Visual Place Recognition with Repetitive Structures

Akihiko Torii 1 Josef Sivic 2, 3 Tomas Pajdla 4 Masatoshi Okutomi 1
2 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. Even more importantly, they violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they form an important distinguishing feature for many places. We describe a representation of repeated structures suitable for scalable retrieval. It is based on robust detection of repeated image structures and a simple modification of weights in the bag-of-visual-word model. Place recognition results are shown on datasets of street-level imagery from Pittsburgh and San Francisco demonstrating significant gains in recognition performance compared to the standard bag-of-visual-words baseline and more recently proposed burstiness weighting.
Document type :
Conference papers
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.inria.fr/hal-00934288
Contributor : Josef Sivic <>
Submitted on : Tuesday, January 21, 2014 - 5:29:49 PM
Last modification on : Thursday, February 7, 2019 - 3:49:48 PM
Long-term archiving on : Tuesday, April 22, 2014 - 10:01:55 AM

File

torii13.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00934288, version 1

Collections

Citation

Akihiko Torii, Josef Sivic, Tomas Pajdla, Masatoshi Okutomi. Visual Place Recognition with Repetitive Structures. CVPR 2013 - 26th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. ⟨hal-00934288⟩

Share

Metrics

Record views

3208

Files downloads

569