首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:201509--1)

基于二次生成对抗的人体姿态估计

Human Pose Estimation Based on Secondary Generation Adversary

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对人体姿态估计中因肢体、环境复杂性导致的估计结果不精确问题,提出了一种基于二次生成对抗的人体姿态估计方法,通过两个阶段对堆叠沙漏网络(SHN)进行生成对抗训练。首先将SHN作为第一个生成对抗网络模型的判别器,通过在线对抗数据加强训练,以提升SHN的估计性能;然后将SHN作为第二个生成对抗网络模型的生成器,将肢体几何约束作为判别器,通过第二次对抗训练再一次提升SHN的估计性能,得到最终的SHN。在公开数据集LSP和MPII上对本方法进行测试,结果表明,该方法能有效提升SHN的估计精确度。

Abstract

Aiming at the problem of inaccurate estimation results caused by the complexity of limbs and environment in human pose estimation, a human pose estimation method based on secondary generation adversary is proposed in this work. The stacked hourglass network (SHN) is trained for generation adversary through two stages. First, the SHN is used as a discriminator in the first generation adversarial network model, and the on-line adversarial data is used to strengthen training to improve the estimation performance of the SHN. Then, the SHN acts as a generator in the second generation adversarial network model, and the limb geometric constraints are used as the discriminator. The estimation performance of the SHN is improved again through the second adversarial training, and the final SHN is obtained. The proposed method is tested on the public data sets LSP and MPII, and the results show that it can effectively improve the estimation accuracy of the SHN.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O436

DOI:10.3788/LOP57.201509

所属栏目:机器视觉

基金项目:贵州省科技计划项目;

收稿日期:2020-01-14

修改稿日期:2020-03-09

网络出版日期:2020-10-01

作者单位    点击查看

张显坤:贵州大学大数据与信息工程学院大数据与智能技术重点实验室, 贵州 贵阳 550025
张荣芬:贵州大学大数据与信息工程学院大数据与智能技术重点实验室, 贵州 贵阳 550025
刘宇红:贵州大学大数据与信息工程学院大数据与智能技术重点实验室, 贵州 贵阳 550025

联系人作者:刘宇红(1693623574@qq.com)

备注:贵州省科技计划项目;

【1】Andriluka M, Roth S, Schiele B. Pictorial structures revisited: people detection and articulated pose estimation . [C]∥2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE. 2009, 1014-1021.

【2】Ladicky L. Torr P H S, Zisserman A. Human pose estimation using a joint pixel-wise and part-wise formulation . [C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013, Portland, OR, USA. New York: IEEE. 2013, 3578-3585.

【3】Toshev A, Szegedy C. DeepPose: human pose estimation via deep neural networks [J]. 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014, 1653-1660.Toshev A, Szegedy C. DeepPose: human pose estimation via deep neural networks [J]. 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014, 1653-1660.

【4】Newell A, Yang K Y, Deng J. Stacked hourglass networks for human pose estimation [M]. ∥Leibe B, Matas J, Sebe N, et al. Computer Vision-ECCV 2016. Lecture Notes in Computer Science. Cham: Springer. 2016, 9912: 483-499.

【5】Luo J Y, Xu Y, Tang C W, et al. Learning inverse mapping by autoencoder based generative adversarial nets [M]. ∥ Liu D, Xie S, Li Y, et al. Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science. Cham: Springer. 2017, 10635: 207-216.

【6】Liu K, Wang D, Rong M X. X-ray image classification algorithm based on semi-supervised generative adversarial networks [J]. Acta Optica Sinica. 2019, 39(8): 0810003.
刘坤, 王典, 荣梦学. 基于半监督生成对抗网络X光图像分类算法 [J]. 光学学报. 2019, 39(8): 0810003.

【7】Yang X L, Lin S Z, Lu X F, et al. Multimodal image fusion based on generative adversarial networks [J]. Laser & Optoelectronics Progress. 2019, 56(16): 161004.
杨晓莉, 蔺素珍, 禄晓飞, 等. 基于生成对抗网络的多模态图像融合 [J]. 激光与光电子学进展. 2019, 56(16): 161004.

【8】Zhang Q B, Zhang X H, Han H W. Backscattered light repairing method for underwater laser image based on improved generative adversarial network [J]. Laser & Optoelectronics Progress. 2019, 56(4): 041004.
张清博, 张晓晖, 韩宏伟. 基于改进生成对抗网络的水下激光图像后向散射光修复方法 [J]. 激光与光电子学进展. 2019, 56(4): 041004.

【9】Wang X L, Shrivastava A, Gupta A. A-fast-RCNN: hard positive generation via adversary for object detection . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 3039-3048.

【10】Peng X, Tang Z Q, Yang F, et al. Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation . [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2018, 2226-2234.

【11】Chou C J, Chien J T, Chen H T. Self adversarial training for human pose estimation [2020-01-02].https:∥arxiv.[2020-01-02]. 0, org/abs/1707: 02439.

【12】Chen Y, Shen C H, Wei X S, et al. Adversarial PoseNet: a structure-aware convolutional network for human pose estimation . [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 2017, 1221-1230.

【13】Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning [2019-12-28].http:∥arxiv.[2019-12-28]. 0, org/abs/1602: 07261.

【14】Tompson J, Jain A, Lecun Y, et al. Joint training of a convolutional network and a graphical model for human pose estimation [2020-01-01].https:∥arxiv.[2020-01-01]. 0, org/abs/1406: 2984.

【15】Berthelot D, Schumm T, Metz L. BEGAN: boundary equilibrium generative adversarial networks [2019-12-30].https:∥www.arxiv.[2019-12-30]. 0, org/abs/1703: 10717.

【16】Johnson S, Everingham M. Clustered pose and nonlinear appearance models for human pose estimation . [C]∥Procedings of the British Machine Vision Conference, BMVC 2010, August 31-September 3, 2010, Aberystwyth, UK. UK: BMVA. 2010, 1-11.

【17】Andriluka M, Pishchulin L, Gehler P, et al. 2D human pose estimation: new benchmark and state of the art analysis . [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE. 2014, 3686-3693.

【18】Sze V, Chen Y H, Yang T J, et al. Efficient processing of deep neural networks: a tutorial and survey [J]. Proceedings of the IEEE. 2017, 105(12): 2295-2329.

【19】Tieleman T, Hinton G. Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude [J]. COURSERA: Neural Networks for Machine Learning. 2012, 4(2): 26-31.

【20】Yang Y, Ramanan D. Articulated pose estimation with flexible mixtures-of-parts . [C]∥CVPR 2011, June 20-25, 2011, Providence, RI, USA. New York: IEEE. 2011, 1385-1392.

【21】Wei S H, Ramakrishna V, Kanade T, et al. Convolutional pose machines . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 4724-4732.

引用该论文

Zhang Xiankun,Zhang Rongfen,Liu Yuhong. Human Pose Estimation Based on Secondary Generation Adversary[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201509

张显坤,张荣芬,刘宇红. 基于二次生成对抗的人体姿态估计[J]. 激光与光电子学进展, 2020, 57(20): 201509

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF