基于带有噪声输入的稀疏高斯过程的人体姿态估计
|
摘要
高斯过程回归(Gaussian process regression, GPR)是一种广泛应用的回归方法,可以用于解决输入输出均为多元变量的人体姿态估计问题.计算复杂度是高斯过程回归的一个重要考虑因素,而常用的降低计算复杂度的方法为稀疏表示算法.在稀疏算法中,完全独立训练条件(Fully independent training conditional, FITC)法是一种较为先进的算法,多用于解决输入变量彼此之间完全独立的回归问题.另外,输入变量的噪声问题是高斯过程回归的另一个需要考虑的重要因素.对于测试的输入变量噪声,可以通过矩匹配的方法进行解决,而训练输入样本的噪声则可通过将其转换为输出噪声的方法进行解决,从而得到更高的计算精度.本文基于以上算法,提出一种基于噪声输入的稀疏高斯算法,同时将其应用于解决人体姿态估计问题.本文实验中的数据集来源于之前的众多研究人员,其输入为从视频序列中截取的图像或通过特征提取得到的图像信息,输出为三维的人体姿态.与其他算法相比,本文的算法在准确性,运行时间与算法稳定性方面均达到了令人满意的效果.
Gaussian process regression(GPR) is a common method for structured prediction and human pose estimation,in which input and output are both multivariate. Computational complexity is a significant consideration of GP regression and it can be reduced by sparse Gaussian algorithm. The fully independent training conditional(FITC) algorithm is a good method for sparse Gaussian process, and it can be applied to fully-independent input problems. Input noise is another significant consideration of GP regression. Moment matching can be used to solve trial input noise while training input noise can be modeled as output noise to achieve higher accuracy. On the basis of above algorithms, this study proposes a sparse Gaussian process with input noise for human pose estimation. A dataset from multiple people is used for experiments, in which the input is the image from video processing or image descriptor obtained by feature extraction,and the output is a three-dimensional human pose. The accuracy, runtime and stability of the algorithm are all satisfactory compared with other methods for human pose estimation.
Gaussian process regression(GPR) is a common method for structured prediction and human pose estimation,in which input and output are both multivariate. Computational complexity is a significant consideration of GP regression and it can be reduced by sparse Gaussian algorithm. The fully independent training conditional(FITC) algorithm is a good method for sparse Gaussian process, and it can be applied to fully-independent input problems. Input noise is another significant consideration of GP regression. Moment matching can be used to solve trial input noise while training input noise can be modeled as output noise to achieve higher accuracy. On the basis of above algorithms, this study proposes a sparse Gaussian process with input noise for human pose estimation. A dataset from multiple people is used for experiments, in which the input is the image from video processing or image descriptor obtained by feature extraction,and the output is a three-dimensional human pose. The accuracy, runtime and stability of the algorithm are all satisfactory compared with other methods for human pose estimation.
引文
1 Shen Jian-Dong, Chen Heng. New human pose estimation algorithm based on HOG and color features. Computer Engineering and Applications, 2017, 53(21):190-194(沈建冬,陈恒.融合HOG和颜色特征的人体姿态估计新算法.计算机工程与应用, 2017, 53(21):190-194)
2 Wang J M, Fleet D J, Hertzmann A. Gaussian process dynamical models for human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2):283-298
3 Yuan Zi-Hua, Li Feng, Zhou Shu-Ren. Human pose estimation based on Haar characteristics LBP texture feature.Computer Engineering, 2015, 41(4):199-204(袁紫华,李峰,周书仁.基于Haar型LBP纹理特征的人体姿态估计.计算机工程, 2015, 41(4):199-204)
4 Zhao X, Ning H Z, Liu Y C, Huang T. Discriminative estimation of 3D human pose using Gaussian processes. In:Proceedings of the 19th International Conference on Pattern Recognition. Tampa, FL, USA:IEEE, 2008. 1-4
5 Bratieres S, Quadrianto N, Ghahramani Z. GPstruct:Bayesian structured prediction using gaussian processes.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(7):1514-1520
6 Ding M, Fan G L. Articulated Gaussian kernel correlation for human pose estimation. In:Proceedings of the 2015IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Boston, MA, USA:IEEE, 2015.57-64
