Novel Multi-Feature Bag-of-Words Descriptor via Subspace Random Projection for Efficient Human-Action Recognition

Maqueda Nieto, Ana I.; Ruano San Martín, Arturo; Blanco Adán, Carlos Roberto del; Carballeira López, Pablo; Jaureguizar Núñez, Fernando y García Santos, Narciso (2015). Novel Multi-Feature Bag-of-Words Descriptor via Subspace Random Projection for Efficient Human-Action Recognition. En: "12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)", 25/08/2015 - 28/08/2015, Karlsruhe, Germany. pp. 1-6. https://doi.org/10.1109/AVSS.2015.7301736.

Descripción

Título: Novel Multi-Feature Bag-of-Words Descriptor via Subspace Random Projection for Efficient Human-Action Recognition
Autor/es:
  • Maqueda Nieto, Ana I.
  • Ruano San Martín, Arturo
  • Blanco Adán, Carlos Roberto del
  • Carballeira López, Pablo
  • Jaureguizar Núñez, Fernando
  • García Santos, Narciso
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)
Fechas del Evento: 25/08/2015 - 28/08/2015
Lugar del Evento: Karlsruhe, Germany
Título del Libro: 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)
Fecha: 2015
Materias:
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Señales, Sistemas y Radiocomunicaciones
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (2MB) | Vista Previa

Resumen

Human-action recognition through local spatio-temporal features have been widely applied because of their simplicity and its reasonable computational complexity. The most common method to represent such features is the well-known Bag-of-Words approach, which turns a Multiple-Instance Learning problem into a supervised learning one, which can be addressed by a standard classifier. In this paper, a learning framework for human-action recognition that follows the previous strategy is presented. First, spatio-temporal features are detected. Second, they are described by HOG-HOF descriptors, and then represented by a Bag of Words approach to create a feature vector representation. The resulting high dimensional features are reduced by means of a subspace-random-projection technique that is able to retain almost all the original information. Lastly, the reduced feature vectors are delivered to a classifier called Citation K-Nearest Neighborhood, especially adapted to Multiple-Instance Learning frameworks. Excellent results have been obtained, outperforming other state-of-the art approaches in a public database.

Proyectos asociados

TipoCódigoAcrónimoResponsableTítulo
Gobierno de EspañaTEC2010-20412Enhanced 3DTVMinisterio de Economía y CompetitividadSin especificar
Gobierno de EspañaTEC2013-48453MR-UHDTVMinisterio de Economía y CompetitividadSin especificar

Más información

ID de Registro: 42760
Identificador DC: http://oa.upm.es/42760/
Identificador OAI: oai:oa.upm.es:42760
Identificador DOI: 10.1109/AVSS.2015.7301736
Depositado por: Memoria Investigacion
Depositado el: 16 Jul 2016 10:29
Ultima Modificación: 16 Jul 2016 10:29
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM