by PD Dr. Slobodan Ilic
: Ivan Shugurov
, Agnieszka Tomczak
, Adrian Haarbach
, Li Fu, You Hao
: Master Practical Course Module IN2106
Informatics (Master), Biomedical Computing (Master)
*Lectures: Mondays 14:00-16:00h via Zoom (Check Moodle for the access code)
*Tutorial(Project discussion): Thursdays 14:00-16:00h via Zoom (Check Moodle for the access code)
See the schedule below. According to the pandemic situation we will partly or fully have our meetings / lectures via zoom.
This course in TUMOnline
The course will be conducted in English.
- Praktikum lecture will take place as of Monday 02.11.2020 and Turorial(Project discussion) from Thursday 05.11.2020 via Zoom(invitation and access code are shared via Moodle)
- Praktikum material will be shared via MOODLE
- Application Deadline: 21-JUL-2020
Deregistration Deadline: *07-AUGUST-2020
For the application, please use the following form (Deadline : 21.07.2020): Application Form.
register in the TUM matching system
for the course registration. Keep in mind that your chances to be assigned to the course increase if you give it a higher rank in your choices. For further details about how the matching system works and its schedule please check this website
We select appropriate candidates based on their background, interests, and motivation.
Tracking and Detection in Computer Vision (TDCV) stem from the TDCV course held in the previous year. The Praktikum will deal with the problems of 3D object detection and 6D pose estimation in various image modalities RGB, depth, RGB-D and point clouds with applications in Augmented Reality, Robotics, Autonomous Driving, Medical Imaging etc. It will consists of around 30% theoretical lectures explaining the key elements of the object detection and 6D object pose estimation followed by practical projects. The first part of the Praktikum will consist of a common project for all groups related to 6D tracking of the objects in sequence of RGB images. There, students will be required to implement a method for object detection and 6D pose estimation using hand-crafted features. This project introduces students to practical aspects of 6D pose parameterization, design and implementation of robust non-linear iterative least square method for 6D pose estimation and tracking. The second part of the Praktikum will be related but not limited to modern Machine Learning and Deep Learning methods for solving the problems of 3D object detection, 6D pose estimation, domain adaptation, 3D reconstruction and shape completion.
Example applications to follow.
- Basic knowledge with C++ and Python programming
- Experience with basic computer vision and machine learning concepts
- Enthusiasm to tackle challenging problems
- Passion to create something new with a team
- Active participation in all mandatory workshops and meetings
- Submission of all individual challenge solutions in time
- Final group presentation with live prototype demonstration
Lecture Schedule and Content (Mondays 14:00-16:00h via Zoom)
Projects Schedule (Thursdays 14:00-16:00h via Zoom)
If you have questions about a specific project, please direct them to the responsible tutor. At the due date the results of the projects will be presented by each group of students followed by the questions of the tutors. The students should be ready to run the code after their presentation as well as show parts of the code and be prepared to answer the questions about their implementation.
Literature and Resources