TeachingSS18PLARR

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

THIS WEBPAGE IS DEPRECATED - please visit our new website

Praktikum/Lab Course - Perception and Learning in Robotics and Augmented Reality

This praktikum introduces common tools and principles in computer vision and machine learning for object recognition and pose estimation, for applications in the field of Augmented Reality and Robotics. Starting from the basics, students are gradually taught to develop a framework that can process images and 3D data with the goal of perceiving shapes and recognizing objects in real environments, under pose variations, clutter and occlusion.

Lecturers: Dr. Federico Tombari, Prof. Nassir Navab
Tutors: Iro Laina, Helisa Dhamo, Fabian Manhardt, Huseyin Coskun, Yida Wang
Type: Master Practical Course Module IN2106
Course Title: Perception and Learning in Robotics and Augmented Reality - Link to TUMOnline

Programs lab course: Biomedical Computing (Master), Informatics (Master), Informatics (Diploma)
Programs elective course: Electrical Engineering, Mechanical Engineering, School of Management
SWS: 6
ECTS: 10 Credits

Meetings:
Preliminary Meeting: Jan. 30th, 14:00, Location: 03.13.010

The course will be conducted in English.

Google Group for Q&A: plarr-2018 |[@]| googlegroups.com



Important News

  • 16/04/2018: The project proposals have been announced. The deadline for submitting your preferences is 23/04/2018.
  • The schedule for the upcoming semester has been announced. In the first lecture, we will additionally hold an (optional) introduction to Git, GitLab and CMake for those who are not familiar with these tools that will be required during the Praktikum.
  • If interested in registering for the Praktikum, you can send us your motivation letter (plus relevant courses that you have taken) at plarr-2018|[at]|googlegroups.com. However, please note that the official application has to be done via the TUM Matching System.


Schedule

Date Location Topic Assignments Conducted by Material Due
30.01.2018, 14:00 03.13.010 Preliminary meeting ("Vorbesprechung") - Federico Tombari Course info -
10.04.2018, 14:00 - 16:00 03.13.010 Introduction and computer vision basics OpenCV Federico Tombari Lecture Exercise CMake GIT Tutorial 16.04.2018 23:59
17.04.2018, 14:00 - 15:30 03.13.010 Feature description and matching OpenCV Federico Tombari Lecture Exercise 23.04.2018 23:59
24.04.2018, 14:00 - 15:30 03.13.010 Fundamentals of Deep Learning and CNNs TensorFlow Iro Laina Lecture Exercise 04.05.2018 23:59
08.05.2018, 14:00 - 15:30 03.13.010 CNNs in computer vision and perception TensorFlow Iro Laina Lecture Exercise 28.05.2018 23:59
29.05.2018, 14:00 - 15:30 03.13.010 3D sensors and 3D representations Eigen / OpenNI Federico Tombari Lecture Exercise ORBBEC Installation 04.06.2018 23:59
05.06.2018, 14:00 - 15:30 03.13.010 Surface matching and registration PCL Federico Tombari Lecture Exercise 11.06.2018 23:59
12.06.2018, 14:00 - 15:30 03.13.010 3D object detection and pose estimation PCL Federico Tombari Lecture Exercise 18.06.2018 23:59
19.06.2018, 14:00 - 16:00 03.13.010 6DoF pose estimation with deep learning Human pose estimation - Fabian Manhardt Huseyin Coskun 6DoF Pose Human Pose -
Project preparation            
03.07.2018, 14:00 - 16:00 03.13.010 Intermediate presentations - Participants    
17.07.2018, 14:00 - 18:00 03.13.010 Final presentations - Participants    


Projects

A list of all projects can be downloaded here.

Topic Project Description Mentor Team Presentation Schedule
Object detection and pose estimation for robotic manipulation Project 1 Fabian Manhardt Team 2 14:10 - 14:20
Monocular estimation of grasp position and pose for robotic grippers Project 2 Ghazal Ghazaei Team 7 14:30 - 14:50
RGB-D detection and pose estimation for bin picking Project 3 Fabian Manhardt / Juan Jose Gonzalez Team 1 14:50 - 15:10
Human sign language from RGB for human-robot interaction Project 4 Yida Wang Team 3 15:10 - 15:30
Augmented reality (AR) for video-gaming Project 5 Helisa Dhamo Team 8 15:30 - 15:50
Depth and surface normals estimation for scene augmentation (AR) Project 6 Iro Laina Team 5 16:10 - 16:30
Black Mirror (diminished reality) Project 7 Iro Laina Team 9 16:30 - 16:50
Multi-camera AR Project 8 Nikolas Brasch Team 10 16:50 - 17:10
Safety distance and brake assistant Project 9 Jakob Mayr Team 4 17:10 - 17:30
Traffic sign detection Project 10 Oliver Scheel Team 6 17:30 - 17:50




TeachingForm
Title: Perception and Learning in Robotics and Augmented Reality
Professor: Dr. Federico Tombari, Prof. Nassir Navab
Tutors: Iro Laina, Helisa Dhamo, Fabian Manhardt, Huseyin Coskun, Yida Wang
Type: Praktikum
Information: 6 SWS, 10 ECTS Credits (IN2106)
Term: 2018SoSe
Abstract: This praktikum introduces common tools and principles in computer vision and machine learning for object recognition and pose estimation, for applications in the field of Augmented Reality and Robotics. Starting from the basics, students are gradually taught to develop a framework that can process images and 3D data with the goal of perceiving shapes and recognizing objects in real environments, under pose variations, clutter and occlusion.


Edit | Attach | Refresh | Diffs | More | Revision r1.44 - 17 Jul 2018 - 10:23 - IroLaina

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