基于单目视频图像处理的铅球成绩测量技术的研究与实现
|
摘要
近年来基于视频图像处理的计算机视觉检测技术已经成为研究热点,在众多的领域中都得到了广泛的应用。在现代体育运动中,应用该技术可使体育比赛成绩的判定从传统的靠人工经验判定阶段提升到自动化的科学判定水平。但是,目前将计算机视觉检测技术应用于铅球比赛成绩的测量中,在国内未见报道。
针对由于在铅球比赛中人工测量存在因测量工具本身弹性、测量场地不平和人为干扰等因素造成的测量误差而影响比赛的科学性、公平性问题,本文在分析当前国内外有关单目视觉测量技术的研究状况基础上,首次提出将单目视觉测量技术应用在铅球成绩测量中。结合铅球场地的特点,提出了“基于规则同视场几何图形标定法”及“基于同视场物像坐标转换的网格匹配数学模型”,该模型利用透视投影几何关系,对摄像机参数进行标定,通过单目CCD摄像机像面坐标,测量铅球落点的地平面坐标。
本文详细阐述了基于单目视觉的铅球测量系统的设计与实现的关键技术,包括硬件系统、前台图像采集系统和后台成绩测量系统等。给出了系统测试与误差分析,通过实例证明了该方法的精确性、稳定性和高效性。如果在系统中加入铅球运行的轨迹,将会扩大系统的使用范围,这一点有待于进一步研究。
本文的研究成果拓展了视觉测量技术在体育运动中的应用,并在黑龙江省高考体育术科测试中得到了应用。实践证明:其具有结构简单、成本低廉、操作方便、速度快、应用范围广等特点,具有广阔的应用前景和推广价值。
In recent years the computer vision inspection technology based on video image processing has become a hotspot, and have been widely used in many areas. In modern sports, the application of the technology can make the judgement of the sports scores from traditional stage by artificial experience ascent to automatic scientific judgement level. However, at present, there is no such report in domestic regarding to the application of the computer visual inspection technology in the measurement of the competition result of shot put.
Against the artificial measurement error in shot game caused by such factors as flexibility of measuring tools, rough site and and man-made interference, and so affects the game's scientific and fair problems, the article analyzes the current domestic and foreign relevant monocular vision measuring technique, and puts forward the idea to use monocular vision measuring technology in the measurement of the competition result of shot put. Combined with the characteristics of shot put field, puts forward "the identical view geometry calibration method based on rules" and "the grid matching mathematical model based on identical view objects coordinate transformation", the model uses the perspective projection of geometric relationships to calibrate camera parameters, and measures the ground plane coordinates of landing shot through the monocular CCD camera image plane coordinates.
This paper expounds the key technologies of design and implementation of the shot put measuring system based on monocular vision, including hardware system, frontend image acquisition system and backend results measuring system, etc. Gives the system test and error analysis, verifies the methond's accuracy, stability and high efficiency. If join the system the trajectory of shot put operation, it will expand system scope of application, and this needs further study.
The result of this paper expands the application in sports of vision measuring technology, and has been applied in sports skill testing of the university entrance exam in Heilongjiang province. Practice shows that it has such characteristics as simple structure, low cost, convenient operation, quick speed and wide range of application, and has wide application future and spreding value.
