Frameless computing for spatial-temporal events

Miklós Koller, András Horváth, Tamás Roska

Research output: Conference contribution

Abstract

The detection of spatial-temporal events is a difficult task in machine vision and it is usually difficult to be handled efficiently with current algorithms and devices. There are many examples in nature, like looming detection or detection of moving objects with given speed and trajectory, which shows that human vision system can solve this extremely difficult task with extremely low power consumption. In this article we show examples how cellular neural networks can be used to detect spatial-temporal events. The detections are done by using continuous dynamics without cutting the input flow into frames. We can observe similar structures and functions (the detection of continuous input-flows with continuous dynamics) in the retina, which performs well and efficiently in image processing tasks.

Original languageEnglish
Title of host publication2013 European Conference on Circuit Theory and Design, ECCTD 2013 - Proceedings
PublisherIEEE Computer Society
ISBN (Print)9783000437854
DOIs
Publication statusPublished - 2013
Event2013 European Conference on Circuit Theory and Design, ECCTD 2013 - Dresden, Germany
Duration: szept. 8 2013szept. 12 2013

Publication series

Name2013 European Conference on Circuit Theory and Design, ECCTD 2013 - Proceedings

Other

Other2013 European Conference on Circuit Theory and Design, ECCTD 2013
CountryGermany
CityDresden
Period9/8/139/12/13

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Frameless computing for spatial-temporal events'. Together they form a unique fingerprint.

  • Cite this

    Koller, M., Horváth, A., & Roska, T. (2013). Frameless computing for spatial-temporal events. In 2013 European Conference on Circuit Theory and Design, ECCTD 2013 - Proceedings [6662262] (2013 European Conference on Circuit Theory and Design, ECCTD 2013 - Proceedings). IEEE Computer Society. https://doi.org/10.1109/ecctd.2013.6662262