TeachingWs20PTDCV

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Lab Course / Praktikum: Master Praktikum - Tracking and Detection on Computer Vision

by PD Dr. Slobodan Ilic
Team: Ivan Shugurov, Agnieszka Tomczak, Adrian Haarbach, MahdiHamad, Li Fu, You Hao
Type: Master Practical Course Module IN2106
SWS: 6
Programs: Informatics (Master), Biomedical Computing (Master)
ECTS: 10 Credits

Further Meetings: 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.

Announcements

  • Application Deadline: 21-JUL-2020
  • Deregistration Deadline: *07-AUGUST-2020*

Registration

For the application, please use the following form (Deadline : 21.07.2020): Application Form
Please also 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.

General Content

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

Example applications to follow.

Prerequisites

  • 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

Passing Requirements

  • Active participation in all mandatory workshops and meetings
  • Submission of all individual challenge solutions in time
  • Final group presentation with live prototype demonstration

Schedule

Lecture Schedule and Content (Mondays at Seminar Room 03.10.011 or via Zoom)

Date Topic Conducted by Material/Literature
02.11 Camera Models Dr. S. Ilic  
09.11 Pose Estimation from 2D-3D correspondences (DLT, PnP?), RANSAC Dr. S. Ilic  
16.11 Rotation Parameterization Dr. S. Ilic  
23.11 Non-linear Optimization Dr. S. Ilic  
30.11 Object Detection with Deep Learning Dr. S. Ilic  
07.12. Object Detection and 6D Pose Estimation    
14.12 Camera relocalization Dr. S. Ilic  

Projects Schedule (Thursdays at Seminar Room 03.10.011 or 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.

Date Topic Conducted by Material/Literature Sample Output
05.11. Introduction to the Praktikum; Keypoint based object detection, 6D pose estimation and tracking (project presentation) Adrian Haarbach    
12.11-03.12 Project consultations with tutors All Tutors    
10.12 Project results presentation All Tutors    
17.12. Second project presentation All Tutors    
17.12-28.01 Project consultations with tutors All Tutors    
04.02. Project results presentation All Tutors    

Literature and Resources

Coding

Versioning


TeachingForm
Title: Tracking and Detection in Computer Vision
Professor: Slobodan Ilic
Tutors: Ivan Shugurov, Agnieszka Tomczak, Adrian Haarbach, MahdiHamad&#44, Li Fu, You Hao
Type: Praktikum
Information: 6 SWS, 10 ECTS Credits (Module IN4023)
Term: 2020WiSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.4 - 03 Aug 2020 - 16:15 - SlobodanIlic

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif