniques for segmentation. Computer Vision, Graphics and Image Processing, 1990, vol52.P.171-P.190
【39】刘万春,贾云得,徐一华等.基于肤色的人脸实时跟踪方法.北京理工大学学报.2000.8 vol20. P.461-P.466
【40】Oliver N ,Pentland A,Berard F.. Lips and face real time tracker with facial expression recognition . Proc IEEE on CVPR ,1997 .P.123-P.129.
【41】LaCascia M, Sclaroff S. .Fast,reliable head tracking under varying illumination.Proc IEEE on CVPR, 1999.P.604-P.610
【42】唐常青等编著. 《数学形态学方法及其应用》.科学出版社.1990.8 P.1-P.32
【43】龚炜,石青云,程民德著, 《数字空间中的数学形态学:理论及应用》,科学出版 社,1997.1. P.1-P100
【44】崔屹. 《图象处理与分析数学形态学方法及应用》.科学出版社.2000.4.P.146,P.1- P.42
【45】陈贺新.《非线性滤波器与数字图像处理》. 国防工业出版社.1997.9.P.138-P.180
【46】Marsala, Ch., Bouchon-Meunier, B.. Fuzzy partitioning using mathematical morphology in a learning scheme , IEEE International Conference on Fuzzy Systems . Sep 1996. P.1512-P.1517
【47】马向英,杜威,袁晓君，李华.基于图象的室内虚拟漫游系统.中国图形图象学报，2001 Vol.6 No.1 P.86-P.91
【48】汪成为. 灵境技术与人机和谐仿真环境. 计算机研究与发展.1997,34(1).P.1-P.12
【49】李书印,万明习,行鸿彦.基于视觉生理的虚拟环境显示.中国图形图象学报.2001 Vol.6 No.2 P.172-P.177
【50】侯格贤,毕笃彦,吴成柯.图象分割质量评价方法研究.中国图形图象学报.2000 Vol.5 No.1 P.38-P.43
【51】Zhang Y J. A survry on evaluation methods for image segmentation. Pattern Recognition, 1996, 29(8). P.1335-P.1346.
【52】汪孔桥,沈兰荪,邢昕,一种基于视觉兴趣性的图象质量评价方法,中国图形图象学报,2000 Vol.5 No.4 P.300-P.303
【53】王楠楠,李桂苓.符合人眼视觉特性的视频质量评价模型.中国图形图象学报.2001 Vol.6 No.6 P.523-P.527
【54】Philips Electronics North American Corporation.TM1300.philips data sheet.Oct 1999.P.1-P.300
【2】 汪成为,高文,王行仁著.《灵境(虚拟现实)技术的理论、实现及应用》,清华大学出版社,1996.9, P.1-P.7
【3】 张茂军.《虚拟现实系统》.科学出版社.2001.9. P.308-P.313
【4】 李祖枢.《网上照相吧及操作方法》.中国发明专利.IPC.01107322.2001.9.12.P.30
【5】邵景莅.虚拟环境下实时照相技术研究及其系统实现.重庆大学硕士学位论文.2000. P.1-P.8
【6】叶庭芳. 一拍即合独领风骚"大头帖"放送流行新魅力.台湾电玩杂志.2000.No.116. P.90-P.92
【7】 戴汝为,王珏,田捷. 《智能自动化丛书 智能系统的综合集成》.1995.P.165-P.232
【8】Misawa, Z., Nakashima, K., Iwamoto, T., Shimoda, S.. Proposed computer-controlled digital HDTV chroma-key system . SMPTE Journal 104. 3 Mar 1995 . P.134-P.138
【9】Ben-Ezra, Moshe.Segmentation with invisible keying signal. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Jun 2000. P.32-P.37
【10】 齐 越,胡晓峰,张茂军.虚拟演播室：结构及关键技术.中国图象图形学报.2000.6 vol6. P.457-P.461
【11】 苏光大.《微机图象处理系统》. 清华大学出版社.2000.7. P.1-P.17
【12】刘健勤,盛津芳,魏敏洁.《面向智能体的视觉信息处理》.科学出版社.2000.4. P.61-P.100
【13】贾云得.《机器视觉》,科学出版社，2000.4,P.48-P.60,P.20-P.22,P.22-P.25
【14】章毓晋.《图象工程（上册）-图象处理和分析》．清华大学出版社．1999.3． P.179-P.215,P.16,P.3,P.96
【15】 罗 涛.头肩视频图像的运动物体自动提取.北京大学学报(自然科学版).2000.9 vol36 NO.5. P.509-P.605
【16】YangG,Huang T. Human Full Detection a Complex Background. Pattern Rcognition.1994. vol27 NO.1.P.53-P.63
【17】Yuille A,Cohen D,Halliana P. Feature Extraction From Face Using Deformable Templates.IEEE Copmputer Spciety Conference on Computer Vision and Pattern Recognition.1989.P.104-P.109
【18】 Kostas Haris, Efstratiadis S N, Maglaveras N． Watershedbased image segm on with fast region merging．In:Proceedings of IEEE International conference on
Image Prccessing．Chicago，IL,USA, 1998,3．P.338-P.342.
