Novelty Detection from an Ego-centric Perspective

This paper demonstrates a system for the automatic ex-traction of novelty in images captured from a small video camera attached to a subject’s chest, replicating his visual perspective, while performing activities which are repeated daily. Novelty is detected when a (sub)sequence cannot be registered to previously stored sequences captured while performing the same daily activity. Sequence registration is performed by measuring appearance and geometric simi-larity of individual frames and exploiting the invariant tem-poral order of the activity. Experimental results demon-strate that this is a robust way to detect novelties induced by variations in the wearer’s ego-motion such as stopping and talking to a person. This is an essentially new and generic way of automatically extracting information of interest to the camera wearer and can be used as input to a system for life logging or memory support. 1