HMM-based segmentation and recognition of human activities from video sequences

Feng Niu; Mohamed Abdel-Mottaleb

doi:10.1109/ICME.2005.1521545

HMM-based segmentation and recognition of human activities from video sequences

Feng Niu, Mohamed Abdel-Mottaleb

Electrical and Computer Engineering

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

57 Scopus citations

Abstract

Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous work on activity recognition focuses on recognition from video clips that show only single activities. There are few published algorithms for segmenting and recognizing complex activities that are composed of more than one single activity. In this paper, we present a novel HMM-based approach that uses threshold and voting to automatically and effectively segment and recognize complex activities. Experiments on a database of video clips of different activities show that our method is effective.

Original language	English
Title of host publication	IEEE International Conference on Multimedia and Expo, ICME 2005
Pages	804-807
Number of pages	4
Volume	2005
DOIs	https://doi.org/10.1109/ICME.2005.1521545
State	Published - Dec 1 2005
Event	IEEE International Conference on Multimedia and Expo, ICME 2005 - Amsterdam, Netherlands Duration: Jul 6 2005 → Jul 8 2005

Other

Other	IEEE International Conference on Multimedia and Expo, ICME 2005
Country	Netherlands
City	Amsterdam
Period	7/6/05 → 7/8/05

Fingerprint

ASJC Scopus subject areas

Engineering(all)

Cite this

Niu, F., & Abdel-Mottaleb, M. (2005). HMM-based segmentation and recognition of human activities from video sequences. In IEEE International Conference on Multimedia and Expo, ICME 2005 (Vol. 2005, pp. 804-807). [1521545] https://doi.org/10.1109/ICME.2005.1521545

@inproceedings{8f2625b4ece548189402d780b2f71e07,

title = "HMM-based segmentation and recognition of human activities from video sequences",

abstract = "Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous work on activity recognition focuses on recognition from video clips that show only single activities. There are few published algorithms for segmenting and recognizing complex activities that are composed of more than one single activity. In this paper, we present a novel HMM-based approach that uses threshold and voting to automatically and effectively segment and recognize complex activities. Experiments on a database of video clips of different activities show that our method is effective.",

author = "Feng Niu and Mohamed Abdel-Mottaleb",

year = "2005",

month = dec

day = "1",

doi = "10.1109/ICME.2005.1521545",

language = "English",

isbn = "0780393325",

volume = "2005",

pages = "804--807",

booktitle = "IEEE International Conference on Multimedia and Expo, ICME 2005",

note = "null ; Conference date: 06-07-2005 Through 08-07-2005",

}

TY - GEN

T1 - HMM-based segmentation and recognition of human activities from video sequences

AU - Niu, Feng

AU - Abdel-Mottaleb, Mohamed

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous work on activity recognition focuses on recognition from video clips that show only single activities. There are few published algorithms for segmenting and recognizing complex activities that are composed of more than one single activity. In this paper, we present a novel HMM-based approach that uses threshold and voting to automatically and effectively segment and recognize complex activities. Experiments on a database of video clips of different activities show that our method is effective.

AB - Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous work on activity recognition focuses on recognition from video clips that show only single activities. There are few published algorithms for segmenting and recognizing complex activities that are composed of more than one single activity. In this paper, we present a novel HMM-based approach that uses threshold and voting to automatically and effectively segment and recognize complex activities. Experiments on a database of video clips of different activities show that our method is effective.

UR - http://www.scopus.com/inward/record.url?scp=33750537020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750537020&partnerID=8YFLogxK

U2 - 10.1109/ICME.2005.1521545

DO - 10.1109/ICME.2005.1521545

M3 - Conference contribution

AN - SCOPUS:33750537020

SN - 0780393325

SN - 9780780393325

VL - 2005

SP - 804

EP - 807

BT - IEEE International Conference on Multimedia and Expo, ICME 2005

Y2 - 6 July 2005 through 8 July 2005

ER -

Access to Document

10.1109/ICME.2005.1521545