Login
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | |||
|
members:steinbrf [2014/02/18 16:53] steinbrf |
members:steinbrf [2014/02/18 17:00] (current) steinbrf |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | {{page> | ||
| + | |||
| + | |||
| + | === Research Interests === | ||
| + | Correspondence Problems, Segmentation, | ||
| + | |||
| + | === Brief Bio === | ||
| + | Frank Steinbrücker received his Bachelor' | ||
| + | Since September 2008 he is a Ph.D. student in the Research Group for Computer Vision, | ||
| + | Image Processing and Pattern Recognition at the University of Bonn headed by | ||
| + | [[cremers|Professor Daniel Cremers]]. | ||
| + | |||
| + | === Visual Odometry === | ||
| + | At ICCV 2011 we published a method for getting a camera pose estimation from RGBD-Images. | ||
| + | In the video below, the Kinect camera is moving in a static scene and the camera poses are being accurately estimated. | ||
| + | |||
| + | < | ||
| + | |||
| + | === Dense Mapping of large RGB-D Sequences === | ||
| + | In our publication at ICCV 2013 I describe a method for the volumetric fusion of large RGB-D sequences. The video below shows the mesh visualization of our office floor, a scene computed from more than 24.000 RGB-D images captured with the Asus Xtion sensor. The reconstruction run at more than 200 Hz on a GTX680. The finest resolution was 5mm and the entire scene fit into approximately 2.5 GB of GPU RAM, including color. | ||
| + | < | ||
| + | |||
| + | While the method published at ICCV 2013 required a GPU to run in real-time, in our paper published at ICRA 2014, we demonstrated that the mapping part of dense volumetric RGB-D image fusion also works on a single standard CPU core at camera speed. Furthermore, | ||
| + | |||
| + | < | ||
| + | |||
| + | |||
| + | ========== Publications ========== | ||
| + | < | ||
| + | < | ||
| + | </ | ||
