Recognizing human actions using novel space-time volume binary patterns

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • University of Science and Technology of China
View graph of relations

Details

Original languageEnglish
Pages (from-to)54-63
Number of pages10
JournalNeurocomputing
Volume173
Publication statusPublished - 7 Aug 2015

Abstract

In this paper, we propose a novel feature type, namely Motion Binary Pattern (MBP) and different computation strategies for the well-known Volume Local Binary Pattern (VLBP). MBPs are a combination of VLBPs and Optical Flow. By combining the benefit of both methods, a simple and efficient descriptor is constructed. Motion Binary Patterns are computed in the spatio-temporal domain while the motion in consecutive frames is described. Finally, a feature descriptor is constructed by a histogram computation. Volume Local Binary Patterns are a feature type to describe object characteristics in the spatio-temporal domain. But apart from the computation of such a pattern further steps are required to create a discriminative feature. These steps are evaluated in detail and the best strategy is shown. For MBPs and VLBPs, a Random Forest classifier is learned and applied to the task of human action recognition. The proposed novel feature type and VLBPs are evaluated on the well-known, publicly available KTH dataset, Weizman dataset and on the IXMAS dataset for multi-view action recognition. The results demonstrate challenging accuracies in comparison to state-of-the-art methods.

Keywords

    Action recognition, IXMAS, KTH, Patterns, Random forest, Volume local binary patterns, Weizman

ASJC Scopus subject areas

Cite this

Recognizing human actions using novel space-time volume binary patterns. / Baumann, Florian; Ehlers, Arne; Rosenhahn, Bodo et al.
In: Neurocomputing, Vol. 173, 07.08.2015, p. 54-63.

Research output: Contribution to journalArticleResearchpeer review

Baumann F, Ehlers A, Rosenhahn B, Liao J. Recognizing human actions using novel space-time volume binary patterns. Neurocomputing. 2015 Aug 7;173:54-63. doi: 10.1016/j.neucom.2015.03.097
Baumann, Florian ; Ehlers, Arne ; Rosenhahn, Bodo et al. / Recognizing human actions using novel space-time volume binary patterns. In: Neurocomputing. 2015 ; Vol. 173. pp. 54-63.
Download
@article{aeba52a82f774aeb950a546fa3181dab,
title = "Recognizing human actions using novel space-time volume binary patterns",
abstract = "In this paper, we propose a novel feature type, namely Motion Binary Pattern (MBP) and different computation strategies for the well-known Volume Local Binary Pattern (VLBP). MBPs are a combination of VLBPs and Optical Flow. By combining the benefit of both methods, a simple and efficient descriptor is constructed. Motion Binary Patterns are computed in the spatio-temporal domain while the motion in consecutive frames is described. Finally, a feature descriptor is constructed by a histogram computation. Volume Local Binary Patterns are a feature type to describe object characteristics in the spatio-temporal domain. But apart from the computation of such a pattern further steps are required to create a discriminative feature. These steps are evaluated in detail and the best strategy is shown. For MBPs and VLBPs, a Random Forest classifier is learned and applied to the task of human action recognition. The proposed novel feature type and VLBPs are evaluated on the well-known, publicly available KTH dataset, Weizman dataset and on the IXMAS dataset for multi-view action recognition. The results demonstrate challenging accuracies in comparison to state-of-the-art methods.",
keywords = "Action recognition, IXMAS, KTH, Patterns, Random forest, Volume local binary patterns, Weizman",
author = "Florian Baumann and Arne Ehlers and Bodo Rosenhahn and Jie Liao",
note = "Funding information: This work has been partially funded by the ERC within the starting grant Dynamic MinVIP (Grant no: 277729) .",
year = "2015",
month = aug,
day = "7",
doi = "10.1016/j.neucom.2015.03.097",
language = "English",
volume = "173",
pages = "54--63",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Recognizing human actions using novel space-time volume binary patterns

AU - Baumann, Florian

AU - Ehlers, Arne

AU - Rosenhahn, Bodo

AU - Liao, Jie

N1 - Funding information: This work has been partially funded by the ERC within the starting grant Dynamic MinVIP (Grant no: 277729) .

PY - 2015/8/7

Y1 - 2015/8/7

N2 - In this paper, we propose a novel feature type, namely Motion Binary Pattern (MBP) and different computation strategies for the well-known Volume Local Binary Pattern (VLBP). MBPs are a combination of VLBPs and Optical Flow. By combining the benefit of both methods, a simple and efficient descriptor is constructed. Motion Binary Patterns are computed in the spatio-temporal domain while the motion in consecutive frames is described. Finally, a feature descriptor is constructed by a histogram computation. Volume Local Binary Patterns are a feature type to describe object characteristics in the spatio-temporal domain. But apart from the computation of such a pattern further steps are required to create a discriminative feature. These steps are evaluated in detail and the best strategy is shown. For MBPs and VLBPs, a Random Forest classifier is learned and applied to the task of human action recognition. The proposed novel feature type and VLBPs are evaluated on the well-known, publicly available KTH dataset, Weizman dataset and on the IXMAS dataset for multi-view action recognition. The results demonstrate challenging accuracies in comparison to state-of-the-art methods.

AB - In this paper, we propose a novel feature type, namely Motion Binary Pattern (MBP) and different computation strategies for the well-known Volume Local Binary Pattern (VLBP). MBPs are a combination of VLBPs and Optical Flow. By combining the benefit of both methods, a simple and efficient descriptor is constructed. Motion Binary Patterns are computed in the spatio-temporal domain while the motion in consecutive frames is described. Finally, a feature descriptor is constructed by a histogram computation. Volume Local Binary Patterns are a feature type to describe object characteristics in the spatio-temporal domain. But apart from the computation of such a pattern further steps are required to create a discriminative feature. These steps are evaluated in detail and the best strategy is shown. For MBPs and VLBPs, a Random Forest classifier is learned and applied to the task of human action recognition. The proposed novel feature type and VLBPs are evaluated on the well-known, publicly available KTH dataset, Weizman dataset and on the IXMAS dataset for multi-view action recognition. The results demonstrate challenging accuracies in comparison to state-of-the-art methods.

KW - Action recognition

KW - IXMAS

KW - KTH

KW - Patterns

KW - Random forest

KW - Volume local binary patterns

KW - Weizman

UR - http://www.scopus.com/inward/record.url?scp=84947863140&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2015.03.097

DO - 10.1016/j.neucom.2015.03.097

M3 - Article

AN - SCOPUS:84947863140

VL - 173

SP - 54

EP - 63

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -

By the same author(s)