Hessian Interest Points on GPU
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00300862" target="_blank" >RIV/68407700:21230/16:00300862 - isvavai.cz</a>
Result on the web
<a href="http://vision.fe.uni-lj.si/cvww2016/proceedings/papers/08.pdf" target="_blank" >http://vision.fe.uni-lj.si/cvww2016/proceedings/papers/08.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Hessian Interest Points on GPU
Original language description
This paper is about interest point detection and GPU programming. We take a popular GPGPU implementation of SIFT - the de-facto standard in fast interest point detectors - SiftGPU and implement modifications that according to recent research result in better performance in terms of repeatability of the detected points. The interest points found at local extrema of the Difference of Gaussians (DoG) function in the original SIFT are replaced by the local extrema of determinant of Hessian matrix of the intensity function. Experimentally we show that the GPU implementation of Hessian-based detector (i) surpasses in repeatability the original DoG-based implementation, (ii) gives result very close to those of a reference CPU implementation, and (iii) is significantly faster than the CPU implementation. We show what speedup is achieved for different image sizes and provide analysis of computational cost of individual steps of the algorithm. The source code is publicly available.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
—
Continuities
N - Vyzkumna aktivita podporovana z neverejnych zdroju
Others
Publication year
2016
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 the 21st Computer Vision Winter Workshop
ISBN
978-961-90901-7-6
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
—
Publisher name
Slovenian Pattern Recognition Society
Place of publication
Ljubljana
Event location
Rimske Toplice
Event date
Feb 3, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—