POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts
We present a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other related state of the art techniques which focus on either segmentation or pose estimation individually, our approach tackles these two tasks together. Normally...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2006
|
| _version_ | 1817931308248072192 |
|---|---|
| author | Bray, M Kohli, P Torr, PHS |
| author_facet | Bray, M Kohli, P Torr, PHS |
| author_sort | Bray, M |
| collection | OXFORD |
| description | We present a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other related state of the art techniques which focus on either segmentation or pose estimation individually, our approach tackles these two tasks together. Normally, when optimizing for pose, it is traditional to use some fixed set of features, e.g. edges or chamfer maps. In contrast, our novel approach consists of optimizing a cost function based on a Markov Random Field (MRF). This has the advantage that we can use all the information in the image: edges, background and foreground appearances, as well as the prior information on the shape and pose of the subject and combine them in a Bayesian framework. Previously, optimizing such a cost function would have been computationally infeasible. However, our recent research in dynamic graph cuts allows this to be done much more efficiently than before. We demonstrate the efficacy of our approach on challenging motion sequences. Note that although we target the human pose inference problem in the paper, our method is completely generic and can be used to segment and infer the pose of any specified rigid, deformable or articulated object. |
| first_indexed | 2024-12-09T03:19:57Z |
| format | Conference item |
| id | oxford-uuid:2518af6e-3baf-4667-a360-028815c03fac |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:19:57Z |
| publishDate | 2006 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:2518af6e-3baf-4667-a360-028815c03fac2024-11-05T15:57:54ZPOSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cutsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:2518af6e-3baf-4667-a360-028815c03facEnglishSymplectic ElementsSpringer2006Bray, MKohli, PTorr, PHSWe present a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other related state of the art techniques which focus on either segmentation or pose estimation individually, our approach tackles these two tasks together. Normally, when optimizing for pose, it is traditional to use some fixed set of features, e.g. edges or chamfer maps. In contrast, our novel approach consists of optimizing a cost function based on a Markov Random Field (MRF). This has the advantage that we can use all the information in the image: edges, background and foreground appearances, as well as the prior information on the shape and pose of the subject and combine them in a Bayesian framework. Previously, optimizing such a cost function would have been computationally infeasible. However, our recent research in dynamic graph cuts allows this to be done much more efficiently than before. We demonstrate the efficacy of our approach on challenging motion sequences. Note that although we target the human pose inference problem in the paper, our method is completely generic and can be used to segment and infer the pose of any specified rigid, deformable or articulated object. |
| spellingShingle | Bray, M Kohli, P Torr, PHS POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts |
| title | POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts |
| title_full | POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts |
| title_fullStr | POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts |
| title_full_unstemmed | POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts |
| title_short | POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts |
| title_sort | posecut simultaneous segmentation and 3d pose estimation of humans using dynamic graph cuts |
| work_keys_str_mv | AT braym posecutsimultaneoussegmentationand3dposeestimationofhumansusingdynamicgraphcuts AT kohlip posecutsimultaneoussegmentationand3dposeestimationofhumansusingdynamicgraphcuts AT torrphs posecutsimultaneoussegmentationand3dposeestimationofhumansusingdynamicgraphcuts |