Hand tracking using a quadric surface model and Bayesian filtering
Within this paper a technique for model-based 3D hand tracking is presented. A hand model is built from a set of truncated quadrics, approximating the anatomy of a real hand with few parameters. Given that the projection of a quadric onto the image plane is a conic, the contours can be generated eff...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer Nature
2003
|
| _version_ | 1826314539517345792 |
|---|---|
| author | Cipolla, R Stenger, B Thayananthan, A Torr, PHS |
| author_facet | Cipolla, R Stenger, B Thayananthan, A Torr, PHS |
| author_sort | Cipolla, R |
| collection | OXFORD |
| description | Within this paper a technique for model-based 3D hand tracking is presented. A hand model is built from a set of truncated quadrics, approximating the anatomy of a real hand with few parameters. Given that the projection of a quadric onto the image plane is a conic, the contours can be generated efficiently. These model contours are used as shape templates to evaluate possible matches in the current frame. The evaluation is done within a hierarchical Bayesian filtering framework, where the posterior distribution is computed efficiently using a tree of templates. We demonstrate the effectiveness of the technique by using it for tracking 3D articulated and non-rigid hand motion from monocular video sequences in front of a cluttered background. |
| first_indexed | 2024-09-25T04:34:02Z |
| format | Conference item |
| id | oxford-uuid:c61d473e-8541-4d40-9ccb-effb94e73e84 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:34:02Z |
| publishDate | 2003 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | oxford-uuid:c61d473e-8541-4d40-9ccb-effb94e73e842024-09-10T15:01:45ZHand tracking using a quadric surface model and Bayesian filteringConference itemhttp://purl.org/coar/resource_type/c_5794uuid:c61d473e-8541-4d40-9ccb-effb94e73e84EnglishSymplectic ElementsSpringer Nature2003Cipolla, RStenger, BThayananthan, ATorr, PHSWithin this paper a technique for model-based 3D hand tracking is presented. A hand model is built from a set of truncated quadrics, approximating the anatomy of a real hand with few parameters. Given that the projection of a quadric onto the image plane is a conic, the contours can be generated efficiently. These model contours are used as shape templates to evaluate possible matches in the current frame. The evaluation is done within a hierarchical Bayesian filtering framework, where the posterior distribution is computed efficiently using a tree of templates. We demonstrate the effectiveness of the technique by using it for tracking 3D articulated and non-rigid hand motion from monocular video sequences in front of a cluttered background. |
| spellingShingle | Cipolla, R Stenger, B Thayananthan, A Torr, PHS Hand tracking using a quadric surface model and Bayesian filtering |
| title | Hand tracking using a quadric surface model and Bayesian filtering |
| title_full | Hand tracking using a quadric surface model and Bayesian filtering |
| title_fullStr | Hand tracking using a quadric surface model and Bayesian filtering |
| title_full_unstemmed | Hand tracking using a quadric surface model and Bayesian filtering |
| title_short | Hand tracking using a quadric surface model and Bayesian filtering |
| title_sort | hand tracking using a quadric surface model and bayesian filtering |
| work_keys_str_mv | AT cipollar handtrackingusingaquadricsurfacemodelandbayesianfiltering AT stengerb handtrackingusingaquadricsurfacemodelandbayesianfiltering AT thayananthana handtrackingusingaquadricsurfacemodelandbayesianfiltering AT torrphs handtrackingusingaquadricsurfacemodelandbayesianfiltering |