Surface Registration using Genetic Algorithm in Reduced Search Space

Abstract

Surface registration is a technique that is used in various areas such as object recognition and 3D model reconstruction. Problem of surface registration can be analyzed as an optimization problem of seeking a rigid motion between two different views. Genetic algorithms can be used for solving this optimization problem, both for obtaining the robust parameter estimation and for its fine-tuning. The main drawback of genetic algorithms is that they are time consuming which makes them unsuitable for online applications. Modern acquisition systems enable the implementation of the solutions that would immediately give the information on the rotational angles between the different views, thus reducing the dimension of the optimization problem. The paper gives an analysis of the genetic algorithm implemented in the conditions when the rotation matrix is known and a comparison of these results with results when this information is not available.

Files

Full Paper as PDF

BibTeX Citation

DOI

10.20532/ccvw.2013.0013

https://doi.org/10.20532/ccvw.2013.0013

BibTeX

@InProceedings{10.20532/ccvw.2013.0013,
  author =       {Vedran Hrgeti{\' c} and Tomislav Pribani{\' c}},
  title =        {Surface Registration Using Genetic Algorithm in
                  Reduced Search Space},
  booktitle =    {Proceedings of the Croatian Compter Vision Workshop,
                  Year 1},
  pages =        {49-52},
  year =         2013,
  editor =       {Lon{\v c}ari{\' c}, Sven and {\v S}egvi{\' c},
                  Sini{\v s}a},
  address =      {Zagreb},
  month =        {September},
  organization = {Center of Excellence for Computer Vision},
  publisher =    {University of Zagreb},
  abstract =     {Surface registration is a technique that is used in
                  various areas such as object recognition and 3D
                  model reconstruction. Problem of surface
                  registration can be analyzed as an optimization
                  problem of seeking an Euclidean motion between two
                  different views. Genetic algorithms have proven to
                  be a suitable method for solving optimization
                  problems and can be used for obtaining robust
                  parameter estimation as well as for their
                  fine-tuning. Their main drawback is that they are
                  time consuming which makes them unsuitable for
                  online applications. Modern acquisition systems
                  enable the implementation of solutions that would
                  immediately give information on the rotational
                  angles between the different views, thus reducing
                  the dimension of the optimization problem. The paper
                  gives an analysis of the genetic algorithm
                  implemented in the conditions when the rotation
                  matrix is known and comparison of these solutions
                  with solutions when this information is not
                  available.},
  doi =          {10.20532/ccvw.2013.0013},
  url =          {https://doi.org/10.20532/ccvw.2013.0013}
}