动态背景下运动目标的提取
|
摘要
在实际的图像处理问题中，图像的边缘作为图像的一种基本特征，被经常应用到较高层次的特征描述、图像识别、图像分割、图像增强以及图像压缩等的图像处理和分析技术中，从而可对图像作进一步的分析和理解。
当前动态背景中运动目标的处理是数字图像处理领域中的一个重要发展方向，对于运动目标的特征提取具有深远的意义。通常，在复杂的背景中，人们更加关心的往往是对人类视觉系统具有很强冲击性的目标或者是人们要特别关注的目标，因此对于该目标的综合处理变得尤为关键。在对运动目标处理的众多方面中，对其精确轮廓的提取是最重要、最基本的环节。因为只有得到运动目标的带纹理精确轮廓图像后，人们才能在此基础上，对其进行进一步的深入研究。
运动目标提取的传统方法是利用各种空间域或频率域的边缘检测算子对原始图像进行分析，再将得到的轮廓进行处理。这样做既没有考虑到原始图像序列中所附带的纹理信息，也没有对已检测得到的轮廓进行深入的、细致的处理，从而使得轮廓图像中存在很多的干扰信息，比如：尚未处理的杂乱孤立干扰点、伪边缘、运动目标边缘不连续等。
本文在实际项目“体育运动员三维人体模拟系统”的开发中，我们发现传统的运动目标边缘轮廓检测算法，已经不能完全地适合本文的需求。因此，在传统边缘检测方法的基础上，本文提出了一套适合于从此类体育运动员图像序列中进行运动目标的带纹理精确轮廓提取的算法理论。并对以下几个方面也进行了重点讨论：1)讨论了数学形态学方法在图像边缘检测中的应用，及其灵活变化与实践。2)在边界连接中，根据对实际情况的研究，提出了一种具有通用意义边界连接算法3)根据精度要求的不同，可以利用膨胀算法简化轮廓提取的步骤，以提高算法的时间效率。4)本文巧妙地将计算机图形学中的扫描线算法利用到轮廓提取中，简单有效地达到了运动目标的带纹理精确轮廓提取的目的。
The edge of image is often considered as its fundamental feature in image processing. It has been used in image processing and analyzing technologies such as feature description, image recognition, image segmentation, image enhancement and image data compression on a high level. Then we can comprehend and analyze the edge image later on .
Now, the extraction of motion object in dynamic background is a important developing-direction in digital image process, and it is very significative. In dynamic background , people commonly care about some objects, which have a strong wallop to people's system of vision or are special object regarded as important things by people. So this aspect is very important. At every aspect of managing of motion object, this aspect is base and important. Because we can go on doing more research after attaining the edge of object with texture.
The traditional way is that analyzing original image with all sorts of edge operator , and do more operations. But This way is not considering the information of texture and not doing more works. So This edge image exists much flaw, such as, disorder interfereing points, fake edges, discontinuity in the edges, etc.
Finally, this thesis considered the traditional way not to adapt to our problem for developing the 3-D stimulating of athlete. So we advance a method that adapting to dealing with our problem, and do some research with several aspect: first, discussing the application of morphology detecting edge of image .Secondly, in the connection of edge, basing on actual problem ,we advance a method of connectin edge that has universal significance. Thirdly, according as the difference of precision, we may short the steps of edge extraction and improve the efficiency of algorithm with dilation algorithm. At last, with felicitical using algorithm of scanning beam, we attain the rigor edge image with texture.
