基于视觉手势识别的人—机器人交互系统研究
|
摘要
随着社会的进步和科学技术的快速发展,机器人技术的应用越来越广泛,在众多的科学领域、工业部门和家庭生活中发挥着重要的作用,而人与机器人需要交互的场景也越来越多,为了提高机器人与人的交互性和协作性,需要对人—机器人交互系统进行研究。在当前的研究中,基于视觉的手势识别因为摄像机的低廉成本和手势的直观性,通用性和强大语义使得其在人机交互研究中具有强大的潜力。
在目前的基于视觉的手势识别研究中,依靠肤色信息来建立模型进而识别手势是较为高效实用的方法,但是由于计算机处理数字摄像机采集到的肤色信息极易受到光照和背景变化的影响,现有的手势识别系统大多在室内固定环境下才能取得理想的识别效果,而在移动的复杂环境下不具有工作能力。针对这一问题,本文主要研究用于移动机器人的基于肤色的手势识别系统,研究的重点集中在肤色模型的建立,复杂环境下的肤色分类和模型的自适应问题。
本文在建立单高斯肤色模型的基础上,提出了一种基于前景加权直方图的动态阈值调整算法,该算法通过肤色模型得到肤色概率图后,在目标区域被识别的前提下,对目标区域的像素的概率建立加权直方图,通过分析该直方图调整肤色分类阈值,在一定程度上解决光照变化对肤色的影响问题。
针对模型对光照和背景变化的自适应问题,文章提出了静态单高斯模型与动态直方图方法结合的自适应算法,该算法以阈值调整和肤色分割结果为依据,在满足一定条件的情况下通过建立前景与背景直方图对单高斯模型进行调整,具有很好的实时性,同时对光照和背景的变化有很好的适应性。
文章最终将人手分割,轨迹跟踪,模型调整,手势分析等手势识别的关键环节串联起来,建立起一个可用于移动智能机器人人机交互中的手势识别系统,实验结果表明该系统准确高效,具有实用价值,并且实验方法具有通用性,可被扩展到各种手势识别交互系统中。
With the fast development of technology, robot has been broadly applied, and has played an important role in many scientific fields as well as some industrial sections and family sections, so human need to interact with robots more. In order to improve the interaction and collaboration between human and robot, Human—Robot Interactive System should be researched. In the current study, vision based hand gesture recognition has strong potential because of its intuitivism, versatileness, powerful semantic and camera’s low cost.
In current research on vision based hand gesture recognition, building skin model to recognize hand gesture is an efficient method. However, skin information captured from digital camera can be effected by lighting condition and background varying. Most current hand gesture recognition systems get good result under indoor and static environment but not mobile complex environment. In order to solve this problem, this paper mainly research hand recognition system based on skin for mobile robots. It focuses on building skin model, skin classification under complicated environment and the adaptability of skin model.
After building a Single Gaussian Skin Model, we propose a dynamic threshold adjust algorithm based on foreground weighted histogram. The algorithm gets skin probability through Gaussian Model and segments object area, then builds weighted histogram of the area. According to analyzing the histogram, the threshold can be adjusted, which to some extent solves light condition varying problem.
This paper proposes an adaptive model algorithm which combines static single Gaussian model and dynamic histogram model for solving lighting and background problem. According to the result of threshold adjusting and image segmentation, the algorithm adjusts the single Gaussian model through building foreground and background histogram. This method is fast and can adapt to lighting and background varying.
We finally integrate hand segmentation, trajectory tracking, model adjustment and gesture analyzing into a gesture recognition system for human—robot interaction. Experiment results show that the system is accurate and efficient. And the method is general and extendable, can be used in other hand gesture recognition interaction system.
