TSBB34 · 6 credits · Advanced level (A1N) · Datateknik, Elektroteknik
Computer Vision for Video Analysis
Active · next start VT 2027
89%
passed the latest regular sitting
LAB1 · 20 Mar 2026 · 19 students
97%
passed the regular sittings, all sittings over the last 5 years
LAB1 · 73 students
26%
Harder than 26% of courses at advanced level
Compared with 285 courses at the same level, ordinary exams over the last three academic years. 31 students.
Part of 8 programmes
- Master of Science in Computer Science and Engineering
- Master of Science in Information Technology
- Master of Science in Biomedical Engineering
- Master of Science in Computer Science and Software Engineering
- Master of Science in Engineering Mathematics
- Master of Science in Applied Physics and Electrical Engineering - International
- Master of Science in Applied Physics and Electrical Engineering
- Master's Programme in Data Science and Information Engineering
Hand-in or lab
LAB1 Laboratory Work
- 5
- 4
- 3
- U
Main rounds
97% passed · 73 students
- 89%19
- 100%12
- 100%17
- 100%25
Later rounds
No sittings with at least 5 students.
- Get 4 or 5: 48% (73 students)
Other modules
Partial exams, hand-ins and labs. They are not part of the figures at the top.
Hand-in or lab
PRA2 Project Work
- 5
- 3
- U
Main rounds
96% passed · 73 students
- 89%19
- 100%12
- 94%17
- 100%25
Later rounds
No sittings with at least 5 students.
- Get 5: 47% (73 students)
About the course
Aim
The course gives knowledge on the algorithms and estimation problems used to extract information from videos or image sequences. This includes both the mathematics used, and how these are put into practice in algorithm implementation.
After the course, the students should be able to:
Goal 1: explain and use algorithms for tracking of regions in image sequences
Goal 2: explain and use algorithms for estimating optical flow
Goal 3: explain and integrate components for object tracking in image sequences
Goal 4: explain and integrate components for debugging, visualization, and performance evaluation
Content
This course teaches methodology related to the goals listed above, with focus on the following:
- Local features and the structure tensor
- Motion estimation and optical flow
- Clustering and background modeling
- Tracking of regions and objects
- Discriminative correlation filters
- Camera surveillance and its ethical/societal aspects
The contents are introduced in a lecture series, and are then put to use in computer exercises and a programming project.
- Examiner
- Henglin Shi
- Scheduled hours
- 100 h
- Main field of study
- Datateknik, Elektroteknik