The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Covariance scaled sampling for monocular 3D body tracking
Open accessAbstract
We present a method for recovering 3D human body motion from monocular video sequences using robust image matching, joint limits and non-self-intersection constraints, and a new sample-and-refine search strategy guided by rescaled cost-function covariances. Monocular 3D body tracking is challenging: for reliable tracking at least 30 joint parameters need to be estimated, subject to highly nonlinear physical constraints; the problem is chronically ill conditioned as about 1/3 of the d.o.f. (the depth-related ones) are almost unobservable in any given monocular image; and matching an imperfect, highly flexible self-occluding model to cluttered image features is intrinsically hard. To reduce correspondence ambiguities we use a carefully designed robust matching-cost metric that combines robust optical flow, edge energy, and motion boundaries. Even so, the ambiguity, nonlinearity and non-observability make the parameter-space cost surface multi-modal, unpredictable and ill conditioned, so minimizing it is difficult. We discuss the limitations of CONDENSATION-like samplers, and introduce a novel hybrid search algorithm that combines inflated-covariance-scaled sampling and continuous optimization subject to physical constraints. Experiments on some challenging monocular sequences show that robust cost modelling, joint and self-intersection constraints, and informed sampling are all essential for reliable monocular 3D body tracking.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Practical Methods of Optimization
Fletcher, R. (2000) · Wiley eBooks · doi:10.1002/9781118723203 · Cited by 7,605
Practical methods of optimization
(1988) · Mathematics and Computers in Simulation · doi:10.1016/0378-4754(88)90129-2 · Cited by 5,818
Bundle Adjustment — A Modern Synthesis
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_21 · Cited by 3,988
Self-citationThe Visual Analysis of Human Movement: A Survey
Gavrila, D. M. (1999) · Computer Vision and Image Understanding · doi:10.1006/cviu.1998.0716 · Cited by 1,782
The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields
Black, M. J., & Anandan, P. (1996) · Computer Vision and Image Understanding · doi:10.1006/cviu.1996.0006 · Cited by 1,570
Articulated body motion capture by annealed particle filtering
Deutscher, J., Blake, A., & Reid, I. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854758 · Cited by 868
Black, M. J., & Rangarajan, A. (1996) · International Journal of Computer Vision · doi:10.1007/bf00131148 · Cited by 757
Global and local deformations of solid primitives
Barr, A. H. (1984) · ACM SIGGRAPH Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) · doi:10.1145/800031.808573 · Cited by 731
Tracking people with twists and exponential maps
Bregler, C., & Malik, J. (2002) · Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231) · doi:10.1109/cvpr.1998.698581 · Cited by 719
3-D model-based tracking of humans in action: a multi-view approach
Gavrila, D. M., & Davis, L. S. (1996) · Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1996.517056 · Cited by 702
Stochastic Tracking of 3D Human Figures Using 2D Image Motion
Sidenbladh, H., Black, M. J., & Fleet, D. J. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45053-x_45 · Cited by 700
Walsh, G. R. (1975) · Cited by 508
Global and local deformations of solid primitives
Barr, A. H. (1984) · ACM SIGGRAPH Computer Graphics · doi:10.1145/964965.808573 · Cited by 480
Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking
MacCormick, J., & Isard, M. (2000) · Lecture notes in computer science · doi:10.1007/3-540-45053-x_1 · Cited by 469
Cardboard people: a parameterized model of articulated image motion
Ju, S. X., Black, M. J., & Yacoob, Y. (2002) · Proceedings of the Second International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.1996.557241 · Cited by 436
Model-based tracking of self-occluding articulated objects
Rehg, J. M., & Kanade, T. (2002) · Proceedings of IEEE International Conference on Computer Vision · doi:10.1109/iccv.1995.466882 · Cited by 392
A multiple hypothesis approach to figure tracking
Cham, T.-J., & Rehg, J. M. (2003) · Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149) · doi:10.1109/cvpr.1999.784636 · Cited by 283
Bayesian Reconstruction of 3D Human Motion from Single-Camera Video
Howe, N. R., Leventon, M. E., & Freeman, W. T. (1999) · Smith ScholarWorks (Smith College) · Cited by 255
Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection
Kakadiaris, I. A., & Metaxas, D. (1996) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1996.517057 · Cited by 220
Monocular tracking of the human arm in 3D
Goncalves, L., Di Bernardo, E., Ursella, E., & Perona, P. (2002) · Proceedings of IEEE International Conference on Computer Vision · doi:10.1109/iccv.1995.466861 · Cited by 204
Tracking Persons in Monocular Image Sequences
Wachter, S., & Nagel, H.-H. (1999) · Computer Vision and Image Understanding · doi:10.1006/cviu.1999.0758 · Cited by 202
Brand, M. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790422 · Cited by 202
Probabilistic tracking in a metric space
Toyama, K., & Blake, A. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937599 · Cited by 197
Inferring body pose without tracking body parts
Rosales, R., & Sclaroff, S. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854946 · Cited by 170
Reconstruction of articulated objects from point correspondences in a single uncalibrated image
Taylor, C. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.855885 · Cited by 159
Articulated soft objects for video-based body modeling
Plankers, R., & Fua, P. (2002) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2001.937545 · Cited by 118
Wormholes in shape space: tracking through discontinuous changes in shape
Heap, T., & Hogg, D. (2002) · International Conference on Computer Vision · doi:10.1109/iccv.1998.710741 · Cited by 114
Tracking self-occluding articulated objects in dense disparity maps
Jojić, N., Turk, M., & Huang, T. S. (1999) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1999.791207 · Cited by 70
Blake, A., North, B., & Isard, M. (1998) · neural information processing systems · Cited by 58
Cited by
Comaniciu, D., Ramesh, V., & Meer, P. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1195991 · Cited by 4,560
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.248 · Cited by 3,653
Self-citationA Survey on Visual Surveillance of Object Motion and Behaviors
Hu, W., Tan, T., Wang, L., & Maybank, S. (2004) · IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2004.829274 · Cited by 2,132
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., & Black, M. J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_34 · Cited by 1,498
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision
Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., & Theobalt, C. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00064 · Cited by 1,142
Metadata
- Authors
- Sminchisescu, C., & Triggs, B.
- Venue
- Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
- Publisher
- IEEE Comput. Soc
- Published
- 2005-08-24
- Volume
- 1
- Pages
- I-447-I-454
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2131432112
- Cited by
- 290
- References
- 29
- FWCI
- 25.01
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.