A Simple Hierarchical Pooling Data Structure for Loop Closure

Abstract

We propose a data structure obtained by hierarchically pooling Bag-of-Words (BoW) descriptors during a sequence of views that achieves average speedups in large-scale loop closure applications ranging from 2 to 20 times on benchmark datasets. Although simple, the method works as well as sophisticated agglomerative schemes at a fraction of the cost with minimal loss of performance.

Cite

Text

Fei et al. "A Simple Hierarchical Pooling Data Structure for Loop Closure." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46487-9_20

Markdown

[Fei et al. "A Simple Hierarchical Pooling Data Structure for Loop Closure." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/fei2016eccv-simple/) doi:10.1007/978-3-319-46487-9_20

BibTeX

@inproceedings{fei2016eccv-simple,
  title     = {{A Simple Hierarchical Pooling Data Structure for Loop Closure}},
  author    = {Fei, Xiaohan and Tsotsos, Konstantine and Soatto, Stefano},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {321-337},
  doi       = {10.1007/978-3-319-46487-9_20},
  url       = {https://mlanthology.org/eccv/2016/fei2016eccv-simple/}
}