Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 68-73 |
| Seitenumfang | 6 |
| ISBN (elektronisch) | 9781479948710 |
| Publikationsstatus | Veröffentlicht - 8 Okt. 2014 |
| Veranstaltung | 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014 - Seoul, Südkorea Dauer: 26 Aug. 2014 → 29 Aug. 2014 Konferenznummer: 11 |
Publikationsreihe
| Name | 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014 |
|---|
Abstract
Volume Local Binary Patterns are a well-known feature type to describe object characteristics in the spatiotemporal domain. Apart from the computation of a binary pattern further steps are required to create a discriminative feature. In this paper we propose different computation methods for Volume Local Binary Patterns. These methods are evaluated in detail and the best strategy is shown. A Random Forest is used to find discriminative patterns. The proposed methods are applied to the well-known and publicly available KTH dataset and Weizman dataset for single-view action recognition and to the IXMAS dataset for multiview action recognition. Furthermore, a comparison of the proposed framework to state-of-the-art methods is given.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Computernetzwerke und -kommunikation
- Informatik (insg.)
- Signalverarbeitung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. S. 68-73 6918646 (11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Computation strategies for volume local binary patterns applied to action recognition
AU - Baumann, F.
AU - Ehlers, A.
AU - Rosenhahn, B.
AU - Liao, Jie
N1 - Conference code: 11
PY - 2014/10/8
Y1 - 2014/10/8
N2 - Volume Local Binary Patterns are a well-known feature type to describe object characteristics in the spatiotemporal domain. Apart from the computation of a binary pattern further steps are required to create a discriminative feature. In this paper we propose different computation methods for Volume Local Binary Patterns. These methods are evaluated in detail and the best strategy is shown. A Random Forest is used to find discriminative patterns. The proposed methods are applied to the well-known and publicly available KTH dataset and Weizman dataset for single-view action recognition and to the IXMAS dataset for multiview action recognition. Furthermore, a comparison of the proposed framework to state-of-the-art methods is given.
AB - Volume Local Binary Patterns are a well-known feature type to describe object characteristics in the spatiotemporal domain. Apart from the computation of a binary pattern further steps are required to create a discriminative feature. In this paper we propose different computation methods for Volume Local Binary Patterns. These methods are evaluated in detail and the best strategy is shown. A Random Forest is used to find discriminative patterns. The proposed methods are applied to the well-known and publicly available KTH dataset and Weizman dataset for single-view action recognition and to the IXMAS dataset for multiview action recognition. Furthermore, a comparison of the proposed framework to state-of-the-art methods is given.
UR - http://www.scopus.com/inward/record.url?scp=84909969303&partnerID=8YFLogxK
U2 - 10.1109/AVSS.2014.6918646
DO - 10.1109/AVSS.2014.6918646
M3 - Conference contribution
AN - SCOPUS:84909969303
T3 - 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
SP - 68
EP - 73
BT - 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
Y2 - 26 August 2014 through 29 August 2014
ER -