在目前的基于视觉的手势识别研究中,依靠肤色信息来建立模型进而识别手势是较为高效实用的方法,但是由于计算机处理数字摄像机采集到的肤色信息极易受到光照和背景变化的影响,现有的手势识别系统大多在室内固定环境下才能取得理想的识别效果,而在移动的复杂环境下不具有工作能力。针对这一问题,本文主要研究用于移动机器人的基于肤色的手势识别系统,研究的重点集中在肤色模型的建立,复杂环境下的肤色分类和模型的自适应问题。
本文在建立单高斯肤色模型的基础上,提出了一种基于前景加权直方图的动态阈值调整算法,该算法通过肤色模型得到肤色概率图后,在目标区域被识别的前提下,对目标区域的像素的概率建立加权直方图,通过分析该直方图调整肤色分类阈值,在一定程度上解决光照变化对肤色的影响问题。
针对模型对光照和背景变化的自适应问题,文章提出了静态单高斯模型与动态直方图方法结合的自适应算法,该算法以阈值调整和肤色分割结果为依据,在满足一定条件的情况下通过建立前景与背景直方图对单高斯模型进行调整,具有很好的实时性,同时对光照和背景的变化有很好的适应性。
文章最终将人手分割,轨迹跟踪,模型调整,手势分析等手势识别的关键环节串联起来,建立起一个可用于移动智能机器人人机交互中的手势识别系统,实验结果表明该系统准确高效,具有实用价值,并且实验方法具有通用性,可被扩展到各种手势识别交互系统中。
With the fast development of technology, robot has been broadly applied, and has played an important role in many scientific fields as well as some industrial sections and family sections, so human need to interact with robots more. In order to improve the interaction and collaboration between human and robot, Human—Robot Interactive System should be researched. In the current study, vision based hand gesture recognition has strong potential because of its intuitivism, versatileness, powerful semantic and camera’s low cost.
In current research on vision based hand gesture recognition, building skin model to recognize hand gesture is an efficient method. However, skin information captured from digital camera can be effected by lighting condition and background varying. Most current hand gesture recognition systems get good result under indoor and static environment but not mobile complex environment. In order to solve this problem, this paper mainly research hand recognition system based on skin for mobile robots. It focuses on building skin model, skin classification under complicated environment and the adaptability of skin model.
After building a Single Gaussian Skin Model, we propose a dynamic threshold adjust algorithm based on foreground weighted histogram. The algorithm gets skin probability through Gaussian Model and segments object area, then builds weighted histogram of the area. According to analyzing the histogram, the threshold can be adjusted, which to some extent solves light condition varying problem.
This paper proposes an adaptive model algorithm which combines static single Gaussian model and dynamic histogram model for solving lighting and background problem. According to the result of threshold adjusting and image segmentation, the algorithm adjusts the single Gaussian model through building foreground and background histogram. This method is fast and can adapt to lighting and background varying.
We finally integrate hand segmentation, trajectory tracking, model adjustment and gesture analyzing into a gesture recognition system for human—robot interaction. Experiment results show that the system is accurate and efficient. And the method is general and extendable, can be used in other hand gesture recognition interaction system.
引文
[1] Starner T, Pentland A. Real-time American Sign Language recognition from video using hidden Markov models[A]. International Symposium on Computer Vision[C]. 1995. 265～270.
[2]张秋余,姚开博,吴佩莉.基于矩形特征和改进Adaboost的手势检测[J].计算机工程, 2008, 34(14): 176～178.
[3] Huang C L, Huang W Y. Sign language recognition using model-based tracking and a 3D Hopfield neural network[J]. Machine Vision and Applications, 1998, 10(5): 292～307.
[4]刘志明.基于动态手势识别的人机交互技术研究[D].杭州:浙江大学电气工程学院, 2007.
[5]任海兵,祝远新,徐光 , et al.基于视觉手势识别的研究—综述[J].电子学报, 2000, (02).
[6]吕颖.基于摄像头的手势交互系统的研究[D].青岛:青岛大学, 2009.
[7]李清水,方志刚等.手势识别技术及其在人机交互中的应用[J].人类工效学,2002,80.
[8] I.Kass M,Witkin A P,TerzopoulosD.Snakes:active contour models[J].Int J Computer Vis,1988.1:321—331.
[9]丁海洋,阮秋琦.多尺度模型与矩描绘子相结合的手势识别算法[J].北京交通大学学报,2004.
[10] Sung K K, Mi Y N, Phill K R. Color Based Hand and Finger Detection Technology for User Interaction[A]. International Conference on Convergence and Hybrid Information Technology[C]. 2008. 229～236.
