嵌入式视频系统人脸朝向定位算法研究及实现
摘要
人体行为分析是模式识别与计算机视觉领域研究的一个热点问题,近些年来吸引了越来越多的目光,取得了飞速的发展。人脸的姿态定位与关注行为分析以其重要的应用价值和较高的准确度,成为了行为分析领域发展最快的研究方向之一。通过模板匹配、机器学习、形态学特征、跟踪预测等方法确定的目标个体头部在三维空间中的角度信息,对安全监控、国防建设、信息社会、消费电子等国民经济的相关领域有着重要的意义。
在现实应用中,我们经常面对的是标清单路摄像头拍摄的黑白或彩色视频,拍摄环境中强烈的光线变化、摄像器材造成的噪声与模糊、复杂多变的背景环境以及其所造成的人脸遮蔽等诸多问题使得精确人脸姿态定位算法的误差显著增大。本文研究的主要目的是设计一种对光线变化、噪声污染、复杂背景环境以及人脸遮蔽具有鲁棒性的精确人脸姿态定位算法。
Histograms of oriented gradients(HOG)算子对图像细节特征的提取具有很强的鲁棒性,通过采用人脸图像的HOG特征作为SVR算法的输入向量,我们设计了分段HOG-SVR人脸方向定位算法,采用分段处理的方式,实现了精确的人脸姿态定位。为了解决遮蔽所造成的影响,我们利用HOG块的局部响应,实现了对人脸遮蔽区域位置的初步定位,并设计了分块Gaussian-HOG-SVR算法,对严重遮蔽状态下的人脸实现了准确的方向推定。实验表明本文提出的人脸姿态定位算法,在环境光线变化、低分辨率图像、噪声污染以及人脸遮蔽的情况下取得了非常精确地预测效果。
最后我们在PC平台上完成了对本文所提出算法的仿真与实现。由于嵌入式平台处理性能的飞速发展以及智能算法逐渐向前端系统推进的趋势,我们对所提出算法的实现与复杂度做了基本的分析,并在TI OMAP3530嵌入式处理平台上建立了一套完整的算法验证系统。
recognition and computer vision research, has attracted more and more attention and achieved a rapid development in recent years. For its value in production and high accuracy, head pose estimation and concern behavior analysis has become the fastest growing research direction. Through the template matching, machine learning, morphological characteristics, track prediction methods, we can get the head pose information in 3D space. Combined with accurate face detection, it is widely used in security monitoring, national defense, information society, consumer electronics and other related areas of national economy.
But in real applications, we often have only a normal camera for image and video capture, with the challenge like strong lighting environment change, the noise caused by camera equipment, complex and changing background environment and the shield of the object. The main purpose of this paper is to develop a robust head pose estimation algorithm.
With the help of Histograms of oriented gradients(HOG) and piecewise processing, we propose an accurate piecewise HOG-SVR head pose estimation algorithm, which has an amazing estimation error, far better than the result of classical Adaboost and SVR method. Finally, we detect the occluded area of face according to the local response of the HOG block, and propose a blocking-Gaussian-HOG-SVR algorithm to handle occlusion issues.
At last, we finish the simulation and implementation of the proposed algorithm in PC platform, and build an integrated verification system on TI OMAP3530 platform.
在现实应用中,我们经常面对的是标清单路摄像头拍摄的黑白或彩色视频,拍摄环境中强烈的光线变化、摄像器材造成的噪声与模糊、复杂多变的背景环境以及其所造成的人脸遮蔽等诸多问题使得精确人脸姿态定位算法的误差显著增大。本文研究的主要目的是设计一种对光线变化、噪声污染、复杂背景环境以及人脸遮蔽具有鲁棒性的精确人脸姿态定位算法。
Histograms of oriented gradients(HOG)算子对图像细节特征的提取具有很强的鲁棒性,通过采用人脸图像的HOG特征作为SVR算法的输入向量,我们设计了分段HOG-SVR人脸方向定位算法,采用分段处理的方式,实现了精确的人脸姿态定位。为了解决遮蔽所造成的影响,我们利用HOG块的局部响应,实现了对人脸遮蔽区域位置的初步定位,并设计了分块Gaussian-HOG-SVR算法,对严重遮蔽状态下的人脸实现了准确的方向推定。实验表明本文提出的人脸姿态定位算法,在环境光线变化、低分辨率图像、噪声污染以及人脸遮蔽的情况下取得了非常精确地预测效果。
最后我们在PC平台上完成了对本文所提出算法的仿真与实现。由于嵌入式平台处理性能的飞速发展以及智能算法逐渐向前端系统推进的趋势,我们对所提出算法的实现与复杂度做了基本的分析,并在TI OMAP3530嵌入式处理平台上建立了一套完整的算法验证系统。
recognition and computer vision research, has attracted more and more attention and achieved a rapid development in recent years. For its value in production and high accuracy, head pose estimation and concern behavior analysis has become the fastest growing research direction. Through the template matching, machine learning, morphological characteristics, track prediction methods, we can get the head pose information in 3D space. Combined with accurate face detection, it is widely used in security monitoring, national defense, information society, consumer electronics and other related areas of national economy.
