Multimedia Computing and Computer Vision Lab

Login  

Home

     

Courses

     

People

     

Research

     

Publications

     

Student Theses

     

Source Code / Datasets

     

Contact

     

SS 12: Multimedia Projekt

From Multimedia Computing Lab - University of Augsburg


Registration is closed


Overview

Instructors: Christian Ries, Prof. Dr. Rainer Lienhart
Time Lecture: Tuesday, 8:15, Room 1020N
Time Exercise: Tuesday, 9:45, Room 1020N
Credits: 6 SWS, 10 LP
Language: German

News

[07.09.2012] The project is finished.

Topic

The topic of this course is the tracking of artificial markers in 2D videos for synchronization with 3D motion capture data.

Our motion capture system is capable of reliably tracking 3D positions of multiple markers in 3D space. However, in many applications it is also important to determine the marker positions in a 2D video recorded by a standard camera.

For this purpose, we need to determine the camera parameters by finding correspondences between 2D and 3D marker positions. It is, however, difficult to track the markers of the motion capture system in a 2D video. Therefore, we will create markers which can be easily detected in a 2D image.

The project will include the following main tasks

  • Create easy-to-track markers as suggested by Schweiger et al. (see 1. below and image on top)
  • Use existing key point detectors to detect the 2D positions of the markers in video frames
  • Synchronize the 2D positions with 3D positions obtained from motion capture data
  • Derive the camera parameters from the point correspondences

As a result we will be able to track markers in 2D and 3D simultaneously, by deducing the 2D marker postions from the 3D marker positions given the camera parameters.

This course is divided into two phases:

  • Weekly assignments will introduce students to programming in OpenCV step-by-step and provide first hands-on experience in image and video processing.
  • Student groups will work on a project in weekly sessions.


Prerequisites

  • Participation in the exercises to prepare for the project
  • Each student must read the related papers thoroughly
  • Teamwork
  • Written documentation of the project (can be done in Word, LaTeX, OpenOffice, etc...)
  • Short presentation of the results
  • Programming will mostly be in C/C++


Language

The course is held in German. You can write the documentation either in German or English, whatever you prefer most.

Material

Date Content Slides Exercise
16.04.2012 Lec 0: Introduction PDF PDF
24.04.2012 Lec 1-1: Tutorial Visual Studio PDF
Lec 1-2: Digital Images, Tutorial OpenCV PDF PDF Video
08.05.2012 Lec 2-1: Image Filters PDF
Lec 2-2: Gradients PDF PDF
15.05.2012 Lec 3-1: Key points and local image features PDF PDF Image 1 Image 2
12.06.2012 Lec 4-1: Maximum Response Markers PDF PDF Images
26.06.2012 Lec 5-1: Camera Calibration PDF PDF Images Points
23.07.2012 Project MC_Tutorial Project LaTeX template

Literature

  1. F. Schweiger, B. Zeisl, P. Georgel, G. Schroth, E. Steinbach, N. Navab, “Maximum Detector Response Markers for SIFT and SURF”, VMV 2009.