Real-time human pose recognition in parts from single depth images

Real-time human pose recognition in parts from single depth images

Cached

Download Links

by Jamie Shotton , Andrew Fitzgibbon , Mat Cook , Toby Sharp , Mark Finocchio , Richard Moore , Alex Kipman , Andrew Blake

Venue:	In In CVPR, 2011. 3
Citations:	36 - 5 self

BibTeX

@INPROCEEDINGS{Shotton_real-timehuman,
    author = {Jamie Shotton and Andrew Fitzgibbon and Mat Cook and Toby Sharp and Mark Finocchio and Richard Moore and Alex Kipman and Andrew Blake},
    title = {Real-time human pose recognition in parts from single depth images},
    booktitle = {In In CVPR, 2011. 3},
    year = {}
}

Bookmark

OpenURL

Abstract

We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem. Our large and highly varied training dataset allows the classifier to estimate body parts invariant to pose, body shape, clothing, etc. Finally we generate confidence-scored 3D proposals of several body joints by reprojecting the classification result and finding local modes. The system runs at 200 frames per second on consumer hardware. Our evaluation shows high accuracy on both synthetic and real test sets, and investigates the effect of several training parameters. We achieve state of the art accuracy in our comparison with related work and demonstrate improved generalization over exact whole-skeleton nearest neighbor matching. 1.

Citations

2888	Induction of Decision Trees - Quinlan - 1986
936	Mean shift: a robust approach toward feature space analysis - Comaniciu, Meer - 2002
850	Shape matching and object recognition using shape contexts - Belongie, Malik, et al. - 2002
786	Random Forest - Breiman - 2001
646	Object class recognition by unsupervised scale-invariant learning - Fergus, Perona, et al.
327	Tracking people with twists and exponential maps - Bregler, Malik - 1998
305	Pictorial structures for object recognition - Felzenszwalb, Huttenlocher - 2005
211	Clustering to minimize the maximum intercluster distance - Gonzalez - 1985
151	A survey of advances in vision-based human motion capture and analysis, Computer Vision and Image Understanding 103 - Moeslund, Hilton, et al. - 2006
131	Implicit probabilistic models of human motion for synthesis and tracking - Sidenbladh, Black, et al. - 2002
126	Shape quantization and recognition with randomized trees - Amit, Geman - 1997
109	3d human pose from silhouettes by relevance vector regression - Agarwal, Triggs
104	Estimating human body configurations using shape context matching - Mori, Malik - 2002
97	Tracking loose-limbed people - Sigal, Bhatia, et al. - 2004
95	Pedestrian detection from a moving vehicle - Gavrila - 2002
87	Finding and tracking people from the bottom up - Ramanan, Forsyth - 2003
77	Probabilistic methods for finding people - Ioffe, Forsyth
75	Randomized Trees for Real-Time Keypoint Recognition - Lepetit, Lagger, et al. - 2005
73	Fast pose estimation with parameter sensitive hashing - Shakhnarovich, Viola, et al. - 2003
72	Semantic texton forests for image categorization and segmentation - SHOTTON, JOHNSON, et al. - 2008
65	Discriminative learning of markov random fields for segmentation of 3d range data - Anguelov, Taskar, et al. - 2005
60	The layout consistent random field for recognizing and segmenting partially occluded objects - Winn, Shotton - 2006
56	Poselets: Body part detectors trained using 3d human pose annotations - Bourdev, Malik - 2009
55	Fast discriminative visual codebooks using randomized clustering forests - MOOSMANN, TRIGGS, et al. - 2007
42	Vision-based human motion analysis: An overview. Computer Vision and Image Understanding 2007 - Poppe
40	Auto-context and its application to high-level vision tasks - Tu - 2008
22	Learning 3D mesh segmentation and labeling - KALOGERAKIS, HERTZMANN, et al. - 2010
20	fusion for 3d human body tracking with an articulated 3d body model - Knoop, Vacek, et al. - 2006
18	The Joint Manifold Model for Semi-Supervised Multi-Valued Regression - Navaratnam, Fitzgibbon, et al. - 2007
15	Real-time handtracking with a color glove - Wang, Popović - 2009
14	Local probabilistic regression for activity-independent human pose inference - Urtasun, Darrell - 2008
13	Implementing decision trees and forests on a GPU - Sharp - 2008
12	Randomized trees for human pose detection - Rogez, Rihan, et al. - 2008
11	D.: Real time motion capture using a single time-of-flight camera - Ganapathi, Plagemann, et al. - 2010
11	An appraisal of a decision tree approach to image classification - Shepherd - 1983
9	Nonlinear body pose estimation from depth images - Grest, Woetzel, et al.
9	S.: Realtime identification and localization of body parts from depth images - Plagemann, Ganapathi, et al. - 2010
8	Discriminative learning of visual words for 3D human pose estimation - Ning, Hu, et al.
5	Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images - Okada, Soatto - 2008
3	Kinect for Xbox 360 - WA
3	G.: Human pose estimation from a single view point, real-time range sensor - Siddiqui, Medioni - 2010
2	Constrained optimization for human pose estimation from depth sequences - Zhu, Fujimura - 2007