Author manuscript, published in 'IEEE Computer Vision and Pattern Recognition (2010) 1-8' Probabilistic 3D Occupancy Flow with Latent Silhouette Cues
Uložené v:
| Názov: | Author manuscript, published in 'IEEE Computer Vision and Pattern Recognition (2010) 1-8' Probabilistic 3D Occupancy Flow with Latent Silhouette Cues |
|---|---|
| Autori: | Li Guan, Jean-sébastien Franco, Marc Pollefeys |
| Prispievatelia: | The Pennsylvania State University CiteSeerX Archives |
| Zdroj: | http://hal.inria.fr/docs/00/49/77/96/PDF/1520.pdf. |
| Rok vydania: | 2010 |
| Zbierka: | CiteSeerX |
| Popis: | In this paper we investigate shape and motion retrieval in the context of multi-camera systems. We propose a new lowlevel analysis based on latent silhouette cues, particularly suited for low-texture and outdoor datasets. Our analysis does not rely on explicit surface representations, instead using an EM framework to simultaneously update a set of volumetric voxel occupancy probabilities and retrieve a best estimate of the dense 3D motion field from the last consecutively observed multi-view frame set. As the framework uses only latent, probabilistic silhouette information, the method yields a promising 3D scene analysis method robust to many sources of noise and arbitrary scene objects. It can be used as input for higher level shape modeling and structural inference tasks. We validate the approach and demonstrate its practical use for shape and motion analysis experimentally. 1. |
| Druh dokumentu: | text |
| Popis súboru: | application/pdf |
| Jazyk: | English |
| Relation: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.168; http://hal.inria.fr/docs/00/49/77/96/PDF/1520.pdf |
| Dostupnosť: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.168 http://hal.inria.fr/docs/00/49/77/96/PDF/1520.pdf |
| Rights: | Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| Prístupové číslo: | edsbas.92C6DEBF |
| Databáza: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | In this paper we investigate shape and motion retrieval in the context of multi-camera systems. We propose a new lowlevel analysis based on latent silhouette cues, particularly suited for low-texture and outdoor datasets. Our analysis does not rely on explicit surface representations, instead using an EM framework to simultaneously update a set of volumetric voxel occupancy probabilities and retrieve a best estimate of the dense 3D motion field from the last consecutively observed multi-view frame set. As the framework uses only latent, probabilistic silhouette information, the method yields a promising 3D scene analysis method robust to many sources of noise and arbitrary scene objects. It can be used as input for higher level shape modeling and structural inference tasks. We validate the approach and demonstrate its practical use for shape and motion analysis experimentally. 1. |
|---|