A human action recognition system for embedded computer vision application

Hongying Meng; Nick Pears; Chris Bailey

A human action recognition system for embedded computer vision application

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose a human action recognition system suitable for embedded computer vision applications in security systems, human-computer interaction and intelligent environments. Our system is suitable for embedded computer vision application based on three reasons. Firstly, the system was based on a linear Support Vector Machine (SVM) classifier where classification progress can be implemented easily and quickly in embedded hardware. Secondly, we use compacted motion features easily obtained from videos. We address the limitations of the well known Motion History Image (MHI) and propose a new Hierarchical Motion History Histogram (HMHH) feature to represent the motion information. HMHH not only provides rich motion information, but also remains computationally inexpensive. Finally, we combine MHI and HMHH together and extract a low dimension feature vector to be used in the SVM classifiers. Experimental results show that our system achieves significant improvement on the recognition performance.

Original language	English
Title of host publication	2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8
Place of Publication	NEW YORK
Publisher	IEEE
Pages	3213-3218
Number of pages	6
ISBN (Print)	978-1-4244-1179-5
Publication status	Published - 2007
Event	IEEE Conference on Computer Vision and Pattern Recognition - Minneapolis Duration: 17 Jun 2007 → 22 Jun 2007

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition
City	Minneapolis
Period	17/06/07 → 22/06/07

Keywords

CLASSIFIER

Cite this

@inproceedings{d5fa47d0742a44fa996338eeff79c4fd,

title = "A human action recognition system for embedded computer vision application",

abstract = "In this paper, we propose a human action recognition system suitable for embedded computer vision applications in security systems, human-computer interaction and intelligent environments. Our system is suitable for embedded computer vision application based on three reasons. Firstly, the system was based on a linear Support Vector Machine (SVM) classifier where classification progress can be implemented easily and quickly in embedded hardware. Secondly, we use compacted motion features easily obtained from videos. We address the limitations of the well known Motion History Image (MHI) and propose a new Hierarchical Motion History Histogram (HMHH) feature to represent the motion information. HMHH not only provides rich motion information, but also remains computationally inexpensive. Finally, we combine MHI and HMHH together and extract a low dimension feature vector to be used in the SVM classifiers. Experimental results show that our system achieves significant improvement on the recognition performance.",

keywords = "CLASSIFIER",

author = "Hongying Meng and Nick Pears and Chris Bailey",

year = "2007",

language = "English",

isbn = "978-1-4244-1179-5",

pages = "3213--3218",

booktitle = "2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8",

publisher = "IEEE",

address = "United States",

note = "IEEE Conference on Computer Vision and Pattern Recognition ; Conference date: 17-06-2007 Through 22-06-2007",

}

TY - GEN

T1 - A human action recognition system for embedded computer vision application

AU - Meng, Hongying

AU - Pears, Nick

AU - Bailey, Chris

PY - 2007

Y1 - 2007

N2 - In this paper, we propose a human action recognition system suitable for embedded computer vision applications in security systems, human-computer interaction and intelligent environments. Our system is suitable for embedded computer vision application based on three reasons. Firstly, the system was based on a linear Support Vector Machine (SVM) classifier where classification progress can be implemented easily and quickly in embedded hardware. Secondly, we use compacted motion features easily obtained from videos. We address the limitations of the well known Motion History Image (MHI) and propose a new Hierarchical Motion History Histogram (HMHH) feature to represent the motion information. HMHH not only provides rich motion information, but also remains computationally inexpensive. Finally, we combine MHI and HMHH together and extract a low dimension feature vector to be used in the SVM classifiers. Experimental results show that our system achieves significant improvement on the recognition performance.

AB - In this paper, we propose a human action recognition system suitable for embedded computer vision applications in security systems, human-computer interaction and intelligent environments. Our system is suitable for embedded computer vision application based on three reasons. Firstly, the system was based on a linear Support Vector Machine (SVM) classifier where classification progress can be implemented easily and quickly in embedded hardware. Secondly, we use compacted motion features easily obtained from videos. We address the limitations of the well known Motion History Image (MHI) and propose a new Hierarchical Motion History Histogram (HMHH) feature to represent the motion information. HMHH not only provides rich motion information, but also remains computationally inexpensive. Finally, we combine MHI and HMHH together and extract a low dimension feature vector to be used in the SVM classifiers. Experimental results show that our system achieves significant improvement on the recognition performance.

KW - CLASSIFIER

M3 - Conference contribution

SN - 978-1-4244-1179-5

SP - 3213

EP - 3218

BT - 2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8

PB - IEEE

CY - NEW YORK

T2 - IEEE Conference on Computer Vision and Pattern Recognition

Y2 - 17 June 2007 through 22 June 2007

ER -