But in real applications, we often have only a normal camera for image and video capture, with the challenge like strong lighting environment change, the noise caused by camera equipment, complex and changing background environment and the shield of the object. The main purpose of this paper is to develop a robust head pose estimation algorithm.
With the help of Histograms of oriented gradients(HOG) and piecewise processing, we propose an accurate piecewise HOG-SVR head pose estimation algorithm, which has an amazing estimation error, far better than the result of classical Adaboost and SVR method. Finally, we detect the occluded area of face according to the local response of the HOG block, and propose a blocking-Gaussian-HOG-SVR algorithm to handle occlusion issues.
At last, we finish the simulation and implementation of the proposed algorithm in PC platform, and build an integrated verification system on TI OMAP3530 platform.
引文
[1]. Cha Zhang, Zhengyou Zhang. A Survey of Recent Advances in Face Detection. Microsoft Research-TR. 2010, 66.
[2]. P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Proc. of CVPR, 2001
[3].?Yang MH, Kriegman D, Ahuja N. Detecting faces in images: A survey. IEEE Trans Pattern Analysis and Machine Intelligence. 2002, 24 (1): 34~58.
[4]. P. Viola, M. Jones. Robust Real-Time Face Detection . International Journal of Computer Vision, 2004, 57(2): 137-154.
[5]. S.Z. Li et al. Statistical Learning of Multi-View Face Detection. Proc. Seventh European Conf. Computer Vision, 2002, 67-81.
[6]. P. Viola, M. Jones, Fast Multi-View Face Detection. MERLTR2003-106, 2003.
[7]. C. Huang, H.Z. Ai, Y. Li, and S.H. Lao. Vector Boosting for Rotation Invariant Multi-View Face Detection. Proc. 10th IEEEInt’l Conf. Computer Vision, 2005.
[8]. R.E. Schapire and Y. Singer. Improved Boosting Algorithms Using Confidence-Rated Predictions. Machine Learning. 1999, vol. 37: 297-336.
[9]. J. Friedman, T. Hastie, and R. Tibshirani. Additive Logistic Regression: A Statistical View of Boosting. Annals of Statistics. 2000, vol. 28: 337-374.
[10]. R. Xiao, L. Zhu, H. Zhang. Boosting Chain Learning for Object Detection. Proc. Ninth IEEE Int’l Conf. Computer Vision. 2003.
[11]. B. Wu, H. Ai, C. Huang, S. Lao. Fast Rotation InvariantMulti-View Face Detection Based on Real AdaBoost. Proc. SixthInt’l Conf. Automatic Face and Gesture Recognition.2004, 79-84.
[12]. Lienhart R, Maydt J. An Extended Set of Haar-like Features for Rapid Object Detection. IEEE ICIP. 2002, 3(7):900~903.
[13]. S. Baluja, M. Sahami, H.A. Rowley. Efficient Face Orientation Discrimination. Proc. IEEE Int’l Conf. Image Processing, 2004.
[14]. P. Wang, Q. Ji. Learning Discriminant Features for Multi-View Face and Eye Detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.
[15]. Y. Abramson, B. Steux. YEF* Real-Time Object Detection. Proc. Int’l Workshop Automatic Learning and Real-Time, 2005.
[16]. B. McCane and K. Novins. On training cascade face detectors.In Image and Vision Computing, 2003.
[17]. S. C. Brubaker, J.Wu, J. Sun, M. D. Mullin, J. M. Rehg. On the design of cascades of boosted ensembles for face detection.Technical report, Georgia Institute of Technology, 2005, GIT-GVU-05-28.
[18]. K. Levi, Y. Weiss. Learning object detection from a small number of examples: The importance of good features. In Proc. of CVPR, 2004.