7 Rasmussen C E, Ghahramani Z. Infinite mixtures of Gaussian process experts. In:Proceedings of the 14th International Conference on Neural Information Processing Systems:Natural and Synthetic. Vancouver, British Columbia,Canada:MIT Press, 2002. 881-888
8 Yu Bin-Feng, Ji Hai-Bo. Sparse Bayesian mixture of experts and its application to spectral multivariate calibration. Acta Automatica Sinica, 2016, 42(4):566-579(俞斌峰,季海波.稀疏贝叶斯混合专家模型及其在光谱数据标定中的应用.自动化学报, 2016, 42(4):566-579)
9 Liu Chang-Hong, Yang Yang, Chen Yong. Incrementally learning human pose mapping model. Computer Science,2010, 37(3):268-270(刘长红,杨扬,陈勇.增量式人体姿态映射模型的学习方法.计算机科学, 2010, 37(3):268-270)
10 Yan Xiao-Xi, Han Chong-Zhao. Maximum likelihood estimation of multiple target states based on incremental finite mixture model. Acta Automatica Sinica, 2011, 37(5):577-584(闫小喜,韩崇昭.基于增量式有限混合模型的多目标状态极大似然估计.自动化学报, 2011, 37(5):577-584)
11 Csat′o L, Opper M. Sparse on-line Gaussian processes. Neural Computation, 2002, 14(3):641-668
12 Bijl H, van Wingerden J W, Sch¨on T B, Verhaegen M.Online sparse Gaussian process regression using FITC and PITC approximations. IFAC-Papers On Line, 2015, 48(28):703-708
13 Snelson E, Ghahramani Z. Sparse Gaussian processes using pseudo-inputs. In:Proceedings of the 18th International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada:MIT Press,2006. 1257-1264
14 Mc Hutchon A, Rasmussen C E. Gaussian process training with input noise. In:Proceedings of the 24th International Conference on Neural Information Processing Systems. Granada, Spain:ACM, 2011. 1341-1349
15 Human Eva Dataset[Online], available:http://humaneva.is.tue.mpg.de/, November 3, 2017
16 Sigal L, Balan A O, Black M J. Human Eva:synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. International Journal of Computer Vision, 2006, 87(1-2):Article No. 4
17 Poppe R. Evaluating example-based pose estimation:experiments on the Human Eva sets. In:Proceedings of the2007 Computer Vision and Pattern Recognition Workshop on Evaluation of Articulated Human Motion and Pose Estimation(EHu M2). Minneapolis, USA:IEEE, 2007.
18 Su Ben-Yue, Jiang Jing, Tang Qing-Feng, Sheng Min. Human dynamic action recognition based on functional data analysis. Acta Automatica Sinica, 2017, 43(5):866-876(苏本跃,蒋京,汤庆丰,盛敏.基于函数型数据分析方法的人体动态行为识别.自动化学报, 2017, 43(5):866-876)
19 Shakhnarovich G, Viola P, Darrell T. Fast pose estimation with parameter-sensitive hashing. In:Proceedings of the 9th IEEE International Conference on Computer Vision. Nice,France:IEEE, 2003. 750-757
20 Han Gui-Jin, Zhu Hong. Human pose estimation algorithm based on pictorial structure model. Computer Engineering and Applications, 2013, 49(14):30-33(韩贵金,朱虹.一种基于图结构模型的人体姿态估计算法.计算机工程与应用, 2013, 49(14):30-33
21 Jiang H. Human pose estimation using consistent max covering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(9):1911-1918
22 Yang W L, Wang Y, Mori G. Recognizing human actions from still images with latent poses. In:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). San Francisco, USA:IEEE, 2010.2030-2037
23 Xu Feng, Zhang Jun-Ping. Facial microexpression recognition:a survey. Acta Automatica Sinica, 2017, 43(3):333-348(徐峰,张军平.人脸微表情识别综述.自动化学报, 2017, 43(3):333-348)
24 Xu Yuan, Xu Xiao-Liang, Li Cai-Nian, Jiang Mei, Zhang Jian-Guo. Pedestrian detection combining with SVM classifier and HOG feature extraction. Computer Engineering,2016, 42(1):56-60, 65(徐渊,许晓亮,李才年,姜梅,张建国.结合SVM分类器与HOG特征提取的行人检测.计算机工程, 2016, 42(1):56-60, 65)
25 Bo L F, Sminchisescu C. Twin gaussian processes for structured prediction. International Journal of Computer Vision,2010, 87(1-2):28-52
26 Cristianini N, Shawe-Taylor J, Elisseeff A, Kandola J. On kernel-target alignment. In:Proceedings of the 14th International Conference on Neural Information Processing Systems:Natural and Synthetic. Vancouver, British Columbia,Canada:MIT Press, 2001. 367-373
27 Gretton A, Bousquet O, Smola A J, Scholkopf B. Measuring statistical dependence with Hilbert-Schmidt norms.Algorithmic Learning Theory. Berlin Heidelberg, Germany:Springer-Verlag, 2005.
