Improving Image Pair Selection for Large Scale Structure from Motion by Introducing Modified Simpson Coefficient

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F22%3A00364315" target="_blank" >RIV/68407700:21730/22:00364315 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1587/transinf.2021EDP7244" target="_blank" >https://doi.org/10.1587/transinf.2021EDP7244</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1587/transinf.2021EDP7244" target="_blank" >10.1587/transinf.2021EDP7244</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving Image Pair Selection for Large Scale Structure from Motion by Introducing Modified Simpson Coefficient

Popis výsledku v původním jazyce

Selecting visually overlapping image pairs without any prior information is an essential task of large-scale structure from motion (SfM) pipelines. To address this problem, many state-of-the-art image re trieval systems adopt the idea of bag of visual words (BoVW) for com puting image-pair similarity. In this paper, we present a method for im proving the image pair selection using BoVW. Our method combines a conventional vector-based approach and a set-based approach. For the set similarity, we introduce a modified version of the Simpson (m-Simpson) coefficient. We show the advantage of this measure over three typical set similarity measures and demonstrate that the combination of vector similar ity and the m-Simpson coefficient effectively reduces false positives and in creases accuracy. To discuss the choice of vocabulary construction, we pre pared both a sampled vocabulary on an evaluation dataset and a basic pre trained vocabulary on a training dataset. In addition, we tested our method on vocabularies of different sizes. Our experimental results show that the proposed method dramatically improves precision scores especially on the sampled vocabulary and performs better than the state-of-the-art methods that use pre-trained vocabularies. We further introduce a method to deter mine the k value of top-k relevant searches for each image and show that it obtains higher precision at the same recall.

Název v anglickém jazyce

Improving Image Pair Selection for Large Scale Structure from Motion by Introducing Modified Simpson Coefficient

Popis výsledku anglicky

Selecting visually overlapping image pairs without any prior information is an essential task of large-scale structure from motion (SfM) pipelines. To address this problem, many state-of-the-art image re trieval systems adopt the idea of bag of visual words (BoVW) for com puting image-pair similarity. In this paper, we present a method for im proving the image pair selection using BoVW. Our method combines a conventional vector-based approach and a set-based approach. For the set similarity, we introduce a modified version of the Simpson (m-Simpson) coefficient. We show the advantage of this measure over three typical set similarity measures and demonstrate that the combination of vector similar ity and the m-Simpson coefficient effectively reduces false positives and in creases accuracy. To discuss the choice of vocabulary construction, we pre pared both a sampled vocabulary on an evaluation dataset and a basic pre trained vocabulary on a training dataset. In addition, we tested our method on vocabularies of different sizes. Our experimental results show that the proposed method dramatically improves precision scores especially on the sampled vocabulary and performs better than the state-of-the-art methods that use pre-trained vocabularies. We further introduce a method to deter mine the k value of top-k relevant searches for each image and show that it obtains higher precision at the same recall.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Inteligentní strojové vnímání</a><br>

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název periodika

IEICE Transactions on Information and Systems

ISSN

0916-8532

e-ISSN

1745-1361

Svazek periodika

E105

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

JP - Japonsko

Počet stran výsledku

10

Strana od-do

1590-1599

Kód UT WoS článku

000852731400009

EID výsledku v databázi Scopus

2-s2.0-85138462029