ML Anthology

Fast Single-Frequency Time-of-Flight Range Imaging

Ryan Crabb, Roberto Manduchi
CVPRW 2015 pp. 58-65
doi:10.1109/CVPRW.2015.7301376 /cvprw/2015/crabb2015cvprw-fast/

Abstract

This paper proposes a solution to the 2-D phase unwrapping problem, inherent to time-of-flight range sensing technology due to the cyclic nature of phase. Our method uses a single frequency capture period to improve frame rate and decrease the presence of motion artifacts encountered in multiple frequency solutions. We present an illumination model that considers intensity image and estimates of the surface normal in addition to the phase image. Considering the number of phase wrap as the `label', the likelihood of each label is estimated at each pixel, and support for the labeling is shared between pixels throughout the image by Non-Local Cost Aggregation. Comparative experimental results confirm the effectiveness of the proposed approach.

PDF CVPRW Semantic Scholar

Cite

Text

Crabb and Manduchi. "Fast Single-Frequency Time-of-Flight Range Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301376

Markdown

[Crabb and Manduchi. "Fast Single-Frequency Time-of-Flight Range Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/crabb2015cvprw-fast/) doi:10.1109/CVPRW.2015.7301376

BibTeX

@inproceedings{crabb2015cvprw-fast,
  title     = {{Fast Single-Frequency Time-of-Flight Range Imaging}},
  author    = {Crabb, Ryan and Manduchi, Roberto},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2015},
  pages     = {58-65},
  doi       = {10.1109/CVPRW.2015.7301376},
  url       = {https://mlanthology.org/cvprw/2015/crabb2015cvprw-fast/}
}