Skip to content

Automated Map Reading: Image Based Localisation in 2-D Maps Using Binary Semantic Descriptors

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)
Subtitle of host publicationProceedings of a meeting held 1-5 October 2018, Madrid, Spain
Publisher or commissioning bodyInstitute of Electrical and Electronics Engineers (IEEE)
Pages6341-6348
Number of pages8
ISBN (Electronic)9781538680940
ISBN (Print)9781538680933
DOIs
DateAccepted/In press - 29 Jun 2018
DateE-pub ahead of print - 7 Jan 2019
DatePublished (current) - Mar 2019

Publication series

Name
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Abstract

We describe a novel approach to image based lo- calisation in urban environments which uses semantic matching between images and a 2-D cartographic map. This contrasts with the majority of existing approaches which use image to image database matching. We use highly compact binary descriptors to represent locations, indicating the presence or not of semantic features, which significantly increases scalability and has the potential for greater invariance to variable imaging conditions. The approach is also more akin to human map reading, making it better suited to human-system interaction. In this initial study we use semantic features relating to buildings and road junctions in discrete viewing directions. CNN classi- fiers are used to detect the features in images and we match descriptor estimates with location tagged descriptors derived from the 2-D map to give localisation. The descriptors are not sufficiently discriminative on their own, but when concatenated sequentially along a route, their combination becomes highly distinctive and allows localisation even when using non-perfect classifiers. Performance is further improved by taking into account left or right turns over a route. Experimental results obtained using Google StreetView and OpenStreetMap data show that the approach has considerable potential, achieving localisation accuracy of around 85% using routes corresponding to approximately 200 meters.

    Research areas

  • Localisation, place recognition, computer vision, robotics

Download statistics

No data available

Documents

Documents

  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/8594253 . Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 3 MB, PDF-document

DOI

View research connections

Related faculties, schools or groups