Authors:
Dennis W. J. M. van de Wouw
1
;
Willem P. Sanberg
2
;
Gijs Dubbelman
2
and
Peter H. N. de With
2
Affiliations:
1
Eindhoven University of Technology and ViNotion B.V., Netherlands
;
2
Eindhoven University of Technology, Netherlands
Keyword(s):
Image Registration, Real-time, View Synthesis, Stixel-World.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Geometry and Modeling
;
Image and Video Analysis
;
Image Registration
;
Image-Based Modeling
;
Pattern Recognition
;
Robotics
;
Software Engineering
Abstract:
Scene alignment for images recorded from different viewpoints is a challenging task, especially considering strong parallax effects. This work proposes a diorama-box model for a 2.5D hierarchical alignment approach, which is specifically designed for image registration from a moving vehicle using a stereo camera. For this purpose, the Stixel World algorithm is used to partition the scene into super-pixels, which are transformed to 3D. This model is further refined by assigning a slanting orientation to each stixel and by interpolating between stixels, to prevent gaps in the 3D model. The resulting alignment shows promising results, where under normal viewing conditions, more than 96% of all annotated points are registered with an alignment error up to 5 pixels at a resolution of 1920x1440 pixels, executing at near-real time performance (4 fps) for the intended application.