Activity recognition from video data using spatial and temporal features

Mohamad Al-Wattar*, Rinat Khusainov, Djamel Azzi, John Chiverton

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

144 Downloads (Pure)

Abstract

A method to monitor elderly people in an indoor environment using conventional cameras is presented. The method can be used to identify people's activities and initiate suitable actions as needed. The originality of our approach is in combining spatial and temporal contexts with the position and orientation for the detected person. Preliminary evaluation, based only on the first two features (spatial and temporal), achieved the accuracy over 60% in a realistic residential environment. Although the results are based on using only two out of the four proposed input features, they already demonstrate a promising improvement over using a single feature in isolation.

Original languageEnglish
Title of host publication2016 12th International Conference on Intelligent Environments
PublisherIEEE
Pages250-253
Number of pages4
ISBN (Electronic)978-1-5090-4056-8
ISBN (Print)978-1-5090-4057-5
DOIs
Publication statusPublished - 27 Oct 2016
Event12th International Conference on Intelligent Environments - London, United Kingdom
Duration: 14 Sep 201616 Sep 2016

Publication series

Name
ISSN (Electronic)2472-7571

Conference

Conference12th International Conference on Intelligent Environments
Abbreviated titleIE 2016
CountryUnited Kingdom
CityLondon
Period14/09/1616/09/16

Keywords

  • Assisted living
  • Activity recognition
  • Context fusion
  • Temporal and spatial contexts

Fingerprint

Dive into the research topics of 'Activity recognition from video data using spatial and temporal features'. Together they form a unique fingerprint.

Cite this