Real time extraction of high level structures using a semi-calibrated stereo system

This research presents a novel methodology that combines stereo vision and parallel processing, based on GPU and the use of binary descriptors, for fast High-Level Structures extraction. Typical stereo algorithms require an image rectification stage that has to run on a frame-to-frame basis, increas...

Descripción completa

Detalles Bibliográficos
Autor: ROBERTO DE LIMA HERNANDEZ
Tipo de recurso: tesis de maestría
Estado:Versión aceptada para publicación
Fecha de publicación:2016
País:México
Institución:Instituto Nacional de Astrofísica, Óptica y Electrónica
Repositorio:Repositorio Institucional del INAOE
Idioma:inglés
OAI Identifier:oai:inaoe.repositorioinstitucional.mx:1009/320
Acceso en línea:http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/320
Access Level:acceso abierto
Palabra clave:info:eu-repo/classification/Stereo vision/Stereo vision
info:eu-repo/classification/Semi-calibrated stereo/Semi-calibrated stereo
info:eu-repo/classification/Stereo images/Stereo images
info:eu-repo/classification/Stereo camera/Stereo camera
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/12
info:eu-repo/classification/cti/1203
Descripción
Sumario:This research presents a novel methodology that combines stereo vision and parallel processing, based on GPU and the use of binary descriptors, for fast High-Level Structures extraction. Typical stereo algorithms require an image rectification stage that has to run on a frame-to-frame basis, increasing the computational burden and with the possibility of compromising high frame rate operation. Hence, it is proposed to use a semi-calibrated stereo approach, meaning that only calibration of extrinsic parameters of the stereo rig is carried out, thus avoiding a rectification process of the frames captured by the stereo camera. For the latter, the proposed approach relies on feature matching of salient points detected on the stereo images, from which image correspondences are obtained. These correspondences are triangulated to generate a point cloud that is passed to a plane fitting module. As feature matching is a cumbersome task, this study presents a novel GPU architecture to accelerate such process, thus achieving a real-time performance of up to 50 fps for the whole process. To demonstrate our approach, we also present an augmented reality application that exploits the planes extracted with our approach.