[19]. D. Keren, M. Osadchy, C. Gotsman. Antifaces: A novel fast method for image detection. 2001, IEEE Trans. on PAMI, 23(7):747–761.
[20]. B. Heisele, T. Poggio, M. Pontil. Face detection in still gray images. Technical report, Center for Biological and Computational Learning, MIT, A.I. Memo 1687, 2000.
[21]. S. Romdhani, P. Torr, B. Sch¨olkopf, A. Blake. Computationally efficient face detection. InProc. of ICCV, 2001.
[22]. Erik Murphy-Chutorian, Mohan Manubhai Trivedi. Head Pose Estimation in Computer Vision: A Survey. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2009, 31(4):607-626
[23]. J. Sherrah, S. Gong, E.-J. Ong, Face Distributions in Similarity Space under Varying Head Pose, Image and Vision Computing, 2001, 19(12):807-819.
[24]. J. Tenenbaum, V. de Silva, J. Langford. A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science. 2000, 290:2319-2323.
[25]. S. Roweis, L. Saul. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science, 2000, 290(5500): 2323-2426.
[26]. M. Belkin, P. Niyogi. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation. 2003, 15(6):1373-1496.
[27]. Y. Fu, T. Huang. Graph Embedded Analysis for Head Pose Estimation. Proc. IEEE Int’l Conf. Automatic Face and Gesture Recognition, 2006, 3-9.
[28]. X. He, S. Yan, Y. Hu, H.J. Zhang. Learning a Locality Preserving Subspace for Visual Recognition. Proc. IEEE Int’l Conf. Computer Vision. 2003, 385-392.
[29]. Y. Li, S. Gong, J. Sherrah, H. Liddell. Support Vector Machine Based Multi-View Face Detection and Recognition. Image and Vision Computing.2004, 22(5): 2004.
[30]. R. Rae, H. Ritter. Recognition of Human Head Orientation Based on Artificial Neural Networks. IEEE Trans. Neural Networks. 1998, 9(2):257-265.
[31].T. Cootes, G. Edwards, C. Taylor. Active Appearance Models. IEEE Trans. Pattern Analysis and Machine Intelligence. 2001, 23(6):681-685.
[32]. S. Ba, J.-M. Odobez. A Probabilistic Framework for Joint Head Tracking and Pose Estimation. Proc. 17th Int’l Conf. PatternRecognition, 2004, 264-267.
[33]. Y. Hu, L. Chen, Y. Zhou, H. Zhang. Estimating Face Pose by Facial Asymmetry and Geometry. Proc. IEEE Int’l Conf. Automatic Face and Gesture Recognition. 2004, 651-656.
[34]. J. Wu and M. Trivedi. A Two-Stage Head Pose Estimation Framework and Evaluation. Pattern Recognition. 2008, 41(3):1138-1158.
[35]. N. Dalal, Triggs. Histograms of oriented gradients for human detection. 2005, CVPR 2005, 1:886–893.
[36].白雪生,徐光祐.基于支持向量机的人脸姿态判定.清华大学学报. 2003, 43(1):67-70
[37]. Qieshi Zhang, Kamata S.-I, Jun Zhang. Face detection and tracking in color images using color centroids segmentation. International Conference on Robotics and Biomimetics. 2009, 1008-1013.
[38]. P. J. Phillips, H. Moon, P. J. Rauss, S. Rizvi, The FERET evaluation methodology for face recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10):1090-1104.
[39] P. Jonathon Phillips, Harry Wechsler, Jeffrey Huang, Patrick J. Rauss. The FERET database and evaluation procedure for face-recognition algorithms. Image Vision Comput, 1998, 16(5): 295-306 .
[40]. Paul Viola, Michael J. Jones. Robust Real-Time Face Detection . International Journal of Computer Vision, 2004, 57(2): 137-154.
[41]. Chang Huang, Haizhou Ai, Yuan Li, Shihong Lao. High-Performance Rotation Invariant Multiview Face Detection. PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2007,29(4):671-684.
[42]陈煜.人脸检测跟踪算法的研究与基于DaVinci的人脸检测系统实现[硕士论文].上海:上海交通大学. 2007
[43]. Y. Freund, R. E. Schapire. Experiments with a New Boosting Algorithm. International Conference on Machine Learning.1996,148-156.
