Combining Orientation Tensors for Human Action Recognition

This paper presents a new tensor motion descriptor based on histogram of oriented gradients. We model the temporal evolution of gradient distribution with orientation tensors in equally sized blocks throughout the video sequence. Subsequently, these blocks are concatenated to create the final descri...

Full description

Saved in:
Bibliographic Details
Published in2013 XXVI Conference on Graphics, Patterns and Images pp. 328 - 333
Main Authors Mota, Virginia F., Souza, Jessica I. C., De A Araujo, Arnaldo, Bernardes Vieira, Marcelo
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2013
Subjects
Computational modeling
Feature extraction
Histogram of gradients
Histograms
Human action recognition
Motion description
Orientation tensor
Support vector machines
Tensile stress
Vectors
Video sequences
Online AccessGet full text

Cover

More Information
Summary:This paper presents a new tensor motion descriptor based on histogram of oriented gradients. We model the temporal evolution of gradient distribution with orientation tensors in equally sized blocks throughout the video sequence. Subsequently, these blocks are concatenated to create the final descriptor. Using a SVM classifier, even without any bag-of-feature based approach, our method achieves recognition rates greater than those found by other HOG techniques on KTH dataset and a competitive recognition rate for UCF11 and Hollywood2 datasets.
ISSN:1530-1834
2377-5416
DOI:10.1109/SIBGRAPI.2013.52