当前动态背景中运动目标的处理是数字图像处理领域中的一个重要发展方向，对于运动目标的特征提取具有深远的意义。通常，在复杂的背景中，人们更加关心的往往是对人类视觉系统具有很强冲击性的目标或者是人们要特别关注的目标，因此对于该目标的综合处理变得尤为关键。在对运动目标处理的众多方面中，对其精确轮廓的提取是最重要、最基本的环节。因为只有得到运动目标的带纹理精确轮廓图像后，人们才能在此基础上，对其进行进一步的深入研究。
运动目标提取的传统方法是利用各种空间域或频率域的边缘检测算子对原始图像进行分析，再将得到的轮廓进行处理。这样做既没有考虑到原始图像序列中所附带的纹理信息，也没有对已检测得到的轮廓进行深入的、细致的处理，从而使得轮廓图像中存在很多的干扰信息，比如：尚未处理的杂乱孤立干扰点、伪边缘、运动目标边缘不连续等。
本文在实际项目“体育运动员三维人体模拟系统”的开发中，我们发现传统的运动目标边缘轮廓检测算法，已经不能完全地适合本文的需求。因此，在传统边缘检测方法的基础上，本文提出了一套适合于从此类体育运动员图像序列中进行运动目标的带纹理精确轮廓提取的算法理论。并对以下几个方面也进行了重点讨论：1)讨论了数学形态学方法在图像边缘检测中的应用，及其灵活变化与实践。2)在边界连接中，根据对实际情况的研究，提出了一种具有通用意义边界连接算法3)根据精度要求的不同，可以利用膨胀算法简化轮廓提取的步骤，以提高算法的时间效率。4)本文巧妙地将计算机图形学中的扫描线算法利用到轮廓提取中，简单有效地达到了运动目标的带纹理精确轮廓提取的目的。
The edge of image is often considered as its fundamental feature in image processing. It has been used in image processing and analyzing technologies such as feature description, image recognition, image segmentation, image enhancement and image data compression on a high level. Then we can comprehend and analyze the edge image later on .
Now, the extraction of motion object in dynamic background is a important developing-direction in digital image process, and it is very significative. In dynamic background , people commonly care about some objects, which have a strong wallop to people's system of vision or are special object regarded as important things by people. So this aspect is very important. At every aspect of managing of motion object, this aspect is base and important. Because we can go on doing more research after attaining the edge of object with texture.
The traditional way is that analyzing original image with all sorts of edge operator , and do more operations. But This way is not considering the information of texture and not doing more works. So This edge image exists much flaw, such as, disorder interfereing points, fake edges, discontinuity in the edges, etc.
Finally, this thesis considered the traditional way not to adapt to our problem for developing the 3-D stimulating of athlete. So we advance a method that adapting to dealing with our problem, and do some research with several aspect: first, discussing the application of morphology detecting edge of image .Secondly, in the connection of edge, basing on actual problem ,we advance a method of connectin edge that has universal significance. Thirdly, according as the difference of precision, we may short the steps of edge extraction and improve the efficiency of algorithm with dilation algorithm. At last, with felicitical using algorithm of scanning beam, we attain the rigor edge image with texture.
引文
[1]Poggio T, Voorhees H and Yuille A. A Regularized Solution to Edge Detection. Tech. Rep. MA, MIT Artificial Intell Lab, May 1985, Rep. AIM: 833
[2]Mallat S, Hwang W L. Singularity detection and processing with wavelets [J]. IEEE Trans on Information Theory, 1992, 38(2): 617-643
[3]崔景泰，小波分析导论[M]．西安：西安交通大学出版社，1995．90-100
[4]程正兴，小波分析算法与应用 [M]．西安：西安交通大学出版社，1998．50-60
[5]Mallat S, Zhong S. Characterization of signal from multiscale edge[J]. IEEE Trans PAMI. 1992(7): 710-732
[6]John Canny. Member A Computational Approach to Edge Detection. IEEE Trans Pattern Analysis and Machine Intelligence, Novmber 1986, Vol. PAMI-8, No. 1:679-697
