Method and system for enhancing authenticity detail of captured video
AssigneeMotorola Solutions, Inc.
InventorsANDRZEJ GRZESIK, RAMIL GALIEW
Life of this patent
Estimating the term…
Abstract
A method and system for enhancing authenticity detail of captured video is disclosed. Objects within a physical environment (and visible within a camera field of view) are captured in video, and by way of video analytics these objects and their respective metadata are employed as part of the method and system for enhancing the authenticity detail of the captured video. Also, rather than the audio/video stream(s) being modified, the actual video scene itself may be modified.
Claims16
A computer-implemented method to enhance authenticity detail of video captured by a first camera having a first Field Of View (FOV), the computer-implemented method comprising:
- repeatedly carrying out the following over a period of time:
- generating, during a respective sub-interval of a plurality of sub-intervals of the period of time, a data structure that is a combination of:
- at least one of timestamping data and a sequence number unique to the respective sub-interval of the period of time, and
- aggregated metadata of a plurality of different objects visible within the first FOV,
- signing the data structure with a private key, and
- generating, from the signed data structure, a portion of a dynamically changing code for the respective sub-interval of the period of time;
- sequentially introducing the portions of the dynamically changing code within the first FOV to be visibly perceived therein;
- and
- operating the first camera to capture the video within which is shown the dynamically changing code and the different objects.
A computer-implemented method to enhance authenticity detail of video captured by a first camera having a first Field Of View (FOV), the first camera also including or being locally coupled to a microphone, and the computer-implemented method comprising:
- repeatedly carrying out the following over a period of time:
- generating, during a respective sub-interval of a plurality of sub-intervals of the period of time, a data structure that is a combination of:
- at least one of timestamping data and a sequence number unique to the respective sub-interval of the period of time, and
- aggregated metadata of a plurality of different objects visible within the first FOV,
- signing the data structure with a private key, and
- generating, from the signed data structure, a portion of a dynamically changing code for the respective sub-interval of the period of time;
- sequentially introducing the portions of the dynamically changing code by production of data-over-sound sufficiently loud to be captured by the microphone;
- and
- concurrently with capturing of the data-over-sound by the microphone, operating the first camera to capture the video within which is shown the different objects, and
- wherein the video captured by the first camera includes the data-over sound as part of a sound track of the video.
A system comprising:
- at least one processor configured to repeatedly carry out the following over a period of time:
- generate, during a respective sub-interval of a plurality of sub-intervals of the period of time, a data structure that is a combination of:
- at least one of timestamping data and a sequence number unique to the respective sub-interval of the period of time, and
- aggregated metadata of a plurality of different objects visible within a camera FOV,
- sign the data structure with a private key, and
- generate, from the signed data structure, a portion of a dynamically changing code for the respective sub-interval of the period of time;
- and
- an electronic projector or an electronic display configured to sequentially introduce the portions of the dynamically changing code within the camera FOV to be visibly perceived therein.
Dependencies are inferred from the claim text.