Method, device, and system for adaptive training of machine learning models via detected in-field contextual sensor events and associated located and retrieved digital audio and/or video imaging
US10354169B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 22, 2017 |
| Grant date | Jul 16, 2019 |
| Priority date | — |
| Expiry date | Mar 13, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/44
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Receive first context information including sensor information values from in-field sensors and a time associated with a capture of the first context information. Access a context to detectable event mapping that maps sets of sensor information values to events and identify a particular event associated with the received first context information. Determine a geographic location associated with the in-field sensors and access an imaging camera location database and identify particular imaging cameras that have a field of view including the determined geographic location during the time associated with the capture of the first context information. Retrieve audio and/or video streams captured by the particular imaging cameras, identify machine learning training modules corresponding to machine learning models for detecting the particular event in audio and/or video streams, and provide the audio and/or video streams to the machine learning training modules for further training of the corresponding machine learning models.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.