实时视频流中人脸检测关键技术的研究
|
摘要
随着计算机科学的飞速发展,计算机相关领域的应用已经深入到人们生活的各个方面,并起着十分巨大的作用。其中,人工智能与模式识别是计算机科学研究中比较前沿的研究课题,是计算机智能化的基础。让计算机拥有人类的视觉辨识能力一直都是人工智能领域的一个重要课题,也是人工智能领域中使计算机认识世界的第一步。
本文主要研究实时视频流中的人脸检测技术。在人脸检测的研究方面,主要侧重于在视频流中人脸检测算法的实时性问题。针对现有人脸检测方法存在的问题及人脸检测技术的主要难点,结合目前人脸检测领域的实际应用情况,提出了一种适合应用于视频流中的人脸检测方法。具体工作如下:
(1)实时视频流与静态图像人脸检测的不同在于前者含有运动信息。针对视频流的这个特点,研究几种主要的运动目标分割的方法,针对背景差分法对于光线干扰较大的缺点,提出一种新的参考背景生成方法来进行目标分割,并设计可以实时更新参考背景的算法。
(2)通过对图像分割时使用不同阈值产生不同分割效果的分析,提出一种新的自适应阈值的分割方法来进行运动目标分割。
(3)针对肤色在YCrCb色彩空间下的聚类特性,对在该空间下的简单区域模型和高斯分布模型进行了研究,提出区域阈值与简单高斯模型相结合的肤色建模方法,并在分割时使用最优阈值的方法使分割的效果达到最佳。
(4)利用分割肤色后的轮廓,使用最小二乘法进行椭圆拟合来精确定位出人脸在视频流中存在的位置,并进行筛选和验证。
With the development of computer science and technology, the computer applications have entered into every aspect of human life, and play a very important role. In which, artificial intelligence is very hot research field, and also the foundation of the artificial computer. It is always a very important subject in the research of artificial intelligence that the computer can recognize the object as a man, and it is also the first step the computer understanding the world.
This paper focuses on face detection technology in real-time videos. The research of face detection focuses on real-time problem in videos. Aiming at the existing disadvantages of face detection method and the main difficulties of face detection technologies, combination of application of face detection, a method for face detection in real-time videos is proposed. Specific tasks are as follows:
(1) The difference of face detection between real-time videos and static image is the former with motion information. Aiming at the characteristic of real-time videos, this paper studies on several major methods of moving object segmentation. Against the disadvantage which is quite sensitive to light in the background subtraction method, the paper has put forward a new method on generation of reference background and algorithm of real-time updating reference background.
(2) When image segmentation, through the analysis of different segmentation result with the use of different thresholds, a new adaptive threshold segmentation approach to segmentation of moving object is put forward.
(3) Aiming at the cluster characteristics of face color in the YCrCb color space, this paper studies on simple regional model and Gaussian distribution model in this color space, and put forward a color modeling method which is combination of regional threshold and Gaussian distribution model, and then segment the skin color with the optimal threshold to make the result best.
(4) Based on the contour after skin color segmentation, the position of face in video streaming is accurately located by ellipse fitting least squares method, and then selected and identified.
本文主要研究实时视频流中的人脸检测技术。在人脸检测的研究方面,主要侧重于在视频流中人脸检测算法的实时性问题。针对现有人脸检测方法存在的问题及人脸检测技术的主要难点,结合目前人脸检测领域的实际应用情况,提出了一种适合应用于视频流中的人脸检测方法。具体工作如下:
(1)实时视频流与静态图像人脸检测的不同在于前者含有运动信息。针对视频流的这个特点,研究几种主要的运动目标分割的方法,针对背景差分法对于光线干扰较大的缺点,提出一种新的参考背景生成方法来进行目标分割,并设计可以实时更新参考背景的算法。
(2)通过对图像分割时使用不同阈值产生不同分割效果的分析,提出一种新的自适应阈值的分割方法来进行运动目标分割。
(3)针对肤色在YCrCb色彩空间下的聚类特性,对在该空间下的简单区域模型和高斯分布模型进行了研究,提出区域阈值与简单高斯模型相结合的肤色建模方法,并在分割时使用最优阈值的方法使分割的效果达到最佳。
(4)利用分割肤色后的轮廓,使用最小二乘法进行椭圆拟合来精确定位出人脸在视频流中存在的位置,并进行筛选和验证。
With the development of computer science and technology, the computer applications have entered into every aspect of human life, and play a very important role. In which, artificial intelligence is very hot research field, and also the foundation of the artificial computer. It is always a very important subject in the research of artificial intelligence that the computer can recognize the object as a man, and it is also the first step the computer understanding the world.
This paper focuses on face detection technology in real-time videos. The research of face detection focuses on real-time problem in videos. Aiming at the existing disadvantages of face detection method and the main difficulties of face detection technologies, combination of application of face detection, a method for face detection in real-time videos is proposed. Specific tasks are as follows:
(1) The difference of face detection between real-time videos and static image is the former with motion information. Aiming at the characteristic of real-time videos, this paper studies on several major methods of moving object segmentation. Against the disadvantage which is quite sensitive to light in the background subtraction method, the paper has put forward a new method on generation of reference background and algorithm of real-time updating reference background.
