Abstract
This chapter will discuss approaches to 2D human pose estimation and tracking in a non-overlapping camera network. It will demonstrate the limitations of current approaches and suggest strategies to overcome them. In particular, computational intractability due to high dimensional limb space, violation of articulation constraints, and view-point dependence. The chapter is divided into three major components; namely, search space reduction, pose validation, and view-invariant pose tracking in a non-overlapping camera network. Firstly, we present approaches for search space reduction, such as Kinematic Tree based sub-region selection for each limb, Mean-Shift based maxima search on the likelihood surface, and temporal based reduction of search in parameter space. Secondly, we devise a PCA based Pose Validation strategy to prune out anatomically incorrect hypotheses. Thirdly, we propose to incorporate articulation constraints while keeping the problem tractable. Finally, we enable view-invariance through the fusion of only two pose detectors and an articulated skeleton tracker.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
In this work, by articulated skeleton we refer to a skeleton in which each pair of adjacent limbs shares a common point (a joint) called articulation point. This common point introduces a joint constraint on the movement of these limbs called articulation constraint.
- 2.
- 3.
- 4.
PCP computes the distance between the estimated skeleton and the ground truth, skeletons found closer than a set threshold (commonly set to \(0.5\)) are considered correct.
References
Andriluka M, Roth S, Schiele B (2010) Monocular 3d pose estimation and tracking by detection. In: CVPR, San Francisco, pp 623–630
Andriluka M, Roth S, Schiele B (2012) Discriminative appearance models for pictorial structures. Int J Comp Vis 99(3):259–280
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, vol 1, pp 886–893
Datta A, Sheikh YA, Kanade T (2008) Linear motion estimation for systems of articulated planes. In: IEEE CVPR, June 2008
Eichner M, Marin-Jimenez M, Zisserman A, Ferrari V (2012) 2D articulated human pose estimation and retrieval in (almost) unconstrained still images. Int J Comp Vis 99:190–214
Ess A, Leibe B, Van Gool L (2007) Depth and appearance for mobile scene analysis. In: IEEE ICCV, Oct 2007
Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans PAMI 32:1627–1645
Fischler MA, Elschlager RA (1973) The representation and matching of PS. IEEE Trans Comput 22(1):67–92
Hassan A, Taj M (2014) 2D articulated pose tracking: a hybrid approach. In: Proceedings of IEEE international conference on image processing, Paris, Oct 2014
Lucey S, Saragih J, Cohn J (2011) Deformable model fitting by regularized landmark mean-shifts. Int J Comp Vis 91(2):200–215
Johnson S, Everingham M (2010) Clustered pose and nonlinear appearance models for human pose estimation. In: Proceedings of British machine vision conference, pp 1–11
Kalal Z, Mikolajczyk K, Matas J (2012) Tracking-learning-detection. IEEE Trans PAMI 34:1409–1422
Khalid AR, Hassan A, Taj M (2014) Efficient 2D pose estimation using mean-shift. In: Proceedings of IEEE international conference on image processing, Paris, Oct 2014
Maji S, Berg AC, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: IEEE CVPR, Anchorage, Alaska
Pishchulin L, Jain A, Andriluka M, Thormaehlen T, Schiele B (2012) Articulated people detection and pose estimation: reshaping the future. In: CVPR, Providence
Ramanan D (2006) Learning to parse images of articulated objects. In: NIPS, Vancouver
Ramanan D (2011) Visual analysis of humans, Chapter 11: part-based models for finding people and estimating their pose, Springer, pp 199–224
Sadeghi MA, Farhadi A (2011) Recognition using visual phrases. In: IEEE CVPR, Colorado Springs, USA, June 2011
Sapp B, Toshev A, Taskar B (2010) Cascaded models for articulated pose estimation. In: Proceedings of the European conference on computer vision, Berlin, Heidelberg, pp 406–420
Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, Kipman A, Blake A (2011) Real-time human pose recognition in parts from single depth images. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 1297–1304
Sigal L, Balan AO, Black MJ (2006) Humaneva: synchronized video and motion capture dataset for evaluation of articulated human motion. Int J Comp Vis 87(1):4–27
Simo-Serra E, Quattoni A, Torras C, Moreno-Noguer F (2013) A joint model for 2D and 3D pose estimation from a single image. In: Proceedings of the conference on computer vision and pattern recognition (CVPR)
Wu C, Aghajan H (2008) Human pose estimation in vision networks via distributed local processing and nonparametric belief propagation. In: Proceedings of the 10th international conference on advanced concepts for intelligent vision systems, ACIVS’08, Springer, Berlin, pp 1006–1017
Yang Y, Ramanan D (2011) Articulated pose estimation with flexible mixtures-of-parts. In: IEEE CVPR, Washington
Zuffi S, Freifeld O, Black MJ (2012) From pictorial structures to deformable structures. In: IEEE CVPR, Washington
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Taj, M., Hassan, A., Khalid, A.R. (2014). 2D Human Pose Estimation and Tracking in Non-overlapping Cameras. In: Spagnolo, P., Mazzeo, P., Distante, C. (eds) Human Behavior Understanding in Networked Sensing. Springer, Cham. https://doi.org/10.1007/978-3-319-10807-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-10807-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10806-3
Online ISBN: 978-3-319-10807-0
eBook Packages: Computer ScienceComputer Science (R0)