【19】 杜啸晓，杨新，施鹏飞．一种新的基于区域和边界的图象分割方法．2001 Vol.6 No.8 P.755-P.759
【20】 Kunt M. Benard M Leonardi R，Recent Results in High Compression Image Coding， IEEE Trans.Circuits and Systems,1987,CAS-34(4):1306～13362
【21】 Willmin P.Reed T.Kunt Image Squence Coding by Split and Merge, IEEE Trans.
Communication,1991,39(12):1845～1855
【22】 庄越挺,刘小明,潘云鹤.一种基于视频的人体动画骨架提取.计算机研究与发展. vol 37 .2000.4.P.498-P.507
【23】 Zhang Y J,Yao Y R, He Y.Automatic Face Segmenation Using Color Cues for Codeing Typical Videophone Scenes. SPIE-VCIP'97.San Jose 1997.P.468-P.479
【24】 Matsui, Toshikazu． New objective performance evaluation criteria for imaging systems based on a human vision model and their fundamental characteristics．Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers v 52 Apr 1998 Ｐ.583-Ｐ.593
【25】 罗晓晖.双高斯差模型的低层次视觉尺度要素检测研究.重庆大学博士论文.2002.
【26】 陈众.在虚拟影像环境中实时人像提取及应用.重庆大学硕士学位论文.2000.P.47-P.67
【27】寿天德.《视觉信息处理的脑机制》.上海科技教育出版社.1997.P.3-P.4,P.25- P.40,P.75-93
【28】[日]福岛邦彦著;马万禄等译.《视觉生理与仿生学》.科学出版社.1980. P.28-P.37,58-P.137
【29】马颂德,张正友著. 《计算机视觉:计算理论与算法基础》.科学出版社.1998.P.2
【30】[美]卡洛琳·M·布鲁墨.《视觉原理》. 北京大学出版社.1987.P.1-P.80
【31】容观澳编著.《计算机图象处理》.清华大学出版社.2000.2 P.24-P.37
【32】[日]应用物理学会光学讨论会编辑 杨雄里译.《生理光学 眼的光学与视觉》.科学出版社.1980.P.295-P.310,P.40-P.78
【33】高文,陈熙霖.《计算机视觉--算法与系统原理》.清华大学出版社.1999.P.1-P.17
【34】李祖枢.仿人智能控制研究20年.中国智能自动化学术会议论文集.重庆.1999.北京. 清华大学出版社.1999.P.20-P.32
【35】Kenneth R.Castleman .《DIGITAL IMAGE PROCESSING》，清华大学出版社,2000.2 P.1-P.35
【36】Rogowitz, B.E., Pappas, T.N., Allebach, J.P..Human vision and electronic imaging .Journal of Electronic Imaging. January 2001. P.10-P.19
【37】A M Van Dijk, J-B Martens. Subjective quality assessment of compressed images. Signal Processing. 1997.vol58.P.235-P.252.
【38】Lee S U, Chung S Y..A comparative performance study of several global thresholding
techniques for segmentation. Computer Vision, Graphics and Image Processing, 1990, vol52.P.171-P.190
【39】刘万春,贾云得,徐一华等.基于肤色的人脸实时跟踪方法.北京理工大学学报.2000.8 vol20. P.461-P.466
【40】Oliver N ,Pentland A,Berard F.. Lips and face real time tracker with facial expression recognition . Proc IEEE on CVPR ,1997 .P.123-P.129.
【41】LaCascia M, Sclaroff S. .Fast,reliable head tracking under varying illumination.Proc IEEE on CVPR, 1999.P.604-P.610
【42】唐常青等编著. 《数学形态学方法及其应用》.科学出版社.1990.8 P.1-P.32
【43】龚炜,石青云,程民德著, 《数字空间中的数学形态学:理论及应用》,科学出版 社,1997.1. P.1-P100
【44】崔屹. 《图象处理与分析数学形态学方法及应用》.科学出版社.2000.4.P.146,P.1- P.42
【45】陈贺新.《非线性滤波器与数字图像处理》. 国防工业出版社.1997.9.P.138-P.180
【46】Marsala, Ch., Bouchon-Meunier, B.. Fuzzy partitioning using mathematical morphology in a learning scheme , IEEE International Conference on Fuzzy Systems . Sep 1996. P.1512-P.1517
【47】马向英,杜威,袁晓君，李华.基于图象的室内虚拟漫游系统.中国图形图象学报，2001 Vol.6 No.1 P.86-P.91
【48】汪成为. 灵境技术与人机和谐仿真环境. 计算机研究与发展.1997,34(1).P.1-P.12
【49】李书印,万明习,行鸿彦.基于视觉生理的虚拟环境显示.中国图形图象学报.2001 Vol.6 No.2 P.172-P.177
【50】侯格贤,毕笃彦,吴成柯.图象分割质量评价方法研究.中国图形图象学报.2000 Vol.5 No.1 P.38-P.43
【51】Zhang Y J. A survry on evaluation methods for image segmentation. Pattern Recognition, 1996, 29(8). P.1335-P.1346.
【52】汪孔桥,沈兰荪,邢昕,一种基于视觉兴趣性的图象质量评价方法,中国图形图象学报,2000 Vol.5 No.4 P.300-P.303
【53】王楠楠,李桂苓.符合人眼视觉特性的视频质量评价模型.中国图形图象学报.2001 Vol.6 No.6 P.523-P.527
【54】Philips Electronics North American Corporation.TM1300.philips data sheet.Oct 1999.P.1-P.300
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |