Technische Universität München Robotics and Embedded Systems
 

Applied Computer Vision for Robotics WS 2012/13

 
Organizer Dipl.-Inf. Philipp Heise, Dipl.-Inf. Brian Jensen, Dipl.-Inf. Sebastian Klose
Type Praktikum
Semester WS 2012/2013
ECTS 10.0
SWS 6
Preliminary Talk 10.07 from 15:00 to 16:00 in room 03.07.023
Time & Location 13:15 - 13:45 in 07.03.023
Starting on 22.10.2012
Certificate successful completion of all exercises
Registration By email to one of the organizers. Confirmation via TUMonline REGISTRATION CLOSED!!!

Course Materials

Date Due Topics Slides Assignment Sheet
22.10.2012 05.11.2012 ROS Intro, nodelets, rViz, Harris corner detector, camera calibration
Sheet1_Harris.png Sheet1_rViz.png
pdf pdf
Updated 29.10.2012
05.11.2012 19.11.2012 Descriptors, Matching, Direct Linear Transform
FeatureMatching.png
Sheet2_Colorama.png
pdf pdf
19.11.2012 03.12.2012 Visual Odometry using Stereo input
VisualOdometryFlow.png
VisualOdometryMap.png
pdf pdf
03.12.2012 17.12.2012 Visual Odometry from RGBD and Occupancy Grids - pdf
17.12.2012   Projects - pdf

Final Projects

Team Project Proposal Midterm Final
Gang of Three Key frame based SLAM with Bundle Adjustment
pdf  pdf pdf
Team 5 Real time sperical mosaicing using whole image alignment
pdf pdf pdf
Team 6 Fusing GPS and Stereo Data pdf pdf pdf
Trashold Color Segmentation in the RoboCup Small Size League
pdf pdf pdf
Waiting List Motion Planning for Autonomous Vehicles
pdf pdf pdf

Description

This lab course will cover various interesting topics of Computer Vision useful for Robotic applications. The participants will start by implementing some fundamental computer vision algorithms. These basic components will be iteratively expanded as the course progresses resulting in the creation of a full featured visual processing pipeline that in turn can be used to solve complex robotic tasks. Participants will then select a specific project from a range of final project topics to further expand their skills and knowledge in desired area of computer vision as the completion of this course. Throughout the course the implemented systems will be tested with real robotic data.

Selection of possibly covered Topics

General Information

External Collaborators

Literature