Skip to main content

Advanced topics in computer vision

2026/2027
Programme:
Computer Science and Mathematics, Second Cycle
Year:
1 ali 2 year
Semester:
second
Kind:
optional
ECTS:
6
Language:
slovenian, english
Course director:

Matej Kristan

Hours per week – 2. semester:
Lectures
3
Seminar
0.67
Tutorial
1.33
Lab
0
Content (Syllabus outline)

The course will include selected advanced topics in motion perception and understanding using computer vision. The content is adjusted each year to reflect the recent trends in research and industry. The core topics include:

  1. Overview of the field motion estimation and applications.
  2. Optical flow estimation using least-squares and variational estimation.
  3. Parametric template tracking using Lucas-Kanade.
  4. Histogram-based tracking using Mean Shift.
  5. Discriminative models for object tracking.
  6. Recursive Bayes filter for online state estimation.
  7. Probabilistic tracking by Kalman filter.
  8. Probabilistic tracking by particle filters.
  9. Deep learning for tracking and segmentation.
  10. Long-term object tracking.
  11. Multiple object tracking methods.
  12. Methodologies of tracker comparison.
Readings

Primarno številni izbrani raziskovalni članki. / Mainly many selected research papers

Simon J. D. Prince, Computer Vision: Models, Learning, and Inference, Cambridge University Press, 2012[CB1]

Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2022

David Barber, Bayesian Reasoning and Machine Learning, Cambridge University Press, 2012

Objectives and competences

The primary objective is obtaining an overview of scientifically challenging topics of computer vision and broader artificial intelligence. In this sense, the course is logical continuation of basic first-level courses in artificial intelligence, specifically, computer vision, multimedia and machine learning. The secondary objective is practical application of analytical and numerical methods that students learn at basic courses, but seldom use in practice. At the end of this course the students will be skilled in modern approaches for motion estimation and tracking using computer vision approaches. The studens will obtain practical experience with these approaches.

Intended learning outcomes

After completing this course a students will be able to:

- know major methods for motion estimation and localization of moving objects,

- understand the concept of optical flow estimation and be able to implement basic approaches,

- understand mathematical background of template alignment using gradient descent,

- understand mathematical background of probabilistic Bayesian models for target position estimation in images and be able to implement the basic algorithms from the family of these approaches,

- understand the approaches for tracker evaluation and be able to critically analyze the algorithms,

- understand the basics of long-term trackers and know the major representatives from this field,

- understand major deep learning techniques and architectures for motion understanding,

- implement applications for image-based object tracking,

- understand modern algorithms in the field of object tracking.

Learning and teaching methods

Lectures, laboratory exercises, homeworks and project work. Special emphasis will be given on individual work.

Assessment

Type (examination, oral, coursework, project):

Continuing (lab exercises, homework, project)
Final (written exam)
5 - 10, a student passes the exam if he is graded from 6 to 10

Lecturer's references

LUKEŽIČ, Alan, TROJER, Žiga, MATAS, Jiří, KRISTAN, Matej. A new dataset and a distractor-aware architecture for transparent object tracking. International journal of computer vision. Feb. 2024, vol. 132, str. 2729-2742, [COBISS-SI-ID 186509827]

BOVCON, Borja, KRISTAN, Matej. WaSR—a water segmentation and refinement maritime obstacle detection network. IEEE transactions on cybernetics.  Dec. 2022, vol. 52, iss. 12, str. 12661-12674, [COBISS-SI-ID 69794307]

LUKEŽIČ, Alan, MATAS, Jiří, KRISTAN, Matej. A discriminative single-shot segmentation network for visual object tracking. IEEE transactions on pattern analysis and machine intelligence. Dec. 2022, vol. 44, no. 12, str. 9742-9755, [COBISS-SI-ID 94955523]

VIDENOVIĆ, Jovana, LUKEŽIČ, Alan, KRISTAN, Matej. A distractor-aware memory for visual object tracking with SAM2. V: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition : CVPR 2025, Str. 24255-24264 [COBISS-SI-ID 245699331]

PELHAN, Jer, LUKEŽIČ, Alan, ZAVRTANIK, Vitjan, KRISTAN, Matej. A novel unified architecture for low-shot counting by detection and segmentation. V: GLOBERSON, Amir (ur.). Advances in neural information processing systems 37 (NeurIPS 2024), 2024. Str. 1-23, [COBISS-SI-ID 225242371]

KRISTAN, Matej, MATAS, Jiří, LEONARDIS, Aleš, VOJÍŘ, Tomáš, PFLUGFELDER, Roman, FERNÁNDEZ, Gustavo, NEBEHAY, Georg, PORIKLI, Fatih, ČEHOVIN ZAJC, Luka. A novel performance evaluation methodology for single-target trackers. IEEE transactions on pattern analysis and machine intelligence, ISSN 0162-8828. [Print ed.], Nov. 2016, vol. 38, no. 11, str. 2137-2155, [COBISS-SI-ID 1536872643]

ČEHOVIN, Luka, KRISTAN, Matej, LEONARDIS, Aleš. Robust visual tracking using an adaptive coupled-layer visual model. IEEE trans. pattern anal. mach. intell.. [Print ed.], 2012, str. [1-14], [COBISS-SI-ID 9431124

Celotna bibliografija je dostopna na SICRISu: http://sicris.izum.si/search/rsr.aspx?lang=slv&id=32801.