IEICE TRANSACTIONS on Information
Self-Similarities in Difference Images: A New Cue for Single-Person Oriented Action Recognition
Summary :
Temporal Self-Similarity Matrix (SSM) based action recognition is one of the important approaches of single-person oriented action analysis in computer vision. In this study, we propose a new kind of SSM and a fast computation method. The computation method does not require time-consuming pre-processing to find bounding boxes of the human body, instead it processes difference images to obtain action patterns which can be done very quickly. The proposed SSM is experimentally confirmed to have high power/capacity to achieve a better classification performance than four typical kinds of SSMs.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.5 pp.1238-1242
- Publication Date
- 2013/05/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.1238
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Guoliang LU, Mineichi KUDO, "Self-Similarities in Difference Images: A New Cue for Single-Person Oriented Action Recognition" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 5, pp. 1238-1242, May 2013, doi: 10.1587/transinf.E96.D.1238.
Abstract: Temporal Self-Similarity Matrix (SSM) based action recognition is one of the important approaches of single-person oriented action analysis in computer vision. In this study, we propose a new kind of SSM and a fast computation method. The computation method does not require time-consuming pre-processing to find bounding boxes of the human body, instead it processes difference images to obtain action patterns which can be done very quickly. The proposed SSM is experimentally confirmed to have high power/capacity to achieve a better classification performance than four typical kinds of SSMs.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.1238/_p
Copy
@ARTICLE{e96-d_5_1238,
author={Guoliang LU, Mineichi KUDO, },
journal={IEICE TRANSACTIONS on Information},
title={Self-Similarities in Difference Images: A New Cue for Single-Person Oriented Action Recognition},
year={2013},
volume={E96-D},
number={5},
pages={1238-1242},
abstract={Temporal Self-Similarity Matrix (SSM) based action recognition is one of the important approaches of single-person oriented action analysis in computer vision. In this study, we propose a new kind of SSM and a fast computation method. The computation method does not require time-consuming pre-processing to find bounding boxes of the human body, instead it processes difference images to obtain action patterns which can be done very quickly. The proposed SSM is experimentally confirmed to have high power/capacity to achieve a better classification performance than four typical kinds of SSMs.},
keywords={},
doi={10.1587/transinf.E96.D.1238},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Self-Similarities in Difference Images: A New Cue for Single-Person Oriented Action Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1238
EP - 1242
AU - Guoliang LU
AU - Mineichi KUDO
PY - 2013
DO - 10.1587/transinf.E96.D.1238
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2013
AB - Temporal Self-Similarity Matrix (SSM) based action recognition is one of the important approaches of single-person oriented action analysis in computer vision. In this study, we propose a new kind of SSM and a fast computation method. The computation method does not require time-consuming pre-processing to find bounding boxes of the human body, instead it processes difference images to obtain action patterns which can be done very quickly. The proposed SSM is experimentally confirmed to have high power/capacity to achieve a better classification performance than four typical kinds of SSMs.
ER -
English