针对由于在铅球比赛中人工测量存在因测量工具本身弹性、测量场地不平和人为干扰等因素造成的测量误差而影响比赛的科学性、公平性问题,本文在分析当前国内外有关单目视觉测量技术的研究状况基础上,首次提出将单目视觉测量技术应用在铅球成绩测量中。结合铅球场地的特点,提出了“基于规则同视场几何图形标定法”及“基于同视场物像坐标转换的网格匹配数学模型”,该模型利用透视投影几何关系,对摄像机参数进行标定,通过单目CCD摄像机像面坐标,测量铅球落点的地平面坐标。
本文详细阐述了基于单目视觉的铅球测量系统的设计与实现的关键技术,包括硬件系统、前台图像采集系统和后台成绩测量系统等。给出了系统测试与误差分析,通过实例证明了该方法的精确性、稳定性和高效性。如果在系统中加入铅球运行的轨迹,将会扩大系统的使用范围,这一点有待于进一步研究。
本文的研究成果拓展了视觉测量技术在体育运动中的应用,并在黑龙江省高考体育术科测试中得到了应用。实践证明:其具有结构简单、成本低廉、操作方便、速度快、应用范围广等特点,具有广阔的应用前景和推广价值。
In recent years the computer vision inspection technology based on video image processing has become a hotspot, and have been widely used in many areas. In modern sports, the application of the technology can make the judgement of the sports scores from traditional stage by artificial experience ascent to automatic scientific judgement level. However, at present, there is no such report in domestic regarding to the application of the computer visual inspection technology in the measurement of the competition result of shot put.
Against the artificial measurement error in shot game caused by such factors as flexibility of measuring tools, rough site and and man-made interference, and so affects the game's scientific and fair problems, the article analyzes the current domestic and foreign relevant monocular vision measuring technique, and puts forward the idea to use monocular vision measuring technology in the measurement of the competition result of shot put. Combined with the characteristics of shot put field, puts forward "the identical view geometry calibration method based on rules" and "the grid matching mathematical model based on identical view objects coordinate transformation", the model uses the perspective projection of geometric relationships to calibrate camera parameters, and measures the ground plane coordinates of landing shot through the monocular CCD camera image plane coordinates.
This paper expounds the key technologies of design and implementation of the shot put measuring system based on monocular vision, including hardware system, frontend image acquisition system and backend results measuring system, etc. Gives the system test and error analysis, verifies the methond's accuracy, stability and high efficiency. If join the system the trajectory of shot put operation, it will expand system scope of application, and this needs further study.
The result of this paper expands the application in sports of vision measuring technology, and has been applied in sports skill testing of the university entrance exam in Heilongjiang province. Practice shows that it has such characteristics as simple structure, low cost, convenient operation, quick speed and wide range of application, and has wide application future and spreding value.
引文
[1]刘传才.图像理解与计算机视觉[M].厦门大学出版社,2002.
[2]章毓晋.图像工程下册[M].北京.清华大学出版社,2000.
[3]包锋张大林摄像与计算机辨析终点裁判管理系统的研制[J].北京体育大学学报2004,36(12).
[4] Criminisi A. Accurate visual metrology from single and multiple uncalibrated mages-distinguished dissertations[J].Springer Verlag Press,2001
[5] Criminisi A;Reid I;Zisserman A. A plane measuring device[J].Image and Vision Computing,,vol.17(8), 625-634,1999
[6] G.H.Wang, Z.Y.Hu and F.C.Wu. Single view based measurement on space planes[J].Journalof Computer Science and Technology.Vol.19(3),2004.
[7]G.H.Wang, Y.H.Wu and Z.Y.Hu. A novel approach for single view Based planemetrology[J]. In Proc. of the 16th International Conference on Patern Recognition, vol.2,556-559,2002.
[8]D Liebowitz and A Zisserman.Metric rectification for perspective images of planes[J].Proc.of CVPR,pp:482-488,Jun.2003.
[9] Kanade T. A stereo matching algorithm with an adaptive window:Theory and Experiment [J] .IEEE Trans.on Pattern Analysis and Machine Intelligence, 2004, 16(9), 920-932.
[10]黄凤山.光笔式单摄像机三维坐标视觉测量系统关键技术的研究[D].天津大学博士学位论文,2005.
[11]马国松.基于单目视觉的位姿测量方法及仿真系统研究[D].哈尔滨工业大学硕士学位论文,2005.
[12]赵锐.基于单目视觉的物体位姿测量方法研究[D].合肥工业大学硕士学位论,2005.
[13] M.S.Lew, N.Sebe,J.P.Eakins. Content Based Analysis for Video from Snooker Broadcasts. Image and Video Retrieval: International Conference. CIVR 2002,London,UK,July 18-19,2002.Proceedings:198-205.
