Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu
Home Members Jakob Engel

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revision Both sides next revision
members:engelj [2016/07/13 09:52]
engelj
members:engelj [2016/11/21 14:25]
Vladyslav Usenko old revision restored (2016/07/14 08:03)
Line 8: Line 8:
 ========== Research Interests ========== ========== Research Interests ==========
  
-  * **Direct Visual SLAM** ​(in particular with a monocular ​camerabut also using stereo ​and RGB-D cameras). This video shows LSD-SLAM: a novel direct, large-scale monocular SLAM technique we developed, published at ECCV '14 ([[research:​vslam:​lsdslam|more details & code here]]):+  * **Direct Visual SLAM**.  
 +This video shows **DSO**: ​novel direct and sparse ​monocular ​VO formulation we developed, and published as pre-print on arXiv in July 2016 ([[research:​vslam:​dso|more details]], code coming soon) 
 +<​html><​center><​iframe width="​640"​ height="​360"​ src="//​www.youtube.com/​embed/​C6-xwSOOdqQ"​ frameborder="​0"​ allowfullscreen></​iframe></​center></​html>​ 
 +<​html><​br /><br /></​html>​ 
 + 
 +This video shows **LSD-SLAM**: a direct, large-scale monocular SLAM technique we developed, published at ECCV '14 ([[research:​vslam:​lsdslam|more details & code here]]):
 <​html><​center><​iframe width="​640"​ height="​360"​ src="//​www.youtube.com/​embed/​GnuQzP3gty4"​ frameborder="​0"​ allowfullscreen></​iframe></​center></​html>​ <​html><​center><​iframe width="​640"​ height="​360"​ src="//​www.youtube.com/​embed/​GnuQzP3gty4"​ frameborder="​0"​ allowfullscreen></​iframe></​center></​html>​
 <​html><​br /><br /></​html>​ <​html><​br /><br /></​html>​
Line 16: Line 21:
 <​html><​center><​iframe width="​560"​ height="​315"​ src="//​www.youtube.com/​embed/​eznMokFQmpc"​ frameborder="​0"​ allowfullscreen></​iframe></​center></​html>​ <​html><​center><​iframe width="​560"​ height="​315"​ src="//​www.youtube.com/​embed/​eznMokFQmpc"​ frameborder="​0"​ allowfullscreen></​iframe></​center></​html>​
 We published the code as [[http://​www.ros.org/​wiki/​tum_ardrone|ROS node]], so you can try it out yourself (provided you have an AR.Drone 1.0 or 2.0). We published the code as [[http://​www.ros.org/​wiki/​tum_ardrone|ROS node]], so you can try it out yourself (provided you have an AR.Drone 1.0 or 2.0).
- 
- 
-  * **Nanocopter**:​ Visual navigation methods for Quadrocopter weighing less than 50g ([[research:​nanocopter|more details here]]). 
- 
- 
-========== Project Topics ========== 
-If you are interested in writing a **Master'​s Thesis** or a **HIWI position** in the area of camera-based navigation (SLAM, visual odometry, 3D reconstruction) and / or quadrocopter,​ you are welcome to contact me or come by my office. Note that I expect you to be well familiar with C++, have a decent mathematical understanding,​ some background (lectures / projects / seminars) in the area of computer vision, and capable of working self-organized. Please also read William Freeman'​s tips on [[http://​people.csail.mit.edu/​billf/​www/​papers/​doresearch.pdf|How to do research]] 
- 
  
  

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de