作者: Farzin Aghdasi , Greg Millar , Lei Wang
DOI:
关键词:
摘要: Embodiments of the disclosure provide for systems and methods creating metadata associated with a video data. The can include data about objects viewed within scene and/or events that occur scene. Some embodiments allow users to search specific by searching recorded metadata. In some embodiments, is created receiving frame developing background model frame. Foreground object(s) then be identified in using model. Once these are they classified an event foreground object may detected. classification as