In this paper, a specifically designed markerless computer vision technique for the detection and tracking of human body silhouette is presented. This innovative method has been called Neural Snake because it is based on the active contour model formulation, known as Snakes, integrated with a Neural Network which acts as a predictor to improve the performance in case of high deformable shapes. Results both on synthetic and experimental images obtained when examining the movement of the upper limb are encouraging and allow to define working direction for the extension of the work and for its application in many contexts.
Goffredo, M., Schmid, M., Conforto, S., D'Alessio, T. (2006). A Neural approach to the tracking of human body silhouette. In Proceedings of the 1st International Conference on Signal and Image Processing (pp.353-358).
A Neural approach to the tracking of human body silhouette
GOFFREDO M;SCHMID, Maurizio;CONFORTO, SILVIA;D'ALESSIO, Tommaso
2006-01-01
Abstract
In this paper, a specifically designed markerless computer vision technique for the detection and tracking of human body silhouette is presented. This innovative method has been called Neural Snake because it is based on the active contour model formulation, known as Snakes, integrated with a Neural Network which acts as a predictor to improve the performance in case of high deformable shapes. Results both on synthetic and experimental images obtained when examining the movement of the upper limb are encouraging and allow to define working direction for the extension of the work and for its application in many contexts.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.