Highly Robust Visual Place Recognition Through Spatial Matching of CNN Features

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F20%3A00348828" target="_blank" >RIV/68407700:21730/20:00348828 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICRA40945.2020.9196967" target="_blank" >https://doi.org/10.1109/ICRA40945.2020.9196967</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICRA40945.2020.9196967" target="_blank" >10.1109/ICRA40945.2020.9196967</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Highly Robust Visual Place Recognition Through Spatial Matching of CNN Features

Popis výsledku v původním jazyce

We revise, improve and extend the system previously introduced by us and named SSM-VPR (Semantic and Spatial Matching Visual Place Recognition), largely boosting its performance above the current state of the art. The system encodes images of places by employing the activations of different layers of a pre-trained, off-the-shelf, VGG16 Convolutional Neural Network (CNN) architecture. It consists of two stages: given a query image of a place, (1) a list of candidates is selected from a database of places and (2) the candidates are geometrically compared with the query. The comparison is made by matching CNN features and, equally important, their spatial locations, selecting the best candidate as the recognized place. The performance of the system is maximized by finding optimal image resolutions during the second stage and by exploiting temporal correlation between consecutive frames in the employed datasets.

Název v anglickém jazyce

Highly Robust Visual Place Recognition Through Spatial Matching of CNN Features

Popis výsledku anglicky

We revise, improve and extend the system previously introduced by us and named SSM-VPR (Semantic and Spatial Matching Visual Place Recognition), largely boosting its performance above the current state of the art. The system encodes images of places by employing the activations of different layers of a pre-trained, off-the-shelf, VGG16 Convolutional Neural Network (CNN) architecture. It consists of two stages: given a query image of a place, (1) a list of candidates is selected from a database of places and (2) the candidates are geometrically compared with the query. The comparison is made by matching CNN features and, equally important, their spatial locations, selecting the best candidate as the recognized place. The performance of the system is maximized by finding optimal image resolutions during the second stage and by exploiting temporal correlation between consecutive frames in the employed datasets.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

<a href="/cs/project/EF15_003%2F0000470" target="_blank" >EF15_003/0000470: Robotika pro Průmysl 4.0</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

IEEE International Conference on Robotics and Automation (ICRA)

ISBN

978-1-7281-7395-5

ISSN

1050-4729

e-ISSN

2577-087X

Počet stran výsledku

8

Strana od-do

3748-3755

Název nakladatele

IEEE Xplore

Místo vydání

—

Místo konání akce

Paris

Datum konání akce

31. 5. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000712319502086