ML Anthology

Improving Constrained Bundle Adjustment Through Semantic Scene Labeling

Achkan Salehi, Vincent Gay-Bellile, Steve Bourgeois, Frédéric Chausse
ECCV 2016 pp. 133-142
doi:10.1007/978-3-319-49409-8_13 /eccv/2016/salehi2016eccv-improving/

Abstract

There is no doubt that SLAM and deep learning methods can benefit from each other. Most recent approaches to coupling those two subjects, however, either use SLAM to improve the learning process, or tend to ignore the geometric solutions that are currently used by SLAM systems. In this work, we focus on improving city-scale SLAM through the use of deep learning. More precisely, we propose to use CNN-based scene labeling to geometrically constrain bundle adjustment. Our experiments indicate a considerable increase in robustness and precision.

PDF ECCV Semantic Scholar

Cite

Text

Salehi et al. "Improving Constrained Bundle Adjustment Through Semantic Scene Labeling." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-49409-8_13

Markdown

[Salehi et al. "Improving Constrained Bundle Adjustment Through Semantic Scene Labeling." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/salehi2016eccv-improving/) doi:10.1007/978-3-319-49409-8_13

BibTeX

@inproceedings{salehi2016eccv-improving,
  title     = {{Improving Constrained Bundle Adjustment Through Semantic Scene Labeling}},
  author    = {Salehi, Achkan and Gay-Bellile, Vincent and Bourgeois, Steve and Chausse, Frédéric},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {133-142},
  doi       = {10.1007/978-3-319-49409-8_13},
  url       = {https://mlanthology.org/eccv/2016/salehi2016eccv-improving/}
}