Abstract:
This paper tackles the recurrent problem of disparity estimation.
The measurement of image disparity is a fundamental
precursor to binocular depth estimation. The mapping from
disparity to depth is well understood, while the automatic
disparity extraction is still subject to errors. We propose
to use the image derivatives with the phase-based approach
to overcome the tuning problem of the filter. Moreover, we
propose a quadratic model for the singularities neighborhood
detection and the phase quasi-linearity will be revisited.
The approach is characterized by the simplicity of its
implementation. It also provides dense and accurate disparity
maps. A numerical error analysis against a ground-truth
shows that the results are very satisfactory.