(2) When image segmentation, through the analysis of different segmentation result with the use of different thresholds, a new adaptive threshold segmentation approach to segmentation of moving object is put forward.
(3) Aiming at the cluster characteristics of face color in the YCrCb color space, this paper studies on simple regional model and Gaussian distribution model in this color space, and put forward a color modeling method which is combination of regional threshold and Gaussian distribution model, and then segment the skin color with the optimal threshold to make the result best.
(4) Based on the contour after skin color segmentation, the position of face in video streaming is accurately located by ellipse fitting least squares method, and then selected and identified.
引文
[1]Yang M H,Kriegman D J,Narendra A.Detecting Face in Image:A Survey[J],Pattern Analysis and Machine Intelligence,2002,24(1):34-54.
[2]梁路宏,艾海舟等.人脸检测研究综述[J],计算机学报,2002,25(5):449-458.
[3]Nefian A V,Hayes M H.Face Detection and Recognition Using Hidden Markov Models[C],Image Proceedings,1998:141-145.
[4]Nefian A V,Hayes M H.An embedded HMM-based approach for face detection and recognition[C].Acoustics,Speech,and Signal Processing,1999:3533-3556.
[5]Romdhani S,Torr P,Scholkopf B etc.Computationally Efficient Face Detection[C],Computer Vision,2001:695-700.
[6]刘党辉,沈兰荪.视频运动对象分割技术的研究[J],电路与系统学报,2002,7(3):77-85.
[7]Cucchiara R,Grana C,Piccardi M etc.Detecting Moving Objects,Ghosts,and Shadows in Video Streams[J],Pattern Analysis and Machine Intelligence,2003,25(10):1337-1342.
[8]Nakazawa A,Kato H,Inokuchi S.Human tracking using distributed video systems[C],Pattern Recognition,1998:593-596.
[9]Haritaoglu I,Harwood D,Davis L S.W4:Who? When? Where? What? -A real time system for detecting and tracking people[C],Automatic Face and Gesture Recognition,1998:222-227.
[10]Lipton A J,Fujiyoshi H,Patil R S.Moving Target Classification and Tracking from Real-Time Video[C],Applications of Computer Vision,1998:8-14.
[11]潘翔鹤,赵曙光,柳宗浦等.一种基于梯度图像帧间差分和背景差分的运动目标检测新方法[D],光电子技术,2009,29(01):33-37.
[12]邱德润,朱明旱,伍宗富.一种基于帧间差分与背景差分的运动目标检测新方法[J],湖南文理学院学报,2007,19(01):81-83,86.
[13]朱明旱,罗大庸.基于帧间差分背景模型的运动物体检测与跟踪[J],计算机测量与控制,2006,14(08):1004-1006,1009.
[14]刘鑫,刘辉,强振平等.混合高斯模型和帧间差分相融合的自适应背景模型[J],中 国图象图形学报,2008,13(04):729-734.
[15]刘强,黄地龙.基于帧间差分与静态特征相结合的人脸跟踪方法[J],2006,19(02):74-78.
[16]Sifakis E,Tziritas G.Moving Object Localization Using a Multi-label Fast Marching Algorithm[J],Signal Processing:Image Communication,2001,16(02):963-976.
[17]张世界.一种新的检测方法在目标跟踪中的应用[J],电子测量技术,2009,32(05):82-82,123.
[18]谭墍元,吴成东,周芸等.智能图像监控系统异常目标检测算法研究[J],机电工程,2009,26(03):12-15.
[19]彭可,陈燕红,唐宜清.一种室内环境的运动目标检测混合算法[J],2008,44(05):239-241.
[20]田小围.视频序列中运动目标跟踪算法研究[D],长春理工大学,2008.
[21]王欣,殷肖川.基于背景重构的运动目标检测方法[J],微计算机信息,2008,24(4-1):284-286.
[22]朱克忠.基于光流法对移动目标的视频检测与应用研究[D],合肥工业大学,2007.
[23]李巍.一种基于光流法的三维互动系统的研究与实现[D],华中科技大学,2007.
[24]夏侯玉娇,龚声蓉,刘纯平等.结合Gaussian分布和LK光流法的视频对象分割算法[J],微电子学与计算机,2009,26(06):239-241,245.
[25]邓辉斌,熊邦书,欧巧凤.基于隔帧差分区域光流法的运动目标检测[J],30(02):300-304,307.
[26]余莉,王润生.基于多尺度变形模板的目标检测与识别[J],2002,39(10):1325-1330.
[27]Friedman N,Russell S.Image segmentation in video sequences:a probabilistic approach[C],Uncertainty in Artificial Intelligence,1997:256-258.
[28]Stringa E.Morphological change detection algorithms for surveillance application[C],Machine Vision Conference,2000:402-411.
[29]齐美彬,安宝磊,蒋建国.利用目标分割指导的背景更新算法[J],工程图学学报,2008,(02):125-130.
[30]雍杨,王敬儒,张启衡.复杂背景下运动目标分割算法研究[J],系统工程与电子技术,2005,27(12):2014,2015,2060.
