Abstract
A new approach for formulating prior knowledge in structure form motion is presented, where the structure is viewed as a 3D stochastic variable, hereby priors are more naturally expressed. It is demonstrated that this formulation is efficient for regularizing structure reconstruction via prior knowledge. Specifically algorithms for imposing priors in the proposed formulation are presented.
Original language | English |
---|---|
Title of host publication | Proceedings of the Scandinavian Image Analysis - SCIA'01 |
Editors | Ivar Austvoll |
Publication date | 2001 |
Pages | 477-481 |
Publication status | Published - 2001 |
Event | 12th Scandinavian Conference on Image Analysis - Bergen, Norway Duration: 11 Jun 2001 → 14 Jun 2001 Conference number: 12 |
Conference
Conference | 12th Scandinavian Conference on Image Analysis |
---|---|
Number | 12 |
Country/Territory | Norway |
City | Bergen |
Period | 11/06/2001 → 14/06/2001 |