[11] Ying W, Huang T S. Human hand modeling, analysis and animation in the context of HCI[A]. International Conference on Image Processing[C]. 1999. 6～103.
[12] J. Lee, T. L. Kunii, "Model-based analysis of hand posture," IEEE Computer Graphics and Applications, v15, 77-86, 1995.
[13] Y. Okada, "3D model matching based on silhouette image matching," Recent Advances in Circuits, Systems and Signal Processing, 380-385, 2002.
[14] T. J. Darrell, I. A. Essa, A. P. Pentland, "Task-specific gesture analysis in real-time using interpolated views," IEEE Transactions on Pattern Analysis and Machine Intelligence, v18,1236-1242, 1996.
[15] S. Kumar, D. K. Kumar, A. Sharma, "Sensitivity analysis of hand movement classification technique using motion templates," Proc. 14th IEEE Workshop on Machine Learning for Signal Processing, 491-498, 2004.
[16] Kakumanu P, Makrogiannis S, Bourbakis N. A survey of skin-color modeling and detection methods[J]. Pattern Recognition, 2007, 40(3): 1106～1122.
[17] Hsu R L, Abdel-Mottaleb M, Jain A K. Face detection in color images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 696～706.
[18] Duan-sheng C, Zheng-kai L. A novel approach to detect and correct highlighted face region in color image[A]. 2003. 7～12.
[19] Browning B, Veloso M. Real-time, adaptive color-based robot vision[A]. 2005. 3871～3876.
[20] Yang J, Lu W, Waibel A, Skin-color modeling and adaptation. In Lecture Notes in Computer Science, Chin R, Pong T C, ''Eds.' ; Springer Berlin / Heidelberg: 1997; 'Vol.' 1352, p 687～694.
[21] Yang J, Waibel A. A real-time face tracker[A]. 1996. 142～147.
[22] Tsapatsoulis N, Kollias S. Face detection in color images and video sequences[A]. 2000. 498～502.
[23] Sigal L, Sclaroff S, Athitsos V. Estimation and prediction of evolving color distributions for skin segmentation under varying illumination[A]. 2000. 152～159.
[24] Soriano M, Martinkauppi B, Huovinen S, et al. Skin detection in video under changing illumination conditions[A]. 2000. 839～842.
[25] Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition[J]. IEEE Transactions on Information Theory, 1975, 21(1): 32～40.
[26] Yizong C. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790～799.
[27]孙玉.基于计算机视觉的手势跟踪与识别算法研究[D].青岛:青岛科技大学, 2009.
[28]刘闯.基于特征融合和Mean Shift的多目标跟踪方法研究[D].苏州:苏州大学, 2009.
[29]李鹏飞.基于Mean Shift的目标跟踪算法研究[D].西安:西安电子科技大学, 2009.
[30]查宇飞,毕笃彦.一种基于粒子滤波的自适应运动目标跟踪方法[J].电子与信息学报, 2007, (01):.
[31]李涛.基于Mean Shift算法和Particle Filter算法的目标跟踪[D].南京:南京理工大学,2007.
[32] Sugandi B, Kim H, Tan J, et al. A moving object tracking based on color information employing a particle filter algorithm[J]. Artificial Life and Robotics, 2009, 14(1): 39～42.
[33] Sugandi B, Kim H, Tan J, et al. A color-based particle filter for multiple object tracking in an outdoor environment[J]. Artificial Life and Robotics, 2010, 15(1): 41～47.
[34] Shan C, Tan T, Wei Y. Real-time hand tracking using a mean shift embedded particle filter[J]. Pattern Recognition, 2007, 40(7): 1958～1970.
[35]刘长明,任一峰.语音识别中DTW特征匹配的改进算法研究[J].中北大学学报:自然科学版, 2006, 27(1): 37～40.
[36] Byung-Woo M, Ho-Sub Y, Jung S, et al. Hand gesture recognition using hidden Markov models[A]. IEEE International Conference on Systems, Man, and Cybernetics, 1997. 'Computational Cybernetics and Simulation'.,.[C] 1997. 4232～4235.
