A survey of vision-based methods for action representation, segmentation and recognitionReportar como inadecuado




A survey of vision-based methods for action representation, segmentation and recognition - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 DT Lab - Deutsche Telekom Laboratories 2 LEAR - Learning and recognition in vision Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble 3 MORPHEO - Capture and Analysis of Shapes in Motion Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble

Abstract : Action recognition has become a very important topic in computer vision, with many fundamental applications, in robotics, video surveillance, human-computer interaction, and multimedia retrieval among others and a large variety of approaches have been described. The purpose of this survey is to give an overview and categorization of the approaches used. We concentrate on approaches that aim on classification of full-body motions, such as kicking, punching, and waving, and we categorize them according to how they represent the spatial and temporal structure of actions; how they segment actions from an input stream of visual data; and how they learn a view-invariant representation of actions.

Résumé : La reconnaissance d-actions est un domaine de recherche actif en vision par ordinateur pour de nombreuses applications pratique : robotique, video surveillance, interaction homme machine, recherche de documents multimedia. Nous proposons une catégorisation des méthodes de reconnaissance d-action en fonction des représentations spatiales et temporelles qu-elles mobilisent; de la facon dont elles permettent ou non de segmenter les actions; et de la facon dont elles abordent le probleme de l-invariance au point de vue.

Keywords : survey activity recognition computer vision action recognition





Autor: Daniel Weinland - Rémi Ronfard - Edmond Boyer -

Fuente: https://hal.archives-ouvertes.fr/



DESCARGAR PDF




Documentos relacionados