Visual Localization

Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00200592" target="_blank" >RIV/68407700:21230/12:00200592 - isvavai.cz</a>
Výsledek na webu
—
DOI - Digital Object Identifier
—

Jazyk výsledku
angličtina
Název v původním jazyce
Visual Localization
Popis výsledku v původním jazyce
The goal of visual-based localization is to retrieve images from a large geotagged image database depicting the same place as a given query photograph. In this report we present system for building a geotagged dataset for place recognition utilizing publically available data from Google Streetview. Second part of this report investigates whether suppressing malicious features in the database images can be cast as learning local per-image distance functions. We demonstrate that finding such local distance functions can be formulated as a linear program and perform initial experiments on a database of 17k street view images of Paris.
Název v anglickém jazyce
Visual Localization
Popis výsledku anglicky
The goal of visual-based localization is to retrieve images from a large geotagged image database depicting the same place as a given query photograph. In this report we present system for building a geotagged dataset for place recognition utilizing publically available data from Google Streetview. Second part of this report investigates whether suppressing malicious features in the database images can be cast as learning local per-image distance functions. We demonstrate that finding such local distance functions can be formulated as a linear program and perform initial experiments on a database of 17k street view images of Paris.

Rok uplatnění
2012
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Podobné výsledky(10)