User:Pedro

From PanoTools.org Wiki
Revision as of 23:20, 19 March 2007 by Pedro (Talk | contribs)

Jump to: navigation, search

My name is Pedro Alonso Ferrer, I'm spanish.


Contents

About

I am attending fourth year undergraduate at Pompeu Fabra University (Barcelona - Spain). I am getting my Computer Science Engineering degree in June 2007.

I will dedicate myself full time to this project.

I have wide experience developing algorithms in C/C++. I have implemented some complex computer graphics algorithms such as:

  • Gimp Perspective Clone, detailed informatión and a video-tutorial available in [1]
  • Image quilting for texture synthesis and transfer. Alexei A. Efros, William T. Freeman Proceedings of ACM-SIGGRAPH 2001.
    • source code and examples available [2]
  • Marching Cubes: A high resolution 3D surface construction algorithm. William E. Lorensen, Harvey E. Cline Proceedings of ACM-SIGGRAPH 1988.
    • source code and examples available [3]
  • Parametrization and smooth approximation of surface triangulations. Michael S. Floater Computer aided geometric design, Elsevier, vol 14, pp. 231-250, 1997.
    • source code and examples available [4]

I also have experience developing websites, mainly using PHP and MySQL. I have also develop several things in Java, web applications mainly. You can see more detailed information in my Resume [5]


Google Summer of Code 2007

I'm applying for:

  1. SoC2007_project_Feature_Descriptor

Project Description

The project consists of fulfilling a library for feature matching 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.

An example of algorithm for the detection step is explained in the paper:

  • Choose some papers that could be use for this purpose.


Once the feature points are detected on each image, to match them and describe the neughbourhood in highly distorted images, the algorithms that could be used for this is explained in the paper:

  • Choose some papers that could be use for this purpose.


To conclude, it would be necessary to facilitate the use of the tool by creating a user's interface. This would allow to choose the set of images to make the panorama. The graphical interface would be developed having in mind the new extensible modular GUI framework SoC_2007_project_New_GUI_Framework.

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 Miko)
  • 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.


Contact

  • E-mail: pedro.paf (at gmail.com
    • I'm on the "panotools-devel" mailing list
  • IM/VoIP
    • MSN, Gtalk: same e-mail address as above
    • Skype: pedropaf
Personal tools
Namespaces

Variants
Actions
Navigation
tools
Tools