Towards fast image-based localization on a city-scale

  • Authors:

  • Torsten Sattler;Bastian Leibe;Leif Kobbelt

  • Affiliations:

  • RWTH Aachen University, Aachen, Germany;UMIC Research Centre, RWTH Aachen University, Aachen, Germany;RWTH Aachen University, Aachen, Germany

  • Venue:
  • Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent developments in Structure-from-Motion approaches allow the reconstructions of large parts of urban scenes. The available models can in turn be used for accurate image-based localization via pose estimation from 2D-to-3D correspondences. In this paper, we analyze a recently proposed localization method that achieves state-of-the-art localization performance using a visual vocabulary quantization for efficient 2D-to-3D correspondence search. We show that using only a subset of the original models allows the method to achieve a similar localization performance. While this gain can come at additional computational cost depending on the dataset, the reduced model requires significantly less memory, allowing the method to handle even larger datasets. We study how the size of the subset, as well as the quantization, affect both the search for matches and the time needed by RANSAC for pose estimation.