Alcatel Lucent

Mihai Fagadar-Cosma

Moulay Fadili

Miguel Casas-Sanchez

Paul Henrys D'Aubigny D'Esmyards

A video conferencing server () receives and combines video streams captured by cameras of plural video clients () and generates immersive video streams () for delivery to and play-out by these video clients (). A cut-out module () in the video conferencing server () generates a foreground mask () for a video frame () received from a conferencing client (). A camera shake detector () determines a displacement vector () for a subset of features in the video frame (). The displacement vector () represents a two-dimensional motion of the subset of features between a background mask and a previous background mask for a previous video frame received from the same conferencing client (). A camera shake correcting module () applies a displacement opposite to the displacement vector () to the foreground mask () before use thereof in the immersive video streams () for conferencing clients (), and a signalling unit () generates a shake indication () into the immersive video stream () delivered to the conferencing client () whose camera is shaking.

Videoconferencing server with camera shake detection

The present invention relates to a method for control of a video interface () associated to a user () for use in conference situations and the like, comprising the steps of capturing a frame () of a video stream originated from the user (), recognizing a face () of the user () within the video frame (), detecting an orientation of the face () of the user () within the video frame (), and providing a control signal indicating the orientation of the face (). The invention also relates to a method for operation of the video interface () comprising the steps of the above control method, mapping the orientation of the face () based on the control signal to a focus area () of the video interface (), and highlighting the focus area (). The invention further relates to a face orientation detector () and a video conferencing server (), which are adapted to perform the above methods.

Method for control of a video interface, method for operation of a video interface, face orientation detector, and video conferencing server

The present invention relates to a method for recognizing gestures within a two-dimensional video stream for use in conference situations and the like, comprising the step of performing a skin-recognition within a screen of the video stream for recognizing skin parts, identifying at least one body part within the recognized skin parts, monitoring a state of at least one predefined screen area in respect to the at least one body part, and providing a control signal indicating a detected gesture upon detection of a change of state. The present invention further relates to a gesture detector adapted to perform the above method, a presentation system comprising the above gesture detector and a video camera device comprising a video camera and the above gesture detector.

Growing community of inventors

Antwerp, Belgium

Mihai Fagadar-Cosma