Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor

Riccardo Mattivi; Ling Shao

doi:10.1007/978-3-642-03767-2_90

Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor

Riccardo Mattivi, Ling Shao

Computer and Information Sciences Department

Research output: Contribution to conference › Paper

61 Citations (Scopus)

Abstract

In this paper we apply the Local Binary Pattern on Three Orthogonal Planes (LBP-TOP) descriptor to the field of human action recognition. A video sequence is described as a collection of spatial-temporal words after the detection of space-time interest points and the description of the area around them. Our contribution has been in the description part, showing LBP-TOP to be a promising descriptor for human action classification purposes. We have also developed several extensions to the descriptor to enhance its performance in human action recognition, showing the method to be computationally efficient.

Original language	English
DOIs	https://doi.org/10.1007/978-3-642-03767-2_90
Publication status	Published - Sept 2009
Event	CAIP 2009 - 13th International Conference on Computer Analysis of Images and Patterns - Münster, Germany Duration: 1 Sept 2009 → …

Conference

Conference	CAIP 2009 - 13th International Conference on Computer Analysis of Images and Patterns
Period	1/09/09 → …

Keywords

Human action recognition
LBP-TOP
bag of words

Access to Document

10.1007/978-3-642-03767-2_90

Cite this

@conference{610443e5df8440d2bd1d24555f9c46d7,

title = "Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor",

abstract = "In this paper we apply the Local Binary Pattern on Three Orthogonal Planes (LBP-TOP) descriptor to the field of human action recognition. A video sequence is described as a collection of spatial-temporal words after the detection of space-time interest points and the description of the area around them. Our contribution has been in the description part, showing LBP-TOP to be a promising descriptor for human action classification purposes. We have also developed several extensions to the descriptor to enhance its performance in human action recognition, showing the method to be computationally efficient.",

keywords = "Human action recognition, LBP-TOP, bag of words",

author = "Riccardo Mattivi and Ling Shao",

year = "2009",

month = sep,

doi = "10.1007/978-3-642-03767-2_90",

language = "English",

note = "CAIP 2009 - 13th International Conference on Computer Analysis of Images and Patterns ; Conference date: 01-09-2009",

}

TY - CONF

T1 - Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor

AU - Mattivi, Riccardo

AU - Shao, Ling

PY - 2009/9

Y1 - 2009/9

N2 - In this paper we apply the Local Binary Pattern on Three Orthogonal Planes (LBP-TOP) descriptor to the field of human action recognition. A video sequence is described as a collection of spatial-temporal words after the detection of space-time interest points and the description of the area around them. Our contribution has been in the description part, showing LBP-TOP to be a promising descriptor for human action classification purposes. We have also developed several extensions to the descriptor to enhance its performance in human action recognition, showing the method to be computationally efficient.

AB - In this paper we apply the Local Binary Pattern on Three Orthogonal Planes (LBP-TOP) descriptor to the field of human action recognition. A video sequence is described as a collection of spatial-temporal words after the detection of space-time interest points and the description of the area around them. Our contribution has been in the description part, showing LBP-TOP to be a promising descriptor for human action classification purposes. We have also developed several extensions to the descriptor to enhance its performance in human action recognition, showing the method to be computationally efficient.

KW - Human action recognition

KW - LBP-TOP

KW - bag of words

U2 - 10.1007/978-3-642-03767-2_90

DO - 10.1007/978-3-642-03767-2_90

M3 - Paper

T2 - CAIP 2009 - 13th International Conference on Computer Analysis of Images and Patterns

Y2 - 1 September 2009

ER -

Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this