Computer Vision (ECOVI)

M.Sc. studies in EMARO and "Robotics" (MEiL Faculty)

Winter 2016/2017


Meeting times and locations

Friday, 12:15-14:00 (i.e. 12:15 p.m.- 2:00 p.m.), room 569, E&IT Faculty

Monday (every second), 14:15-16:00, lab P113/P109, E&IT Faculty

[go to top]

Teaching staff and contact info

prof. Włodzimierz Kasprzak
Office: room 565, E&IT Faculty, Institute of Control and Computation Eng.
Office hours: Tuesday, 12.15-14 (i.e. 0.15 p.m. - 2 p.m.)
Phone: +22 234 7866
W.Kasprzak at

Jan Figat, M.Sc.
Office: room 571, E&IT Faculty, Institute of Control and Computation Eng.
Office hours:
Phone: +22 234 7861
J.Figat at

[go to top],

Short course description

Course objectives This course provides an introduction to computer vision from the perspective of robotics. Three parts are distinguished: 2-D image image analysis, 3-D scene analysis and image sequence analysis. Topics include: basic 2-D image analysis - filtering, segmentation, 2-D object classification, projective geometry and camera calibration, stereo-vision, RGB-D image processing, 3-D object recognition, image motion estimation, 3-D structure-from-motion, visual SLAM, 3-D object tracking.

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- 91 90-81 80-71 70-61 60-51 50 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 51 pts. Credits will be awarded to candidates who pass this course.

[go to top]


Lecture schedule (tentative):


  1. [2.12] Part I (1-4), time 12.15.
  2. [3.02] Part II (5, 7-9), time 12.15.

[go to top]

Textbooks and suggested readings

Lecture notes
  1. W.Kasprzak: Computer Vision, lecture notes, WUT, 2008-2015.
  1. [OpenCV] OpenCV tutorials page:
  2. [Pitas] I. Pitas. Digital Image Processing Algorithms and Applications. John Wiley, New York, 2000.
  3. [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:
Other books:
  1. [Kasprzak] W. Kasprzak: Adaptive computation methods in digital image sequence analysis. Prace Naukowe - Elektronika, Warsaw University of Technology Publishing House, Warszawa, No. 127 (2000), 172 pages. 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 1-4) 1. Image processing. 2. Image segmentation. [Pitas, ch. 5, 6, 7], CV-tutorial 1, CV-tutorial 2 Pitas5 slides, Pitas6 slides, Pitas7 slides
(Week 5-6) 3. 2-D object recognition CV-tutorial 3
(Week 7-8) 4. Camera model and calibration. [Ma, ch. 3], CV-tutorial 4 Ma-3.pdf,
(Week 9) Exam - part 1
(Week 10) 5A. Stereo-vision [Faugeras, ch.6] [Ma, ch. 5] Ma-5.pdf
(Week 11) 5B. Depth map/point cloud segmentation CV-tutorial 5, CV-tutorial 6
(Week 12) 6. 3-D object recognition [Ballard, ch. 11.1-11.4], [Faugeras, ch. 11], [Kasprzak, sec. 6.3], CV-tutorial 7
(Week 13) 7. Image motion estimation [Kasprzak, ch.5], [Ballard, sec. 3.6] Ballard, sec. 3.6
(Week 14) 8. 3-D structure from motion
(Week 15) 9. State estimation and object tracking [Faugeras, ch. 8], [Kasprzak, ch. 6.1-6.2,7,8], CV-tutorial 8 c-A443-estimation.pdf
(Week 16) Exam - part 2

[go to top]


Laboratory exercises will be solved, which are related to the algorithms presented during the lecture. Students will select their homework tasks.

Tutorial schedule

Monday, 14.15-16

  1. T1: [10.10] -
  2. T2: [24.10] -
  3. T3: [14.11] -
  4. T4: [28.11] -
  5. T5: [12.12] -
  6. T6: [2.01] -
  7. T7: [16.01] -
  8. T8: [24.01] -
Suitable implementation tool - library with open source: openCV (image analysis in C++)

[go to top]

W. Kasprzak.
Last modification: 13.01.2017.