Detail publikace

Action recognition using combined local features

Originální název

Action recognition using combined local features

Anglický název

Action recognition using combined local features

Jazyk

en

Originální abstrakt

This paper presents a new algorithm for recognition of actions based on local space-time features. The algorithm resulted from intensive research of classification and feature extraction and it is an extension of the previously known ones. The most important achievement is that it is shown that through carefully selected combination of space-time features leads into better precision of recognition on some events comparing to the state-of-the-art algorithms while it is comparable on all other events. The paper describes the algorithm, its main features and improvements, demonstrates the achieved result, and draws conclusions.

Anglický abstrakt

This paper presents a new algorithm for recognition of actions based on local space-time features. The algorithm resulted from intensive research of classification and feature extraction and it is an extension of the previously known ones. The most important achievement is that it is shown that through carefully selected combination of space-time features leads into better precision of recognition on some events comparing to the state-of-the-art algorithms while it is comparable on all other events. The paper describes the algorithm, its main features and improvements, demonstrates the achieved result, and draws conclusions.

BibTex


@inproceedings{BUT103514,
  author="Ivo {Řezníček} and Pavel {Zemčík}",
  title="Action recognition using combined local features",
  annote="This paper presents a new algorithm for recognition of actions based on local
space-time features. The algorithm resulted from intensive research of
classification and feature extraction and it is an extension of the previously
known ones. The most important achievement is that it is shown that through
carefully selected combination of space-time features leads into better precision
of recognition on some events comparing to the state-of-the-art algorithms while
it is comparable on all other events. The paper describes the algorithm, its main
features and improvements, demonstrates the achieved result, and draws
conclusions.",
  address="IADIS",
  booktitle="Proceedings of the IADIS Computer graphics, Visulisation, Coputer Vision and Image Processing 2013",
  chapter="103514",
  edition="NEUVEDEN",
  howpublished="electronic, physical medium",
  institution="IADIS",
  year="2013",
  month="june",
  pages="111--118",
  publisher="IADIS",
  type="conference paper"
}