[7]Abdou I E and Pratt W K. Quantitative Design and Evalution of Enhancementand Thrsholding Edge Detectors. Proc. IEEE, Novmber 1986, Vol. 67, No. 5:753-763
[8]Pratt W K. Digital Image Processing. New York: Wiley-Interscience, 1978. 78-90
[9]Rice S O. Mathematical Analysis of Random Noise. Bell Syst Tech. J, 1945, vol. 24:46-156
[10]杨枝灵，王开．数字图像获取、处理、及实践应用．人民邮电出版社，2003年1月．457-461
[11]徐长发，李国宽．实用小波方法．华中科技大学出版社，2001年7月．104-144
[12]张益贞，刘滔．VC++实现MPEG／JPEG编解码技术．人民邮电出版社，2002年11月．100-156
[13]Gonzalez Rafael C, Richard E Woods. Digital Image Processing(Second Edition)电子工业出版社，2003年3月．59-112
[14]刘亚，艾海舟：一种基于背景模型的运动目标检测与跟踪算法[硕士学位论文]． 信息与控制，31(4)， 2002
[15]Tekalp A M. Digital Video Processing. Rochester, NY, 1995:109-120
[16]Pratt W K. Digital Image Processing , 3rd ed. John Wiley & Sons, NY, 2001:120-130
[17]Shapiro, L G and Stockman G C. Computer Vision. Prentice Hall, Upper Saddle River, NJ, 2001:56-85
[18]Dougherty E R. Random Processes for Image and Signal Processing. IEEE Press, NY, 2000:89-108
[19]Goutsias, Vincent J L and Bloombery D S. Mathematical Morphology and Its Applications to Image and Signal Processing. Kluwer Academic Publishers, Boston, MA, 2000. 68-98
[20]Marchand, Maillet S and Sharaiha Y M. Binary Digital Image Processing:A Discrete Approch. Academic Press, NY, 2000. 100-150
[21]Petrou M and Bosdogianni P. Image Processing:The Fundantmentals. John Wiley & Sons, UK, 1999. 100-120
[22]Smirnov A. Processing of Multidimensional Signals. Springer-Verlag, NY, 1999. 130-140
[23]Haskell B G and Netravali A N. Digital Picture:Representation, Compression, and Standards. Preseus Publishing, NY, 1997. 145-160
[24]Castleman K R. Digital Image Processing, 2nd ed. Prentice Hall, Upper Saddle River, NJ, 1996. 78-98
[25]Sid-Ahmed M A. Image Processing :Theroy, Algorithms, and Architecture. McGraw-Hill NY, 1995. 150-170
[26]Jain R, Rangachar K and Schunk B. Computer Vision. McGraw-Hill, NY, 1995. 125-145
[27]Gonzalez R C and Woods R E. Digital Image Processing. Addison-Wesley, Reading, M. A, 1992. 125-155
[28]Pratt W K. Digital Image Processing, 2nd ed. Wiley-Interscience, NY, 1991. 55-95
[29]Jain A K. Fundamental of Digital Image Processing. Prentice Hall, Upper Saddle River NY, 1989. 75-105
[30]Duda R O, Hart P E and Stork D G. Pattern Classification, 2nd ed. John Wiley & Sons, NY, [2001]. 68-78
[31]Chui C K. An overview of wavelets, in Approximation Theory and Functional Analysis, Chui C K (ed). Boston:Academic Press, MA, 1991. 47-72
[32]Chui C K and Wang J Z. Acardinal spline approach to wavelets. Proc Amer Math Soc, 1991, 113:785-793
[33]Cohen A. Wavelets and digital signal processing, in Wavelets and Their Applications, Beylkin G, etc(eds), Boston:Jones and Bartlett, MA, 1992. 105-121
[34]Cohen A and Daubechies I. Nonseparable bidimensional wavelet bases. Rev Mat Iberoamericana 1993.9:51-137
[35]Mallat S. A theory of multiresolution signal decomposition:the wavelet represtation. IEEE Trans Pattern Anal Machine Intell, 1989.11:604-614
[2]Mallat S, Hwang W L. Singularity detection and processing with wavelets [J]. IEEE Trans on Information Theory, 1992, 38(2): 617-643
[3]崔景泰，小波分析导论[M]．西安：西安交通大学出版社，1995．90-100
[4]程正兴，小波分析算法与应用 [M]．西安：西安交通大学出版社，1998．50-60
[5]Mallat S, Zhong S. Characterization of signal from multiscale edge[J]. IEEE Trans PAMI. 1992(7): 710-732
