Incremental PCA: an alternative approach for novelty detection

Exploration and inspection of dynamic environments using mobile robots are applications that benefit immensely from novelty detection algorithms. In this paper we propose the use of a new approach for on-line novelty detection based on incremental Principal Component Analysis and compare its perform...

ver descrição completa

Principais autores: Nehmzow, Ulrich, Vieira Neto, Hugo
Formato: Trabalho Apresentado em Evento
Idioma: Inglês
Publicado em: Curitiba 2013
Assuntos:
Acesso em linha: http://repositorio.utfpr.edu.br/jspui/handle/1/661
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
id riut-1-661
recordtype dspace
spelling riut-1-6612015-03-07T06:12:31Z Incremental PCA: an alternative approach for novelty detection Nehmzow, Ulrich Vieira Neto, Hugo Robôs móveis Visão por computador Análise de componentes principais Mobile robots Computer vision Principal components analysis Exploration and inspection of dynamic environments using mobile robots are applications that benefit immensely from novelty detection algorithms. In this paper we propose the use of a new approach for on-line novelty detection based on incremental Principal Component Analysis and compare its performance and functionality with a previously studied technique based on a GWR neural network. We have conducted a series of experiments using visual input from a mobile robot interacting with a controlled laboratory environment that show advantages and disadvantages for each method. 5000 2013-11-21T23:28:36Z 2005 conferenceObject VIEIRA NETO, Hugo; NEHMZOW, Ulrich. Incremental PCA: an alternative approach for novelty detection. In: TOWARDS AUTONOMOUS ROBOTIC SYSTEMS, 10., 2005, Londres. Anais eletrônicos… Londres, 2005. Disponível em: <http://www.iis.ee.ic.ac.uk/~taros05/papers/vieira.pdf>. Acesso em: 16 jul. 2013. 0-905247-03-5 http://repositorio.utfpr.edu.br/jspui/handle/1/661 eng Towards Autonomous Robotic Systems http://www.iis.ee.ic.ac.uk/~taros05/papers/vieira.pdf application/pdf Curitiba
institution Universidade Tecnológica Federal do Paraná
collection RIUT
language Inglês
topic Robôs móveis
Visão por computador
Análise de componentes principais
Mobile robots
Computer vision
Principal components analysis
spellingShingle Robôs móveis
Visão por computador
Análise de componentes principais
Mobile robots
Computer vision
Principal components analysis
Nehmzow, Ulrich
Vieira Neto, Hugo
Incremental PCA: an alternative approach for novelty detection
description Exploration and inspection of dynamic environments using mobile robots are applications that benefit immensely from novelty detection algorithms. In this paper we propose the use of a new approach for on-line novelty detection based on incremental Principal Component Analysis and compare its performance and functionality with a previously studied technique based on a GWR neural network. We have conducted a series of experiments using visual input from a mobile robot interacting with a controlled laboratory environment that show advantages and disadvantages for each method.
format Trabalho Apresentado em Evento
author Nehmzow, Ulrich
Vieira Neto, Hugo
author_sort Nehmzow, Ulrich
title Incremental PCA: an alternative approach for novelty detection
title_short Incremental PCA: an alternative approach for novelty detection
title_full Incremental PCA: an alternative approach for novelty detection
title_fullStr Incremental PCA: an alternative approach for novelty detection
title_full_unstemmed Incremental PCA: an alternative approach for novelty detection
title_sort incremental pca: an alternative approach for novelty detection
publisher Curitiba
publishDate 2013
citation VIEIRA NETO, Hugo; NEHMZOW, Ulrich. Incremental PCA: an alternative approach for novelty detection. In: TOWARDS AUTONOMOUS ROBOTIC SYSTEMS, 10., 2005, Londres. Anais eletrônicos… Londres, 2005. Disponível em: <http://www.iis.ee.ic.ac.uk/~taros05/papers/vieira.pdf>. Acesso em: 16 jul. 2013.
0-905247-03-5
url http://repositorio.utfpr.edu.br/jspui/handle/1/661
_version_ 1805315536235528192
score 10,814766