A Scalable High-Performance Hardware Architecture for Real-Time Stereo Vision by Semi-Global Matching

Abstract

Perceiving distance from two camera images, a task called stereo vision, is fundamental for many applications in robotics or automation. However, algorithms that compute this information at high accuracy have a high computational complexity. One such algorithm, Semi Global Matching (SGM), performs well in many stereo vision benchmarks, while maintaining a manageable computational complexity. Nevertheless, CPU and GPU implementations of this algorithm often fail to achieve real-time processing of camera images, especially in power-constrained embedded environments. This work presents a novel architecture to calculate disparities through SGM. The proposed architecture is highly scalable and applicable for low-power embedded as well as high-performance multicamera high-resolution applications.

Cite

Text

Hofmann et al. "A Scalable High-Performance Hardware Architecture for Real-Time Stereo Vision by Semi-Global Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016. doi:10.1109/CVPRW.2016.110

Markdown

[Hofmann et al. "A Scalable High-Performance Hardware Architecture for Real-Time Stereo Vision by Semi-Global Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016.](https://mlanthology.org/cvprw/2016/hofmann2016cvprw-scalable/) doi:10.1109/CVPRW.2016.110

BibTeX

@inproceedings{hofmann2016cvprw-scalable,
  title     = {{A Scalable High-Performance Hardware Architecture for Real-Time Stereo Vision by Semi-Global Matching}},
  author    = {Hofmann, Jaco A. and Korinth, Jens and Koch, Andreas},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2016},
  pages     = {845-853},
  doi       = {10.1109/CVPRW.2016.110},
  url       = {https://mlanthology.org/cvprw/2016/hofmann2016cvprw-scalable/}
}