26.03.2021 There will be a test run for the retake graded online exercise in TUMexam starting tonight. The test run will be open until Monday (29.03.2021) 10pm.
01.03.2021 The retake exam will take place on 31.03.2021 (8:00 - 9:30) in the format of a graded online exercise.
15.02.2021 There will be a test run for the graded online exercise in TUMexam starting on Wednesday (17.02.2021). Additional information can be found in Moodle.
15.02.2021 I have create a separate forum in Moodle to share information regarding the graded online exercise.
09.02.2021 Solutions for Exercise Sheet 6 are now available.
30.01.2021 Due to new COVID-19 regulations the exam must take place in an online format. Details will be announce soon.
30.01.2021 Exercise Sheet 6 and solutions for Exercise Sheet 5 are now available on the course webpage.
16.01.2021 Exercise Sheet 5 is now available on the course webpage.
13.01.2021 Solutions for Exercise Sheet 4 are now available.
28.12.2020 Exercise Sheet 4 is now available on the course webpage.
25.12.2020 Solutions for Exercise Sheet 3 are now available on the course webpage.
06.12.2020 Exercise Sheet 3 and solutions for Exercise Sheet 2 are now available on the course webpage.
22.11.2020 I've set up a Moodle for associated with this course. Please feel free to ask there any related questions. Moodle
22.11.2020 Exercise Sheet 2 and solutions for Exercise Sheet 1 are now available on the course webpage.
09.11.2020 Exercise Sheet 1 is available on the course webpage.

Time and Date:
Wednesday (every week), 14.00h - 15.30h online (starting from Nov 4th)
Friday (every second week, alternating with exercises), 14.00h - 15.30h online

Lecturer: Dr. Niclas Zeller

The lectures are held in English.

Time and Date:
Friday (every second week, alternating with lecture), 14.00h - 15.30h online (starting from Nov 13th)
Organizer/Tutor: Patrick Wenzel

Study programme: M. Sc. Informatics

Exam date: 24.02.2021, 14:15 - 15:45
will take place as a graded online exercise

Retake date: 31.03.2021, 8:00 - 9:30
the retake will take place as a graded online exercise

If you plan to attend, please register for the course in TUMonline.
Later during the semester you will have to register for the exam.

This lecture will cover vision-based approaches to 3D robotic perception such as 3D simultaneous localization and mapping or 3D object detection with monocular, stereo and RGB-D cameras. Vision-based approaches attract significant attention in research and industrial applications due to the cost-effectiveness of passive cameras but also RGB-D cameras in comparison to sensors such as lasers or radars. The course will treat the following topics:

• Multi-view geometry
• Probabilistic filtering
• Non-linear least squares optimization
• Indirect and direct methods for rigid image alignment
• Visual odometry, indirect and direct methods
• Visual-inertial odometry
• Visual SLAM, pose graph optimization
• 3D map representations
• 3D object detection and tracking

Passion for solving complex computer vision problems. A solid background in basic mathematics such as linear algebra and analysis is required. Background in basics of multi-view geometry (f.e. acquired through successful participation in the lecture “Computer Vision II: Multi-View Geometry” (IN2228)) is recommended. The course will include exercises for which previous knowledge in programming with Python and Matlab will be required.

All lecture and exercise material will be made available here.