Understanding of human behaviors from videos in nursing care monitoring systems

Chin De Liu, Pau Choo Chung, Yi Nung Chung, Monique Thonnat

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This paper addresses the issue in scenario-based understanding of human behavior from videos in a nursing care monitoring system. The analysis is carried out based on experiments consisting of single-state scenarios and multi-state scenarios where the former monitors activities under contextual contexts for elementary behavior reasoning, while the latter dictating the elementary behavior order for behavior reasoning, with a priori knowledge in system profile for normality detection. By integrating the activities, situation context, and profile knowledge we can have a better understanding of patients in a monitoring system. In activity recognition, a Negation-Selection mechanism is developed. which employs a divide-and-conquer concept with the Negation using posture transition to preclude the negative set from the activities. The Selection that follows the Negation uses a moving history trace for activity recognition. Such a history trace composes not only the pose from single frame, but also history trajectory information. As a result, the activity can be more accurately identified. The developed approach has been established into a nursing care monitoring system for elder's daily life behaviors. Results have shown the promise of the approach which can accurately interpret 85% of the regular daily behavior. In addition, the approach is also applied to accident detection which was found to have 90% accuracy with 0% false alarm.

Original languageEnglish
Pages (from-to)91-103
Number of pages13
JournalJournal of High Speed Networks
Volume16
Issue number1
Publication statusPublished - 2007 Mar 8

Fingerprint

Nursing
Monitoring
Accidents
Trajectories
Experiments

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Liu, Chin De ; Chung, Pau Choo ; Chung, Yi Nung ; Thonnat, Monique. / Understanding of human behaviors from videos in nursing care monitoring systems. In: Journal of High Speed Networks. 2007 ; Vol. 16, No. 1. pp. 91-103.
@article{d876f7ff45fa4b9b81f14e938fafba4a,
title = "Understanding of human behaviors from videos in nursing care monitoring systems",
abstract = "This paper addresses the issue in scenario-based understanding of human behavior from videos in a nursing care monitoring system. The analysis is carried out based on experiments consisting of single-state scenarios and multi-state scenarios where the former monitors activities under contextual contexts for elementary behavior reasoning, while the latter dictating the elementary behavior order for behavior reasoning, with a priori knowledge in system profile for normality detection. By integrating the activities, situation context, and profile knowledge we can have a better understanding of patients in a monitoring system. In activity recognition, a Negation-Selection mechanism is developed. which employs a divide-and-conquer concept with the Negation using posture transition to preclude the negative set from the activities. The Selection that follows the Negation uses a moving history trace for activity recognition. Such a history trace composes not only the pose from single frame, but also history trajectory information. As a result, the activity can be more accurately identified. The developed approach has been established into a nursing care monitoring system for elder's daily life behaviors. Results have shown the promise of the approach which can accurately interpret 85{\%} of the regular daily behavior. In addition, the approach is also applied to accident detection which was found to have 90{\%} accuracy with 0{\%} false alarm.",
author = "Liu, {Chin De} and Chung, {Pau Choo} and Chung, {Yi Nung} and Monique Thonnat",
year = "2007",
month = "3",
day = "8",
language = "English",
volume = "16",
pages = "91--103",
journal = "Journal of High Speed Networks",
issn = "0926-6801",
publisher = "IOS Press",
number = "1",

}

Understanding of human behaviors from videos in nursing care monitoring systems. / Liu, Chin De; Chung, Pau Choo; Chung, Yi Nung; Thonnat, Monique.

In: Journal of High Speed Networks, Vol. 16, No. 1, 08.03.2007, p. 91-103.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Understanding of human behaviors from videos in nursing care monitoring systems

AU - Liu, Chin De

AU - Chung, Pau Choo

AU - Chung, Yi Nung

AU - Thonnat, Monique

PY - 2007/3/8

Y1 - 2007/3/8

N2 - This paper addresses the issue in scenario-based understanding of human behavior from videos in a nursing care monitoring system. The analysis is carried out based on experiments consisting of single-state scenarios and multi-state scenarios where the former monitors activities under contextual contexts for elementary behavior reasoning, while the latter dictating the elementary behavior order for behavior reasoning, with a priori knowledge in system profile for normality detection. By integrating the activities, situation context, and profile knowledge we can have a better understanding of patients in a monitoring system. In activity recognition, a Negation-Selection mechanism is developed. which employs a divide-and-conquer concept with the Negation using posture transition to preclude the negative set from the activities. The Selection that follows the Negation uses a moving history trace for activity recognition. Such a history trace composes not only the pose from single frame, but also history trajectory information. As a result, the activity can be more accurately identified. The developed approach has been established into a nursing care monitoring system for elder's daily life behaviors. Results have shown the promise of the approach which can accurately interpret 85% of the regular daily behavior. In addition, the approach is also applied to accident detection which was found to have 90% accuracy with 0% false alarm.

AB - This paper addresses the issue in scenario-based understanding of human behavior from videos in a nursing care monitoring system. The analysis is carried out based on experiments consisting of single-state scenarios and multi-state scenarios where the former monitors activities under contextual contexts for elementary behavior reasoning, while the latter dictating the elementary behavior order for behavior reasoning, with a priori knowledge in system profile for normality detection. By integrating the activities, situation context, and profile knowledge we can have a better understanding of patients in a monitoring system. In activity recognition, a Negation-Selection mechanism is developed. which employs a divide-and-conquer concept with the Negation using posture transition to preclude the negative set from the activities. The Selection that follows the Negation uses a moving history trace for activity recognition. Such a history trace composes not only the pose from single frame, but also history trajectory information. As a result, the activity can be more accurately identified. The developed approach has been established into a nursing care monitoring system for elder's daily life behaviors. Results have shown the promise of the approach which can accurately interpret 85% of the regular daily behavior. In addition, the approach is also applied to accident detection which was found to have 90% accuracy with 0% false alarm.

UR - http://www.scopus.com/inward/record.url?scp=33847352566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847352566&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33847352566

VL - 16

SP - 91

EP - 103

JO - Journal of High Speed Networks

JF - Journal of High Speed Networks

SN - 0926-6801

IS - 1

ER -