Publication detail

Action recognition using combined local features

ŘEZNÍČEK, I. ZEMČÍK, P.

Original Title

Action recognition using combined local features

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

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.

Keywords

Action recognition, SVM, combination of features, space-time features.

Authors

ŘEZNÍČEK, I.; ZEMČÍK, P.

RIV year

2013

Released

4. 6. 2013

Publisher

IADIS

Location

Praha

ISBN

978-972-8939-89-2

Book

Proceedings of the IADIS Computer graphics, Visulisation, Coputer Vision and Image Processing 2013

Pages from

111

Pages to

118

Pages count

8

URL

https://www.fit.vut.cz/research/publication/10369/

BibTex

@inproceedings{BUT103514,
  author="Ivo {Řezníček} and Pavel {Zemčík}",
  title="Action recognition using combined local features",
  booktitle="Proceedings of the IADIS Computer graphics, Visulisation, Coputer Vision and Image Processing 2013",
  year="2013",
  pages="111--118",
  publisher="IADIS",
  address="Praha",
  isbn="978-972-8939-89-2",
  url="https://www.fit.vut.cz/research/publication/10369/"
}