IEICE TRANSACTIONS on Information
Vote Distribution Model for Hough-Based Action Detection
Summary :
Hough-based voting approaches have been widely used to solve many detection problems such as object and action detection. These approaches for action detection cast votes for action classes and positions based on the local spatio-temporal features of given videos. The voting process of each local feature is performed independently of the other local features. This independence enables the method to be robust to occlusions because votes based on visible local features are not influenced by occluded local features. However, such independence makes discrimination of similar motions between different classes difficult and causes the method to cast many false votes. We propose a novel Hough-based action detection method to overcome the problem of false votes. The false votes do not occur randomly such that they depend on relevant action classes. We introduce vote distributions, which represent the number of votes for each action class. We assume that the distribution of false votes include important information necessary to improving action detection. These distributions are used to build a model that represents the characteristics of Hough voting that include false votes. The method estimates the likelihood using the model and reduces the influence of false votes. In experiments, we confirmed that the proposed method reduces false positive detection and improves action detection accuracy when using the IXMAS dataset and the UT-Interaction dataset.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.11 pp.2796-2808
- Publication Date
- 2016/11/01
- Publicized
- 2016/08/18
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2015EDP7503
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
Kensho HARA
Nagoya University
Takatsugu HIRAYAMA
Nagoya University
Kenji MASE
Nagoya University
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
Kensho HARA, Takatsugu HIRAYAMA, Kenji MASE, "Vote Distribution Model for Hough-Based Action Detection" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 11, pp. 2796-2808, November 2016, doi: 10.1587/transinf.2015EDP7503.
Abstract: Hough-based voting approaches have been widely used to solve many detection problems such as object and action detection. These approaches for action detection cast votes for action classes and positions based on the local spatio-temporal features of given videos. The voting process of each local feature is performed independently of the other local features. This independence enables the method to be robust to occlusions because votes based on visible local features are not influenced by occluded local features. However, such independence makes discrimination of similar motions between different classes difficult and causes the method to cast many false votes. We propose a novel Hough-based action detection method to overcome the problem of false votes. The false votes do not occur randomly such that they depend on relevant action classes. We introduce vote distributions, which represent the number of votes for each action class. We assume that the distribution of false votes include important information necessary to improving action detection. These distributions are used to build a model that represents the characteristics of Hough voting that include false votes. The method estimates the likelihood using the model and reduces the influence of false votes. In experiments, we confirmed that the proposed method reduces false positive detection and improves action detection accuracy when using the IXMAS dataset and the UT-Interaction dataset.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7503/_p
Copy
@ARTICLE{e99-d_11_2796,
author={Kensho HARA, Takatsugu HIRAYAMA, Kenji MASE, },
journal={IEICE TRANSACTIONS on Information},
title={Vote Distribution Model for Hough-Based Action Detection},
year={2016},
volume={E99-D},
number={11},
pages={2796-2808},
abstract={Hough-based voting approaches have been widely used to solve many detection problems such as object and action detection. These approaches for action detection cast votes for action classes and positions based on the local spatio-temporal features of given videos. The voting process of each local feature is performed independently of the other local features. This independence enables the method to be robust to occlusions because votes based on visible local features are not influenced by occluded local features. However, such independence makes discrimination of similar motions between different classes difficult and causes the method to cast many false votes. We propose a novel Hough-based action detection method to overcome the problem of false votes. The false votes do not occur randomly such that they depend on relevant action classes. We introduce vote distributions, which represent the number of votes for each action class. We assume that the distribution of false votes include important information necessary to improving action detection. These distributions are used to build a model that represents the characteristics of Hough voting that include false votes. The method estimates the likelihood using the model and reduces the influence of false votes. In experiments, we confirmed that the proposed method reduces false positive detection and improves action detection accuracy when using the IXMAS dataset and the UT-Interaction dataset.},
keywords={},
doi={10.1587/transinf.2015EDP7503},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Vote Distribution Model for Hough-Based Action Detection
T2 - IEICE TRANSACTIONS on Information
SP - 2796
EP - 2808
AU - Kensho HARA
AU - Takatsugu HIRAYAMA
AU - Kenji MASE
PY - 2016
DO - 10.1587/transinf.2015EDP7503
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2016
AB - Hough-based voting approaches have been widely used to solve many detection problems such as object and action detection. These approaches for action detection cast votes for action classes and positions based on the local spatio-temporal features of given videos. The voting process of each local feature is performed independently of the other local features. This independence enables the method to be robust to occlusions because votes based on visible local features are not influenced by occluded local features. However, such independence makes discrimination of similar motions between different classes difficult and causes the method to cast many false votes. We propose a novel Hough-based action detection method to overcome the problem of false votes. The false votes do not occur randomly such that they depend on relevant action classes. We introduce vote distributions, which represent the number of votes for each action class. We assume that the distribution of false votes include important information necessary to improving action detection. These distributions are used to build a model that represents the characteristics of Hough voting that include false votes. The method estimates the likelihood using the model and reduces the influence of false votes. In experiments, we confirmed that the proposed method reduces false positive detection and improves action detection accuracy when using the IXMAS dataset and the UT-Interaction dataset.
ER -
English
