Human action recognition using Lagrangian descriptors

Human action recognition requires the description of complex motion patterns in image sequences. In general, these patterns span varying temporal scales. In this context, Lagrangian methods have proven to be valuable for crowd analysis tasks such as crowd segmentation. In this paper, we show that, b...

Full description

Saved in:
Bibliographic Details
Published in2012 IEEE 14th International Workshop on Multimedia Signal Processing pp. 360 - 365
Main Authors Acar, Esra, Senst, Tobias, Kuhn, Alexander, Keller, Ivo, Theisel, Holger, Albayrak, Sahin, Sikora, Thomas
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2012
Subjects
Accuracy
Context
Feature extraction
Humans
Image sequences
Legged locomotion
Optical imaging
Online AccessGet full text
ISBN9781467345705
1467345709
DOI10.1109/MMSP.2012.6343469

Cover

More Information
Summary:Human action recognition requires the description of complex motion patterns in image sequences. In general, these patterns span varying temporal scales. In this context, Lagrangian methods have proven to be valuable for crowd analysis tasks such as crowd segmentation. In this paper, we show that, besides their potential in describing large scale motion patterns, Lagrangian methods are also well suited to model complex individual human activities over variable time intervals. We use Finite Time Lyapunov Exponents and time-normalized arc length measures in a linear SVM classification scheme. We evaluated our method on the Weizmann and KTH datasets. The results demonstrate that our approach is promising and that human action recognition performance is improved by fusing Lagrangian measures.
ISBN:9781467345705
1467345709
DOI:10.1109/MMSP.2012.6343469