Cisco Technology, Inc.

Muybridge As

Tandberg Telecom As

Cisco Systems International S.a.r.l.

Espen Christensen

Hallgrim Sagen

Geir Sandbakken

Nicolai Grødum

Nicolai Grodum

Snorre Kjesbu

Norma Lovhaugen

Vegard Nitter Vestad

Norma LØVHAUGEN

Geir Arne Sandbakken

The present invention provides a system and method for utilizing multiple camera systems for extracting obstructing objects or foreground close to primary camera(s) and filling in the unknown area using pixel information obtained from multiple cameras, i.e. synthesized images where foreground obstructions are removed is provided. This is done by using a primary camera capturing a target scene in the background, obstructed by foreground, and secondary cameras with viewpoints different from the primary camera provide coverage of the scene behind the foreground obstructions. A processing unit will synthesize the image from the primary camera by replacing foreground obstructions with pixels from secondary cameras, or a combination of both to obtain a transparent obstructing object with the background visible through the object. The area to be replaced is identified by calculating depths in the captured area of the primary camera, estimated by comparing images from multiple cameras.

Method for extracting obstructing objects from an image captured in a multiple camera system

The present invention relates to video conferencing and multimedia messaging, and takes advantage of the capabilities of the communication system to which the audio participants are connected, in order to increase the performance of all the participants in a mixed conference. In a preferred embodiment, the audio participants are provided with a MMS device, and a MMS Engine captures periodically, or at certain events, video conference data attached to MMS messages and addressed to the MMS device. In the opposite direction, the MMS device provides multimedia data to the conventional video conference participants by attaching the multimedia data to MMS messages, which are sent to the IP-addressable MMS Engine. The MMS Engine separates the multimedia data and converts it to a format compatible with the video conference. The converted multimedia data is then provided to video conference participants, and treated like any other multimedia stream included in the video conference.

Enhanced multimedia capabilities in video conferencing

The present invention provides a system and a method making an archived conference or presentation searchable after being stored in the archive server. According to the invention, one or more media streams coded according to H.323 or SIP are transmitted to a conversion engine for converting multimedia content into a standard streaming format, which may be a cluster of files, each representing a certain medium (audio, video, data) and/or a structure file that synchronizes and associates the different media together. When the conversion is carried out, the structure file is copied and forwarded to a post-processing server. The post-processing server includes i.a. a speech recognition engine generating a text file of alphanumeric characters representing all recognized words in the audio file. The text file is then entered into the cluster of files associating each identified word to a timing tag in the structure file. After this post-processing, finding key words and associated points of time in the media stream could easily be executed by a conventional search engine.

Searchable multimedia stream

Growing community of inventors

Oslo, Norway

Espen Christensen