[44] P. Viola, M. Jones. Robust Real-time Object Detection. In Proc. 2nd Int'l Workshop on Statistical and Computational Theories of Vision -- Modeling, Learning, Computing and Sampling, Vancouver. 2001.
[45]. Alex J. Smola, Bernhard Sch?lkopf. A Tutorial on Support Vector Regression. Statistics and Computing, 2004, 14(3): 199-222.
[46]. Hirata.J, Morimoto, M., Fujii, K. Estimating face direction from low resolution images. Automation Congress, 2008:1-6.
[47]. Shingo ANDO, Yoshinori KUSACHI, Akira SUZUKI, Kenichi ARAKAWA. APPEARANCE BASED POSE ESTIMATION OF 3D OBJECT USING SUPPORT VECTOR REGRESSION. Image Processing, 2005, 1:341-344.
[48]. D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004,60(2):91–110.
[49]. Qing Jun Wang, Ru Bo Zhang. LPP-HOG: A New Local Image Descriptor for Fast Human Detection. Knowledge Acquisition and Modeling Workshop, 2008: 640 - 643
[50]. Renhaoyu. Multi-Cue Onboard Pedestrian Detection[EB/OL]. http://www.jdl.ac.cn/project/ aceId/paperreading/PPTs/hyren_20090522_CVPR2009_PedestrianDetection.ppt, 2009
[51]. D. Little, S. Krishna, J. Black, S. Panchanathan. A Methodology for Evaluating Robustness of Face RecognitionAlgorithms with Respect to Variations in Pose Angle and Illumination Angle. Proc. IEEE Int’l Conf. Acoustics, Speech, and Signal Processing, 2005, 2: 89-92.
[52]. Yang wang, Lei Zhang, Zicheng Liu, Gang Hua, Zhen Wen, Zhengyou Zhang Dimitris Samaras. Face Relighting from a Single Image under Arbitrary Unknown Lighting Conditions. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2009, 31(11): 1968-1984.
[53]. Yang wang, Zicheng Liu, Gang Hua, Zhengyou Zhang Dimitris Samaras. Face Re-Lighting from a Single Image under Harsh Lighting Conditions. Computer Vision and Pattern Recognition. 2007, 1-8.
[54]. Xiaoyu Wang, Tony X. Han, Shuicheng Yan. An HOG-LBP Human Detector with Partial Occlusion Handling. 2009, IEEE International Conference on Computer Vision .
[55]. Shingo Ando, Akira Suzuki, Takayuki Yasuno. SVR-based Robust Pose Estimation of 3D Objects under Local Occlusion and Non-stationary Backgrounds. PRMU DE, 2007, 107(114):75-80.
[56]. Hotta,k. Support Vector Machine with Local Summation Kernel for Robust Face Recognition. Pattern Recognition, Proceedings of the 17th International Conference on. 2004, 3: 482– 485
[57]. OMAP3530/25 Applications Processor (SPRS507F).
[58]. Davinci Multimedia Application Interface [EB/OL]. http://processors.wiki.ti.com/index.php /Davinci_Multimedia_Application_Interface, 2009.
[2]. P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Proc. of CVPR, 2001
[3].?Yang MH, Kriegman D, Ahuja N. Detecting faces in images: A survey. IEEE Trans Pattern Analysis and Machine Intelligence. 2002, 24 (1): 34~58.
[4]. P. Viola, M. Jones. Robust Real-Time Face Detection . International Journal of Computer Vision, 2004, 57(2): 137-154.
[5]. S.Z. Li et al. Statistical Learning of Multi-View Face Detection. Proc. Seventh European Conf. Computer Vision, 2002, 67-81.
[6]. P. Viola, M. Jones, Fast Multi-View Face Detection. MERLTR2003-106, 2003.
[7]. C. Huang, H.Z. Ai, Y. Li, and S.H. Lao. Vector Boosting for Rotation Invariant Multi-View Face Detection. Proc. 10th IEEEInt’l Conf. Computer Vision, 2005.
[8]. R.E. Schapire and Y. Singer. Improved Boosting Algorithms Using Confidence-Rated Predictions. Machine Learning. 1999, vol. 37: 297-336.
[9]. J. Friedman, T. Hastie, and R. Tibshirani. Additive Logistic Regression: A Statistical View of Boosting. Annals of Statistics. 2000, vol. 28: 337-374.
[10]. R. Xiao, L. Zhu, H. Zhang. Boosting Chain Learning for Object Detection. Proc. Ninth IEEE Int’l Conf. Computer Vision. 2003.
