Publicado

2014-01-01

SIMULTANEOUS LOCALIZATION OF A MONOCULAR CAMERA AND MAPPING OF THE ENVIRONMENT IN REAL TIME

LOCALIZACIÓN DE UNA CÁMARA MONOCULAR Y MAPEO SIMULTÁNEO DEL ENTORNO EN TIEMPO REAL

DOI:

https://doi.org/10.15446/dyna.v81n183.34745

Palabras clave:

localization, mapping, EKF, monocular camera, inverse depth, real time, 6DOF, active search (en)
Localización, mapeo, EKF, cámara monocular, inverso de la profundidad, tiempo real, 6DOF, búsqueda activa. (es)

Descargas

Autores/as

  • ANDRÉS DÍAZ Universidad del Valle
  • LINA PAZ Universidad de Zaragoza
  • EDUARDO CAICEDO Universidad del Valle
  • PEDRO PINIÉS Universidad de Zaragoza
In this work a Visual SLAM system (Simultaneous Localization and Mapping) that performs in real time, building feature-based maps and estimating the camera trajectory is presented. The camera is carried by a person that moves it smoothly with six degrees of freedom in indoor environments. The features correspond to high quality corners parametrized with inverse depth representation. They are detected inside regions of interest and an occupancy criterion is applied in order to avoid feature agglomeration. The association process is developed using active search. The final representation is made in a three-dimensional environment.
En este trabajo se presenta el desarrollo de un sistema de SLAM Visual (Simultaneous Localization and Mapping) que se desempeña en tiempo real, construyendo mapas basados en puntos característicos y estimando la trayectoria de la cámara. La cámara es transportada por una persona que la mueve suavemente con seis grados de libertad en entornos interiores. Los puntos característicos corresponden a esquinas de alta calidad parametrizados con el inverso de su profundidad. Estos son detectados dentro de regiones de interés y se aplica un criterio de ocupación con el fin de evitar aglomeración de características. El proceso de asociación se desarrolla usando búsqueda activa. La representación final se realiza en un entorno tridimensional.

Referencias

Smith, R. C., and Cheeseman P. On the representation and estimation of spatial uncertainty. Int. J. Robotics Research, 5(4): pp.56-68, 1986.

Davison, A. J., and Murray, D. W. Simultaneous localization and map-building using active vision. IEEE Trans. Pattern Analysis and Machine Intelligence, 24(7): pp.865-880, 2002.

Davison, A. J., Reid, I. D., Molton, N. D., and Stasse, O. Monoslam: Real-time single camera slam. IEEE Trans. Pattern Analysis and Machine Intelligence, 29(6):pp.1052-1067, June 2007.

Quintián, H., Calvo, J. L., and Fontenla, O. Aplicación de un robot comercial de bajo coste en tareas de seguimiento de objetos. Revista Dyna, 175, pp.24-33, 2012.

Castellanos, J. A. Mobile Robot Localization and Map Building: A Multisensor Fusion Approach. PhD thesis, Dpto. de Informática e Ingeniería de Sistemas, University of Zaragoza, Spain, May 1998.

Davison, A.J. Mobile Robot Navigation using Active Vision. PhD thesis, University of Oxford, 1998.

Lacroix, S., and Jung, I. K. High resolution terrain mapping using low altitude aerial stereo imagery. In Proc. of the 9th Int. Conf. on Computer Vision, pages pp.946-951, 2003.

Saez, J.M., Escolano, F., and Penalver, A. First Steps towards Stereobased 6DOF SLAM for the Visually Impaired. In Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR'05)- Workshops-Volume 03. IEEE Computer Society Washington, DC, USA, 2005.

Bailey, T. Constrained initialization for bearing-only SLAM. In Proc. IEEE Int. Conf. on Robotics and Automation, (ICRA'03), volume 2, 2003.

Kwok, N. M., Dissanayake, G. An efficient multiple hypothesis filter for bearing-only SLAM. In Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, (IROS'04)., volume 1, 2004.

Lemaire, T., Lacroix, S., and Sola, J. A practical 3D bearing-only SLAM algorithm. In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS'05), pp. 2449-2454, 2005.

Civera, J., Davison, A. J., and Montiel, J. M. Inverse depth parametrization for monocular SLAM. IEEE Transactions on Robotics, 24(5): pp932-945, October 2008.

Tully, S., Moon, H., Kantor, G., and Choset, H. Iterated filters for bearing-only slam. In IEEE International Conference on Robotics and Automation, 2008.

Clemente, L., Davison, A. J., Reid, I. D., Neira, J., and Tardos, J. D. Mapping large loops with a single hand-held camera. In Proc. Robotics: Science and Systems, Atlanta, GA, USA, June 2007.

Marzorati, D., Matteucci, M., Migliore, D., and Sorrenti, D. On the use of inverse scaling in monocular slam. In IEEE International Conference on Robotics and Automation, 2009.

Bosse, M., Newman, P. M., Leonard, J. J., Soika, M., Feiten, W., and Teller, S. An atlas framework for scalable mapping. In Proc. IEEE Int. Conf. Robotics and Automation, pp. 1899-1906, Taipei, Taiwan, 2003.

Leonard, J. J., and Newman, P. M. Consistent, convergent and constant time SLAM. In Int. Joint Conf. Artificial Intelligence, Acapulco, Mexico, August 2003.

Paz, L. M., Tardós, J. D., Neira, J. Divide and Conquer: EKF SLAM in O(n). Accepted in Transactions on Robotics (in Print), 24(5), October 2008.

Piniés, P., and Tardós, J. D. Large Scale SLAM Building Conditionally Independent Local Maps: Application to Monocular Vision. Accepted in Transactions on Robotics (in print)., 24(5), October 2008.

Montiel, J. M., and Civera, J., Davison, A. J. Unified inverse depth parametrization for monocular SLAM. In Proc. Robotics: Science and Systems, Philadelphia, USA, August 2006.

Dimensions

PlumX

Visitas a la página del resumen del artículo

546

Descargas

Los datos de descarga aún no están disponibles.

Cómo citar

[1]
“LOCALIZACIÓN DE UNA CÁMARA MONOCULAR Y MAPEO SIMULTÁNEO DEL ENTORNO EN TIEMPO REAL”, DYNA, vol. 81, no. 183, pp. 7–15, Jan. 2014, doi: 10.15446/dyna.v81n183.34745.