Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free

  • Suenderhauf N
  • Shirazi S
  • Jacobson A
 et al. 
  • 135

    Readers

    Mendeley users who have this article in their library.
  • 40

    Citations

    Citations of this article.

Abstract

Place recognition has long been an incompletely solved problem in that all approaches involve significant com- promises. Current methods address many but never all of the critical challenges of place recognition – viewpoint-invariance, condition-invariance and minimizing training requirements. Here we present an approach that adapts state-of-the-art object proposal techniques to identify potential landmarks within an image for place recognition. We use the astonishing power of convolutional neural network features to identify matching landmark proposals between images to perform place recognition over extreme appearance and viewpoint variations. Our system does not require any form of training, all components are generic enough to be used off-the-shelf.We present a range of challenging experiments in varied viewpoint and environmental conditions. We demonstrate superior performance to current state-of-the- art techniques. Furthermore, by building on existing and widely used recognition frameworks, this approach provides a highly compatible place recognition system with the potential for easy integration of other techniques such as object detection and semantic scene interpretation.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text

Authors

  • Niko Suenderhauf

  • Sareh Shirazi

  • Adam Jacobson

  • Feras Dayoub

  • Edward Pepperell

  • Ben Upcroft

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free