Bió-inspired models for motión estimatión and analysis: human actión recognitión and motión integratión.

Abstract

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.