[11]. B. Wu, H. Ai, C. Huang, S. Lao. Fast Rotation InvariantMulti-View Face Detection Based on Real AdaBoost. Proc. SixthInt’l Conf. Automatic Face and Gesture Recognition.2004, 79-84.
[12]. Lienhart R, Maydt J. An Extended Set of Haar-like Features for Rapid Object Detection. IEEE ICIP. 2002, 3(7):900~903.
[13]. S. Baluja, M. Sahami, H.A. Rowley. Efficient Face Orientation Discrimination. Proc. IEEE Int’l Conf. Image Processing, 2004.
[14]. P. Wang, Q. Ji. Learning Discriminant Features for Multi-View Face and Eye Detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.
[15]. Y. Abramson, B. Steux. YEF* Real-Time Object Detection. Proc. Int’l Workshop Automatic Learning and Real-Time, 2005.
[16]. B. McCane and K. Novins. On training cascade face detectors.In Image and Vision Computing, 2003.
[17]. S. C. Brubaker, J.Wu, J. Sun, M. D. Mullin, J. M. Rehg. On the design of cascades of boosted ensembles for face detection.Technical report, Georgia Institute of Technology, 2005, GIT-GVU-05-28.
[18]. K. Levi, Y. Weiss. Learning object detection from a small number of examples: The importance of good features. In Proc. of CVPR, 2004.
[19]. D. Keren, M. Osadchy, C. Gotsman. Antifaces: A novel fast method for image detection. 2001, IEEE Trans. on PAMI, 23(7):747–761.
[20]. B. Heisele, T. Poggio, M. Pontil. Face detection in still gray images. Technical report, Center for Biological and Computational Learning, MIT, A.I. Memo 1687, 2000.
[21]. S. Romdhani, P. Torr, B. Sch¨olkopf, A. Blake. Computationally efficient face detection. InProc. of ICCV, 2001.
[22]. Erik Murphy-Chutorian, Mohan Manubhai Trivedi. Head Pose Estimation in Computer Vision: A Survey. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2009, 31(4):607-626
[23]. J. Sherrah, S. Gong, E.-J. Ong, Face Distributions in Similarity Space under Varying Head Pose, Image and Vision Computing, 2001, 19(12):807-819.
[24]. J. Tenenbaum, V. de Silva, J. Langford. A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science. 2000, 290:2319-2323.
[25]. S. Roweis, L. Saul. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science, 2000, 290(5500): 2323-2426.
[26]. M. Belkin, P. Niyogi. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation. 2003, 15(6):1373-1496.
[27]. Y. Fu, T. Huang. Graph Embedded Analysis for Head Pose Estimation. Proc. IEEE Int’l Conf. Automatic Face and Gesture Recognition, 2006, 3-9.
[28]. X. He, S. Yan, Y. Hu, H.J. Zhang. Learning a Locality Preserving Subspace for Visual Recognition. Proc. IEEE Int’l Conf. Computer Vision. 2003, 385-392.
[29]. Y. Li, S. Gong, J. Sherrah, H. Liddell. Support Vector Machine Based Multi-View Face Detection and Recognition. Image and Vision Computing.2004, 22(5): 2004.
[30]. R. Rae, H. Ritter. Recognition of Human Head Orientation Based on Artificial Neural Networks. IEEE Trans. Neural Networks. 1998, 9(2):257-265.
[31].T. Cootes, G. Edwards, C. Taylor. Active Appearance Models. IEEE Trans. Pattern Analysis and Machine Intelligence. 2001, 23(6):681-685.
[32]. S. Ba, J.-M. Odobez. A Probabilistic Framework for Joint Head Tracking and Pose Estimation. Proc. 17th Int’l Conf. PatternRecognition, 2004, 264-267.
[33]. Y. Hu, L. Chen, Y. Zhou, H. Zhang. Estimating Face Pose by Facial Asymmetry and Geometry. Proc. IEEE Int’l Conf. Automatic Face and Gesture Recognition. 2004, 651-656.
[34]. J. Wu and M. Trivedi. A Two-Stage Head Pose Estimation Framework and Evaluation. Pattern Recognition. 2008, 41(3):1138-1158.
[35]. N. Dalal, Triggs. Histograms of oriented gradients for human detection. 2005, CVPR 2005, 1:886–893.
