Abstract
This article tackles the problem of multi-person 3D human pose estimation based on monocular image sequence in a three-step framework: (1) we detect 2D human skeletons in each frame across the image sequence; (2) we track each person through the image sequence and identify the sequence of 2D skeletons for each person; (3) we reconstruct the 3D human skeleton for each person from the detected 2D human joints, by using prelearned base poses and considering the temporal smoothness. We evaluate our framework on the Human3.6M dataset and the multi-person image sequence captured by ourselves. The quantitative results on the Human3.6M dataset and the qualitative results on our constructed test data demonstrate the effectiveness of our proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
3D shape estimation from 2D landmarks: a convex relaxation approach (2015)
Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: CVPR, pp. 1446–1455 (2015)
Boumal, N.: Manopt, a matlab toolbox for optimization on manifolds. JMLR 15(1), 1455–1459 (2014)
Danelljan, M., Häger, G.: Accurate scale estimation for robust visual tracking. In: BMVC. BMVA Press (2014)
Fang, H.: RMPE: regional multi-person pose estimation. CoRR abs/1612.00137, 4321–4330 (2016)
Huang, Z., Wan, C., Probst, T., Van Gool, L.: Deep learning on lie groups for skeleton-based action recognition. In: CVPR, pp. 1243–1252 (2017)
Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. T-PAMI 36(7), 1325–1339 (2014)
Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: CVPR, pp. 4570–4579 (2017)
Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: CVPR, vol. 7, p. 43 (2017)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Nesterov, Y., et al.: Gradient methods for minimizing composite objective function (2007)
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_29
Ramakrishna, V., Kanade, T., Sheikh, Y.: Reconstructing 3D human pose from 2D image landmarks. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 573–586. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33765-9_41
Simo-Serra, E., Quattoni, A.: A joint model for 2D and 3D pose estimation from a single image. In: CVPR, pp. 3634–3641 (2013)
Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: CVPR, pp. 1677–1684 (2000)
Tekin, B., Sun, X., Wang, X., Lepetit, V., Fua, P.: Predicting people’s 3D poses from short sequences. CoRR abs/1504.08200 (2015)
Vemulapalli, R., Arrate, F.: Human action recognition by representing 3D skeletons as points in a lie group. In: CVPR, pp. 588–595 (2014)
Wandt, B.: 3D reconstruction of human motion from monocular image sequences. T-PAMI 38, 1505–1516 (2016)
Wang, C., Wang, Y.: Robust estimation of 3D human poses from a single image. In: CVPR, pp. 2369–2376 (2014)
Yasin, H., Iqbal, U.: A dual-source approach for 3D pose estimation from a single image. In: CVPR, pp. 4948–4956 (2016)
Zhou, X., Zhu, M.: Sparseness meets deepness: 3d human pose estimation from monocular video. In: CVPR, pp. 4966–4975 (2016)
Acknowledgements
The work was supported by the National Basic Research Program of China under Grant (No. 2015CB856004) and the Key Basic Research Program of Shanghai Science and Technology Commission, China under Grant (Nos. 15JC1400103, 16JC1402800).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, R. et al. (2019). Multi-person 3D Pose Estimation from Monocular Image Sequences. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11954. Springer, Cham. https://doi.org/10.1007/978-3-030-36711-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-36711-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36710-7
Online ISBN: 978-3-030-36711-4
eBook Packages: Computer ScienceComputer Science (R0)