A reduced LTP coding on spatial interest points for Human Action Recognition

DOI

10.2991/iccsee.2013.270How to use a DOI?

Keywords

reduced LTP, interest points ,action recognition,

Abstract

We present a novel action recognition method which is based on combining detecting 2D informative feature points and coding their local changes in motion directions by Local Trinary Patterns. The resulting method is extremely efficient, and thus is suitable for real-time uses of simultaneous recovery of human action of several lengths and starting points. Tested on some publicity available datasets in the literature known to us, our method can make good performance both on accuracy and efficiency for recognition.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Chunkeng Dong
AU  - Hao Song
PY  - 2013/03
DA  - 2013/03
TI  - A reduced LTP coding on spatial interest points for Human Action Recognition
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 1076
EP  - 1079
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.270
DO  - 10.2991/iccsee.2013.270
ID  - Dong2013/03
ER  -