Abstract
Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.
| Original language | English |
|---|---|
| Title of host publication | ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings |
| Publisher | SciTePress |
| Pages | 150-157 |
| Number of pages | 8 |
| Volume | 2 |
| ISBN (Print) | 9789897580772 |
| Publication status | Published - 2015 |
| Event | 4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015 - Lisbon, Portugal Duration: 2015 Jan 10 → 2015 Jan 12 |
Other
| Other | 4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015 |
|---|---|
| Country | Portugal |
| City | Lisbon |
| Period | 15/1/10 → 15/1/12 |
Fingerprint
Keywords
- Denoising
- Depth map
- GPU
- Plane fitting
- ToF depth sensor
- Upsampling
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time. / Matsumoto, Kazuki; De Sorbier, Francois; Saito, Hideo.
ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings. Vol. 2 SciTePress, 2015. p. 150-157.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time
AU - Matsumoto, Kazuki
AU - De Sorbier, Francois
AU - Saito, Hideo
PY - 2015
Y1 - 2015
N2 - Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.
AB - Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.
KW - Denoising
KW - Depth map
KW - GPU
KW - Plane fitting
KW - ToF depth sensor
KW - Upsampling
UR - http://www.scopus.com/inward/record.url?scp=84938839983&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84938839983&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84938839983
SN - 9789897580772
VL - 2
SP - 150
EP - 157
BT - ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings
PB - SciTePress
ER -