[14] A.Ekin, A.M.Tekalp. Shot type classification by dominant color for sports video segmentation and summarization.Acoustics, Speech,and Signal Processing, 2003.Proceedings.(ICASSP'03).2003 IEEE International Conference on,April 2003. vol.3:73-176.
[15] Ohno Y,Miura J,Shirai Y. Tracking players and estimation of the 3Dposition of a ball in soccer games.Pattern Recognition,2000.Proceedings.15thInternational Conference on,Volume 1,3-7 Sept.2000:145-148 vol.1.
[16] Chen Jianyun,Li Yunhao,Lao Songyang,Wu Lingda. A BSU-based sportsvideo content analysis framework for content0based streams filtering.ComputerNetworksand Mobile Computing, 2003 InternationalConference on,20-23 Oct.2003:446-449.
[17] Tong Lin,Chong-Wah Ngo,Hong-Jiang Zhang,Qing-Yun Shi. Integratingcolor and spatial features for content-based video retrieval.Image Processing, 2001. Proceedings. 2001 International Conference on,7-10 Oct.2001 Vol.3:592-595.
[18] G.S.Pingali,Y.Jean,and I.Carlbom. Real time tracking for enhanced tennis broadcasts. Proc.IEEE Comp.Vision Patt.Rec.(CVPR),1998:260-265.
[19]Leonardi,R,Migliorati,P.,Prandini,M..Semantic indexing of soccer audio-visual sequences: a multimodal approach based on controlled Markov chains.Circuits and Systems for Video Technology,IEEE Transactions on Vol. 14(5),May 2004 Page(s):634-643.
[20]S.Intille,A.Bobick.Recognizing planned,multi-person action.Comput.Vis. Image Understand,vol.81,no.3,Mar.2001:414-445.
[21]Y.Rui,A.Gupta,A.Acero.Automatically Extracting Highlights for TV Baseball Programs.In Proc.of ACM Multimedia,2000:105-115.
[22] D.Q.Zhang,R.Raj,S.F.Chang.General and Domain-specific Techniques for Detecting and Recognizing Superimposed Text in Video.In Proc.of IEEE International Conference on Image Processing,2002.
[23]周平,王从军,陈鑫.计算机单目视觉测量系统.光电工程[J].2005年12月.vol 32 ,12,P90~91.
[24] Wang J.,Cohen P,Herniou M.Camera calibration with distortion models end accuracy evaluation . IEEE Transaction on Pattern analysis and Machine intelligence.1992.14(10):965～980
[25] Hartley R. Estimation of relative camera positions for uncalibrated cameras. In: Proc European Conference on Computer Vision, NLCS 588, Springer-Verlag, 1992. 579-387.
[26]Faugeras O D. What can be seen in three dimensions with an uncalibrated stereo rig. In: Proc European Conference on Computer Vision, NLCS 588, Springer-Verlag, 1992. 563-578 .
[27]吕强.基于特征点提取的单目视觉里程计的研究.浙江大学硕士论文.20070501.
[28]刘长英高印寒车仁生.单目视觉测量系统不确定度的分析[J].机械工程学报.2008.第44卷第7期,75-78
[29] Rocchini,Cignoni P,Montani M.A Low Cost 3D Scanner Based on Structured Light[J].EG 2001 Proc.2001,20(3),299-308
[30] Juergen Peipe,Peter Andrae.Optical 3D Coordinate Measurement using a Range Sensor and Photogrammetry.Proceeding of Videometrics VII,Santa Clara,CA,USA,2003[J]. Proceedings SPIE.2003,5013:110-116
[31]章毓晋.图像分割[M],北京:科学出版社.2001,2.
[32]张勇.远程视频监控系统的传输技术的实现[M].电子科技大学.2004
[33]蒋先刚.基于Delphi的数字图像处理工程软件设计[M ].北京:中国水利水电出版社, 2006.
[34]韩思奇,王蕾图像分割的阈值法综述(J),系统工程与电子技术.2000,6(24):91-102。
[35]章毓晋.图像工程(上册)--图像处理与分析[M]。北京:清华大学出版社, 1999,3.
