Seguimiento de objetos utilizando vision foveal basada en un nuevo método de foveación
Several works in machine vision propose different methods to adapt and use a vision system inspired in mammals vision system called foveal vision. Log Polar Transform and Exponential Cartesian Geometries can be found among the most representatives. However, there are important limits in their defini...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2007 |
| País: | México |
| Institución: | Instituto Nacional de Astrofísica, Óptica y Electrónica |
| Repositorio: | Repositorio Institucional del INAOE |
| Idioma: | español |
| OAI Identifier: | oai:inaoe.repositorioinstitucional.mx:1009/630 |
| Acceso en línea: | http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/630 |
| Access Level: | acceso abierto |
| Palabra clave: | info:eu-repo/classification/Visión/Vision info:eu-repo/classification/Seguimiento del objetivo/Target tracking info:eu-repo/classification/Visión foveal/Foveal vision info:eu-repo/classification/cti/7 info:eu-repo/classification/cti/33 info:eu-repo/classification/cti/3304 info:eu-repo/classification/cti/120323 |
| Sumario: | Several works in machine vision propose different methods to adapt and use a vision system inspired in mammals vision system called foveal vision. Log Polar Transform and Exponential Cartesian Geometries can be found among the most representatives. However, there are important limits in their definition making hard their use in the object tracking task. This work presents a study concerning with the foveal vision and its application in the object tracking task. Also, a new foveal transform proposal is presented. The images generated with the new foveation method were used in a single object tracking application working with more complex scenes than those treated with the previous proposals. The obtained performance in the tracking is similar to the obtained performance in the tracking task when cartesian images are used. Results show that it is possible to continue working under this topic concerning with foveal vision and with the key idea of inspiring artificial vision systems on natural topologies and mechanisms. |
|---|