P33ZVD - Introduction to Computer Vision

Winter 2005/2006, 2 hours lecture + 2 hours exercises per week, i.e., 90 minutes lecture weekly + exercises.

The lecture in the lecture room G205, building G at the Karlovo namesti campus of the CTU on Thursdays 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
, http://cmp.felk.cvut.cz/~hlavac

Instructor of the exercises    Dr Tomas Pajdla (make an arrangement with him individually by an email.)
pajdla@fel.cvut.cz, http://cmp.felk.cvut.cz/~pajdla}

Plan of the lectures

No Date Lecture content Electronic material
1 29.09.2005 What is computer vision? Low-level image processing and high-level vision. Digital image.  Digital image (cz).
2 6.10.2005 Image formation, acquisition. Color. (Lecturer T. Pajdla) Image formation (cz), geom. optics (cz), cameras (cz). Color.
3 13.10.2005 Image analysis as analysis of a 2D signal. Fourier transform rehearsal. Linear integral transformations, image preprocessing in freq. domain. Fourier tx 1D. Fourier tx 2D (cz). Fourierova filtrace. FFT.
4 20.10.2005 Image preprocessing in image domain. Marr's theory of edge detection. Scale space.  (Lecturer T. Werner) Preprocessing in the image domain. Edge detection.
5 27.10.2005 Image segmentation. (Lecturer T. Werner) Segmentation (taxonomy, thresholding, spatial coherence).
6 3.11.2005 Mathematical morphology. Math. morphology. Binary (cz), gray scale (cz).
7 10.11.2005 Basics of pattern recognition. Basics of PR (cz).
8 17.11.2005 Public holiday. No lecture.  
9 24.11.2005 Description of objects in images. Detection of distinguished primitives in images.  
10 1.12.2005 Texture. Introduction to 3D vision. Marr's theory.  
11 8.12.2005 3D vision geometry. More cameras.  
12 15.12.2005 Correspondence problem. Reconstruction of 3D scenes.  
13 5.01.2006 Motion analysis.  
14 12.01.2006 Image and video compression. (Lecturer T. Werner)  


The aim of the exercise is 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 exercise is conducted in a close cooperation with the instructor Dr Tomas Pajdla. The student either works on his own research paper to be submitted elsewhere which is related at least loosely to computer vision. If the student own research is too far from this subject then he is given a topic which is expected to be studied and described in a research report. 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.

Maintained by V. Hlavac, hlavac@fel.cvut.cz
Last modification 10.11.2005 11:21