A Simple Hierarchical Pooling Data Structure for Loop Closure

Abstract

We propose a data structure obtained by hierarchically pool-ing Bag-of-Words (BoW) descriptors during a sequence of views that achieves average speedups in large-scale loop closure applications rang-ing 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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 16, 2016
Accession Number
AD1024359

Entities

People

  • Konstantine Tsotsos
  • Stefano Soatto
  • Xiaohan Fei

Organizations

  • University of California

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Autonomous Navigation
  • Computational Science
  • Computer Vision
  • Computers
  • Detection
  • False Alarms
  • Machine Learning
  • Navigation
  • Neural Networks
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Robotics
  • Simultaneous Localization And Mapping
  • Topology
  • Urban Areas
  • Warning Systems

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.