| dc.contributor | Kornprobst, Pierre | |
| dc.contributor | Vieville, Thierry | |
| dc.contributor | University of Nice | |
| dc.creator | Escobar, María José | |
| dc.date | 2017-03-23T15:51:12Z | |
| dc.date | 2022-08-22T19:18:24Z | |
| dc.date | 2017-03-23T15:51:12Z | |
| dc.date | 2022-08-22T19:18:24Z | |
| dc.date | 2009 | |
| dc.date | instname: Conicyt | |
| dc.date | reponame: Repositorio Digital RI2.0 | |
| dc.date | 2009 | |
| dc.date | 2009 | |
| dc.date.accessioned | 2023-08-22T23:19:01Z | |
| dc.date.available | 2023-08-22T23:19:01Z | |
| dc.identifier | https://hdl.handle.net/10533/175846 | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8350628 | |
| dc.description | This thesis addresses the study of the motion perception in mammals and how bioinspired
systems can be applied to real applications. The first part of this thesis
relates how the visual information is processed in the mammal's brains and how motion
estimation is usually modeled. Based on this analysis of the state of the art, we
propose a feedforward Vi-MT core architecture. This feedforward Vi-MT core architecture
will be a basis to study two different kinds of applications. The first application
is human action recognition, which is still a challenging problem in the computer
vision community. We show how our bio-inspired method can be successfully applied
to this real application. Interestingly, we show how several computational properties
inspired from motion processing in mammals, allow us to reach high quality results,
which will be compared to latest reference results. The second application of the bioinspired
architecture proposed in this thesis, is to consider the problem of motion
integration for the solution of the aperture problem. We investigate the role of delayed
Vi surround suppression, and how the 21) information extracted through this
mechanism can be integrated to propose a solution for the aperture problem. Finaily,
we highlight a variety of important issues in the determination of motion estimation
and additionally we present many potential avenues for future research efforts. | |
| dc.description | PFCHA-Becas | |
| dc.description | Doctor en Ciencias Mención Control, Señal y Procesamiento de Imágenes | |
| dc.description | 224 p. | |
| dc.description | PFCHA-Becas | |
| dc.description | Finalizada | |
| dc.format | application/pdf | |
| dc.language | eng | |
| dc.relation | instname: Conicyt | |
| dc.relation | reponame: Repositorio Digital RI2.0 | |
| dc.relation | http://creativecommons.org/licenses/by-nc-nd/3.0/cl/ | |
| dc.relation | info:eu-repo/semantics/dataset/hdl.handle.net/10533/93488 | |
| dc.relation | Atribución-NoComercial-SinDerivadas 3.0 Chile | |
| dc.rights | handle/10533/108040 | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.title | Bió-inspired models for motión estimatión and analysis: human actión recognitión and motión integratión. | |
| dc.type | Tesis Doctorado | |
| dc.type | info:eu-repo/semantics/doctoralThesis | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
| dc.type | Tesis | |
| dc.coverage | fra | |
