- Nazwa przedmiotu:
- Computer vision
- Koordynator przedmiotu:
- Włodzimierz Kasprzak, Ph.D., D.Sc. Professor
- Status przedmiotu:
- Obowiązkowy
- Poziom kształcenia:
- Studia II stopnia
- Program:
- Robotics
- Grupa przedmiotów:
- Przedmioty obowiązkowe
- Kod przedmiotu:
- EM04
- Semestr nominalny:
- 1 / rok ak. 2020/2021
- Liczba punktów ECTS:
- 5
- Liczba godzin pracy studenta związanych z osiągnięciem efektów uczenia się:
- 1) Number of hours that require the presence of a teacher – 50, including
a) presence of the lectures - 30;
b) presence in the exercises - 15
c) presence on consultation - 5
2) The number of hours of independent work of student - 85
- Liczba punktów ECTS na zajęciach wymagających bezpośredniego udziału nauczycieli akademickich:
- 3 ECTS credits – number of hours that require the presence of a teacher – 50, including
a) presence of the lectures - 30;
b) presence in the exercises - 15
c) presence on consultation - 5
- Język prowadzenia zajęć:
- angielski
- Liczba punktów ECTS, którą student uzyskuje w ramach zajęć o charakterze praktycznym:
- 3 ECTS credits – which are obtained during classes of a practical nature;
number of hours during classes of a practical nature - 80, including
b) presence in the exercises - 15
c) presence on consultation – 5
d) independent work of student on solving practical exercise tasks and a homework task – 60
- Formy zajęć i ich wymiar w semestrze:
-
- Wykład30h
- Ćwiczenia15h
- Laboratorium0h
- Projekt0h
- Lekcje komputerowe0h
- Wymagania wstępne:
- -
- Limit liczby studentów:
- 100
- Cel przedmiotu:
- -
- Treści kształcenia:
- Contents:
Image formation and auto-calibration. Low-level image processing: image normalization, colour spaces, image compression and image filtering. Image segmentation: edge detection, chain and line segment detection, Hough transforms, homogeneous region-, shape- and texture description. Object classification: the potential functions-, Bayes-, k-NN, SVM- and MLP- classifiers. Object recognition: dynamic programming, hypothesis generation-and-test, model-to-image matching and graph search. Image motion estimation: gradient- and block-based optical flow, discrete feature motion and active contour tracking. Two-view geometry - stereo-vision. Multi-view and motion-based 3-D object reconstruction. Dynamic vision: object tracking – recursive state estimation, autonomous navigation, discrete self-localization.
Practical Work: Exercises on image processing for recognition purposes
- Metody oceny:
- Assessment will be marked out of a hundred points, where 70% comes from continuous assessment, and 30% comes from end-semester examination. In particular, points can be earned from:
• tutorial, including a practical homework task, 0-40 pts.;
• midterm test, 0-30 pts.;
• final exam, 0-30 pts.
The attendance requirements: an obligatory attendance of tutorial and an optional attendance of lecture.
- Egzamin:
- tak
- Literatura:
- Recommended texts:
- W. Kasprzak, Computer Vision, lecture e-notes, WUT, 2008-2014.
- 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: vision.ucla.edu/MASKS/
- I. Pitas, Digital Image Processing Algorithms, Prentice Hall, New York, 1993.
- O. Faugeras, Three-dimensional computer vision. A geometric viewpoint, The MIT Press. Cambridge, Mass. 1993, 2001
Further readings:
• B. Siciliano, O. Khatib (eds.): Handbook of Robotics. Springer, Berlin Heidelberg, 2008
• OpenCV documentation: http://opencv.org/documentation.html
• PCL (point clouds library) documentation: http://pointclouds.org/documentation/
- Witryna www przedmiotu:
- http://studia.elka.pw.edu.pl/pub/14Z/ECOVI.A/
- Uwagi:
- -
Efekty uczenia się
Profil ogólnoakademicki - wiedza
- Charakterystyka EM04_W1
- Knowledge of different image processing methods
Weryfikacja: Continuous assessment at tutorials regarding the acquired knowledge needed to solve computational and algorithmic exercise tasks, related to the content of this course.
Written assessment of the course outcomes by a written mid-time test.
Written assessment of the course outcomes by a final exam
Powiązane charakterystyki kierunkowe:
AiR2_W01, AiR2_W04, AiR2_W11, AiR2_W12
Powiązane charakterystyki obszarowe:
I.P7S_WG, P7U_W, III.P7S_WG.o, I.P7S_WK, III.P7S_WK.o, III.P7S_WG
Profil ogólnoakademicki - umiejętności
- Charakterystyka EM04_U1
- Ability to select proper image processing method for a specific purpose.
Weryfikacja: Continuous assessment at tutorials regarding the acquired knowledge needed to solve computational and algorithmic exercise tasks, related to the content of this course.
Powiązane charakterystyki kierunkowe:
AiR2_U01, AiR2_U06, AiR2_U16
Powiązane charakterystyki obszarowe:
I.P7S_UW.o, III.P7S_UW.o, I.P7S_UW, III.P7S_UW.2.o, III.P7S_UW.4.o, III.P7S_UW.1.o, III.P7S_UW.3.o, P7U_U
- Charakterystyka EM04_U2
- Able to process the images for the purpose of getting the required information
Weryfikacja: Continuous assessment at tutorials regarding the acquired knowledge needed to solve computational and algorithmic exercise tasks, related to the content of this course.
Powiązane charakterystyki kierunkowe:
AiR2_U06, AiR2_U12, AiR2_U16
Powiązane charakterystyki obszarowe:
I.P7S_UW, III.P7S_UW.2.o, III.P7S_UW.4.o, III.P7S_UW.1.o, III.P7S_UW.3.o
- Charakterystyka EM04_U3
- Able to use the vision for objects recognition and robot motion guidance
Weryfikacja: Continuous assessment at tutorials regarding the acquired knowledge needed to solve computational and algorithmic exercise tasks, related to the content of this course.
Powiązane charakterystyki kierunkowe:
AiR2_U14, AiR2_U17
Powiązane charakterystyki obszarowe:
I.P7S_UW, III.P7S_UW.2.o, III.P7S_UW.4.o, III.P7S_UW.3.o