In the markerless analysis of human movement, one of the most used algorithms for the tracking of human body segments in visual hull sequences [1] is the Iterative Closest Point (ICP) algorithm [2]. This latter is used to execute the registration of three-dimensional images; it does not require the assignment of a priori correspondences between the geometricdata of two sets of points, lines, curves, etc. and it can be applied to a wide typology of geometric entities. This work is aimed at the comparison of the accuracy obtainable from the ICP algorithm and the classic stereovisionalgorithm described in [3].
Comparison between ICP and a stereo-vision algoritnm / Sgattoni, D; Fioretti, Sandro. - In: GAIT & POSTURE. - ISSN 0966-6362. - 28:(2008), pp. S6-S6. [10.1016/j.gaitpost.2007.12.017]
Comparison between ICP and a stereo-vision algoritnm.
FIORETTI, Sandro
2008-01-01
Abstract
In the markerless analysis of human movement, one of the most used algorithms for the tracking of human body segments in visual hull sequences [1] is the Iterative Closest Point (ICP) algorithm [2]. This latter is used to execute the registration of three-dimensional images; it does not require the assignment of a priori correspondences between the geometricdata of two sets of points, lines, curves, etc. and it can be applied to a wide typology of geometric entities. This work is aimed at the comparison of the accuracy obtainable from the ICP algorithm and the classic stereovisionalgorithm described in [3].I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.