2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) 2015
DOI: 10.1109/aipr.2015.7444530
|View full text |Cite
|
Sign up to set email alerts
|

Bandelet transformation based image registration

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
1
0
3

Year Published

2016
2016
2020
2020

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 36 publications
0
1
0
3
Order By: Relevance
“…One possible solution is by utilizing image fusion techniques to consolidate images of the same scene but captured from different focus, sensors, or modalities to diminish the resource requirements to deploy the network. By fusing images into a single stream of data to test a neural network model, images that have been captured from various angles, or with multimodal or multi-spectral sensors can be analyzed simultaneously rather than being considered separately [4,5,6,7]. Multisensory applications were first created as a subset of remote sensing and have been developed as a subset of data fusion.…”
Section: Introductionmentioning
confidence: 99%
“…One possible solution is by utilizing image fusion techniques to consolidate images of the same scene but captured from different focus, sensors, or modalities to diminish the resource requirements to deploy the network. By fusing images into a single stream of data to test a neural network model, images that have been captured from various angles, or with multimodal or multi-spectral sensors can be analyzed simultaneously rather than being considered separately [4,5,6,7]. Multisensory applications were first created as a subset of remote sensing and have been developed as a subset of data fusion.…”
Section: Introductionmentioning
confidence: 99%
“…Existem diversas aplicações em sistemas de visão computacional cuja solução representa um desafio. A determinação dos pares de pixels correspondentes, ou de regiões correspondentes, é uma delas (BAUMBERG, 2000;MARSHALL;DOUCETTE, 2011;LUTZ et al, 2015). Esta correspondência de imagens, também denominada registro de imagens, tem vasta aplicação em sistemas de reconstrução de informação tridimensional de uma cena, robótica móvel, rastreamento de objetos, sensoriamento remoto, inspeção industrial e controle de qualidade, biometria facial, vigilância e segurança, dentre outras (LUTZ et al, 2015;LUMINI, 2013;MARSHALL;DOUCETTE, 2011;MA;CANTERS, 2010;HOSSAIN et al, 2010;HUANG et al, 2008).…”
Section: Motivaçãounclassified
“…As imagens a serem analisadas podem ter sido capturadas em diferentes instantes de tempo, de diferentes pontos de vista e/ou por diferentes câmeras (LUTZ et al, 2015;HUANG et al, 2008), sendo assim, podem apresentar diversas transformações, como rotação, variação de iluminação, compressão, mudança de ponto de vista, e outras, sendo necessário que os descritores de características sejam invariantes a tais transformações. Dificilmente, um único descritor de características será suficientemente robusto a uma grande quantidade de transformações.…”
Section: Motivaçãounclassified
See 1 more Smart Citation