Publication detail

Human action recognition for real-time applications

ŘEZNÍČEK, I. ZEMČÍK, P.

Original Title

Human action recognition for real-time applications

Type

conference paper

Language

English

Original Abstract

Action recognition in video is an important part of many applications. While the performance of action recognition has been intensively investigated, not much research so far has been done in the understanding of how long a sequence of video frames is needed to correctly recognize certain actions. This paper presents a new method of measurement of the length of the video sequence necessary to recognize the actions based on space-time feature points. Such length is the key information necessary to successfully recognize the actions in real-time or performance critical applications. The action recognition used in the presented approach is the state-of-the-art one; vocabulary, bag of words and SVM processing. The proposed methods is experimentally evaluated on human action recognition dataset.

Keywords

Space-time interest points, action recognition, real-time processing, SVM

Authors

ŘEZNÍČEK, I.; ZEMČÍK, P.

Released

6. 3. 2014

Location

Angers

ISBN

978-989-758-018-5

Book

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

Pages from

646

Pages to

653

Pages count

8

URL

BibTex

@inproceedings{BUT162727,
  author="Ivo {Řezníček} and Pavel {Zemčík}",
  title="Human action recognition for real-time applications",
  booktitle="Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods",
  year="2014",
  pages="646--653",
  address="Angers",
  isbn="978-989-758-018-5",
  url="https://www.fit.vut.cz/research/publication/10501/"
}