Computer Vision

This is the course page for the computer vision course, for the Semester I, 2014-2015, being taught by Subhashis Banerjee at the Department of Computer Science and Engineering, IIT, New Delhi.

General Information
Notices
Books, Papers and other Documentation
Software
Vision Sites

General Information

• Tuesday, 10:00-11:30
• Friday, 10:00-11:30

Our mailing list: CSL840@courses.iitd.ernet.in

1. Minor I (PDF) (also contains Assignment I.)
2. Major take-home part (PDF) (last date of submission: May 8, 11:59:59)

Books, Papers and other Documentation

1. General reading
   
   • Multiple View Geometry, by Richard Hartley and Andrew Zisserman, Cambridge University Press. (electronic copy of only some chapters are available).
   • Three dimensional Computer Vision: A geometric approach, by Olivier Faugeras, MIT Press.
   • Computer Vision: A Modern Approach, by David Forsyth and Jean Ponce.
   • Projective Geometry Tutorial, by Mohr and Triggs
   • The Geometry of Multiple Views, by Andrew Zisserman.
     • Part 1: Epipolar Geometry and the Fundamental Matrix
     • Part 2: Uncalibrated 3D Reconstruction
     • Part 3: Planes
     • Part 4: Points, Lines and Curves
   • Mathematics for Computer Vision, by Carlo Tomasi
2. suban's notes
   
   • Camera models and affine multiple views geometry (PDF,ps.gz)
   • Projective geometry for computer vision (PDF,ps.gz)
   • Multiple Views Geometry (PDF,ps.gz)

3. Papers discussed in class (electronic copies can be downloaded only from within IITD)
   
   • Single View Metrology
     A. Criminisi, I. Reid, and A. Zisserman. IJCV, 40(2):123--148, 2000.
   • Multilevel modelling and rendering of architectural scenes
     Submitted to Eurographics, 2003.
   • Affine Structure from Motion.
     Koenderink and van Doorn, Journal of the Optical Society of America, A8:377-385, 1991.
     (No electronic copy available. Paper copy may be obtained from the Central Library).
   • Projective Structure from Two Uncalibrated Images: Structure from Motion and Recognition
     Amnon Shashua, (A.I. Memo 1363)
4. Some more papers discussed in the class.

Software

• MATLAB: the high-performance language for technical computing. We have the compilers, plus toolboxes for image processing,optimization, signal processing, simulink, state flow, wavelets, and control.
  • MATLAB help desk

Vision Sites

• The Computer Vision Homepage, CMU
• Compendium of Computer Vision A tremendous amount of information, including image processing, camera calibration, geometry, mathematics. If you find something especially useful, let me know, and I'll mirror it locally.
• Robotvis, the robotics and vision group at INRIA, Sophia Antipolis. There are some impressive demos, check out the one on Epipolar Geometry