International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

Realtime Multi-Person 2D Pose Estimation


Affiliations
1 Department of Information systems, Helwan University – Cairo, Egypt
2 Department of Computer science, Helwan University – Cairo, Egypt
 

This paper explains how to detect the 2D pose of multiple people in an image. We use in this paper Part Affinity Fields for Part Association (It is non-parametric representation), Confidence Maps for Part Detection, Multi-Person Parsing using PAFs, Simultaneous Detection and Association, this method achieve high accuracy and performance regardless the number of people in the image. This architecture placed first within the inaugural COCO 2016 key points challenge. Also, this architecture exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.

Keywords

Real Time Performance, Part Affinity Fields, Part Detection, Multi-person Parsing, Confidence Maps.
User
Notifications
Font Size

  • . A. Newell, K. Yang, and J. Deng. Stacked hourglass networks for human pose estimation. In ECCV, 2016. 1 [18] W. Ouyang, X. Chu, and X. Wang. Multi-source deep l.

  • . W. Ouyang, X. Chu, and X. Wang. Multi-source deep learning for human pose estimation. In CVPR, 2014. 1

  • . J. Tompson, R. Goroshin, A. Jain, Y. LeCun, and C. Bregler. Efficient object localization using convolutional networks. In CVPR, 2015. 1

  • . J. J. Tompson, A. Jain, Y. LeCun, and C. Bregler. Joint training of a convolutional network and a graphical model for human pose estimation. In NIPS, 2014

  • . X. Chen and A. Yuille. Articulated pose estimation by a graphical model with image dependent pairwise relations. In NIPS, 2014

  • . A. Toshev and C. Szegedy. Deeppose: Human pose estimation via deep neural networks. In CVPR, 2014

  • . V. Belagiannis and A. Zisserman. Recurrent human pose estimation. In 12th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2017.

  • . T. Pfister, J. Charles, and A. Zisserman. Flowing convnets for human pose estimation in videos. In ICCV, 2015.

  • . V. Ramakrishna, D. Munoz, M. Hebert, J. A. Bagnell, and Y. Sheikh. Pose machines: Articulated pose estimation via inference machines. In ECCV, 2014. 1.

  • . A. Bulat and G. Tzimiropoulos. Human pose estimation via convolutional part heatmap regression. In ECCV, 2016. 1

  • . D. Ramanan, D. A. Forsyth, and A. Zisserman. Strike a Pose: Tracking people by finding stylized poses. In CVPR, 2005. 1.

  • . D. Ramanan, D. A. Forsyth, and A. Zisserman. Strike a Pose: Tracking people by finding stylized poses. In CVPR, 2005. 1.

  • . Y. Yang and D. Ramanan. Articulated human detection with flexible mixtures of parts. In TPAMI, 2013. 1

  • . L. Pishchulin, M. Andriluka, P. Gehler, and B. Schiele. Poselet conditioned pictorial structures. In CVPR, 2013. 1.

  • . P. F. Felzenszwalb and D. P. Huttenlocher. Pictorial structures for object recognition. In IJCV, 2005. 1.

  • . S.-E. Wei, V. Ramakrishna, T. Kanade, and Y. Sheikh. Convolutional pose machines. In CVPR, 2016. 1, 2, 3, 6.

  • . W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed. Ssd: Single shot multibox detector. In ECCV, 2016. 6.

  • . M. Andriluka, S. Roth, and B. Schiele. Monocular 3D pose estimation and tracking by detection. In CVPR, 2010. 1.

  • . M. Andriluka, S. Roth, and B. Schiele. Pictorial structures revisited: people detection and articulated pose estimation. In CVPR, 2009. 1.


Abstract Views: 205

PDF Views: 0




  • Realtime Multi-Person 2D Pose Estimation

Abstract Views: 205  |  PDF Views: 0

Authors

Mona Nasr
Department of Information systems, Helwan University – Cairo, Egypt
Rana Osama
Department of Computer science, Helwan University – Cairo, Egypt
Hussein Ayman
Department of Computer science, Helwan University – Cairo, Egypt
Nouran Mosaad
Department of Computer science, Helwan University – Cairo, Egypt
Nourhan Ebrahim
Department of Computer science, Helwan University – Cairo, Egypt
Adriana mounir
Department of Information systems, Helwan University – Cairo, Egypt

Abstract


This paper explains how to detect the 2D pose of multiple people in an image. We use in this paper Part Affinity Fields for Part Association (It is non-parametric representation), Confidence Maps for Part Detection, Multi-Person Parsing using PAFs, Simultaneous Detection and Association, this method achieve high accuracy and performance regardless the number of people in the image. This architecture placed first within the inaugural COCO 2016 key points challenge. Also, this architecture exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.

Keywords


Real Time Performance, Part Affinity Fields, Part Detection, Multi-person Parsing, Confidence Maps.

References