Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking

Marinas Mateos, Javier; Salgado Álvarez de Sotomayor, Luis; Arróspide Laborda, Jon y Camplani, Massimo (2012). Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking. En: "Intelligent Robots and Computer Vision XXIX: Algorithms and Techniques", 23/01/2012 - 24/01/2012, Burlingame, California, USA. pp. 1-15. https://doi.org/10.1117/12.908585.

Descripción

Título: Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking
Autor/es:
  • Marinas Mateos, Javier
  • Salgado Álvarez de Sotomayor, Luis
  • Arróspide Laborda, Jon
  • Camplani, Massimo
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: Intelligent Robots and Computer Vision XXIX: Algorithms and Techniques
Fechas del Evento: 23/01/2012 - 24/01/2012
Lugar del Evento: Burlingame, California, USA
Título del Libro: Intelligent Robots and Computer Vision XXIX: Algorithms and Techniques
Fecha: 2012
Volumen: 830106
Materias:
Palabras Clave Informales: Stereo processing, traffic sign detection and tracking, RANSAC, Kalman filter.
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Señales, Sistemas y Radiocomunicaciones
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img] PDF (Document Portable Format) - Acceso permitido solamente a usuarios en el campus de la UPM - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (4MB)

Resumen

In this paper we propose an innovative method for the automatic detection and tracking of road traffic signs using an onboard stereo camera. It involves a combination of monocular and stereo analysis strategies to increase the reliability of the detections such that it can boost the performance of any traffic sign recognition scheme. Firstly, an adaptive color and appearance based detection is applied at single camera level to generate a set of traffic sign hypotheses. In turn, stereo information allows for sparse 3D reconstruction of potential traffic signs through a SURF-based matching strategy. Namely, the plane that best fits the cloud of 3D points traced back from feature matches is estimated using a RANSAC based approach to improve robustness to outliers. Temporal consistency of the 3D information is ensured through a Kalman-based tracking stage. This also allows for the generation of a predicted 3D traffic sign model, which is in turn used to enhance the previously mentioned color-based detector through a feedback loop, thus improving detection accuracy. The proposed solution has been tested with real sequences under several illumination conditions and in both urban areas and highways, achieving very high detection rates in challenging environments, including rapid motion and significant perspective distortion

Más información

ID de Registro: 30513
Identificador DC: http://oa.upm.es/30513/
Identificador OAI: oai:oa.upm.es:30513
Identificador DOI: 10.1117/12.908585
Depositado por: Memoria Investigacion
Depositado el: 13 Sep 2014 08:50
Ultima Modificación: 22 Sep 2014 11:49
  • 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