Object of interest based image processing
AssigneeIntel Corporation
InventorsQiang Li, Wenlong Li, Peng Wang, Tao Wang, Yangzhou Du, Jianguo Li
Life of this patent
Estimating the term…
Abstract
Various embodiments of this disclosure may describe apparatuses, methods, and systems including an encoding engine to encode and/or compress one or more objects of interest within individual image frames with higher bit densities than the bit density employed to encode and/or compress their background. The image processing system may further include a context engine to identify a region of interest including at least a part of the one or more objects of interest, and scale the region of interest within individual image frames to emphasize the objects of interest. Other embodiments may also be disclosed or claimed.
Claims18
An apparatus comprising:
- a context engine to:
- receive a plurality of image frames of a video signal;
- analyze the respective image frames;
- identify, based upon the analysis of the respective image frames, a plurality of objects of interest within the respective image frames;
- and
- identify, based on the plurality of objects of interest, a plurality of regions of interest within the respective image frames;
- an encoding engine coupled to the context engine, the encoding engine to:
- adjust, based on a context information, size, position, or scaling of the region of interest to re-center the region of interest within the respective image frames, wherein the context information includes a detection of one or more changes from one or more previous image frames of one of the plurality of objects of interest;
- and
- encode the region associated with the plurality of objects of interest within respective image frames based on one or more bit densities that are higher than a bit density of a background region, wherein the background region surrounds the region associated with the plurality of objects of interest;
- and
- a transmitter coupled to the encoding engine, the transmitter to transmit the encoded plurality of image frames to one or more recipients.
A method comprising:
- receiving a plurality of image frames of a video signal;
- analyzing the respective image frames;
- identifying, based on the analysis, a plurality of objects of interest within the respective image frames;
- identifying a region of interest within the respective image frames associated with the plurality of objects of interest;
- adjusting, based on a context information, size, position, or scaling of the region of interest to re-center the region of interest within the respective image frames, wherein the context information includes a detection of one or more changes from one or more previous image frames of one of the plurality of objects of interest;
- and
- encoding the region of interest associated with a plurality of objects of interest within respective image frames based on one or more bit densities higher than a bit density of a background region, wherein the background region surrounds a plurality of regions of interest associated with the plurality of objects of interest.
A system comprising:
- a camera configured to capture a video signal having a plurality of image frames;
- a context engine coupled to the camera, the context engine to:
- receive the plurality of captured image frames;
- analyze the plurality of captured image frames;
- and
- identify, based on the analysis, a plurality of objects of interest in the respective image frames;
- and
- identify, based on the plurality of objects of interest, a region of interest within the respective image frames;
- an encoding engine operatively coupled to the camera, the encoding engine to:
- adjust, based on a context information, size, position, or scaling of the region of interest to re-center the region of interest within the respective image frames, wherein the context information includes a detection of one or more changes from one or more previous image frames of one of the plurality of objects of interest;
- and
- encode the region of interest associated with the plurality of objects of interest within respective image frames based on one or more bit densities that are higher than a bit density of a background region of the respective image frames, wherein the background region surrounds the plurality of objects of interest;
- and
- a transmitter coupled to the encoding engine, the transmitter to transmit the encoded plurality of image frames to one or more recipients.
An article of manufacture comprising:
- a tangible and non-transitory computer-readable storage medium;
- and
- a plurality of programming instructions stored in the storage medium, and configured to cause an apparatus, in response to execution of the programming instructions, to perform operations including:
- receiving a plurality of image frames of a video signal;
- analyzing the plurality of image frames of the video signal;
- identifying, based on the analysis, a plurality of objects of interest within the respective image frames;
- identifying, based on the plurality of objects of interest, a region of interest within the respective image frames, wherein a context information includes a detection of one or more changes from one or more previous image frames of one of the plurality of objects of interest;
- encoding the region within respective image frames based on one or more bit densities that are higher than a bit density of a background region of the respective image frames, wherein the background region surrounds the region associated with the plurality of objects of interest;
- and
- adjusting, based on the context information, size, position, or scaling of the region of interest to re-center the region of interest within the respective image frames, wherein the context information includes an orientation of one of the plurality of objects of interest.
Dependencies are inferred from the claim text.