1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | mtc-m16c.sid.inpe.br |
Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Repository | sid.inpe.br/mtc-m18@80/2008/07.16.12.31 (restricted access) |
Last Update | 2008:07.16.12.33.23 (UTC) administrator |
Metadata Repository | sid.inpe.br/mtc-m18@80/2008/07.16.12.31.19 |
Metadata Last Update | 2021:02.03.17.56.35 (UTC) administrator |
Secondary Key | INPE--PRE/ |
Citation Key | GarciaArau:2008:ViMuTr |
Title | Visual Multi-Target Tracking by using Modified Kohonen Neural Networks/Rastreamento Visual de Multiplos Alvos pelo uso da Rede Neural Kohonen Modificada |
Year | 2008 |
Access Date | 2024, Apr. 28 |
Secondary Type | PRE CI |
Number of Files | 1 |
Size | 202 KiB |
|
2. Context | |
Author | 1 Garcia, F. 2 Araujo, José Ernesto de |
Group | 1 2 LIT-LIT-INPE-MCT-BR |
Affiliation | 1 2 Instituto Nacional de Pesquisas Espaciais (INPE) |
Conference Name | EEE World Congress on Computational Intelligence (WCCI 2008) / International Joint Conference on Neural Networks (IJCNN) |
Conference Location | Hong Kong |
Date | 1-6 June 2008 |
Book Title | Proceedings |
History (UTC) | 2008-07-16 12:36:57 :: marciana -> administrator :: 2021-02-03 17:56:35 :: administrator -> marciana :: 2008 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Content Type | External Contribution |
Abstract | A visual target tracking identification by employing using a Winner-takes-all artificial neural network is proposed in this paper. In this approach a modified Kohonen Neural Network is the mechanism used both to determine the position as to represent the target trajectory given a sequence of images. Some of the advantages employing this technique is that the initial condition are supplied randomly and that the performance of the algorithm is independent of the initial condition as well as of the number of them. Besides, this algorithm converge for the center of mass of the target. This methodology is useful in remote and local systems when information is given by images be it related to aerospace applications, robotics, radar systems, or industrial applications. The proposed algorithm is here used in the identification of airplane trajectory by using digital images. Resumo: Uma identificacao visual de rastreamento de alvos moveis usando uma rede neural artificial do tipo "o vencedor-leva-tudo" é proposta neste artigo. Nesta abordagem uma rede neural Kohonen modificada é o mecanismo usado tanto para determinar a posicao quanto para representar a trajetoria do alvo dado uma sequencia de imagens. Algumas das vantagens de se empregar esta tecnicaq é que as condicoes iniciais sao fornecidas aleatoriamente e que o desempenho do algoritmo é independente das condicoes iniciais assim como do numero delas. Adicionalmente este algoritmo converge para o centro de massa do alvo. Esta metodologia é util em sistemas locais e remotos quando a informacao é dada por imagens, seja ela relacionada com aplicacoes espaciais, robotica, sistemas de radar, ou aplicacoes industriais. O algoritmo proposto é aqui usado na identificacao de trajetoria de aeronaves pelo uso de imagens digitais. |
Area | ETES |
Arrangement | urlib.net > BDMCI > Fonds > Produção anterior à 2021 > COLIT > Visual Multi-Target Tracking... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | there are no files |
|
4. Conditions of access and use | |
Language | en |
Target File | Garcia-Araujo_IJCNN-IEEE-08_KNN-Target_pdf.pdf |
User Group | administrator marciana administrator |
Visibility | shown |
Read Permission | deny from all and allow from 150.163 |
|
5. Allied materials | |
Next Higher Units | 8JMKD3MGPCW/444BQ9E |
Host Collection | sid.inpe.br/mtc-m18@80/2008/03.17.15.17 |
|
6. Notes | |
Empty Fields | archivingpolicy archivist callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress edition editor electronicmailaddress format identifier isbn issn keywords label lineage mark mirrorrepository nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress readergroup resumeid rightsholder schedulinginformation secondarydate secondarymark serieseditor session shorttitle sponsor subject tertiarymark tertiarytype type url versiontype volume |
|
7. Description control | |
e-Mail (login) | marciana |
update | |
|