[37]徐战武.静态图象肤色检测研究[D].杭州:浙江大学, 2006.
[38]苏奕霖,移动机器人视觉系统的研究与实现[D].广州:华南理工大学,2004.
[39]汤思维.移动机器人实时彩色视觉系统[D].上海:上海交通大学, 2003.
[40] R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, Wiley InterScience, New York, 2002.
[41] Gu L, Bone D. Skin colour region detection in MPEG video sequences[A]. 1999. 898～903.
[42] M.H. Yang, N. Ahuja, Gaussian Mixture model for human skin color and its application in image and video databases, Proceedings of SPIE: Conference on Storage and Retrieval for Image and Video Databases, vol. 3656, 1999, pp. 458–466.
[43] Hao-kui T, Zhi-quan F. Hand's Skin Detection Based on Ellipse Clustering[A]. International Symposium on Computer Science and Computational Technology[C]. 2008. 758～761.
[44]王航宇.基于YCbCr高斯肤色模型的人脸检测技术研究[J].现代电子技术, 2008, (22):.
[45]蒙丰博,张新荣,李雪威.一种新的基于颜色恒常性的肤色分割算法[J].计算机工程与应用, 2007, (17):.
[46] Soriano M, Martinkauppi B, Huovinen S, et al. Adaptive skin color modeling using the skin locus for selecting training pixels[J]. Pattern Recognition, 2003, 36(3): 681～690.
[47] Lim W H, Wong F, Chekima A. Comparison of hand segmentation methodologies for Hand gesture recognition[A]. International Symposium on Information Technology[C]. 2008. 1～7.
[48]刘俊梅.基于视觉的手势识别技术研究[D].北京:北京交通大学, 2006.
[49]马颂德,张正友,计算机视觉—计算理论与算法基础[M],北京,科学出版社,1998.1
[50]朱胜利. Mean Shift及相关算法在视频跟踪中的研究[D].杭州:浙江大学, 2006.
[51] Chai D, Ngan K N. Face segmentation using skin-color map in videophone applications[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999, 9(4): 551～564.
[52] Ruiz-del-Solar J, Verschae R. Skin detection using neighborhood information[A]. Sixth IEEE International Conference on Automatic Face and Gesture Recognition[C].2004. 463～468.
[53] Phung S L, Chai D, Bouzerdoum A. A universal and robust human skin color model using neural networks[A]. International Joint Conference on Neural Networks[C].2001. 2844～284.
[54]冯元戬,施鹏飞.基于支持向量机的彩色图像人脸检测方法[J].上海交通大学学报, 2003, 37(6): 947～950.
[55]陈峰,朱淼良,王东辉.基于多特征的综合皮肤检测方法[J].计算机工程与设计, 2003, 24(11): 4～7.
[56] Chaves-Gonz J M, Vega-Rodr M A, G P J, et al. Detecting skin in face recognition systems: A colour spaces study[J]. Digital Signal Processing, 2010, 20(3): 806～823. Sigal L, Sclaroff S, Athitsos V. Skin color-based video segmentation under time-varying illumination[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2004, 26(7): 862～877.
[57] Dempster A P, Laird N M, Rubin D B. Maximum likelihood from incomplete data via the EM algorithm[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY, SERIES B, 1977, 39(1): 1--38.
[58] http://eom.springer.de/E/e120120.htm
[59] http://baike.baidu.com/view/1541707.html
[60] Sigal L, Sclaroff S, Athitsos V. Skin color-based video segmentation under time-varying illumination[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(7): 862～877.
[2]张秋余,姚开博,吴佩莉.基于矩形特征和改进Adaboost的手势检测[J].计算机工程, 2008, 34(14): 176～178.
[3] Huang C L, Huang W Y. Sign language recognition using model-based tracking and a 3D Hopfield neural network[J]. Machine Vision and Applications, 1998, 10(5): 292～307.
[4]刘志明.基于动态手势识别的人机交互技术研究[D].杭州:浙江大学电气工程学院, 2007.
[5]任海兵,祝远新,徐光 , et al.基于视觉手势识别的研究—综述[J].电子学报, 2000, (02).
