正在加载图片...
·386· 智能系统学报 第10卷 4 结束语 segmentation using slow feature analysis C//2011 IEEE Intelligent Vehicles Symposium (IV).Baden-Baden,Ger- 本文提出了视频中人体行为的慢特征提取方法, many,2011:800-806. 首先收集训练立方体,然后分别用SFA算法和D [12]DENG Xiaogang,TIAN Xuemin,HU Xiangyang.Nonlinear SFA算法进行慢特征函数的机器学习,经慢特征函数 process fault diagnosis based on slow feature analysis[C]// 变换后得到慢特征,并进一步构建ASD特征。实验 2012 10th World Congress on Intelligent Control and Auto- 结果表明D-SFA算法能更有效地提取出人体行为的 mation.Beijing,China,2012:3152-3156. 慢特征。由于特征点跟踪的过程中,少量特征点在后 [13]ZHANG Zhang,TAO Dacheng.Slow feature analysis for 续帧中会出现漂移现象,对后面的处理会产生一定的 human action recognition[J].IEEE Transactions on Pat- 影响,今后将进一步研究以取得更好的效果。 tern Analysis and Machine Intelligence,2012,34(3): 436-450. 参考文献: [14]王丽辉,袁保宗.三维散乱点云模型的特征点检测[J]. 信号处理,2011,27(6):932-938. [1]VENKATASUBRAMANIAN V,RENGASWAMY R,KA- WANG Lihui,YUAN Baozong.Feature point detection for VURI S N,et al.A review of process fault detection and di- agnosis:Part III:process history based methods[J].Com- 3D scattered point cloud model [J].Signal Processing. 2011,27(6):932-938. puters Chemical Engineering,2003,27(3):327-346. [15]马龙,王鲁平,陈小天,等.噪声环境下光流场估计方法 [2]CHERRY G A,QIN S J.Multiblock principal component [J].信号处理,2012,28(1):87-91. analysis based on a combined index for semiconductor fault MA Long,WANG Luping,CHEN Xiaotian,et al.Determi- detection and diagnosis[J].IEEE Transactions on Semi- conductor Manufacturing,2006,19(2):159-172. ning optical flow field in the presence of noise[J].Signal Processing,2012,28(1):87-91. [3]DUNIA R,QIN S J.Joint diagnosis of process and sensor [16]江志军,易华蓉.一种基于图像金字塔光流的特征跟踪 faults using principal component analysis[J].Control Engi- 方法[J].武汉大学学报:信息科学版,2007,32(8): neering Practice,1998,6(4):457-469. 680-683. [4]SCHOLKPOF B,SMOLA A,MOLLER K R.Nonlinear com- JIANG Zhijun,YI Huarong.An image pyramid-based fea- ponent analysis as a kernel eigenvalue problem[J].Neural ture detection and tracking algorithmJ.Geomatics and In- Computation,1998,10(5):1299-1319. formation Science of Wuhan University,2007,32(8):680- [5]WISKOTT L,SEINOWSKI T L.Slow feature analysis:unsu- 683. pervised learning of invariances [J].Neural Computation, 作者简介: 2002,14(4):715-770. 陈婷婷,女,1987年生,硕士研究生, 6]BERKES P,WISKOTT L.Slow feature analysis vields a rich 主要研究方向为人体行为分析。 repertoire of complex cell properties[J].Journal of Vision, 2005,5(6):579-602 [7]XIA Qi,GAO Jianbin,XU Chunxiang.A new watermarking algorithm based on slowly feature analysis[C]//International Conference on Apperceiving Computing and Intelligence Anal- ysis.Chengdu,China,2008:70-72. 阮秋琦,男,1944年生,教授,博士 [8]GAO Jianbin,LI Jianping,XIA Qi.Slowly feature analysis of 生导师,主要研究方向为数字图像处 Gabor feature for face recognition [C]//2008 International 理、计算机视觉。曾多次获得省部级 Conference on Apperceiving Computing and Intelligence Anal- ysis.Chengdu,China,2008:177-180. 科技进步奖,发表学术论文350余篇, 出版专著4部。 [9]HUANG Yaping,ZHAO Jiali,TIAN Mei,et al.Slow feature discriminant analysis and its application on handwritten digit recognition [C]//International Joint Conference on Neural 安高云,男,1980年生,副教授,主要 Networks.Atlanta,USA.2009:1294-1297. 研究方向为图像处理、人脸识别、统计模 [10]MA Kuijun,TAO Qing,WANG Jue.Nonlinear blind source 式识别。 separation using slow feature analysis with random features [C]//2010 20th International Conference on Pattern Recog- nition.Istanbul,Turkey,2010:830-833. [11 KOHNL T,KUMMERT F,FRITSCH J.Monocular road4 结束语 本文提出了视频中人体行为的慢特征提取方法, 首先收集训练立方体,然后分别用 SFA 算法和 D⁃ SFA 算法进行慢特征函数的机器学习,经慢特征函数 变换后得到慢特征,并进一步构建 ASD 特征。 实验 结果表明 D⁃SFA 算法能更有效地提取出人体行为的 慢特征。 