[36] N.Otsu. A threshold seleetion method from gray-level histograms[J], IEEE TransSystem, Man and CybernetieS,1979,9(l):62-66.
[37]何斌等,Visual C++数字图像处理,北京:人民邮电出版社,2001.4.
[38] N.Otsu.A Threshold Selection Method from Gray-Level Histograms[J].IEEE Transactions on Systems,Man and Cybemetics, 1979,9(1):62---66.
[39] SteveTeixeira, Xavier Pacheco. Delphi 5开发人员指南[M ].北京:机械工业出版社, 2000.
[40]苏小华,赵继广,张慧星.CCD摄像机成像畸变的研究.物理实验[J].第23卷第9期,39-41.
[41] Bertalmio,M,Sapiro,G,Randall,G.Region tracking on level-set meth-ods. IEEE Transactions on Medical Imaging, 1999,18(5):448~451.
[42]林瑶,田捷.医学图像分割方法综述.模式识别与人工智能[J], 2002,(6):192~204.
[2]章毓晋.图像工程下册[M].北京.清华大学出版社,2000.
[3]包锋张大林摄像与计算机辨析终点裁判管理系统的研制[J].北京体育大学学报2004,36(12).
[4] Criminisi A. Accurate visual metrology from single and multiple uncalibrated mages-distinguished dissertations[J].Springer Verlag Press,2001
[5] Criminisi A;Reid I;Zisserman A. A plane measuring device[J].Image and Vision Computing,,vol.17(8), 625-634,1999
[6] G.H.Wang, Z.Y.Hu and F.C.Wu. Single view based measurement on space planes[J].Journalof Computer Science and Technology.Vol.19(3),2004.
[7]G.H.Wang, Y.H.Wu and Z.Y.Hu. A novel approach for single view Based planemetrology[J]. In Proc. of the 16th International Conference on Patern Recognition, vol.2,556-559,2002.
[8]D Liebowitz and A Zisserman.Metric rectification for perspective images of planes[J].Proc.of CVPR,pp:482-488,Jun.2003.
[9] Kanade T. A stereo matching algorithm with an adaptive window:Theory and Experiment [J] .IEEE Trans.on Pattern Analysis and Machine Intelligence, 2004, 16(9), 920-932.
[10]黄凤山.光笔式单摄像机三维坐标视觉测量系统关键技术的研究[D].天津大学博士学位论文,2005.
[11]马国松.基于单目视觉的位姿测量方法及仿真系统研究[D].哈尔滨工业大学硕士学位论文,2005.
[12]赵锐.基于单目视觉的物体位姿测量方法研究[D].合肥工业大学硕士学位论,2005.
[13] M.S.Lew, N.Sebe,J.P.Eakins. Content Based Analysis for Video from Snooker Broadcasts. Image and Video Retrieval: International Conference. CIVR 2002,London,UK,July 18-19,2002.Proceedings:198-205.
[14] A.Ekin, A.M.Tekalp. Shot type classification by dominant color for sports video segmentation and summarization.Acoustics, Speech,and Signal Processing, 2003.Proceedings.(ICASSP'03).2003 IEEE International Conference on,April 2003. vol.3:73-176.
[15] Ohno Y,Miura J,Shirai Y. Tracking players and estimation of the 3Dposition of a ball in soccer games.Pattern Recognition,2000.Proceedings.15thInternational Conference on,Volume 1,3-7 Sept.2000:145-148 vol.1.
[16] Chen Jianyun,Li Yunhao,Lao Songyang,Wu Lingda. A BSU-based sportsvideo content analysis framework for content0based streams filtering.ComputerNetworksand Mobile Computing, 2003 InternationalConference on,20-23 Oct.2003:446-449.
[17] Tong Lin,Chong-Wah Ngo,Hong-Jiang Zhang,Qing-Yun Shi. Integratingcolor and spatial features for content-based video retrieval.Image Processing, 2001. Proceedings. 2001 International Conference on,7-10 Oct.2001 Vol.3:592-595.
