Ponencias en congresos:
Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking
Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking
Año:2012
Áreas de investigación
-
Procesado y análisis de la señal
Datos
|
Descripción
|
|
|---|---|
| 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 | |
|
Internacional
|
Si |
|
Nombre congreso
|
IS&T/SPIE Int. Conf. on Intelligent Robots and Computer Vision XXIX: Algorithms and Techniques |
|
Tipo de participación
|
960 |
|
Lugar del congreso
|
San Francisco (CA), USA |
|
Revisores
|
Si |
|
ISBN o ISSN
|
9780819489487 |
|
DOI
|
10.1117/12.908585 |
|
Fecha inicio congreso
|
23/01/2012 |
|
Fecha fin congreso
|
24/01/2012 |
|
Desde la página
|
1 |
|
Hasta la página
|
15 |
|
Título de las actas
|
Proceedings of SPIE Vol. 8301 |
Ver publicación en Archivo digital upm
Participantes
- Autor: Javier Marinas Mateos (UPM)
- Autor: Luis Salgado Alvarez de Sotomayor (UPM)
- Autor: Jon Arróspide Laborda (UPM)
- Autor: Massimo Camplani (UPM)
Grupos de investigación, Departamentos, Centros e Institutos de I+D+i relacionados
- Creador: Grupo de Investigación: Grupo de Tratamiento de Imágenes (GTI)
S2i 2023 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)