Computer Vision Team Project

The following project contains matlab implementation of algorithms for:

Computer Vision 1

• Photometric Stereo (Assignment 1, Report)

• Gaussian and Gaussian derivative filters (Assignment 2, Report)

• Harris Corner Detector and tracking with Optical Flow (Assignment 3, Report)

• Image Stitching and Alignment (Assignment 4, Report)

• Bag of words image classification (Final Project, Report)

  

Computer Vision 2

• Iterative Closest Point (Assignment 1, Report)

• Structure from Motion (Assignment 2, Report)

• 3D meshing and texturing (Final Project, Report)

  

Slides

• Slides for a talk about R-CNN papers (PDF)

Dependencies

For Matlab code:

• VLFeat
• libsvm

For C++ code:

• cmake
• OpenCV >= 3.0
• PCL >= 1.7.0
• VTK >= 6.0
• C++11 supported compiler

Configuring

After building dependencies from Matlab:

addpath <path to the libsvm folder>/matlab/
run('<path to the vlfeat folder>/toolbox/vl_setup')

Copyright

Copyright (c) 2016 Minh Ngo, Riaan Zoetmulder ^

^{^ These authors contributed equally to this work inspite of the fact that one doesn't use git :)}

This project is distributed under the MIT license. It's a part of the Computer Vision 1 and Computer Vision 2 courses taught by Theo Gevers and guest lecturers at the University of Amsterdam. Please follow the UvA regulations governing Fraud and Plagiarism in the case if you are a student.

fscatter3 is distributed under the BSD 2-Clause license. VLFeat is distributed under the BSD license. SIFT image descriptor used in our project is patented by David Lowe (University of British Columbia) and cannot be used for comercial purpose.