Planificador de vistas para reconstrucción tridimensional de objetos
For manipulating an unknown object, a robot needs a 3D model of it. Given the limited eld of view of a camera and self occlusions, a set of views is required to build a complete 3D model. So, an important problem is how to select these views optimally according to certain criteria. We propose a nove...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2009 |
| País: | México |
| Institución: | Instituto Nacional de Astrofísica, Óptica y Electrónica |
| Repositorio: | Repositorio Institucional del INAOE |
| Idioma: | español |
| OAI Identifier: | oai:inaoe.repositorioinstitucional.mx:1009/469 |
| Acceso en línea: | http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/469 |
| Access Level: | acceso abierto |
| Palabra clave: | info:eu-repo/classification/Planificación/Planning info:eu-repo/classification/Visión/Vision info:eu-repo/classification/Robots móviles/Mobile robots info:eu-repo/classification/cti/1 info:eu-repo/classification/cti/12 info:eu-repo/classification/cti/1203 |
| Sumario: | For manipulating an unknown object, a robot needs a 3D model of it. Given the limited eld of view of a camera and self occlusions, a set of views is required to build a complete 3D model. So, an important problem is how to select these views optimally according to certain criteria. We propose a novel algorithm (view planner) to select the next-best-view (NBV) for a range camera to model 3D arbitrary objects. We use a volumetric representation. We propose a new utility function considering amount of unknown information, quality and navigation. We also propose two novel strategies to accelerate the search of the NBV. One strategy is based on a hierarchical decomposition of the search space and the other is based on a multi-resolution of ray tracing. We have tested our planner in simulation with 7 different 3D objects, showing good results in terms of quality of the models and computation time required, and at the same time reducing the distance that the sensor has to travel to obtain the set of views. We also have tested the planner in a robot with a stereo camera, as a result we reconstructed a real object. |
|---|