https://wiki.panotools.org/api.php?action=feedcontributions&user=JossSpot&feedformat=atomPanoTools.org Wiki - User contributions [en]2024-03-19T03:15:18ZUser contributionsMediaWiki 1.35.3https://wiki.panotools.org/index.php?title=Historical:SoC2007_project_Feature_Descriptor&diff=13131Historical:SoC2007 project Feature Descriptor2011-02-09T18:21:22Z<p>JossSpot: /* Literature */</p>
<hr />
<div><br />
See [[SoC 2007 overview]] for usage hints and a page list.<br />
<br />
= Robust local feature detector and descriptor =<br />
<br />
Goal: Robust matching of features between multiple images using a Hessian-based detector and a suitable descriptor.<br />
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. <br />
<br />
* Implementation of the feature detector and descriptor, and a suitable test suite to verify the correctness of the implementation.<br />
<br />
== Deliverables ==<br />
A desired result of the projects would be:<br />
* C or C++ library that implements the detection and description steps.<br />
* An executable for extracting features from image file.<br />
* Test suite to evaluate descriptor on a large amount of images.<br />
* Integration of the library into [[hugin]]<br />
<br />
== Project Schedule ==<br />
* 0w April 9 - Application selection<br />
<br />
* 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.<br />
<br />
* 0w May 28 - Begin coding for the project<br />
<br />
* 1w June 4 - Create all the evaluation software, (mainly available from the website of Krystian Mikolajczyk)<br />
<br />
* 3w June 18 - Implement of the algorithm chosen for the detector of feature points on the image.<br />
<br />
* July 9: Students upload code to code.google.com/hosting; mentors begin mid-term evaluations<br />
<br />
* 7w July 23 - Implementation of the descriptor to match the feature points detected.<br />
<br />
* 10w August 13 - Benchmark and code optimization.<br />
<br />
* 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.<br />
<br />
== Required/available ressources ==<br />
Required knowledge or interest in:<br />
* signal or image processing background<br />
* C or C++ development skills.<br />
* Matlab or octave<br />
<br />
== Ressources ==<br />
=== Literature ===<br />
Literature about feature detection<br />
* [http://en.wikipedia.org/wiki/Scale-invariant_feature_transform Wikipedia article on SIFT], contains several good references<br />
* [http://homes.esat.kuleuven.be/%7Etuytelaa/ECCV06tutorial.html Tutorial on local invariant features]<br />
* [http://www.mis.informatik.tu-darmstadt.de/Education/Courses/cv/index.html Lecture notes] on feature detection/matching<br />
* [http://www.pokerenfrancais.eu/poker-en-ligne-gratuit/ poker gratuit en ligne]<br />
<br />
=== Software ===<br />
* Framework for [http://www.robots.ox.ac.uk/~vgg/research/affine/ testing descriptors]<br />
<br />
Mentor: Pablo d'Angelo, Herbert Bay, ?<br />
<br />
License: LGPL<br />
<br />
== Students planning to apply ==<br />
<br />
* [[User:pedro|Pedro Alonso Ferrer]]<br />
<br />
[[Category:Community:Project]]</div>JossSpot