Technische Universität München Robotics and Embedded Systems

Real-time visual tracking techniques

Veranstalter Giorgio Panin, Ph.D., Dipl.-Ing. Claus Lenz, Thorsten Röder M.Sc., Dipl.-Inf. Sebastian Klose
Modul IN8901
Typ Hauptseminar
Semester Ss 2010
ECTS 4.0
Vorbesprechung Di. 09.02.10 um 14:00-15:00 im Seminarraum 03.07.023
Zeit & Ort Donnerstags um 14:00-16:00 im Seminarraum 03.07.023
Schein erfolgreiche Teilnahme am Seminar (Vortrag, schriftliche Ausarbeitung, aktive Teilnahme)



Datum Titel Vortragender Betreuer Material
22.04.2010 3D tracking techniques using depth information Clemens Binder Claus Lenz 1 2 3 4
29.04.2010 Object detection and pose estimation with scale-invariant keypoints Evi Andergassen-Sölva Giorgio Panin 1 2 3
29.04.2010 Template-based tracking : the EigenTracking technique Janosch Peters Claus Lenz 1 2
06.05.2010 Particle filters for color- and contour-based tracking Simon Sklenak Sebastian Klose 1 2
06.05.2010 The Mean-shift algorithm for color segmentation and object tracking Alexander Lechner Thorsten Röder 1 2
20.05.2010 Template-based tracking: Active Appearance Models Robert Maier Giorgio Panin 1 2 3 4
20.05.2010 Contour tracking based on intensity edges Florian Fembacher Sebastian Klose 1 2
27.05.2010 Contour tracking based on local color statistics - the CCD Algorithm Andreas Bayha Giorgio Panin 1 2 3
27.05.2010 Fast keypoints tracking: the Shi-Tomasi approach Tobias Weigl Thorsten Röder 1 2 3


Latex Vorlage


Beschreibung (Englisch)

From Wikipedia: definition of Visual Tracking

Visual tracking is the process of locating a moving object (or several ones) in time using a camera. An algorithm analyzes the video frames and outputs the location, optionally in real time. A visual tracking algorithm is based on a motion model which describes how the image of the target changes depending on a vector of motion parameters. When the target is a rigid 3D object, the motion model defines its aspect depending on its 3D position and orientation. The role of the tracking algorithm is to analyse the video frames in order to estimate the motion parameters. These parameters characterize the location of the target.

Applications of real-time 3D tracking cover many fields of interest, for which commercial products are increasingly becoming available. Today there are several known approaches for this task, and we consider here some advanced techniques, by organizing them into

Lecture Slides from our WS09/10 Course "Model-Based Visual Tracking" provide also useful material for this Seminar. They are available (with password) at

Model-Based Visual Tracking.