This paper describes a real-time system developedfor the derivation of low-level visual cues targeted atthe recognition of simple hand, head and bodygestures. A novel, adaptive background subtractiontechnique is presented together with a tool formonitoring repetitive movements, e.g. fidgeting.To monitor subtle body movements in anunconstrained environment, active cameras with pan,tilt and zoom capabilities must be employed to track anindividual`s actions more closely. This paper thenexplores a means of detecting small and large scalehuman activity within images produced from activecameras that may be reoriented during monitoring.
Towards Automatic Body Language Annotation
Chippendale, Paul Ian
2006-01-01
Abstract
This paper describes a real-time system developedfor the derivation of low-level visual cues targeted atthe recognition of simple hand, head and bodygestures. A novel, adaptive background subtractiontechnique is presented together with a tool formonitoring repetitive movements, e.g. fidgeting.To monitor subtle body movements in anunconstrained environment, active cameras with pan,tilt and zoom capabilities must be employed to track anindividual`s actions more closely. This paper thenexplores a means of detecting small and large scalehuman activity within images produced from activecameras that may be reoriented during monitoring.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.