Machine perception

Lectures:
Overview of the field of Machine perception and scientific challenges
Image processing
Image formation
Binarization, morfology, segmentation
Colour spaces and colour perception
Linear and nonlinear filters
Image derivatives and edge perception
Derivative-based edge perception
Edge-based object perception
Parametric shape perception
Model fitting
Normal equations
Homogenous systems
Robust approaches
Local features
Corner perception
Local descriptors in scale space and affine adaptation
Stereoscopy and depth perception
Calibrated and uncalibrated systems and reconstruction
Object recognition
Subspace methods (PCA, LDA)
Local-features-based recognition
Object detection
Visual features and detection approaches
Motion perception
Local motion perception and object tracking
Exercises:
Exercises will take a form of project-oriented exercises in properly equipped student laboratories. Students will implement various algorithms and test them on different datasets using a variety of sensor systems. Exercises will support an in-depth understanding of the theory. They will also encourage independent thinking and creativity.

Obvezna:
D. Forsyth and J. Ponce, Computer Vision: A modern approach, Prentice Hall 2011.
R. Szeliski,Computer Vision: Algorithms and Applications, Springer, 2011
Dopolnilna:
H. R. Schiffman: Sensation and Perception, An Integrated Approach, John Wilez &, Sons 2001.
Izbrani članki iz revij IEEE PAMI, CVIU, IJCV, Pattern Recognition (dostopno na spletu)

In the framework of this course, the students will acquire concrete knowledge and skills in the area of machine perception. The students will develop competences in low-level image processing, 3D geometry of stereo systems, object detection, object recognition, and motion extraction in video sequences. The students will also practice mathematical basics crucial for solving demanding engineering problems, which are essential for analysis of complex signals such as images and video.
In addition, the students will obtain the following competences:
The ability to understand and solve professional challenges in computer and information science.
The ability of professional communication in the native language as well as a foreign language.
The ability to independently perform both less demanding and complex engineering and organisational tasks in certain narrow areas and independently solve specific well-defined tasks in computer and information science.

Knowledge and understanding:
Understanding of computer technology and computational methodology for use and development of components for machine vision systems.
Application:
Use of computer technology and computational methodology for specific applications of autonomous intelligent cognitive systems.
Reflection:
Understanding how the theory can be tuned for different application scenarios in the area of intelligent perceptual/cognitive systems.
Transferable skills: Solving other conceptually similar problems (e.g., other modalities) based on the models of machine and artificial cognitive perception.

Lectures, laboratory exercises in computer classroom with active participation. Individual work on exercises. Theory from the lectures made concrete with hands-on laboratory exercises. Special emphasis will be put on continuous assessment at exercises.

Final (written and oral exam)
grading: 5 (fail), 6-10 (pass) (according to the Statute of UL)

KRISTAN, Matej, LEONARDIS, Aleš. Online discriminative kernel density estimator with Gaussian kernels. IEEE transactions on cybernetics, ISSN 2168-2267. [Print ed.], 2014, vol. 44, no. 3, str. 355-365. , doi: . [COBISS-SI-ID 9907284]
ČEHOVIN, Luka, KRISTAN, Matej, LEONARDIS, Aleš. Robust visual tracking using an adaptive coupled-layer visual model. IEEE transactions on pattern analysis and machine intelligence, ISSN 0162-8828. [Print ed.], Apr. 2012, vol. 35, no. 4, str. 941-953, ilustr. , doi: . [COBISS-SI-ID 9431124]
KRISTAN, Matej, LEONARDIS, Aleš, SKOČAJ, Danijel. Multivariate online kernel density estimation with Gaussian kernels. Pattern recognition, ISSN 0031-3203. [Print ed.], 2011, vol. 44, no. 10/11, str. 2630-2642, ilustr. [COBISS-SI-ID 8289876]
KRISTAN, Matej, SKOČAJ, Danijel, LEONARDIS, Aleš. Online kernel density estimation for interactive learning. Image and vision computing, ISSN 0262-8856. [Print ed.], Jul. 2010, vol. 28, no. 7, str. 1106-1116, ilustr. [COBISS-SI-ID 7326804]
KRISTAN, Matej, KOVAČIČ, Stanislav, LEONARDIS, Aleš, PERŠ, Janez. A two-stage dynamic model for visual tracking. IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics, ISSN 1083-4419. [Print ed.], Dec. 2010, vol. 40, no. 6, str. 1505-1520, ilustr. [COBISS-SI-ID 7709524]