Toward Object based Place Recognition in Dense RGB-D Maps

Abstract

Longterm localization and mapping requires the ability to detect when places are being revisited to "close loops" and mitigate odometry drift. The appearance-based approaches solve this problem by using visual descriptors to associate camera imagery. This method has proven remarkably successful, yet performance will always degrade with drastic changes in viewpoint or illumination. In this paper, we propose to leverage the recent results in dense RGB-D mapping to perform place recognition in the space of objects. We detect objects from the dense 3-D data using a novel feature descriptor generated using primitive kernels. These objects are then connected in a sparse graph which can be quickly searched for place matches. The developed algorithm allows for multi-floor or multi-session building-scale dense mapping and is invariant to viewpoint and illumination. We validate the approach on a number of real datasets collected with a handheld RGB-D camera.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2015
Accession Number
AD1137014

Entities

People

  • John J. Leonard
  • Liam Paull
  • Ross Finman

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Cartography
  • Change Detection
  • Computer Vision
  • Coordinate Systems
  • Data Sets
  • Detection
  • Detectors
  • Image Processing
  • Maps
  • Object Recognition
  • Pattern Recognition
  • Point Clouds
  • Recognition
  • Robotics
  • Simultaneous Localization And Mapping
  • Three Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Systems Analysis and Design

Technology Areas

  • Space
  • Space - Space Objects