Egomotion estimation and the detection of moving objects with delayed-type CNN templates

Andras Horvath, T. Roska

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Spatial-temporal event detections are crucial tasks in machine-vision and they are usually difficult to be handled efficiently with current algorithms and devices. In this article we show how cellular neural networks with delayed type templates are capable of detecting certain spatial-temporal features and how these features can be used for simple egomotion estimation. The detection and estimation is done by using continuous dynamics without cutting the input flow into frames. We can observe similar structures-the analogy of delayed type templates-in the retina, which performs well and efficiently in image processing tasks. Delayed type templates can provide us with even more flexibilities and possibilities in new applications including frameless detection of motion features.

Original languageEnglish
Title of host publicationInternational Workshop on Cellular Nanoscale Networks and their Applications
PublisherIEEE Computer Society
ISBN (Print)9781479964680
DOIs
Publication statusPublished - Aug 29 2014
Event2014 14th International Workshop on Cellular Nanoscale Networks and Their Applications, CNNA 2014 - Notre Dame, United States
Duration: Jul 29 2014Jul 31 2014

Other

Other2014 14th International Workshop on Cellular Nanoscale Networks and Their Applications, CNNA 2014
CountryUnited States
CityNotre Dame
Period7/29/147/31/14

Fingerprint

Cellular neural networks
Computer vision
Image processing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Horvath, A., & Roska, T. (2014). Egomotion estimation and the detection of moving objects with delayed-type CNN templates. In International Workshop on Cellular Nanoscale Networks and their Applications [6888598] IEEE Computer Society. https://doi.org/10.1109/CNNA.2014.6888598

Egomotion estimation and the detection of moving objects with delayed-type CNN templates. / Horvath, Andras; Roska, T.

International Workshop on Cellular Nanoscale Networks and their Applications. IEEE Computer Society, 2014. 6888598.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Horvath, A & Roska, T 2014, Egomotion estimation and the detection of moving objects with delayed-type CNN templates. in International Workshop on Cellular Nanoscale Networks and their Applications., 6888598, IEEE Computer Society, 2014 14th International Workshop on Cellular Nanoscale Networks and Their Applications, CNNA 2014, Notre Dame, United States, 7/29/14. https://doi.org/10.1109/CNNA.2014.6888598
Horvath A, Roska T. Egomotion estimation and the detection of moving objects with delayed-type CNN templates. In International Workshop on Cellular Nanoscale Networks and their Applications. IEEE Computer Society. 2014. 6888598 https://doi.org/10.1109/CNNA.2014.6888598
Horvath, Andras ; Roska, T. / Egomotion estimation and the detection of moving objects with delayed-type CNN templates. International Workshop on Cellular Nanoscale Networks and their Applications. IEEE Computer Society, 2014.
@inproceedings{735aa9bbd7134fc1a8c7bdff01f212ae,
title = "Egomotion estimation and the detection of moving objects with delayed-type CNN templates",
abstract = "Spatial-temporal event detections are crucial tasks in machine-vision and they are usually difficult to be handled efficiently with current algorithms and devices. In this article we show how cellular neural networks with delayed type templates are capable of detecting certain spatial-temporal features and how these features can be used for simple egomotion estimation. The detection and estimation is done by using continuous dynamics without cutting the input flow into frames. We can observe similar structures-the analogy of delayed type templates-in the retina, which performs well and efficiently in image processing tasks. Delayed type templates can provide us with even more flexibilities and possibilities in new applications including frameless detection of motion features.",
author = "Andras Horvath and T. Roska",
year = "2014",
month = "8",
day = "29",
doi = "10.1109/CNNA.2014.6888598",
language = "English",
isbn = "9781479964680",
booktitle = "International Workshop on Cellular Nanoscale Networks and their Applications",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Egomotion estimation and the detection of moving objects with delayed-type CNN templates

AU - Horvath, Andras

AU - Roska, T.

PY - 2014/8/29

Y1 - 2014/8/29

N2 - Spatial-temporal event detections are crucial tasks in machine-vision and they are usually difficult to be handled efficiently with current algorithms and devices. In this article we show how cellular neural networks with delayed type templates are capable of detecting certain spatial-temporal features and how these features can be used for simple egomotion estimation. The detection and estimation is done by using continuous dynamics without cutting the input flow into frames. We can observe similar structures-the analogy of delayed type templates-in the retina, which performs well and efficiently in image processing tasks. Delayed type templates can provide us with even more flexibilities and possibilities in new applications including frameless detection of motion features.

AB - Spatial-temporal event detections are crucial tasks in machine-vision and they are usually difficult to be handled efficiently with current algorithms and devices. In this article we show how cellular neural networks with delayed type templates are capable of detecting certain spatial-temporal features and how these features can be used for simple egomotion estimation. The detection and estimation is done by using continuous dynamics without cutting the input flow into frames. We can observe similar structures-the analogy of delayed type templates-in the retina, which performs well and efficiently in image processing tasks. Delayed type templates can provide us with even more flexibilities and possibilities in new applications including frameless detection of motion features.

UR - http://www.scopus.com/inward/record.url?scp=84907734971&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907734971&partnerID=8YFLogxK

U2 - 10.1109/CNNA.2014.6888598

DO - 10.1109/CNNA.2014.6888598

M3 - Conference contribution

AN - SCOPUS:84907734971

SN - 9781479964680

BT - International Workshop on Cellular Nanoscale Networks and their Applications

PB - IEEE Computer Society

ER -