P33ZVD - Introduction to Computer Vision

Winter 2007/2008, 2 hours lecture + 2 hours exercises per week, i.e., 90 minutes lecture weekly + exercises.

The lecture is in the lecture room G102a, building G at the Karlovo namesti campus of CVUT on Fridays from 9:15 till 10:45. Click here for the map.

Lecturer  Professor Vaclav Hlavac
Center for Machine Perception, Department of Cybernetics
Faculty of Electrical Engineering, CTU Prague
hlavac@fel.cvut.cz, http://cmp.felk.cvut.cz/~hlavac

Instructor of the exercises    Prof. Vaclav Hlavac
                                                Ing. Tomáš Pajdla, PhD., pajdla@cmp.felk.cvut.cz, http://cmp.felk.cvut.cz/~pajdla
Plan of the lectures (see V. Hlavac's teaching material for presentations in electronic form, in English click here, in Czech click here.)

No Date Lecturer Lecture content
1 05.10.2007 V. Hlavac What is computer vision? Low-level image processing and high-level vision. Digital image. Image formation, acquisition.
2 12.10.2007 V. Hlavac Image analysis as analysis of a 2D signal. Fourier transform rehearsal. Linear integral transformations, image preprocessing in frequency domain.
3 19.10.2007 V. Hlavac Image preprocessing in image domain. Edge detection. Scale space.
4 26.10.2007 V. Hlavac Basics of pattern recognition.
5 02.11.2007 V. Hlavac Image segmentation.
6 09.11.2007 V. Hlavac Description of objects in images. Detection of distinguished primitives in images.
7 16.11.2007 T. Pajdla 3D vision geometry. A single camera and more cameras.
8 23.11.2007 V. Hlavac Correspondence problem. Reconstruction of 3D scenes.
9 30.11.2007 V. Hlavac Mathematical morphology.
10 07.12.2007 V. Hlavac Color. Texture.
11 14.12.2007 V. Hlavac Image and video compression.
12 21.12.2007 V. Hlavac Motion analysis. Motion detection. Optical flow.
13 04.01.2008 V. Hlavac Tracking in videosequences.
14 11.01.2008 T. Pajdla Practical applications of computer vision, a practitioner's view with real life examples.

Exercises

The exercises have two goals.

  1. We like to teach a PhD candidate how to write a scientific paper and prove it on a domain related both to student's own research and computer vision. The student either works on his own research paper to be submitted elsewhere the topic of which is related at least loosely to computer vision. If the student's own research is too far from this subject then he will be given a topic which is expected to be studied and described in a research report. The text has to be written in English. After the topic is agreed with the instructor, the students works on it individually. However, the student is recommended to conduct personal consultations with the instructor regularly. The job has to be finished before the end of the lecturing, ideally.
  2. The student has to acquire some practical skills with computer vision algorithms. The student has to solve one of the \Matlab programming assignments from the Svoboda T., Kybic J., Hlavac V.: Image Processing, Analysis and Machine vision - A Matlab Companion, Thomson Engineering, Toronto, Canada, August 2007, see http://visionbook.felk.cvut.cz. The particular assignment will be selected in cooperation with V. Hlavac. The student is supposed to document well the solution in the protocol written in English.

Requirements for the credit: approved own paper and one solved assignment which will contribute to visionbook.felk.cvut.cz.

Examination: Written test + oral discussion.

Maintained by V. Hlavac, hlavac@fel.cvut.cz
Last modification 13.08.2008 04:49