Abstract
A Dynamic Programming (DP) based algorithm that achieves real-time, high quality stereo-matching is presented. A special coarse to fine approach as well as the MMX based assembler implementation mainly contribute to the reached computation speed. A novel vertical smoothing approach by re-integrating paths inside the DP matching allows the avoidance of noisy horizontal strokes, so that high quality stereo-matching is achieved. The current implementation capable of running at about 30 FPS on an 2.2GHz PC, which is sufficient for the utilization in real-time applications.
| Original language | English |
|---|---|
| Title of host publication | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
| Publisher | IEEE Computer Society |
| Volume | 2004-January |
| Edition | January |
| DOIs | |
| Publication status | Published - 2004 |
| Event | 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 - Washington, United States Duration: 2004 Jun 27 → 2004 Jul 2 |
Other
| Other | 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 |
|---|---|
| Country | United States |
| City | Washington |
| Period | 04/6/27 → 04/7/2 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
Cite this
Real-time stereo by using dynamic programming. / Forstmann, Sven; Kanou, Yutaka; Ohya, Jun; Thuering, Sven; Schmitt, Alfred.
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Vol. 2004-January January. ed. IEEE Computer Society, 2004. 1384820.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Real-time stereo by using dynamic programming
AU - Forstmann, Sven
AU - Kanou, Yutaka
AU - Ohya, Jun
AU - Thuering, Sven
AU - Schmitt, Alfred
PY - 2004
Y1 - 2004
N2 - A Dynamic Programming (DP) based algorithm that achieves real-time, high quality stereo-matching is presented. A special coarse to fine approach as well as the MMX based assembler implementation mainly contribute to the reached computation speed. A novel vertical smoothing approach by re-integrating paths inside the DP matching allows the avoidance of noisy horizontal strokes, so that high quality stereo-matching is achieved. The current implementation capable of running at about 30 FPS on an 2.2GHz PC, which is sufficient for the utilization in real-time applications.
AB - A Dynamic Programming (DP) based algorithm that achieves real-time, high quality stereo-matching is presented. A special coarse to fine approach as well as the MMX based assembler implementation mainly contribute to the reached computation speed. A novel vertical smoothing approach by re-integrating paths inside the DP matching allows the avoidance of noisy horizontal strokes, so that high quality stereo-matching is achieved. The current implementation capable of running at about 30 FPS on an 2.2GHz PC, which is sufficient for the utilization in real-time applications.
UR - http://www.scopus.com/inward/record.url?scp=84932642434&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84932642434&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2004.428
DO - 10.1109/CVPR.2004.428
M3 - Conference contribution
VL - 2004-January
BT - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
PB - IEEE Computer Society
ER -