Computer Vision (CV)

EMARO course, Winter 2008/09


Meeting times and locations

Wednesday, 14:15-16:00 (i.e. 2:15 p.m.- 4:00 p.m.), room 117, E&IT Faculty

Thursday, 11:15-12:00 a.m., room 031, E&IT Faculty

[go to top]

Teaching staff and contact info

Professor Włodzimierz Kasprzak
Office: room 554, E&IT Faculty, Institute of Control and Computation Eng.
Office hours: Wednesday, 12-14 (i.e. 12 a.m.-2 p.m.)
22 234 7866.

[go to top],

Short course description

Course objectives This course provides an introduction to computer vision from the perspective of robotics. Four parts are distinguished: image formation, image analysis, pattern recognition and 3-D dynamic vision. Topics include: camera calibration, stereo-vision, image binarization, line segment detection, region-based segmentation, image motion estimation, supervised learning and pattern classification, unsupervised learning and clustering, model-based object recognition, state estimation and object tracking, vision-based servoing and navigation.

Students are expected to have the following background:

Course materials
Lecture notes will be posted periodically on the course web site. Selected chapters from the books below are recommended as optional reading.

[go to top]

Marks and Grading

Assessment will be marked out of a hundred. The marks equate to ECTS grades as given below:
mark 100- 90 89-80 79-70 69-65 64-60 59 or less
Students are collecting assessment points. They come from a continuous assessment in the semester time: The assessment method of this course consists of: In addition to satisfying the above assessment requirements, each student must satisfy the attendance requirements. There is an obligatory attendance of exercises and laboratory and an optional attendance of the lecture. The Pass mark for this course will be set at 60 pts. Credits will be awarded to candidates who pass this course.

Grades will be signed at the office on Wednesday, 4.02.2009, time 12-13.

[go to top]


Lecture schedule (24 h):

  1. [19.11] Half-time test, 14.15 - 15.15
  2. [28.01.09] Final exam, 12.15 - 14.00, room 120.

[go to top]

Textbooks and suggested readings

  1. [Faugeras] O. Faugeras: Three-dimensional computer vision. A geometric viewpoint. The MIT Press. Cambridge, Mass. 1993, 2001.
  2. [Pitas] I. Pitas. Digital Image Processing Algorithms and Applications. John Wiley, New York, 2000.
  3. [Duda] R.O.Duda, P.E.Hart, D.G.Stork: Pattern Classification. Second Edition. John Wiley, 2000.
Other books:
  1. [Ma] Y. Ma, S. Soatto, J. Kosecka, S. Sastry: An Invitation to 3D Vision. From Images to Geometric Models. Springer-Verlag, New York 2004. on-line:
  2. [Gonzalez] R. C. Gonzalez, P.C. Wintz: Digital Image Processing. Addison-Wesley, Reading, MA, 1987.
  3. [Ballard] D. H. Ballard, Ch. M. Brown: Computer Vision. Prentice Hall, 1982.
  4. [HofR] B. Siciliano, O. Khatib (eds.): Handbook of Robotics. Springer, Berlin Heidelberg, 2008.
Suggested Readings
For each lecture section, one or more suggested readings are given below.
(Week) Topic Readings PDF
(Week 1) 1. Image formation [Ma, ch. 3] Ma-3.pdf
(Week 2 and 3) 2. Stereo-vision [Faugeras, ch.6] [Ma, ch. 5] Ma5.pdf
(Week 4 and 5) 3. Segmentation I [Pitas, ch. 5] Pitas5 slides
(Week 6) 4. Segmentation II [Pitas, ch.6 and 7] Pitas6 slides Pitas7 slides
(Week 7) Midterm test
(Week 8) 5. Image motion [Ballard, ch. 3.6] Ballard, ch. 3.6
(Week 9) 6. Classification [Duda, ch. 2.1-2.6, 3.1-3.4] Duda2.ppt, Duda3-1.ppt
(Week 10) 7. Clustering [Duda, ch. 10.1-10.4, 10.6-10.7] Duda10.ppt
(Week 11) 8. Object recognition [Ballard, ch. 11.1-11.4], [Faugeras, ch. 11]
(Week 12) 9. 3-D reconstruction [Faugeras, ch.7] [Ma, ch. 2] Ma-2.pdf
(Week 13) 10. Estimaton and tracking [Faugeras, ch. 8]
(Week 14) free
(Week 15) Final test. Time: 12.15, Room: 120.

[go to top]


During the exercises some tasks will be solved, which are related to the algorithms presented during the lecture. Students will also select their homework problems. The lecture tests will consist of smilar tasks as solved during exercises.

Exercise schedule (16h)

  1. Week 1 [2.10.08] Introduction to the lab.
  2. Week 2 [9.10.08] Homework 1 starts.
  3. Week 3, 4, 5, 6, 7, 8 :
  4. Week 9 [27.11.08] Homework 1 evaluation.
  5. Week 10 [ 4.12] Homework 2 starts.
  6. Week 11 - 14 :
  7. Week 15 [22.01.09] Homework 2 evaluation.
Suitable implementation tools - libraries with open surces: openCV (image analysis in C++) and Marf (among others classification and clustering - in Java).

[go to top]

W. Kasprzak.
Last modification: 12.01.2009.