Saddle: Fast and repeatable features with good coverage
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00334662" target="_blank" >RIV/68407700:21230/20:00334662 - isvavai.cz</a>
Výsledek na webu
<a href="https://doi.org/10.1016/j.imavis.2019.08.011" target="_blank" >https://doi.org/10.1016/j.imavis.2019.08.011</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.imavis.2019.08.011" target="_blank" >10.1016/j.imavis.2019.08.011</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Saddle: Fast and repeatable features with good coverage
Popis výsledku v původním jazyce
A novel similarity-covariant feature detector that extracts points whose neighborhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile is presented. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Saddle is a fast approximation of Hessian detector as ORB, that implements the FAST detector, is for Harris detector. We propose to use the matching strategy called the first geometric inconsistent with binary descriptors that is suitable for our feature detector, including experiments with fix point descriptors hand-crafted and learned. Experiments show that the Saddle features are general, evenly spread and appearing in high density in a range of images. The Saddle detector is among the fastest proposed. In comparison with detector with similar speed, the Saddle features show superior matching performance on number of challenging datasets. Compared to recently proposed deep-learning based interest point detectors and popular hand-crafted keypoint detectors, evaluated for repeatability in the ApolloScape dataset [1], the Saddle detectors shows the best performance in most of the street-level view sequences a.k.a. traversals.
Název v anglickém jazyce
Saddle: Fast and repeatable features with good coverage
Popis výsledku anglicky
A novel similarity-covariant feature detector that extracts points whose neighborhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile is presented. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Saddle is a fast approximation of Hessian detector as ORB, that implements the FAST detector, is for Harris detector. We propose to use the matching strategy called the first geometric inconsistent with binary descriptors that is suitable for our feature detector, including experiments with fix point descriptors hand-crafted and learned. Experiments show that the Saddle features are general, evenly spread and appearing in high density in a range of images. The Saddle detector is among the fastest proposed. In comparison with detector with similar speed, the Saddle features show superior matching performance on number of challenging datasets. Compared to recently proposed deep-learning based interest point detectors and popular hand-crafted keypoint detectors, evaluated for repeatability in the ApolloScape dataset [1], the Saddle detectors shows the best performance in most of the street-level view sequences a.k.a. traversals.
Klasifikace
Druh
J<sub>imp</sub> - 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)
Návaznosti výsledku
Projekt
Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2020
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Image and Vision Computing
ISSN
0262-8856
e-ISSN
1872-8138
Svazek periodika
97
Číslo periodika v rámci svazku
May
Stát vydavatele periodika
GB - Spojené království Velké Británie a Severního Irska
Počet stran výsledku
17
Strana od-do
—
Kód UT WoS článku
000535899900001
EID výsledku v databázi Scopus
2-s2.0-85079534086