由于特征点跟踪的过程中,少量特征点在后 续帧中会出现漂移现象,对后面的处理会产生一定的 影响,今后将进一步研究以取得更好的效果。 参考文献: [1 ] VENKATASUBRAMANIAN V, RENGASWAMY R, KA⁃ VURI S N, et al. A review of process fault detection and di⁃ agnosis: Part III: process history based methods[ J]. Com⁃ puters & Chemical Engineering, 2003, 27(3): 327⁃346. [2]CHERRY G A, QIN S J. Multiblock principal component analysis based on a combined index for semiconductor fault detection and diagnosis [ J] . IEEE Transactions on Semi⁃ conductor Manufacturing, 2006, 19( 2) : 159⁃172. [3] DUNIA R, QIN S J. Joint diagnosis of process and sensor faults using principal component analysis[ J]. Control Engi⁃ neering Practice, 1998, 6(4): 457⁃469. [4]SCHÖLKPOF B, SMOLA A, MÜLLER K R. Nonlinear com⁃ ponent analysis as a kernel eigenvalue problem[ J]. Neural Computation, 1998, 10(5): 1299⁃1319. [5]WISKOTT L, SEINOWSKI T L. Slow feature analysis: unsu⁃ pervised learning of invariances [ J]. Neural Computation, 2002, 14(4): 715⁃770. [6]BERKES P, WISKOTT L. Slow feature analysis yields a rich repertoire of complex cell properties [ J]. Journal of Vision, 2005, 5(6): 579⁃602. [7]XIA Qi, GAO Jianbin, XU Chunxiang. A new watermarking algorithm based on slowly feature analysis[C] / / International Conference on Apperceiving Computing and Intelligence Anal⁃ ysis. Chengdu, China, 2008: 70⁃72. [8]GAO Jianbin, LI Jianping, XIA Qi. Slowly feature analysis of Gabor feature for face recognition [ C] / / 2008 International Conference on Apperceiving Computing and Intelligence Anal⁃ ysis. Chengdu, China, 2008: 177⁃180. [9]HUANG Yaping, ZHAO Jiali, TIAN Mei, et al. Slow feature discriminant analysis and its application on handwritten digit recognition [ C] / / International Joint Conference on Neural Networks. Atlanta, USA, 2009: 1294⁃1297. [10]MA Kuijun, TAO Qing, WANG Jue. Nonlinear blind source separation using slow feature analysis with random features [C] / / 2010 20th International Conference on Pattern Recog⁃ nition. Istanbul, Turkey, 2010: 830⁃833. [11] KÜHNL T, KUMMERT F, FRITSCH J. Monocular road segmentation using slow feature analysis [ C] / / 2011 IEEE Intelligent Vehicles Symposium ( IV). Baden⁃Baden, Ger⁃ many, 2011: 800⁃806. [12]DENG Xiaogang, TIAN Xuemin, HU Xiangyang. Nonlinear process fault diagnosis based on slow feature analysis[C] / / 2012 10th World Congress on Intelligent Control and Auto⁃ mation. Beijing, China, 2012: 3152⁃3156. [13]ZHANG Zhang, TAO Dacheng. Slow feature analysis for human action recognition[ J] . IEEE Transactions on Pat⁃ tern Analysis and Machine Intelligence, 2012, 34 ( 3) : 436⁃450. [14]王丽辉, 袁保宗. 三维散乱点云模型的特征点检测[ J]. 信号处理, 2011, 27(6): 932⁃938. WANG Lihui, YUAN Baozong. Feature point detection for 3D scattered point cloud model [ J ]. Signal Processing, 2011, 27(6): 932⁃938. [15]马龙, 王鲁平, 陈小天, 等. 噪声环境下光流场估计方法 [J]. 信号处理, 2012, 28(1): 87⁃91. MA Long, WANG Luping, CHEN Xiaotian, et al. Determi⁃ ning optical flow field in the presence of noise [ J]. Signal Processing, 2012, 28(1): 87⁃91. [16]江志军, 易华蓉. 一种基于图像金字塔光流的特征跟踪 方法[ J]. 武汉大学学报:信息科学版, 2007, 32 ( 8): 680⁃683. JIANG Zhijun, YI Huarong. An image pyramid⁃based fea⁃ ture detection and tracking algorithm[J]. Geomatics and In⁃ formation Science of Wuhan University, 2007, 32(8): 680⁃ 683. 作者简介: 陈婷婷,女,1987 年生,硕士研究生, 主要研究方向为人体行为分析。 阮秋琦,男,1944 年生,教授,博士 生导师,主要研究方向为数字图像处 理、计算机 视 觉。 曾 多 次 获 得 省 部 级 科技进步奖,发表学术论文 350 余篇, 出版专著 4 部。 安高云,男,1980 年生,副教授,主要 研究方向为图像处理、人脸识别、统计模 式识别。 ·386· 智 能 系 统 学 报 第 10 卷
<<向上翻页
©2008-现在 cucdc.com 高等教育资讯网 版权所有