[6]吕颖.基于摄像头的手势交互系统的研究[D].青岛:青岛大学, 2009.
[7]李清水,方志刚等.手势识别技术及其在人机交互中的应用[J].人类工效学,2002,80.
[8] I.Kass M,Witkin A P,TerzopoulosD.Snakes:active contour models[J].Int J Computer Vis,1988.1:321—331.
[9]丁海洋,阮秋琦.多尺度模型与矩描绘子相结合的手势识别算法[J].北京交通大学学报,2004.
[10] Sung K K, Mi Y N, Phill K R. Color Based Hand and Finger Detection Technology for User Interaction[A]. International Conference on Convergence and Hybrid Information Technology[C]. 2008. 229～236.
[11] Ying W, Huang T S. Human hand modeling, analysis and animation in the context of HCI[A]. International Conference on Image Processing[C]. 1999. 6～103.
[12] J. Lee, T. L. Kunii, "Model-based analysis of hand posture," IEEE Computer Graphics and Applications, v15, 77-86, 1995.
[13] Y. Okada, "3D model matching based on silhouette image matching," Recent Advances in Circuits, Systems and Signal Processing, 380-385, 2002.
[14] T. J. Darrell, I. A. Essa, A. P. Pentland, "Task-specific gesture analysis in real-time using interpolated views," IEEE Transactions on Pattern Analysis and Machine Intelligence, v18,1236-1242, 1996.
[15] S. Kumar, D. K. Kumar, A. Sharma, "Sensitivity analysis of hand movement classification technique using motion templates," Proc. 14th IEEE Workshop on Machine Learning for Signal Processing, 491-498, 2004.
[16] Kakumanu P, Makrogiannis S, Bourbakis N. A survey of skin-color modeling and detection methods[J]. Pattern Recognition, 2007, 40(3): 1106～1122.
[17] Hsu R L, Abdel-Mottaleb M, Jain A K. Face detection in color images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 696～706.
[18] Duan-sheng C, Zheng-kai L. A novel approach to detect and correct highlighted face region in color image[A]. 2003. 7～12.
[19] Browning B, Veloso M. Real-time, adaptive color-based robot vision[A]. 2005. 3871～3876.
[20] Yang J, Lu W, Waibel A, Skin-color modeling and adaptation. In Lecture Notes in Computer Science, Chin R, Pong T C, ''Eds.' ; Springer Berlin / Heidelberg: 1997; 'Vol.' 1352, p 687～694.
[21] Yang J, Waibel A. A real-time face tracker[A]. 1996. 142～147.
[22] Tsapatsoulis N, Kollias S. Face detection in color images and video sequences[A]. 2000. 498～502.
[23] Sigal L, Sclaroff S, Athitsos V. Estimation and prediction of evolving color distributions for skin segmentation under varying illumination[A]. 2000. 152～159.
[24] Soriano M, Martinkauppi B, Huovinen S, et al. Skin detection in video under changing illumination conditions[A]. 2000. 839～842.
[25] Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition[J]. IEEE Transactions on Information Theory, 1975, 21(1): 32～40.
[26] Yizong C. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790～799.
[27]孙玉.基于计算机视觉的手势跟踪与识别算法研究[D].青岛:青岛科技大学, 2009.
[28]刘闯.基于特征融合和Mean Shift的多目标跟踪方法研究[D].苏州:苏州大学, 2009.
[29]李鹏飞.基于Mean Shift的目标跟踪算法研究[D].西安:西安电子科技大学, 2009.
[30]查宇飞,毕笃彦.一种基于粒子滤波的自适应运动目标跟踪方法[J].电子与信息学报, 2007, (01):.
[31]李涛.基于Mean Shift算法和Particle Filter算法的目标跟踪[D].南京:南京理工大学,2007.
[32] Sugandi B, Kim H, Tan J, et al. A moving object tracking based on color information employing a particle filter algorithm[J]. Artificial Life and Robotics, 2009, 14(1): 39～42.
[33] Sugandi B, Kim H, Tan J, et al. A color-based particle filter for multiple object tracking in an outdoor environment[J]. Artificial Life and Robotics, 2010, 15(1): 41～47.
