- From: Adam Sobieski <adamsobieski@hotmail.com>
- Date: Mon, 30 Mar 2015 14:24:33 +0000
- To: "public-opengov@w3.org" <public-opengov@w3.org>, "public-egovernance@w3.org" <public-egovernance@w3.org>
- Message-ID: <SNT150-W651512AFD9406C620AE27C5F50@phx.gbl>
Open Government Community Group, Greetings. I would like to present to interested colleagues some information about technology in the overlap of artificial intelligence with meetings, meetings occurring in academia, science, industry and government. The topics presented include the processing of data from arrays of sensors, from which data including pointclouds as well as binaural, surround sound or ambisonic audio are obtained, software technology to obtain photographs or videos from those pointclouds, conveniencing production teams with advanced features. The topics presented can convenience as well as enhance videos from all meetings of people, academia, science, industry as well as the public sector, e.g. the United States federal government, 50 state governments, 19,429 municipal governments. Ten topics are presented: 1. Obtaining 3D data, pointclouds, from multiple sensors, obtaining photographs, video, 3D audio from multiple sensors, including binaural audio, surround sound, ambisonics. 2. Natural language understanding, multiperson speech recognition, multiperson nonverbal gesture recognition. 3. Transcription, keyword generation, enhancing the indexing of video, video segments, video clips. 4. Modeling discourse, modeling debates, modeling meetings, detecting events, categorizing events. 5. Interpreting meetings, interpreting narratives or storyboards from meetings, summarizing meetings, motions of attention during meetings. 6. The virtual cinematography or videography utilizing virtual cameras, the capability to position virtual cameras in space, to adjust virtual camera settings, to move virtual cameras around, to obtain photographs or videos. 7. The capability to, beyond outputting one video stream, output multiple simultaneous multimedia streams, multiple simultaneous virtual cameras, as per multiview video. 8. The processing of photographs from meetings or video cinematography, utilizing photographs, videos as well as pointclouds data. Machine learning from human photographers, videographers. 9. The storage of pointcloud video, archiving of the raw preprocessed 3D data, the indexing, search, retrieval of 3D multimedia content. 10. The summarization of sets of meetings, dashboard summarizations of sets of meetings. Kind regards, Adam Sobieski http://www.phoster.com
Received on Monday, 30 March 2015 14:25:10 UTC