Details
Original language | English |
---|---|
Pages (from-to) | 54-63 |
Number of pages | 10 |
Journal | Neurocomputing |
Volume | 173 |
Publication status | Published - 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
- Computer Science(all)
- Computer Science Applications
- Neuroscience(all)
- Cognitive Neuroscience
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Neurocomputing, Vol. 173, 07.08.2015, p. 54-63.
Research output: Contribution to journal › Article › Research › peer review
}
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 -