Method and system for profiling a reference image and an object-of-interest therewithin
AssigneeMotorola Solutions, Inc.
InventorsYIN WANG, EUAN BRODIE, LUKASZ OSUCH
Life of this patent
Estimating the term…
Abstract
A method and system for profiling a reference image and an object-of-interest therewithin is disclosed. The method includes storing semantic metadata that provides semantic information about environments for respective areas covered by respective Fields Of View (FOVs) of video cameras. The method also includes comparing the semantic metadata to additional metadata corresponding to at least one of an object accessory and a non-permanent object facet to identify a subset of the video cameras, less than an entire video camera universe, that meet a similarity score condition.
Claims20
A computer-implemented method comprising:
- in relation to a plurality of video cameras within a video camera universe, storing semantic metadata that provides semantic information about environments for respective areas covered by respective Fields Of View (FOVs) of the video cameras;
- detecting and recognizing at least one of an object accessory and a non-permanent object facet possessed by an object-of-interest within at least one reference image;
- comparing the semantic metadata to additional metadata corresponding to the at least one of the object accessory and the non-permanent object facet to identify a subset of the video cameras, less than the entire video camera universe, that meet a similarity score condition;
- and
- after the subset of the video cameras is identified, creating or modifying an analytics criteria or analytics prioritization to be applied to the subset of the video cameras.
A system comprising:
- a plurality of video cameras belonging to a video camera universe;
- and
- at least one processor communicatively coupled to the video cameras and configured to:
- store semantic metadata in relation to the video cameras, the semantic metadata providing semantic information about environments for respective areas covered by respective Fields Of View (FOVs) of the video cameras;
- detect and recognize at least one of an object accessory and a non-permanent object facet possessed by an object-of-interest within at least one reference image;
- compare the semantic metadata to additional metadata corresponding to the at least one of the object accessory and the non-permanent object facet to identify a subset of the video cameras, less than the entire video camera universe, that meet a similarity score condition;
- and
- after the subset of the video cameras is identified, create or modify an analytics criteria or analytics prioritization to be applied to the subset of the video cameras.
Dependencies are inferred from the claim text.