[31]朱音.复杂背景下运动目标的分割与跟踪[D],苏州大学,2003.
[32]黄飞,吴敏渊,曹开田.基于HIS空间的彩色图像分割[J],小型微型计算机系统,2004,25(03):471-474.
[33]沈常宇,许潘园.肤色建模和肤色分割的人脸定位研究[J],光电工程,2007,34(09):103-107.
[2]梁路宏,艾海舟等.人脸检测研究综述[J],计算机学报,2002,25(5):449-458.
[3]Nefian A V,Hayes M H.Face Detection and Recognition Using Hidden Markov Models[C],Image Proceedings,1998:141-145.
[4]Nefian A V,Hayes M H.An embedded HMM-based approach for face detection and recognition[C].Acoustics,Speech,and Signal Processing,1999:3533-3556.
[5]Romdhani S,Torr P,Scholkopf B etc.Computationally Efficient Face Detection[C],Computer Vision,2001:695-700.
[6]刘党辉,沈兰荪.视频运动对象分割技术的研究[J],电路与系统学报,2002,7(3):77-85.
[7]Cucchiara R,Grana C,Piccardi M etc.Detecting Moving Objects,Ghosts,and Shadows in Video Streams[J],Pattern Analysis and Machine Intelligence,2003,25(10):1337-1342.
[8]Nakazawa A,Kato H,Inokuchi S.Human tracking using distributed video systems[C],Pattern Recognition,1998:593-596.
[9]Haritaoglu I,Harwood D,Davis L S.W4:Who? When? Where? What? -A real time system for detecting and tracking people[C],Automatic Face and Gesture Recognition,1998:222-227.
[10]Lipton A J,Fujiyoshi H,Patil R S.Moving Target Classification and Tracking from Real-Time Video[C],Applications of Computer Vision,1998:8-14.
[11]潘翔鹤,赵曙光,柳宗浦等.一种基于梯度图像帧间差分和背景差分的运动目标检测新方法[D],光电子技术,2009,29(01):33-37.
[12]邱德润,朱明旱,伍宗富.一种基于帧间差分与背景差分的运动目标检测新方法[J],湖南文理学院学报,2007,19(01):81-83,86.
[13]朱明旱,罗大庸.基于帧间差分背景模型的运动物体检测与跟踪[J],计算机测量与控制,2006,14(08):1004-1006,1009.
[14]刘鑫,刘辉,强振平等.混合高斯模型和帧间差分相融合的自适应背景模型[J],中 国图象图形学报,2008,13(04):729-734.
[15]刘强,黄地龙.基于帧间差分与静态特征相结合的人脸跟踪方法[J],2006,19(02):74-78.
[16]Sifakis E,Tziritas G.Moving Object Localization Using a Multi-label Fast Marching Algorithm[J],Signal Processing:Image Communication,2001,16(02):963-976.
[17]张世界.一种新的检测方法在目标跟踪中的应用[J],电子测量技术,2009,32(05):82-82,123.
[18]谭墍元,吴成东,周芸等.智能图像监控系统异常目标检测算法研究[J],机电工程,2009,26(03):12-15.
[19]彭可,陈燕红,唐宜清.一种室内环境的运动目标检测混合算法[J],2008,44(05):239-241.
[20]田小围.视频序列中运动目标跟踪算法研究[D],长春理工大学,2008.
[21]王欣,殷肖川.基于背景重构的运动目标检测方法[J],微计算机信息,2008,24(4-1):284-286.
[22]朱克忠.基于光流法对移动目标的视频检测与应用研究[D],合肥工业大学,2007.
[23]李巍.一种基于光流法的三维互动系统的研究与实现[D],华中科技大学,2007.
[24]夏侯玉娇,龚声蓉,刘纯平等.结合Gaussian分布和LK光流法的视频对象分割算法[J],微电子学与计算机,2009,26(06):239-241,245.
[25]邓辉斌,熊邦书,欧巧凤.基于隔帧差分区域光流法的运动目标检测[J],30(02):300-304,307.
[26]余莉,王润生.基于多尺度变形模板的目标检测与识别[J],2002,39(10):1325-1330.
[27]Friedman N,Russell S.Image segmentation in video sequences:a probabilistic approach[C],Uncertainty in Artificial Intelligence,1997:256-258.
[28]Stringa E.Morphological change detection algorithms for surveillance application[C],Machine Vision Conference,2000:402-411.
[29]齐美彬,安宝磊,蒋建国.利用目标分割指导的背景更新算法[J],工程图学学报,2008,(02):125-130.
[30]雍杨,王敬儒,张启衡.复杂背景下运动目标分割算法研究[J],系统工程与电子技术,2005,27(12):2014,2015,2060.
[31]朱音.复杂背景下运动目标的分割与跟踪[D],苏州大学,2003.
[32]黄飞,吴敏渊,曹开田.基于HIS空间的彩色图像分割[J],小型微型计算机系统,2004,25(03):471-474.
[33]沈常宇,许潘园.肤色建模和肤色分割的人脸定位研究[J],光电工程,2007,34(09):103-107.