Efficient Large-Scale Semantic Visual Localization in 2D Maps

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00349961" target="_blank" >RIV/68407700:21230/21:00349961 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-69535-4_17" target="_blank" >https://doi.org/10.1007/978-3-030-69535-4_17</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-69535-4_17" target="_blank" >10.1007/978-3-030-69535-4_17</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Large-Scale Semantic Visual Localization in 2D Maps

Popis výsledku v původním jazyce

With the emergence of autonomous navigation systems, image-based localization is one of the essential tasks to be tackled. However, most of the current algorithms struggle to scale to city-size environments mainly because of the need to collect large (semi-)annotated datasets for CNN training and create databases for test environment of images, key-point level features or image embeddings. This data acquisition is not only expensive and time-consuming but also may cause privacy concerns. In this work, we propose a novel framework for semantic visual localization in city-scale environments which alleviates the aforementioned problem by using freely available 2D maps such as OpenStreetMap. Our method does not require any images or image-map pairs for training or test environment database collection. Instead, a robust embedding is learned from a depth and building instance label information of a particular location in the 2D map. At test time, this embedding is extracted from a panoramic building instance label and depth images. It is then used to retrieve the closest match in the database. We evaluate our localization framework on two large-scale datasets consisting of Cambridge and San Francisco cities with a total length of drivable roads spanning 500 km and including approximately 110k unique locations. To the best of our knowledge, this is the first large-scale semantic localization method which works on par with approaches that require the availability of images at train time or for test environment database creation.

Název v anglickém jazyce

Efficient Large-Scale Semantic Visual Localization in 2D Maps

Popis výsledku anglicky

With the emergence of autonomous navigation systems, image-based localization is one of the essential tasks to be tackled. However, most of the current algorithms struggle to scale to city-size environments mainly because of the need to collect large (semi-)annotated datasets for CNN training and create databases for test environment of images, key-point level features or image embeddings. This data acquisition is not only expensive and time-consuming but also may cause privacy concerns. In this work, we propose a novel framework for semantic visual localization in city-scale environments which alleviates the aforementioned problem by using freely available 2D maps such as OpenStreetMap. Our method does not require any images or image-map pairs for training or test environment database collection. Instead, a robust embedding is learned from a depth and building instance label information of a particular location in the 2D map. At test time, this embedding is extracted from a panoramic building instance label and depth images. It is then used to retrieve the closest match in the database. We evaluate our localization framework on two large-scale datasets consisting of Cambridge and San Francisco cities with a total length of drivable roads spanning 500 km and including approximately 110k unique locations. To the best of our knowledge, this is the first large-scale semantic localization method which works on par with approaches that require the availability of images at train time or for test environment database creation.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ACCV2020: Proceedings of the 15th Asian Conference on Computer Vision - Part III

ISBN

978-3-030-69534-7

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

16

Strana od-do

273-288

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Kyoto

Datum konání akce

30. 11. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—