English

A Simple Hierarchical Pooling Data Structure for Loop Closure

Computer Vision and Pattern Recognition 2018-10-25 v2 Robotics

Abstract

We propose a data structure obtained by hierarchically averaging bag-of-word descriptors during a sequence of views that achieves average speedups in large-scale loop closure applications ranging from 4 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

@article{arxiv.1511.06489,
  title  = {A Simple Hierarchical Pooling Data Structure for Loop Closure},
  author = {Xiaohan Fei and Konstantine Tsotsos and Stefano Soatto},
  journal= {arXiv preprint arXiv:1511.06489},
  year   = {2018}
}
R2 v1 2026-06-22T11:50:10.521Z