[36].白雪生,徐光祐.基于支持向量机的人脸姿态判定.清华大学学报. 2003, 43(1):67-70
[37]. Qieshi Zhang, Kamata S.-I, Jun Zhang. Face detection and tracking in color images using color centroids segmentation. International Conference on Robotics and Biomimetics. 2009, 1008-1013.
[38]. P. J. Phillips, H. Moon, P. J. Rauss, S. Rizvi, The FERET evaluation methodology for face recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10):1090-1104.
[39] P. Jonathon Phillips, Harry Wechsler, Jeffrey Huang, Patrick J. Rauss. The FERET database and evaluation procedure for face-recognition algorithms. Image Vision Comput, 1998, 16(5): 295-306 .
[40]. Paul Viola, Michael J. Jones. Robust Real-Time Face Detection . International Journal of Computer Vision, 2004, 57(2): 137-154.
[41]. Chang Huang, Haizhou Ai, Yuan Li, Shihong Lao. High-Performance Rotation Invariant Multiview Face Detection. PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2007,29(4):671-684.
[42]陈煜.人脸检测跟踪算法的研究与基于DaVinci的人脸检测系统实现[硕士论文].上海:上海交通大学. 2007
[43]. Y. Freund, R. E. Schapire. Experiments with a New Boosting Algorithm. International Conference on Machine Learning.1996,148-156.
[44] P. Viola, M. Jones. Robust Real-time Object Detection. In Proc. 2nd Int'l Workshop on Statistical and Computational Theories of Vision -- Modeling, Learning, Computing and Sampling, Vancouver. 2001.
[45]. Alex J. Smola, Bernhard Sch?lkopf. A Tutorial on Support Vector Regression. Statistics and Computing, 2004, 14(3): 199-222.
[46]. Hirata.J, Morimoto, M., Fujii, K. Estimating face direction from low resolution images. Automation Congress, 2008:1-6.
[47]. Shingo ANDO, Yoshinori KUSACHI, Akira SUZUKI, Kenichi ARAKAWA. APPEARANCE BASED POSE ESTIMATION OF 3D OBJECT USING SUPPORT VECTOR REGRESSION. Image Processing, 2005, 1:341-344.
[48]. D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004,60(2):91–110.
[49]. Qing Jun Wang, Ru Bo Zhang. LPP-HOG: A New Local Image Descriptor for Fast Human Detection. Knowledge Acquisition and Modeling Workshop, 2008: 640 - 643
[50]. Renhaoyu. Multi-Cue Onboard Pedestrian Detection[EB/OL]. http://www.jdl.ac.cn/project/ aceId/paperreading/PPTs/hyren_20090522_CVPR2009_PedestrianDetection.ppt, 2009
[51]. D. Little, S. Krishna, J. Black, S. Panchanathan. A Methodology for Evaluating Robustness of Face RecognitionAlgorithms with Respect to Variations in Pose Angle and Illumination Angle. Proc. IEEE Int’l Conf. Acoustics, Speech, and Signal Processing, 2005, 2: 89-92.
[52]. Yang wang, Lei Zhang, Zicheng Liu, Gang Hua, Zhen Wen, Zhengyou Zhang Dimitris Samaras. Face Relighting from a Single Image under Arbitrary Unknown Lighting Conditions. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2009, 31(11): 1968-1984.
[53]. Yang wang, Zicheng Liu, Gang Hua, Zhengyou Zhang Dimitris Samaras. Face Re-Lighting from a Single Image under Harsh Lighting Conditions. Computer Vision and Pattern Recognition. 2007, 1-8.
[54]. Xiaoyu Wang, Tony X. Han, Shuicheng Yan. An HOG-LBP Human Detector with Partial Occlusion Handling. 2009, IEEE International Conference on Computer Vision .
[55]. Shingo Ando, Akira Suzuki, Takayuki Yasuno. SVR-based Robust Pose Estimation of 3D Objects under Local Occlusion and Non-stationary Backgrounds. PRMU DE, 2007, 107(114):75-80.
[56]. Hotta,k. Support Vector Machine with Local Summation Kernel for Robust Face Recognition. Pattern Recognition, Proceedings of the 17th International Conference on. 2004, 3: 482– 485
[57]. OMAP3530/25 Applications Processor (SPRS507F).
[58]. Davinci Multimedia Application Interface [EB/OL]. http://processors.wiki.ti.com/index.php /Davinci_Multimedia_Application_Interface, 2009.