Abstract
In this paper, we consider the problem of stereo matching using loopy belief propagation. Unlike previous methods which focus on the original spatial resolution, we hierarchically reduce the disparity search range. By fixing the number of disparity levels on the original resolution, our method solves the message updating problem in a time linear in the number of pixels contained in the image and requires only constant memory space. Specifically, for a 800 x 600 image with 300 disparities, our message updating method is about 30 x faster (1.5 second) than standard method, and requires only about 0.6% memory (9 MB). Also, our algorithm lends itself to a parallel implementation. Our GPU implementation (NVIDIA Geforce 8800GTX) is about 10 x faster than our CPU implementation. Given the trend toward higher-resolution images, stereo matching using belief propagation with large number of disparity levels as efficient as the small ones makes our method future-proof. In addition to the computational and memory advantages, our method is straightforward to implement.
| Original language | English (US) |
|---|---|
| Title of host publication | 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 |
| Pages | 1458-1465 |
| Number of pages | 8 |
| DOIs | |
| State | Published - Aug 31 2010 |
| Event | 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, CA, United States Duration: Jun 13 2010 → Jun 18 2010 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Other
| Other | 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 |
|---|---|
| Country | United States |
| City | San Francisco, CA |
| Period | 6/13/10 → 6/18/10 |
Fingerprint
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
Cite this
A constant-space belief propagation algorithm for stereo matching. / Yang, Qingxiong; Wang, Liang; Ahuja, Narendra.
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. p. 1458-1465 5539797 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A constant-space belief propagation algorithm for stereo matching
AU - Yang, Qingxiong
AU - Wang, Liang
AU - Ahuja, Narendra
PY - 2010/8/31
Y1 - 2010/8/31
N2 - In this paper, we consider the problem of stereo matching using loopy belief propagation. Unlike previous methods which focus on the original spatial resolution, we hierarchically reduce the disparity search range. By fixing the number of disparity levels on the original resolution, our method solves the message updating problem in a time linear in the number of pixels contained in the image and requires only constant memory space. Specifically, for a 800 x 600 image with 300 disparities, our message updating method is about 30 x faster (1.5 second) than standard method, and requires only about 0.6% memory (9 MB). Also, our algorithm lends itself to a parallel implementation. Our GPU implementation (NVIDIA Geforce 8800GTX) is about 10 x faster than our CPU implementation. Given the trend toward higher-resolution images, stereo matching using belief propagation with large number of disparity levels as efficient as the small ones makes our method future-proof. In addition to the computational and memory advantages, our method is straightforward to implement.
AB - In this paper, we consider the problem of stereo matching using loopy belief propagation. Unlike previous methods which focus on the original spatial resolution, we hierarchically reduce the disparity search range. By fixing the number of disparity levels on the original resolution, our method solves the message updating problem in a time linear in the number of pixels contained in the image and requires only constant memory space. Specifically, for a 800 x 600 image with 300 disparities, our message updating method is about 30 x faster (1.5 second) than standard method, and requires only about 0.6% memory (9 MB). Also, our algorithm lends itself to a parallel implementation. Our GPU implementation (NVIDIA Geforce 8800GTX) is about 10 x faster than our CPU implementation. Given the trend toward higher-resolution images, stereo matching using belief propagation with large number of disparity levels as efficient as the small ones makes our method future-proof. In addition to the computational and memory advantages, our method is straightforward to implement.
UR - http://www.scopus.com/inward/record.url?scp=77955985724&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77955985724&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2010.5539797
DO - 10.1109/CVPR.2010.5539797
M3 - Conference contribution
AN - SCOPUS:77955985724
SN - 9781424469840
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1458
EP - 1465
BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
ER -