[18] G.S.Pingali,Y.Jean,and I.Carlbom. Real time tracking for enhanced tennis broadcasts. Proc.IEEE Comp.Vision Patt.Rec.(CVPR),1998:260-265.
[19]Leonardi,R,Migliorati,P.,Prandini,M..Semantic indexing of soccer audio-visual sequences: a multimodal approach based on controlled Markov chains.Circuits and Systems for Video Technology,IEEE Transactions on Vol. 14(5),May 2004 Page(s):634-643.
[20]S.Intille,A.Bobick.Recognizing planned,multi-person action.Comput.Vis. Image Understand,vol.81,no.3,Mar.2001:414-445.
[21]Y.Rui,A.Gupta,A.Acero.Automatically Extracting Highlights for TV Baseball Programs.In Proc.of ACM Multimedia,2000:105-115.
[22] D.Q.Zhang,R.Raj,S.F.Chang.General and Domain-specific Techniques for Detecting and Recognizing Superimposed Text in Video.In Proc.of IEEE International Conference on Image Processing,2002.
[23]周平,王从军,陈鑫.计算机单目视觉测量系统.光电工程[J].2005年12月.vol 32 ,12,P90~91.
[24] Wang J.,Cohen P,Herniou M.Camera calibration with distortion models end accuracy evaluation . IEEE Transaction on Pattern analysis and Machine intelligence.1992.14(10):965～980
[25] Hartley R. Estimation of relative camera positions for uncalibrated cameras. In: Proc European Conference on Computer Vision, NLCS 588, Springer-Verlag, 1992. 579-387.
[26]Faugeras O D. What can be seen in three dimensions with an uncalibrated stereo rig. In: Proc European Conference on Computer Vision, NLCS 588, Springer-Verlag, 1992. 563-578 .
[27]吕强.基于特征点提取的单目视觉里程计的研究.浙江大学硕士论文.20070501.
[28]刘长英高印寒车仁生.单目视觉测量系统不确定度的分析[J].机械工程学报.2008.第44卷第7期,75-78
[29] Rocchini,Cignoni P,Montani M.A Low Cost 3D Scanner Based on Structured Light[J].EG 2001 Proc.2001,20(3),299-308
[30] Juergen Peipe,Peter Andrae.Optical 3D Coordinate Measurement using a Range Sensor and Photogrammetry.Proceeding of Videometrics VII,Santa Clara,CA,USA,2003[J]. Proceedings SPIE.2003,5013:110-116
[31]章毓晋.图像分割[M],北京:科学出版社.2001,2.
[32]张勇.远程视频监控系统的传输技术的实现[M].电子科技大学.2004
[33]蒋先刚.基于Delphi的数字图像处理工程软件设计[M ].北京:中国水利水电出版社, 2006.
[34]韩思奇,王蕾图像分割的阈值法综述(J),系统工程与电子技术.2000,6(24):91-102。
[35]章毓晋.图像工程(上册)--图像处理与分析[M]。北京:清华大学出版社, 1999,3.
[36] N.Otsu. A threshold seleetion method from gray-level histograms[J], IEEE TransSystem, Man and CybernetieS,1979,9(l):62-66.
[37]何斌等,Visual C++数字图像处理,北京:人民邮电出版社,2001.4.
[38] N.Otsu.A Threshold Selection Method from Gray-Level Histograms[J].IEEE Transactions on Systems,Man and Cybemetics, 1979,9(1):62---66.
[39] SteveTeixeira, Xavier Pacheco. Delphi 5开发人员指南[M ].北京:机械工业出版社, 2000.
[40]苏小华,赵继广,张慧星.CCD摄像机成像畸变的研究.物理实验[J].第23卷第9期,39-41.
[41] Bertalmio,M,Sapiro,G,Randall,G.Region tracking on level-set meth-ods. IEEE Transactions on Medical Imaging, 1999,18(5):448~451.
[42]林瑶,田捷.医学图像分割方法综述.模式识别与人工智能[J], 2002,(6):192~204.