The Community for Technology Leaders
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2339-2
pp: 1-8
Jacobo Garcia Miro , Dep. Inteligencia Artificial Facultad Informática, Universidad Politécnica de Madrid, Spain
Jose M. Buenaposada , Dep. Ciencias de la Computación E.T.S.I. Informática Universidad Rey Juan Carlos, Spain
Luis Baumela , Dep. Inteligencia Artificial Facultad Informática, Universidad Politécnica de Madrid, Spain
Pablo Marquez-Neila , Dep. Inteligencia Artificial Facultad Informática, Universidad Politécnica de Madrid, Spain
ABSTRACT
We introduce a procedure for recognizing and locating planar landmarks for mobile robot navigation, based in the detection and recognition of a set of interest points. We use RANSAC for fitting a homography and locating the landmark. Our main contribution is the introduction of a geometrical constraint that reduces the number of RANSAC iterations by discarding minimal subsets. In the experiments conducted we conclude that this constraint increases RANSAC performance by reducing in about 35% and 75% the number of iterations for affine and projective cameras, respectively.
INDEX TERMS
CITATION
Jacobo Garcia Miro, Jose M. Buenaposada, Luis Baumela, Pablo Marquez-Neila, "Improving RANSAC for fast landmark recognition", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-8, 2008, doi:10.1109/CVPRW.2008.4563138
94 ms
(Ver )