Header logo is ps

Distribution Fields with Adaptive Kernels for Large Displacement Image Alignment

2013

Conference Paper

ps


While region-based image alignment algorithms that use gradient descent can achieve sub-pixel accuracy when they converge, their convergence depends on the smoothness of the image intensity values. Image smoothness is often enforced through the use of multiscale approaches in which images are smoothed and downsampled. Yet, these approaches typically use fixed smoothing parameters which may be appropriate for some images but not for others. Even for a particular image, the optimal smoothing parameters may depend on the magnitude of the transformation. When the transformation is large, the image should be smoothed more than when the transformation is small. Further, with gradient-based approaches, the optimal smoothing parameters may change with each iteration as the algorithm proceeds towards convergence. We address convergence issues related to the choice of smoothing parameters by deriving a Gauss-Newton gradient descent algorithm based on distribution fields (DFs) and proposing a method to dynamically select smoothing parameters at each iteration. DF and DF-like representations have previously been used in the context of tracking. In this work we incorporate DFs into a full affine model for region-based alignment and simultaneously search over parameterized sets of geometric and photometric transforms. We use a probabilistic interpretation of DFs to select smoothing parameters at each step in the optimization and show that this results in improved convergence rates.

Author(s): Benjamin Mears and Laura Sevilla-Lara and Erik Learned-Miller
Book Title: British Machine Vision Conference (BMVC)
Year: 2013
Month: September
Publisher: BMVA Press

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference
Attachments: pdf
code

BibTex

@inproceedings{sevilla:BMVC:2013,
  title = {Distribution Fields with Adaptive Kernels for Large Displacement Image Alignment },
  author = {Mears, Benjamin and Sevilla-Lara, Laura and Learned-Miller, Erik},
  booktitle = {British Machine Vision Conference (BMVC) },
  publisher = {BMVA Press},
  month = sep,
  year = {2013},
  month_numeric = {9}
}