Detalhes bibliográficos
| Ano de defesa: |
2015 |
| Autor(a) principal: |
Salamon, Nestor Ziliotto
 |
| Orientador(a): |
Musse , Soraia Raupp |
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Pontifícia Universidade Católica do Rio Grande do Sul
|
| Programa de Pós-Graduação: |
Programa de Pós-Graduação em Ciência da Computação
|
| Departamento: |
Faculdade de Informática
|
| País: |
Brasil
|
| Palavras-chave em Português: |
|
| Área do conhecimento CNPq: |
|
| Link de acesso: |
http://tede2.pucrs.br/tede2/handle/tede/5968
|
Resumo: |
The re-identification of people and groups in real environments is still a difficult task due to several changes in illuminance, viewpoints, image resolution and many other challenges. In this work we propose a person re-identification approach applied as a softbiometric tool. The goal is to recognize a person by combining low-level and high-level (when possible) description of him/her, such as color appearance of clothes or objects he/she is carrying on (low-level) and group belonging (high-level).The input features for each person are manually informed by a user using sample patches from any source (a gallery repository, a picture taken or a color palette selection) and semantically organized in a 2D body model. In addition, groups of two persons (both defined as 2D body models) are specified. Finally, each 2D model is then confronted with databases using a color distance based metric, extended through an adaptive threshold and, if applicable, the color signatures of both persons into the group is used to search for a group composition with such characteristics. |
