Modeling Video Activity with Dynamic Phrases and Its Application to Action Recognition in Tennis Videos

We present a novel approach to action recognition in tennis shot sequences. The underlying model considers the per-frame motion to be regarded as a word (within an alphabet of possible motions), and the sequence of frames as a phrase whose meaning is determined by the words given in a specific order. This feature extraction mechanism allows a semantic treatment of the classification stage using Conditional Random Fields. The system was applied on the RGB videos of the THETIS dataset, achieving an accuracy of over 86% in recognizing 12 different tennis shots among several takes produced by 55 different amateur and professional players.

Palabras clave: Action Recognition , Conditional Random Fields , Support Vector Ma- Chines , Optical Flow , Motion Description

Ver el registro completo

Archivos asociados

Tamaño: 757.5Kb

Formato: PDF

Descargar

Licencia

Excepto donde se diga explícitamente, este item se publica bajo la siguiente descripción: Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Unported (CC BY-NC-SA 2.5)

Identificadores

URI: http://hdl.handle.net/11336/11845

URL: http://link.springer.com/chapter/10.1007%2F978-3-319-12568-8_110

DOI: http://dx.doi.org/10.1007/978-3-319-12568-8_110

Colecciones

Articulos(IIIE)
Articulos de INST.DE INVEST.EN ING.ELECTRICA "A.DESAGES"

Citación

Vainstein, Jonathan Javier; Manera, José Francisco; Negri, Pablo Augusto; Delrieux, Claudio Augusto; Maguitman, Ana Gabriela; Modeling Video Activity with Dynamic Phrases and Its Application to Action Recognition in Tennis Videos; Springer; Lecture Notes In Computer Science; 8827; 11-2014; 909-916

Altmétricas