This paper presents an approach for human activity recognition by representing the frames of the video sequence with the distribution of local motion features and their spatiotemp...
Video surveillance systems produce huge amounts of data for storage and display. Long-term human monitoring of the acquired video is impractical and ineffective. Automatic abnorma...
Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and man...
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
This paper deals with video segmentation based on motion and spatial information. Classically, the motion term is based on a motion compensation error (MCE) between two consecutiv...
Sylvain Boltz, Ariane Herbulot, Eric Debreuve, Mic...