Advertisement

Occlusion-Aware Siamese Network for Human Pose Estimation

Conference paper
  • 571 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12365)

Abstract

Pose estimation usually suffers from varying degrees of performance degeneration owing to occlusion. To conquer this dilemma, we propose an occlusion-aware siamese network to improve the performance. Specifically, we introduce scheme of feature erasing and reconstruction. Firstly, we utilize attention mechanism to predict the occlusion-aware attention map which is explicitly supervised and clean the feature map which is contaminated by different types of occlusions. Nevertheless, the cleaning procedure not only removes the useless information but also erases some valuable details. To overcome the defects caused by the erasing operation, we perform feature reconstruction to recover the information destroyed by occlusion and details lost in cleaning procedure. To make reconstructed features more precise and informative, we adopt siamese network equipped with OT divergence to guide the features of occluded images towards those of the un-occluded images. Algorithm is validated on MPII, LSP and COCO benchmarks and we achieve promising results.

Keywords

Siamese network Occlusion Human pose estimation 

Notes

Acknowledgements

This work was supported by the Research and Development Projects in the Key Areas of Guangdong Province (No.2019B010153001), National Natural Science Foundation of China under Grants 61772527, 61976520 and 61806200. This work was also supported by the Technology Cooperation Project of Application Laboratory, Huawei Technologies Co., Ltd. (FA2018111061-2019SOW05).

References

  1. 1.
    Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686–3693 (2014)Google Scholar
  2. 2.
    Chen, L., et al.: Symmetric variational autoencoder and connections to adversarial learning. In: International Conference on Artificial Intelligence and Statistics, pp. 661–669 (2018)Google Scholar
  3. 3.
    Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103–7112 (2018)Google Scholar
  4. 4.
    Chen, Y., Shen, C., Wei, X.S., Liu, L., Yang, J.: Adversarial PoseNet: a structure-aware convolutional network for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1212–1221 (2017)Google Scholar
  5. 5.
    Chou, C.J., Chien, J.T., Chen, H.T.: Self adversarial training for human pose estimation. arXiv preprint arXiv:1707.02439 (2017)
  6. 6.
    Chu, X., Ouyang, W., Li, H., Wang, X.: Structured feature learning for pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4715–4723 (2016)Google Scholar
  7. 7.
    Chu, X., Ouyang, W., Wang, X., et al.: CRF-CNN: modeling structured information in human pose estimation. In: Advances in Neural Information Processing Systems, pp. 316–324 (2016)Google Scholar
  8. 8.
    Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1831–1840 (2017)Google Scholar
  9. 9.
    Genevay, A., Peyré, G., Cuturi, M.: Learning generative models with Sinkhorn divergences. arXiv preprint arXiv:1706.00292 (2017)
  10. 10.
    Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34–50. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_3CrossRefGoogle Scholar
  11. 11.
    Jain, A., Tompson, J., Andriluka, M., Taylor, G.W., Bregler, C.: Learning human pose estimation features with convolutional networks. arXiv preprint arXiv:1312.7302 (2013)
  12. 12.
    Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol. 2, p. 5. Citeseer (2010)Google Scholar
  13. 13.
    Ke, L., Chang, M.-C., Qi, H., Lyu, S.: Multi-scale structure-aware network for human pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 731–746. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01216-8_44CrossRefGoogle Scholar
  14. 14.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  15. 15.
    Li, H., Dai, B., Shi, S., Ouyang, W., Wang, X.: Feature intertwiner for object detection. In: International Conference on Learning Representations (2018)Google Scholar
  16. 16.
    Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10602-1_48CrossRefGoogle Scholar
  17. 17.
    Liu, W., Chen, J., Li, C., Qian, C., Chu, X., Hu, X.: A cascaded inception of inception network with attention modulated feature fusion for human pose estimation. In: AAAI (2018)Google Scholar
  18. 18.
    Lu, Y., Chen, L., Saidi, A.: Optimal transport for deep joint transfer learning. arXiv preprint arXiv:1709.02995 (2017)
  19. 19.
    Marras, I., Palasek, P., Patras, I.: Deep globally constrained MRFs for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3466–3475 (2017)Google Scholar
  20. 20.
    Moeslund, T.B., Granum, E.: A survey of computer vision-based human motion capture. Comput. Vis. Image Underst. 81(3), 231–268 (2001)CrossRefGoogle Scholar
  21. 21.
    Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46484-8_29CrossRefGoogle Scholar
  22. 22.
    Nie, X., Feng, J., Zuo, Y., Yan, S.: Human pose estimation with parsing induced learner. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2100–2108 (2018)Google Scholar
  23. 23.
    Ning, G., Zhang, Z., He, Z.: Knowledge-guided deep fractal neural networks for human pose estimation. IEEE Trans. Multimedia 20(5), 1246–1259 (2018)CrossRefGoogle Scholar
  24. 24.
    Rafi, U., Leibe, B., Gall, J., Kostrikov, I.: An efficient convolutional network for human pose estimation. In: BMVC, vol. 1, p. 2 (2016)Google Scholar
  25. 25.
    Salimans, T., Zhang, H., Radford, A., Metaxas, D.: Improving GANs using optimal transport. arXiv preprint arXiv:1803.05573 (2018)
  26. 26.
    Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7912–7921 (2019)Google Scholar
  27. 27.
    Su, C., Li, J., Zhang, S., Xing, J., Gao, W., Tian, Q.: Pose-driven deep convolutional model for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3960–3969 (2017)Google Scholar
  28. 28.
    Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693–5703 (2019)Google Scholar
  29. 29.
    Tang, W., Wu, Y.: Does learning specific features for related parts help human pose estimation? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1107–1116 (2019)Google Scholar
  30. 30.
    Tang, W., Yu, P., Wu, Y.: Deeply learned compositional models for human pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 197–214. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_12CrossRefGoogle Scholar
  31. 31.
    Tieleman, T., Hinton, G.: Lecture 6.5-RMSprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. 4(2), 26–31 (2012)Google Scholar
  32. 32.
    Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 648–656 (2015)Google Scholar
  33. 33.
    Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp. 1799–1807 (2014)Google Scholar
  34. 34.
    Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653–1660 (2014)Google Scholar
  35. 35.
    Wang, W., Xu, H., Wang, G., Wang, W., Carin, L.: An optimal transport framework for zero-shot learning. arXiv preprint arXiv:1910.09057 (2019)
  36. 36.
    Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724–4732 (2016)Google Scholar
  37. 37.
    Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472–487. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01231-1_29CrossRefGoogle Scholar
  38. 38.
    Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  39. 39.
    Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1290–1299. IEEE (2017)Google Scholar
  40. 40.
    Zhang, H., et al.: Human pose estimation with spatial contextual information. arXiv preprint arXiv:1901.01760 (2019)
  41. 41.
    Zhou, L., Chen, Y., Wang, J., Lu, H.: Progressive bi-c3d pose grammar for human pose estimation. In: AAAI, pp. 13033–13040 (2020)Google Scholar
  42. 42.
    Zhou, L., Chen, Y., Wang, J., Tang, M., Lu, H.: Bi-directional message passing based scanet for human pose estimation. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 1048–1053. IEEE (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.National Laboratory of Pattern RecognitionInstitute of Automation, Chinese Academy of SciencesBeijingChina
  2. 2.School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijingChina
  3. 3.ObjectEye Inc.BeijingChina
  4. 4.NEXWISE Co., Ltd.GuangzhouChina

Personalised recommendations