Abstract
While recent progress in pose recognition has been impressive, there remains ample margin for improvement, particularly in challenging scenarios such as low resolution images. In this paper, we consider the problem of recognizing pose from tiny images of people, down to 24px high. This is relevant when interpreting people at a distance, which is important in applications such as autonomous driving and surveillance in crowds. Addressing this challenge, which has received little attention so far, can inspire modifications of traditional deep learning approaches that are likely to be applicable well beyond the case of pose recognition.
Given the intrinsic ambiguity of recovering a person’s pose from a small image, we propose to predict a posterior probability over pose configurations. In order to do so we: (1) define a new neural network architecture that explicitly expresses uncertainty; (2) train the network by explicitly minimizing a novel loss function based on the data log-likelihood; and (3) estimate posterior probability maps for all joints as a semi-dense sub-pixel Gaussian mixture model. We asses our method on downsampled versions of popular pose recognition benchmarks as well as on an additional newly-introduced testing dataset. Compared to state-of-the-art techniques, we show far superior performance at low resolution for both deterministic and probabilistic pose prediction.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The dataset can be downloaded at http://www.robots.ox.ac.uk/vgg/data/tinyPeople/.
References
Andriluka, M., Pishchulin, L., Gehler, P., Bernt, S.: 2D human pose estimation: new benchmark and state of the art analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014
Belagiannis, V., Zisserman, A.: Recurrent human pose estimation. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp. 468–475. IEEE (2017)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531 (2014)
Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
Dutta, A., Gupta, A., Zissermann, A.: VGG image annotator (VIA) (2016). http://www.robots.ox.ac.uk/vgg/software/via/. Accessed 14 Nov 2017
Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: null. p. 726. IEEE (2003)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008. pp. 1–8. IEEE (2008)
Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Trans. Comput. 100(1), 67–92 (1973)
Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hu, P., Ramanan, D.: Finding tiny faces. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
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_3
Kendall, A., Cipolla, R.: Modelling uncertainty in deep learning for camera relocalization. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 4762–4769. IEEE (2016)
Kendall, A., Gal, Y.: What uncertainties do we need in bayesian deep learning for computer vision? arXiv preprint arXiv:1703.04977 (2017)
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_48
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
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
Novotny, D., Larlus, D., Vedaldi, A.: Learning 3D object categories by looking around them. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild, July 2017
Park, D., Ramanan, D.: Articulated pose estimation with tiny synthetic videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 58–66 (2015)
Pfister, T., Charles, J., Zisserman, A.: Flowing convnets for human pose estimation in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1913–1921 (2015)
Pishchulin, L., Jain, A., Andriluka, M., Thormählen, T., Schiele, B.: Articulated people detection and pose estimation: reshaping the future. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3178–3185. IEEE (2012)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Rupprecht, C., et al.: Learning in an uncertain world: representing ambiguity through multiple hypotheses. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
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)
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)
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)
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)
Acknowledgement
We are very grateful to Continental Corporation for sponsoring this research.
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
Neumann, L., Vedaldi, A. (2019). Tiny People Pose. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11363. Springer, Cham. https://doi.org/10.1007/978-3-030-20893-6_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-20893-6_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20892-9
Online ISBN: 978-3-030-20893-6
eBook Packages: Computer ScienceComputer Science (R0)