BMVC 2004, Kingston, 7th-9th Sept, 2004
Locally Planar Patch Features for Real-Time Structure from Motion
N. Molton, A. Davison and I. Reid (University of Oxford)
The performance of sequential structure from motion systems, where scene
mapping is sparse to permit real-time operation, depends greatly on the ability
to repeatedly measure the same visual features from a wide range of viewpoints.
While previous systems have tracked features as 2D templates in image
space, we show that long-term tracking is improved by treating salient
feature patches as observations of locally planar regions on 3D world surfaces.
Within a SLAM framework for motion and structure estimation, a
gradient-based image alignment method is used to deduce estimates feature
surface normal estimates, enabling pre-warping of templates for matching.
As an added benefit these normals provide a richer description of the scene.