ML Anthology

Way to Go! Detecting Open Areas Ahead of a Walking Person

Boris Schauerte, Daniel Koester, Manuel Martínez, Rainer Stiefelhagen
ECCVW 2014 pp. 349-360
doi:10.1007/978-3-319-16199-0_25 /eccvw/2014/schauerte2014eccvw-way/

Abstract

We determine the region in front of a walking person that is not blocked by obstacles. This is an important task when trying to assist visually impaired people or navigate autonomous robots in urban environments. We use conditional random fields to learn how to interpret texture and depth information for their accessibility. We demonstrate the effectiveness of the proposed approach on a novel dataset, which consists of urban outdoor and indoor scenes that were recorded with a handheld stereo camera.

PDF ECCVW Semantic Scholar

Cite

Text

Schauerte et al. "Way to Go! Detecting Open Areas Ahead of a Walking Person." European Conference on Computer Vision Workshops, 2014. doi:10.1007/978-3-319-16199-0_25

Markdown

[Schauerte et al. "Way to Go! Detecting Open Areas Ahead of a Walking Person." European Conference on Computer Vision Workshops, 2014.](https://mlanthology.org/eccvw/2014/schauerte2014eccvw-way/) doi:10.1007/978-3-319-16199-0_25

BibTeX

@inproceedings{schauerte2014eccvw-way,
  title     = {{Way to Go! Detecting Open Areas Ahead of a Walking Person}},
  author    = {Schauerte, Boris and Koester, Daniel and Martínez, Manuel and Stiefelhagen, Rainer},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2014},
  pages     = {349-360},
  doi       = {10.1007/978-3-319-16199-0_25},
  url       = {https://mlanthology.org/eccvw/2014/schauerte2014eccvw-way/}
}