[6]John Canny. Member A Computational Approach to Edge Detection. IEEE Trans Pattern Analysis and Machine Intelligence, Novmber 1986, Vol. PAMI-8, No. 1:679-697
[7]Abdou I E and Pratt W K. Quantitative Design and Evalution of Enhancementand Thrsholding Edge Detectors. Proc. IEEE, Novmber 1986, Vol. 67, No. 5:753-763
[8]Pratt W K. Digital Image Processing. New York: Wiley-Interscience, 1978. 78-90
[9]Rice S O. Mathematical Analysis of Random Noise. Bell Syst Tech. J, 1945, vol. 24:46-156
[10]杨枝灵，王开．数字图像获取、处理、及实践应用．人民邮电出版社，2003年1月．457-461
[11]徐长发，李国宽．实用小波方法．华中科技大学出版社，2001年7月．104-144
[12]张益贞，刘滔．VC++实现MPEG／JPEG编解码技术．人民邮电出版社，2002年11月．100-156
[13]Gonzalez Rafael C, Richard E Woods. Digital Image Processing(Second Edition)电子工业出版社，2003年3月．59-112
[14]刘亚，艾海舟：一种基于背景模型的运动目标检测与跟踪算法[硕士学位论文]． 信息与控制，31(4)， 2002
[15]Tekalp A M. Digital Video Processing. Rochester, NY, 1995:109-120
[16]Pratt W K. Digital Image Processing , 3rd ed. John Wiley & Sons, NY, 2001:120-130
[17]Shapiro, L G and Stockman G C. Computer Vision. Prentice Hall, Upper Saddle River, NJ, 2001:56-85
[18]Dougherty E R. Random Processes for Image and Signal Processing. IEEE Press, NY, 2000:89-108
[19]Goutsias, Vincent J L and Bloombery D S. Mathematical Morphology and Its Applications to Image and Signal Processing. Kluwer Academic Publishers, Boston, MA, 2000. 68-98
[20]Marchand, Maillet S and Sharaiha Y M. Binary Digital Image Processing:A Discrete Approch. Academic Press, NY, 2000. 100-150
[21]Petrou M and Bosdogianni P. Image Processing:The Fundantmentals. John Wiley & Sons, UK, 1999. 100-120
[22]Smirnov A. Processing of Multidimensional Signals. Springer-Verlag, NY, 1999. 130-140
[23]Haskell B G and Netravali A N. Digital Picture:Representation, Compression, and Standards. Preseus Publishing, NY, 1997. 145-160
[24]Castleman K R. Digital Image Processing, 2nd ed. Prentice Hall, Upper Saddle River, NJ, 1996. 78-98
[25]Sid-Ahmed M A. Image Processing :Theroy, Algorithms, and Architecture. McGraw-Hill NY, 1995. 150-170
[26]Jain R, Rangachar K and Schunk B. Computer Vision. McGraw-Hill, NY, 1995. 125-145
[27]Gonzalez R C and Woods R E. Digital Image Processing. Addison-Wesley, Reading, M. A, 1992. 125-155
[28]Pratt W K. Digital Image Processing, 2nd ed. Wiley-Interscience, NY, 1991. 55-95
[29]Jain A K. Fundamental of Digital Image Processing. Prentice Hall, Upper Saddle River NY, 1989. 75-105
[30]Duda R O, Hart P E and Stork D G. Pattern Classification, 2nd ed. John Wiley & Sons, NY, [2001]. 68-78
[31]Chui C K. An overview of wavelets, in Approximation Theory and Functional Analysis, Chui C K (ed). Boston:Academic Press, MA, 1991. 47-72
[32]Chui C K and Wang J Z. Acardinal spline approach to wavelets. Proc Amer Math Soc, 1991, 113:785-793
[33]Cohen A. Wavelets and digital signal processing, in Wavelets and Their Applications, Beylkin G, etc(eds), Boston:Jones and Bartlett, MA, 1992. 105-121
[34]Cohen A and Daubechies I. Nonseparable bidimensional wavelet bases. Rev Mat Iberoamericana 1993.9:51-137
[35]Mallat S. A theory of multiresolution signal decomposition:the wavelet represtation. IEEE Trans Pattern Anal Machine Intell, 1989.11:604-614
© 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 |