Service Communautaire d'Information sur la Recherche et le Développement - CORDIS

Human action recognition and segmentation

Methods have been developed that takes as input video sequences depicting a human action with a specific limited repertoire. Based on spatial and spatiotemporal data the sequence in segmented into frames or blocks of frames containing similar actions. An example of this is the segmentation of a sequence of tennis playing into elementary strokes. The methods will allow for automatic editing of long video sequences and extraction of user specified information. This and other applications are being pursued by the partners.

Reported by

reserach dept.
100 44 Stockholm