Para acceder a los documentos con el texto completo, por favor, siga el siguiente enlace: http://hdl.handle.net/2117/28303

A new relational geometric feature for human action recognition
Vinagre Ruiz, Manuel; Aranda López, Juan; Casals Gelpi, Alicia
Universitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial; Universitat Politècnica de Catalunya. GRINS - Robòtica Intel·ligent i Sistemes
Pose-based features have demonstrated to outperform low-levelappearance features in human action recognition. New RGB-D cameras provide locations of human joints with which geometric correspondences can be easily calculated. In this article, a new geometric correspondence between joints called Trisarea feature is presented. It is defined as the area of the triangle formed by three joints. Relevant triangles describing human pose are identified and it is shown how the variation over time of the selected Trisarea features constitutes a descriptor of human action. Experimental results show a comparison with other methods and demonstrate how this Trisarea-based representation can be applied to human action recognition.
Peer Reviewed
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes
Human activity recognition
Pattern recognition systems
Pose-based feature
Action descriptor
Action recognition
Reconeixement de formes (Informàtica)
info:eu-repo/semantics/publishedVersion
Artículo
Springer
         

Mostrar el registro completo del ítem

Documentos relacionados

Otros documentos del mismo autor/a

Vinagre Ruiz, Manuel; Aranda López, Juan; Casals Gelpi, Alicia
Morales Vidal, Ricardo; Badesa Clemente, Francisco Javier; García Aracil, Nicolás; Aranda López, Juan; Casals Gelpi, Alicia
Vaca Alzate, Rubén Hernando; Aranda López, Juan; Thomas, Federico
Urra, Oiane; Casals Gelpi, Alicia; Jané Campos, Raimon