Human Activity Recognition in Smart Environments

Author

Dragan, Monica-Andreea ; Mocanu, Irina

Author_Institution

Comput. Sci. Dept., Univ. Politeh. of Bucharest, Bucharest, Romania

fYear

2013

fDate

29-31 May 2013

Firstpage

495

Lastpage

502

Abstract

This paper presents a method for image based human activity recognition, in a smart environment. We use background subtraction and skeletisation as image processing techniques, combined with Artificial Neural Networks for human posture classification and Hidden Markov Models for activity interpretation. By this approach we successfully recognized basic human actions such as walking, rotating, sitting and bending up/down, lying and falling. The method can be applied in smart houses, for elderly people who live alone.

Keywords

biomechanics; geriatrics; hidden Markov models; home computing; image classification; image thinning; neural nets; object recognition; activity interpretation; artificial neural networks; background skeletisation; background subtraction; bending down; bending up; elderly people; falling; hidden Markov models; human posture classification; image based human activity recognition; image processing techniques; lying; rotating; sitting; smart environments; smart houses; walking; Analytical models; Artificial neural networks; Cameras; Hidden Markov models; Legged locomotion; Unified modeling language; Activity recognition; Artificial Neural Network; Background subtraction; Hidden Markov Model; Smart environment;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Systems and Computer Science (CSCS), 2013 19th International Conference on

Conference_Location

Bucharest

Print_ISBN

978-1-4673-6140-8

Type

conf

DOI

10.1109/CSCS.2013.78

Filename

6569310