Performance analysis of sliding window filtering of two dimensional signals based on stream data processing systems

Nikolay Kazanskiy; Vladimir Protsenko; Pavel Serafimovich

doi:10.1117/12.2231384

26 March 2016 Performance analysis of sliding window filtering of two dimensional signals based on stream data processing systems

Nikolay Kazanskiy, Vladimir Protsenko, Pavel Serafimovich

Author Affiliations +

Proceedings Volume 9807, Optical Technologies for Telecommunications 2015; 98070Z (2016) https://doi.org/10.1117/12.2231384
Event: XIII International Scientific and Technical Conference on Optical Technologies in Telecommunications, 2015, Ufa, Russian Federation

Abstract

This research article contains an experiment with implementation of image filtering task in Apache Storm and IBM InfoSphere Streams stream data processing systems. The aim of presented research is to show that new technologies could be effectively used for sliding window filtering of image sequences. The analysis of execution was focused on two parameters: throughput and memory consumption. Profiling was performed on CentOS operating systems running on two virtual machines for each system. The experiment results showed that IBM InfoSphere Streams has about 1.5 to 13.5 times lower memory footprint than Apache Storm, but could be about 2.0 to 2.5 slower on a real hardware.

Citation Download Citation

Nikolay Kazanskiy, Vladimir Protsenko, and Pavel Serafimovich "Performance analysis of sliding window filtering of two dimensional signals based on stream data processing systems", Proc. SPIE 9807, Optical Technologies for Telecommunications 2015, 98070Z (26 March 2016); https://doi.org/10.1117/12.2231384

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available