ITK/Release 4 Planning: Difference between revisions

From KitwarePublic
< ITK
Jump to navigationJump to search
No edit summary
Line 28: Line 28:
** Requires several types of update rules (additive, compositional, inverse compositional, etc.)
** Requires several types of update rules (additive, compositional, inverse compositional, etc.)
** References: "Lucas-Kanade 20 years on" by Baker et al.; "Homography-based 2D Visual Tracking and Servoing" by Benhimane and Malis, "Groupwise Geometric and Photometric Direct Image Registration" by Bartoli; etc.
** References: "Lucas-Kanade 20 years on" by Baker et al.; "Homography-based 2D Visual Tracking and Servoing" by Benhimane and Malis, "Groupwise Geometric and Photometric Direct Image Registration" by Bartoli; etc.
* Clean up the use of parameter scaling in the optimizers
** One possibility would be that the optimizers only perform unscaled minimization. It would then be up to a cost function wrapper to do the rescaling and potentially return the opposite of the cost function. This is similar to how vnl optimizers are used in ITK
* Optimizers should return the best visited value
** See [http://public.kitware.com/Bug/bug_view_page.php?bug_id=3205 Bug 3205]


== Proper resampling/consistency in IndexToPhysicalPoint, ContinuousIndexToPhysicalPoint, Point* ==
== Proper resampling/consistency in IndexToPhysicalPoint, ContinuousIndexToPhysicalPoint, Point* ==

Revision as of 11:31, 7 August 2008

Wish List

Oriented Images

  • Support ND oriented images
    • Using anything other than 3D images won't compile
  • Support ND image in N+1 dimension
    • 2D image can have an origin specified in 3D, thus a series of 2D images is not always Z-aligned
  • All images are oriented - remove concept of an un-oriented image
  • Check use of orientation throughout ITK
    • Spatial Objects
    • Meshes

Image Representation

  • Allow the use of strides that are not equal to the image width
    • Would ease the collaboration of ITK with opencv
    • Would allow the use of sse operations
    • Might be redundant with correct use of image regions

Statistics

  • Complete statistics refactoring (see NAMIC sandbox)

FEM Meshes

  • Consolidate FEM Meshes and ITK Meshes

Image Registration

  • Set up the infrastructure to ease the implementation of modern optimization schemes for image registration
    • Requires Hessian or pseudo-Hessians of the cost function
    • Requires several types of update rules (additive, compositional, inverse compositional, etc.)
    • References: "Lucas-Kanade 20 years on" by Baker et al.; "Homography-based 2D Visual Tracking and Servoing" by Benhimane and Malis, "Groupwise Geometric and Photometric Direct Image Registration" by Bartoli; etc.
  • Clean up the use of parameter scaling in the optimizers
    • One possibility would be that the optimizers only perform unscaled minimization. It would then be up to a cost function wrapper to do the rescaling and potentially return the opposite of the cost function. This is similar to how vnl optimizers are used in ITK
  • Optimizers should return the best visited value

Proper resampling/consistency in IndexToPhysicalPoint, ContinuousIndexToPhysicalPoint, Point*