Mobile Multimedia Communications. 7th International ICST Conference, MOBIMEDIA 2011, Cagliari, Italy, September 5-7, 2011, Revised Selected Papers

Research Article

3D Wide Baseline Correspondences Using Depth-Maps

Download94 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-30419-4_17,
        author={Marco Marcon and Eliana Frigerio and Augusto Sarti and Stefano Tubaro},
        title={3D Wide Baseline Correspondences Using Depth-Maps},
        proceedings={Mobile Multimedia Communications. 7th International ICST Conference, MOBIMEDIA 2011, Cagliari, Italy, September 5-7, 2011, Revised Selected Papers},
        proceedings_a={MOBIMEDIA},
        year={2012},
        month={5},
        keywords={Machine vision feature extraction 3D descriptors},
        doi={10.1007/978-3-642-30419-4_17}
    }
    
  • Marco Marcon
    Eliana Frigerio
    Augusto Sarti
    Stefano Tubaro
    Year: 2012
    3D Wide Baseline Correspondences Using Depth-Maps
    MOBIMEDIA
    Springer
    DOI: 10.1007/978-3-642-30419-4_17
Marco Marcon1,*, Eliana Frigerio1,*, Augusto Sarti1, Stefano Tubaro1
  • 1: Politecnico di Milano
*Contact email: marco.marcon@polimi.it, efrigerio@elet.polimi.it

Abstract

Points matching between two or more images of a scene shot from different viewpoints is the crucial step to defining epipolar geometry between views, recover the camera’s egomotion or build a 3D model of the framed scene. Unfortunately in most of the common cases robust correspondences between points in different images can be defined only when small variations in viewpoint position, focal length or lighting are present between images. While in all the other conditions ad-hoc assumptions on the 3D scene or just weak correspondences can be used. In this paper, we present a novel matching method where depth-maps, nowadays available from cheap and off the shelf devices, are integrated with 2D images to provide robust descriptors even when wide baseline or strong lighting variations are present.