Active view selection for efficient 3D scene reconstruction
This paper presents an active sensing process for the efficient reconstruction of a real world environment using multiple views of a scene captured by a laser finder onboard a mobile robot. To resolve the ambiguities caused by occlusions there is the need to acquire multiple range views at different viewpoints. A strategy for optimizing the selection of the next sensing position and orientation based on previously detected occlusions is proposed. No priori knowledge about the scene is used for planning the next views. The system evaluates the set of capture points from which all the necessary data can be acquired aiming at minimizing its number. Among these points it then selects the one(s) maximizing the occluded areas to be resolved.
Bibliographic Reference: Paper presented: ICPR 96, Vienna (AT), August 25-30, 1996
Availability: Available from (1) as Paper EN 39989 ORA
Record Number: 199611262 / Last updated on: 1996-10-29
Original language: en
Available languages: en