Video sequence learning and recognition via dynamic SOM

Qiong Liu, Yong Rui, Thomas S Huang, Stephen E Levinson

Research output: Contribution to conferencePaper

Abstract

Information contained in the video sequences is crucial for an autonomous robot or a computer to learn and respond to its surrounding environment. In the past, robot vision is mainly concentrated on still image processing and small `image cube' processing. Continuous video sequence learning and recognition is rarely addressed in the literature due to its high requirement on dynamic processing. In this paper, we propose a novel neural network structure called Dynamic Self-Organizing Map (DSOM) for video sequence processing. The proposed technique has been tested on simulation data sets, and the results validate its learning/recognition ability.

Original languageEnglish (US)
Pages93-97
Number of pages5
StatePublished - Dec 1 1999
EventInternational Conference on Image Processing (ICIP'99) - Kobe, Jpn
Duration: Oct 24 1999Oct 28 1999

Other

OtherInternational Conference on Image Processing (ICIP'99)
CityKobe, Jpn
Period10/24/9910/28/99

Fingerprint

Image processing
Self organizing maps
Processing
Computer vision
Robots
Neural networks

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Liu, Q., Rui, Y., Huang, T. S., & Levinson, S. E. (1999). Video sequence learning and recognition via dynamic SOM. 93-97. Paper presented at International Conference on Image Processing (ICIP'99), Kobe, Jpn, .

Video sequence learning and recognition via dynamic SOM. / Liu, Qiong; Rui, Yong; Huang, Thomas S; Levinson, Stephen E.

1999. 93-97 Paper presented at International Conference on Image Processing (ICIP'99), Kobe, Jpn, .

Research output: Contribution to conferencePaper

Liu, Q, Rui, Y, Huang, TS & Levinson, SE 1999, 'Video sequence learning and recognition via dynamic SOM' Paper presented at International Conference on Image Processing (ICIP'99), Kobe, Jpn, 10/24/99 - 10/28/99, pp. 93-97.
Liu Q, Rui Y, Huang TS, Levinson SE. Video sequence learning and recognition via dynamic SOM. 1999. Paper presented at International Conference on Image Processing (ICIP'99), Kobe, Jpn, .
Liu, Qiong ; Rui, Yong ; Huang, Thomas S ; Levinson, Stephen E. / Video sequence learning and recognition via dynamic SOM. Paper presented at International Conference on Image Processing (ICIP'99), Kobe, Jpn, .5 p.
@conference{f596e4296dc6448d9bd82819be512d7a,
title = "Video sequence learning and recognition via dynamic SOM",
abstract = "Information contained in the video sequences is crucial for an autonomous robot or a computer to learn and respond to its surrounding environment. In the past, robot vision is mainly concentrated on still image processing and small `image cube' processing. Continuous video sequence learning and recognition is rarely addressed in the literature due to its high requirement on dynamic processing. In this paper, we propose a novel neural network structure called Dynamic Self-Organizing Map (DSOM) for video sequence processing. The proposed technique has been tested on simulation data sets, and the results validate its learning/recognition ability.",
author = "Qiong Liu and Yong Rui and Huang, {Thomas S} and Levinson, {Stephen E}",
year = "1999",
month = "12",
day = "1",
language = "English (US)",
pages = "93--97",
note = "International Conference on Image Processing (ICIP'99) ; Conference date: 24-10-1999 Through 28-10-1999",

}

TY - CONF

T1 - Video sequence learning and recognition via dynamic SOM

AU - Liu, Qiong

AU - Rui, Yong

AU - Huang, Thomas S

AU - Levinson, Stephen E

PY - 1999/12/1

Y1 - 1999/12/1

N2 - Information contained in the video sequences is crucial for an autonomous robot or a computer to learn and respond to its surrounding environment. In the past, robot vision is mainly concentrated on still image processing and small `image cube' processing. Continuous video sequence learning and recognition is rarely addressed in the literature due to its high requirement on dynamic processing. In this paper, we propose a novel neural network structure called Dynamic Self-Organizing Map (DSOM) for video sequence processing. The proposed technique has been tested on simulation data sets, and the results validate its learning/recognition ability.

AB - Information contained in the video sequences is crucial for an autonomous robot or a computer to learn and respond to its surrounding environment. In the past, robot vision is mainly concentrated on still image processing and small `image cube' processing. Continuous video sequence learning and recognition is rarely addressed in the literature due to its high requirement on dynamic processing. In this paper, we propose a novel neural network structure called Dynamic Self-Organizing Map (DSOM) for video sequence processing. The proposed technique has been tested on simulation data sets, and the results validate its learning/recognition ability.

UR - http://www.scopus.com/inward/record.url?scp=0033352906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033352906&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0033352906

SP - 93

EP - 97

ER -