Layer extraction with a Bayesian model of shapes
This paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method differ...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2003
|
| _version_ | 1826315101057056768 |
|---|---|
| author | Torr, PHS Dick, AR Cipolla, R |
| author_facet | Torr, PHS Dick, AR Cipolla, R |
| author_sort | Torr, PHS |
| collection | OXFORD |
| description | This paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method differs from previous methods in that it uses a specific prior model for layer shape. A probabilistic hierarchical model of layer shape is constructed, which assigns a density function to the shape and spatial relationships between layers. This allows accurate and efficient algorithms to be used when finding the best segmentation. Here this framework is applied to architectural scenes, in which layers commonly correspond to windows or doors and hence belong to a tightly constrained family of shapes. |
| first_indexed | 2024-12-09T03:19:55Z |
| format | Conference item |
| id | oxford-uuid:204e967a-d14e-4386-b7b3-ba1ba5db46bd |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:19:55Z |
| publishDate | 2003 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:204e967a-d14e-4386-b7b3-ba1ba5db46bd2024-11-08T11:45:43ZLayer extraction with a Bayesian model of shapesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:204e967a-d14e-4386-b7b3-ba1ba5db46bdEnglishSymplectic ElementsSpringer2003Torr, PHSDick, ARCipolla, RThis paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method differs from previous methods in that it uses a specific prior model for layer shape. A probabilistic hierarchical model of layer shape is constructed, which assigns a density function to the shape and spatial relationships between layers. This allows accurate and efficient algorithms to be used when finding the best segmentation. Here this framework is applied to architectural scenes, in which layers commonly correspond to windows or doors and hence belong to a tightly constrained family of shapes. |
| spellingShingle | Torr, PHS Dick, AR Cipolla, R Layer extraction with a Bayesian model of shapes |
| title | Layer extraction with a Bayesian model of shapes |
| title_full | Layer extraction with a Bayesian model of shapes |
| title_fullStr | Layer extraction with a Bayesian model of shapes |
| title_full_unstemmed | Layer extraction with a Bayesian model of shapes |
| title_short | Layer extraction with a Bayesian model of shapes |
| title_sort | layer extraction with a bayesian model of shapes |
| work_keys_str_mv | AT torrphs layerextractionwithabayesianmodelofshapes AT dickar layerextractionwithabayesianmodelofshapes AT cipollar layerextractionwithabayesianmodelofshapes |