2 Wang J M, Fleet D J, Hertzmann A. Gaussian process dynamical models for human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2):283-298
3 Yuan Zi-Hua, Li Feng, Zhou Shu-Ren. Human pose estimation based on Haar characteristics LBP texture feature.Computer Engineering, 2015, 41(4):199-204(袁紫华,李峰,周书仁.基于Haar型LBP纹理特征的人体姿态估计.计算机工程, 2015, 41(4):199-204)
4 Zhao X, Ning H Z, Liu Y C, Huang T. Discriminative estimation of 3D human pose using Gaussian processes. In:Proceedings of the 19th International Conference on Pattern Recognition. Tampa, FL, USA:IEEE, 2008. 1-4
5 Bratieres S, Quadrianto N, Ghahramani Z. GPstruct:Bayesian structured prediction using gaussian processes.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(7):1514-1520
6 Ding M, Fan G L. Articulated Gaussian kernel correlation for human pose estimation. In:Proceedings of the 2015IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Boston, MA, USA:IEEE, 2015.57-64
7 Rasmussen C E, Ghahramani Z. Infinite mixtures of Gaussian process experts. In:Proceedings of the 14th International Conference on Neural Information Processing Systems:Natural and Synthetic. Vancouver, British Columbia,Canada:MIT Press, 2002. 881-888
8 Yu Bin-Feng, Ji Hai-Bo. Sparse Bayesian mixture of experts and its application to spectral multivariate calibration. Acta Automatica Sinica, 2016, 42(4):566-579(俞斌峰,季海波.稀疏贝叶斯混合专家模型及其在光谱数据标定中的应用.自动化学报, 2016, 42(4):566-579)
9 Liu Chang-Hong, Yang Yang, Chen Yong. Incrementally learning human pose mapping model. Computer Science,2010, 37(3):268-270(刘长红,杨扬,陈勇.增量式人体姿态映射模型的学习方法.计算机科学, 2010, 37(3):268-270)
10 Yan Xiao-Xi, Han Chong-Zhao. Maximum likelihood estimation of multiple target states based on incremental finite mixture model. Acta Automatica Sinica, 2011, 37(5):577-584(闫小喜,韩崇昭.基于增量式有限混合模型的多目标状态极大似然估计.自动化学报, 2011, 37(5):577-584)
11 Csat′o L, Opper M. Sparse on-line Gaussian processes. Neural Computation, 2002, 14(3):641-668
12 Bijl H, van Wingerden J W, Sch¨on T B, Verhaegen M.Online sparse Gaussian process regression using FITC and PITC approximations. IFAC-Papers On Line, 2015, 48(28):703-708
13 Snelson E, Ghahramani Z. Sparse Gaussian processes using pseudo-inputs. In:Proceedings of the 18th International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada:MIT Press,2006. 1257-1264
14 Mc Hutchon A, Rasmussen C E. Gaussian process training with input noise. In:Proceedings of the 24th International Conference on Neural Information Processing Systems. Granada, Spain:ACM, 2011. 1341-1349
15 Human Eva Dataset[Online], available:http://humaneva.is.tue.mpg.de/, November 3, 2017
16 Sigal L, Balan A O, Black M J. Human Eva:synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. International Journal of Computer Vision, 2006, 87(1-2):Article No. 4
17 Poppe R. Evaluating example-based pose estimation:experiments on the Human Eva sets. In:Proceedings of the2007 Computer Vision and Pattern Recognition Workshop on Evaluation of Articulated Human Motion and Pose Estimation(EHu M2). Minneapolis, USA:IEEE, 2007.
18 Su Ben-Yue, Jiang Jing, Tang Qing-Feng, Sheng Min. Human dynamic action recognition based on functional data analysis. Acta Automatica Sinica, 2017, 43(5):866-876(苏本跃,蒋京,汤庆丰,盛敏.基于函数型数据分析方法的人体动态行为识别.自动化学报, 2017, 43(5):866-876)
19 Shakhnarovich G, Viola P, Darrell T. Fast pose estimation with parameter-sensitive hashing. In:Proceedings of the 9th IEEE International Conference on Computer Vision. Nice,France:IEEE, 2003. 750-757
20 Han Gui-Jin, Zhu Hong. Human pose estimation algorithm based on pictorial structure model. Computer Engineering and Applications, 2013, 49(14):30-33(韩贵金,朱虹.一种基于图结构模型的人体姿态估计算法.计算机工程与应用, 2013, 49(14):30-33
21 Jiang H. Human pose estimation using consistent max covering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(9):1911-1918
22 Yang W L, Wang Y, Mori G. Recognizing human actions from still images with latent poses. In:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). San Francisco, USA:IEEE, 2010.2030-2037
23 Xu Feng, Zhang Jun-Ping. Facial microexpression recognition:a survey. Acta Automatica Sinica, 2017, 43(3):333-348(徐峰,张军平.人脸微表情识别综述.自动化学报, 2017, 43(3):333-348)
24 Xu Yuan, Xu Xiao-Liang, Li Cai-Nian, Jiang Mei, Zhang Jian-Guo. Pedestrian detection combining with SVM classifier and HOG feature extraction. Computer Engineering,2016, 42(1):56-60, 65(徐渊,许晓亮,李才年,姜梅,张建国.结合SVM分类器与HOG特征提取的行人检测.计算机工程, 2016, 42(1):56-60, 65)
25 Bo L F, Sminchisescu C. Twin gaussian processes for structured prediction. International Journal of Computer Vision,2010, 87(1-2):28-52
26 Cristianini N, Shawe-Taylor J, Elisseeff A, Kandola J. On kernel-target alignment. In:Proceedings of the 14th International Conference on Neural Information Processing Systems:Natural and Synthetic. Vancouver, British Columbia,Canada:MIT Press, 2001. 367-373
27 Gretton A, Bousquet O, Smola A J, Scholkopf B. Measuring statistical dependence with Hilbert-Schmidt norms.Algorithmic Learning Theory. Berlin Heidelberg, Germany:Springer-Verlag, 2005.