Seminar: Image Understanding

Dauer	2 SWS (4 ECTS)
Art	Seminar
Semester	WS 2014/2015
Vortragende	Prof. Michael Beetz, Ferenc Balint-Benczedi, Thiemo Wiedemeyer, Jan-Hendrik Worch
Sprache	Englisch
Termine	Di. 10:00-12:00
Ort	TAB-Gebäude (Am Fallturm 1), Eingang E, Raum 0.31
Bemerkungen	Veranstaltungsbeginn: 14.10.2014

Topics:

Camera Model | RGBD-Camera Registration
3D-Feature Detectors and Descriptors
Hough Transformation
RANSAC | ICP
Object Recognition
Object Detection
Object Model Reconstruction
Human Detection
Probability Theory
Tracking Algorithms
Watson | RoboSherlock

Nähere Informationen zum Ablauf des Seminars finden sich hier

For a general overview about perception in robotics students are encouraged to look at the following paper :

Vision for Robotics, Markus Vincze and Danica Kragic in Foundations and Trends in Robotics Vol. 1, No. 1 (2010) 1–78 [pdf]

Object Detecion and recogniotion

Richard Szeliski: Computer Vision:Algorithms and Applications, Chapter 14 (link),
Collet et.al. Object Recognition and Full Pose Registration from a Single Image for Robotic Manipulation

Hough Transform, RANSAC, ICP

Wikipedia is normally a great place for geting familiar with these algorithms
Papzov et.el. An Efficient RANSAC for 3D Object Recognition in Noisy and Occluded Scenes
Find more applications of these algorithms in robotics e.g.:

Tracking and Recognizing Humans

Forsyth et.al. Computational Studies of Human Motion: Part 1, Tracking and Motion Synthesis(pdf)
Pons-Moll et.al. Metric Regression Forests for Human Pose Estimation( pdf)