[34] Shan C, Tan T, Wei Y. Real-time hand tracking using a mean shift embedded particle filter[J]. Pattern Recognition, 2007, 40(7): 1958～1970.
[35]刘长明,任一峰.语音识别中DTW特征匹配的改进算法研究[J].中北大学学报:自然科学版, 2006, 27(1): 37～40.
[36] Byung-Woo M, Ho-Sub Y, Jung S, et al. Hand gesture recognition using hidden Markov models[A]. IEEE International Conference on Systems, Man, and Cybernetics, 1997. 'Computational Cybernetics and Simulation'.,.[C] 1997. 4232～4235.
[37]徐战武.静态图象肤色检测研究[D].杭州:浙江大学, 2006.
[38]苏奕霖,移动机器人视觉系统的研究与实现[D].广州:华南理工大学,2004.
[39]汤思维.移动机器人实时彩色视觉系统[D].上海:上海交通大学, 2003.
[40] R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, Wiley InterScience, New York, 2002.
[41] Gu L, Bone D. Skin colour region detection in MPEG video sequences[A]. 1999. 898～903.
[42] M.H. Yang, N. Ahuja, Gaussian Mixture model for human skin color and its application in image and video databases, Proceedings of SPIE: Conference on Storage and Retrieval for Image and Video Databases, vol. 3656, 1999, pp. 458–466.
[43] Hao-kui T, Zhi-quan F. Hand's Skin Detection Based on Ellipse Clustering[A]. International Symposium on Computer Science and Computational Technology[C]. 2008. 758～761.
[44]王航宇.基于YCbCr高斯肤色模型的人脸检测技术研究[J].现代电子技术, 2008, (22):.
[45]蒙丰博,张新荣,李雪威.一种新的基于颜色恒常性的肤色分割算法[J].计算机工程与应用, 2007, (17):.
[46] Soriano M, Martinkauppi B, Huovinen S, et al. Adaptive skin color modeling using the skin locus for selecting training pixels[J]. Pattern Recognition, 2003, 36(3): 681～690.
[47] Lim W H, Wong F, Chekima A. Comparison of hand segmentation methodologies for Hand gesture recognition[A]. International Symposium on Information Technology[C]. 2008. 1～7.
[48]刘俊梅.基于视觉的手势识别技术研究[D].北京:北京交通大学, 2006.
[49]马颂德,张正友,计算机视觉—计算理论与算法基础[M],北京,科学出版社,1998.1
[50]朱胜利. Mean Shift及相关算法在视频跟踪中的研究[D].杭州:浙江大学, 2006.
[51] Chai D, Ngan K N. Face segmentation using skin-color map in videophone applications[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999, 9(4): 551～564.
[52] Ruiz-del-Solar J, Verschae R. Skin detection using neighborhood information[A]. Sixth IEEE International Conference on Automatic Face and Gesture Recognition[C].2004. 463～468.
[53] Phung S L, Chai D, Bouzerdoum A. A universal and robust human skin color model using neural networks[A]. International Joint Conference on Neural Networks[C].2001. 2844～284.
[54]冯元戬,施鹏飞.基于支持向量机的彩色图像人脸检测方法[J].上海交通大学学报, 2003, 37(6): 947～950.
[55]陈峰,朱淼良,王东辉.基于多特征的综合皮肤检测方法[J].计算机工程与设计, 2003, 24(11): 4～7.
[56] Chaves-Gonz J M, Vega-Rodr M A, G P J, et al. Detecting skin in face recognition systems: A colour spaces study[J]. Digital Signal Processing, 2010, 20(3): 806～823. Sigal L, Sclaroff S, Athitsos V. Skin color-based video segmentation under time-varying illumination[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2004, 26(7): 862～877.
[57] Dempster A P, Laird N M, Rubin D B. Maximum likelihood from incomplete data via the EM algorithm[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY, SERIES B, 1977, 39(1): 1--38.
[58] http://eom.springer.de/E/e120120.htm
[59] http://baike.baidu.com/view/1541707.html
[60] Sigal L, Sclaroff S, Athitsos V. Skin color-based video segmentation under time-varying illumination[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(7): 862～877.