====== Image Understanding ======

|< 100% 33% 66%>|
^Dauer^4 SWS^
^Art^Seminar^
^Semester^SS2015^
^Vortragende^Prof. Michael Beetz, Ferenc Balint-Benczedi, Thiemo Wiedemeyer, Jan-Hendrik Worch^
^Sprache^Deutsch, Englisch^
^Termine^ Mo., 10:00 - 12:00, Ort: TAB 1.58^
^Bemerkungen^Vorlesungsbeginn: 13.04.2015^ \\ \\

Organizational Issues and Materials can be found at our
[[https://elearning.uni-bremen.de/details.php?sem_id=7bbb93cc50d8ac44b1f2edd11f8434af&send_from_search=1&send_from_search_page=sem_portal.php%3Fkeep_result_set%3D11|Stud.IP page]]

===== Description =====
The seminar will deal with the challenges of semantic perception in the context of robotics, presenting various aspects of it. Students will be presented with an overview of the field followed by individual presentations and reports of pre-defined topics.

===== News =====
  * Please register for the seminar on [[https://elearning.uni-bremen.de|Stud.IP]].
  * First seminar will be held on 20.4.

=== 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

==Literature== 

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 [[http://www.nowpublishers.com/media/Journal-Article-PDFs/2300000001.pdf|[pdf]]] 

==Object Detection and Recognition== 
  *Richard Szeliski: Computer Vision:Algorithms and Applications, Chapter 14 [[http://szeliski.org/Book/|(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([[http://luthuli.cs.uiuc.edu/~daf/Papers-local/0600000005.pdf|pdf]])
  *Pons-Moll et.al. Metric Regression Forests for Human Pose Estimation( [[http://www.bmva.org/bmvc/2013/Papers/paper0004/paper0004.pdf|pdf]])