Motion estimation through efficient matching of a reduced number of reliable singular points

Blanco Adán, Carlos Roberto del; Jaureguizar Núñez, Fernando; Salgado Álvarez de Sotomayor, Luis y García Santos, Narciso (2008). Motion estimation through efficient matching of a reduced number of reliable singular points. En: "IS&T / SPIE Electronic Imaging 2008", 28/01/2008-29/01/2008, San Jose, California (Estados Unidos). ISBN 978-0819469830. pp. 681102201-681102212. https://doi.org/10.1117/12.768125.

Descripción

Título: Motion estimation through efficient matching of a reduced number of reliable singular points
Autor/es:
  • Blanco Adán, Carlos Roberto del
  • Jaureguizar Núñez, Fernando
  • Salgado Álvarez de Sotomayor, Luis
  • García Santos, Narciso
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: IS&T / SPIE Electronic Imaging 2008
Fechas del Evento: 28/01/2008-29/01/2008
Lugar del Evento: San Jose, California (Estados Unidos)
Título del Libro: Real-Time Image Processing 2008: Proceedings of Electronic Imaging, Science and Technology
Fecha: 2008
ISBN: 978-0819469830
Materias:
Palabras Clave Informales: Real Time, Motion Estimation, Singular Point, Noise Adaptive, Point descriptor, Point Matching
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Señales, Sistemas y Radiocomunicaciones
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (908kB) | Vista Previa

Resumen

Motion estimation in video sequences is a classical intensive computational task that is required for a wide range of applications. Many different methods have been proposed to reduce the computational complexity, but the achieved reduction is not enough to allow real time operation in a non-specialized hardware. In this paper an efficient selection of singular points for fast matching between consecutive images is presented, which allows to achieve real time operation. The selection of singular points lies in finding the image points that are robust to the noise and the aperture problem. This is accomplished by imposing restrictions related to the gradient magnitude and the cornerness. The neighborhood of each singular point is characterized by a complex descriptor vector, which presents a high robustness to illumination changes and small variations in the 3D camera viewpoint. The matching between singular points of consecutive images is performed by maximizing a similarity measure based on the previous descriptor vector. The set of correspondences yields a sparse motion vector field that accurately outlines the image motion. In order to demonstrate the efficiency of this approach, a video stabilization application has been developed, which uses the sparse motion vector field as input. Excellent results have been obtained in synthetic and real sequences, demonstrating the efficiency of the proposed motion estimation technique.

Más información

ID de Registro: 3802
Identificador DC: http://oa.upm.es/3802/
Identificador OAI: oai:oa.upm.es:3802
Identificador DOI: 10.1117/12.768125
Depositado por: Memoria Investigacion
Depositado el: 21 Jul 2010 12:03
Ultima Modificación: 20 Abr 2016 13:16
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM