KLN: a deep neural network architecture for keypoint localization
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA21024FM" target="_blank" >RIV/61988987:17610/20:A21024FM - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/9204211" target="_blank" >https://ieeexplore.ieee.org/document/9204211</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/DSMP47368.2020.9204211" target="_blank" >10.1109/DSMP47368.2020.9204211</a>
Alternative languages
Result language
angličtina
Original language name
KLN: a deep neural network architecture for keypoint localization
Original language description
Pixel-precision level localization of keypoints is an essential step for stitching panoramic images as these keypoints are matching, and their locations are used for computing stitching transformation. We recall the main standard computer vision techniques for keypoint localization and focus on the precise localization. Based on the SIFT technique, we design a neural network architecture containing an encoder, a latent representation handler, and a decoder. In contrast to domain-agnostic neural network architectures, the developed encoder reflects the scale-space construction as well as the difference of Gaussians estimation used in SIFT. In the benchmark, we show that our architecture has a higher number of keypoints localized with pixel precision considering flips, intensity changes, and blurrings than other standard and neural network-based approaches.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10102 - Applied mathematics
Result continuities
Project
<a href="/en/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centre for the development of Artificial Intelligence Methods for the Automotive Industry of the region</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of IEEE Third International Conference Data Stream Mining & Processing 2020
ISBN
978-1-7281-3215-0
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
—
Publisher name
IEEE
Place of publication
Lvov, Ukraina
Event location
Lvov, Ukraina
Event date
Aug 21, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—