SoC2007 project Feature Descriptor

From PanoTools.org Wiki
(Difference between revisions)
Jump to: navigation, search
(changed license to LGPL)
m (Reverted edits by JossSpot (Talk) to last version by Erik Krause)
 
(8 intermediate revisions by 5 users not shown)
Line 1: Line 1:
 +
 +
See [[SoC 2007 overview]] for usage hints and a page list.
 +
 
= Robust local feature detector and descriptor =
 
= Robust local feature detector and descriptor =
  
Line 13: Line 16:
 
* Integration of the library into [[hugin]]
 
* Integration of the library into [[hugin]]
  
== Timeline ==
+
== Project Schedule ==
 +
* 0w    April    9 - Application selection
 +
 
 +
* Interim Period: Learn more about the project, the literature that is being used to develop it, and  build a testing set with ground truth ~200 images. This can be done asking for pictures to the mailing list.
 +
 
 +
* 0w    May    28 - Begin coding for the project
 +
 
 +
* 1w    June    4  - Create all the evaluation software, (mainly available from the website of Krystian Mikolajczyk)
 +
 
 +
* 3w    June    18 - Implement of the algorithm chosen for the detector of feature points on the image.
 +
 
 +
* July 9: Students upload code to code.google.com/hosting; mentors begin mid-term evaluations
 +
 
 +
* 7w    July    23 - Implementation of the descriptor to match the feature points detected.
 +
 
 +
* 10w  August  13 - Benchmark and code optimization.
 +
 
 +
* 11w  August  20 - Final report (Google Deadline for all student work),students upload code to code.google.com/hosting; mentors begin final evaluations; students begin final program evaluations.
  
 
== Required/available ressources ==
 
== Required/available ressources ==
Line 26: Line 46:
 
* [http://en.wikipedia.org/wiki/Scale-invariant_feature_transform Wikipedia article on SIFT], contains several good references
 
* [http://en.wikipedia.org/wiki/Scale-invariant_feature_transform Wikipedia article on SIFT], contains several good references
 
* [http://homes.esat.kuleuven.be/%7Etuytelaa/ECCV06tutorial.html Tutorial on local invariant features]
 
* [http://homes.esat.kuleuven.be/%7Etuytelaa/ECCV06tutorial.html Tutorial on local invariant features]
* [http://www.mis.informatik.tu-darmstadt.de/Education/Courses/cv/index.html Lecture notes] on feature detection/matching]
+
* [http://www.mis.informatik.tu-darmstadt.de/Education/Courses/cv/index.html Lecture notes] on feature detection/matching
  
 
=== Software ===
 
=== Software ===
Line 34: Line 54:
  
 
License: LGPL
 
License: LGPL
 +
 +
== Students planning to apply ==
 +
 +
* [[User:pedro|Pedro Alonso Ferrer]]
 +
 +
[[Category:Community:Project]]

Latest revision as of 21:06, 9 February 2011

See SoC 2007 overview for usage hints and a page list.

Contents

[edit] Robust local feature detector and descriptor

Goal: Robust matching of features between multiple images using a Hessian-based detector and a suitable descriptor. A detector and descriptor that takes into account the approximately known distortions will have a much higher matching rate, especially when fisheye or wide angle images are used.

  • Implementation of the feature detector and descriptor, and a suitable test suite to verify the correctness of the implementation.

[edit] Deliverables

A desired result of the projects would be:

  • C or C++ library that implements the detection and description steps.
  • An executable for extracting features from image file.
  • Test suite to evaluate descriptor on a large amount of images.
  • Integration of the library into hugin

[edit] Project Schedule

  • 0w April 9 - Application selection
  • Interim Period: Learn more about the project, the literature that is being used to develop it, and build a testing set with ground truth ~200 images. This can be done asking for pictures to the mailing list.
  • 0w May 28 - Begin coding for the project
  • 1w June 4 - Create all the evaluation software, (mainly available from the website of Krystian Mikolajczyk)
  • 3w June 18 - Implement of the algorithm chosen for the detector of feature points on the image.
  • July 9: Students upload code to code.google.com/hosting; mentors begin mid-term evaluations
  • 7w July 23 - Implementation of the descriptor to match the feature points detected.
  • 10w August 13 - Benchmark and code optimization.
  • 11w August 20 - Final report (Google Deadline for all student work),students upload code to code.google.com/hosting; mentors begin final evaluations; students begin final program evaluations.

[edit] Required/available ressources

Required knowledge or interest in:

  • signal or image processing background
  • C or C++ development skills.
  • Matlab or octave

[edit] Ressources

[edit] Literature

Literature about feature detection

[edit] Software

Mentor: Pablo d'Angelo, Herbert Bay, ?

License: LGPL

[edit] Students planning to apply

Personal tools
Namespaces

Variants
Actions
Navigation
tools
Tools