This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
Last revision Both sides next revision
teaching:le-sem-perc-ws19 [2019/10/11 07:39]
balintbe created
teaching:le-sem-perc-ws19 [2019/10/11 08:32]
Line 1: Line 1:
-Content ​to be added soon+====Semantische 3D-Perzeption für robotische Systeme==== 
 +|< 100% 33% 66%>| 
 +^Dauer^4 SWS^ 
 +^Art^Vorlesung mit Übung^ 
 +^Vortragende^Dr. Ing. Michael Suppa^ 
 +^Übungsleitung^Ferenc Balint-Benczedi,​Jan-Hendrik Worch^ 
 +^Sprache^Deutsch und English^ 
 +^Termine Vorlesung und Übungen^17.10.2019-02.02.2020 10:​00-14:​00^ 
 +^Ort^ [[https://​www.google.de/​maps/​place/​Technische+Akademie+Bremen,​+Universit%C3%A4t+Bremen,​+28359+Bremen/​@53.1099364,​8.8592024,​17z/​data=!3m1!4b1!4m2!3m1!1s0x47b126315a2e1755:​0x74c75b0bda3dec4f?​hl=de|TAB-Gebäude (Am Fallturm 1)]], [[https://​ai.uni-bremen.de/​_media/​contact/​tab1.png|Eingang E]], Raum 0.36^ 
 +^**Wichtige Bemerkungen**^Course and exercise alternate. Check Schedule below^ \\ 
 +**Pleas sign up for the course on [[http://​www.elearning.uni-bremen.de|StudIP]]** 
 +=== Description === 
 +Dr. Michael Suppa is a leading expert in robot perception and visiting professor at the University of Bremen. He worked as project manager and researcher at the Institute of Robotics and Mechatronics of the German Aerospace Center (DLR) in the research areas: robotic exploration,​ 3-D vision, and data fusion. From 2009 until 2015, he was the Head of the Department Perception and Cognition, a recognized world leader on key robotic 
 +research topics such as complex scene analysis, perception for resource-limited systems and robotic cognition. In March 2015 he co-founded Roboception,​ a DLR spin-off company devoted ​to advancing the State-of-the -Art in 3D sensors and vision.  
 +The lecture covers all important aspects of 3D semantic perception with a high focus on applicability and real world tasks. Some of the topics covered by the lecture: 
 +  * Introduction to 3D 
 +  * Features and Descriptors 
 +  * From features to semantics 
 +  * Scene registration – RGBD SLAM 
 +  * Handling uncertainty in 3D 
 +  * Perception Systems 
 +  * Convolutional Neural Networks 
 +  * and more 
 +=== Course Schedule (subject to change): === 
 +**The order and date of exercises is subject to change. Check back regularly.**  
 +|< 100% 35% 65%>| 
 +^17.10 10:00-11:30 and 12:​30-14:​00^**Lecture**:​ Introduction to 3D and Acquisition of 3D data^ 
 +^24.10 10:​00-11:​30^Exercise:​ Introduction to 3D^ 
 +^07.11 10:00-11:30 and 12:​30-14:​00^ **Lecture**:​ Features and Filters^ 
 +^14.11 10:​00-11:​30^Exercise:​ 2D Keypoints and descriptors^ 
 +^28.11 10:00-11:30 and 12:​30-14:​00^ **Lecture**:​ Objects I and Objects II^ 
 +^05.12 10:​00-11:​30^Exercise:​ 3D Features and Object recognition^ 
 +^19.12 10:00-11:30 and 12:​30-14:​00^ **Lecture**:​ Scenes I and Scenes II^ 
 +^16.01 10:00-11:30 and 12:​30-14:​00^ **Lecture**:​ CNNs and Applications^ 
 +^23.01 10:​00-11:​30^Exercise:​ Segmentation of kitchen scene^ 
 +^30.01 10:​00-11:​30^Exercise:​ Exercise using CNNs^ 
 +=== Assignments Schedule: === 
 +|< 100% 20% 40% 40%>| 
 +^**Assignment nr.**^**Handed out**^**Submission date**^ 
 +^A1^24th October^13th November 08:00 AM^ 
 +^A2^14th November^4th December 08:00 AM^ 
 +^A3^5th ​ December^12th January 08:00 AM^ 
 +^A4^23rd January^10th February 12:00 PM^ 
 +**Three out of the four assignments must be submitted on time to enter to oral exam. Assignments will not be graded, but they will form a basis for discussion during the oral exam**