| Revision as of 20:30, 29 April 2015 view sourceWikiDan61 (talk | contribs)Extended confirmed users, New page reviewers, Pending changes reviewers103,106 edits Cleanup. Fixed infobox. Removed "Use Cases" (that can only be considered marketing).← Previous edit | Revision as of 20:34, 29 April 2015 view source Papagreg32 (talk | contribs)51 editsNo edit summaryNext edit → | ||
| Line 15: | Line 15: | ||
| == Metadata == | == Metadata == | ||
| Vu Digital's service uses predictive analytics, ], ], object recognition, and audio/image detection to extract ] from video including transcripts of the audio, and time-tagged references to screen text and appearances of persons or images of interest, such as objects or logos. | Vu Digital's service uses predictive analytics, ], ], object recognition, and audio/image detection to extract ] from video including transcripts of the audio, and time-tagged references to screen text and appearances of persons or images of interest, such as objects or logos. The core technology includes splitting a video into two components, audio and the video frames. Both components are then processed using speech-to-text transcription, text extraction from images, facial recognition and image recognition. The output is not only the transcript of the video and image frames, but metadata that is timestamped with frame references. For example, if a brand logo is found an hour and a half into a video, the metadata would include that time reference a 01:30. With this technological approach video classification/clustering, search engine indexing, and personalization for content, including targeted advertisements are possible. | ||
| == Technologies and patents == | == Technologies and patents == | ||
Revision as of 20:34, 29 April 2015
 | This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages)
|
| Industry | Video Analytics |
|---|---|
| Founded | 2013 |
| Key people |
|
| Products | Video-to-Data (V2D) |
| Services | Video Analytics and Metadata extraction |
Vu Digital LLC is a cloud-based service provider of video analytics and metadata extraction formed in 2013. It is an affiliate of C Spire Wireless, with between 1-10 employees.
Metadata
Vu Digital's service uses predictive analytics, natural language processing, face recognition, object recognition, and audio/image detection to extract metadata from video including transcripts of the audio, and time-tagged references to screen text and appearances of persons or images of interest, such as objects or logos. The core technology includes splitting a video into two components, audio and the video frames. Both components are then processed using speech-to-text transcription, text extraction from images, facial recognition and image recognition. The output is not only the transcript of the video and image frames, but metadata that is timestamped with frame references. For example, if a brand logo is found an hour and a half into a video, the metadata would include that time reference a 01:30. With this technological approach video classification/clustering, search engine indexing, and personalization for content, including targeted advertisements are possible.
Technologies and patents
Vu Video-to-Data (V2D) translates video images and audio to text, affording video producers the ability to tag their content with metadata making it more searchable. Vu Digital has patents pending for Video-to-Data & Vu Finder.