Region of interest determination in video
AssigneeArm Limited
InventorsYuhao Zhu, Paul Nicholas Whatmough
Life of this patent
Estimating the term…
Abstract
A method of processing a video is provided. The method includes detecting a region of interest in a detection frame of the video. The method includes estimating a motion of the region of interest between the detection frame and an estimation frame of the video subsequent to the detection frame. The estimating is based on tracking of a characteristic of the detected region of interest into at least one portion of the estimation frame. The method includes, based on the estimated motion, estimating a location of the region of interest in the estimation frame. An apparatus for processing a video is also provided. A related non-transitory computer-readable storage medium comprising a set of computer-readable instructions is also provided.
Claims20
A method of processing a video, the method comprising:
- detecting a region of interest in a detection frame of the video;
- estimating a motion of the region of interest across a plurality of frames comprising the detection frame and at least one estimation frame of the video subsequent to the detection frame, wherein, for each of the at least one estimation frame, the estimating is based on tracking of a characteristic of the detected region of interest into at least one portion of the estimation frame;
- determining a confidence level of the estimating the motion of the region of interest between at least one pair of frames of the plurality of frames, wherein the at least one estimation frame comprises a number of estimation frames determined based on the confidence level;
- and
- based on the estimated motion, estimating a location of the region of interest in the at least one estimation frame.
An apparatus for processing a video, the apparatus comprising:
- a detection module configured to detect a region of interest in a detection frame of the video;
- a motion estimation module configured to:
- estimate a motion of the region of interest across a plurality of frames comprising the detection frame and at least one estimation frame of the video subsequent to the detection frame, wherein, for each of the at least one estimation frame, the estimating is based on tracking of a characteristic of the detected region into at least one portion of the estimation frame;
- and
- determine a confidence level of the estimating the motion of the region of interest between at least one pair of frames of the plurality of frames, wherein the at least one estimation frame comprises a number of estimation frames determined based on the confidence level;
- and
- a position estimation module configured to:
- based on the estimated motion between the detection frame and the estimation frame, estimate a location of the region of interest in the at least one estimation frame.
A non-transitory, computer-readable storage medium comprising a set of computer-readable instructions which, when executed by at least one processor, cause the at least one processor to:
- detect a region of interest in a detection frame of the video;
- estimate a motion of the region of interest across a plurality of frames comprising the detection frame and at least one estimation frame of the video subsequent to the detection frame, wherein, for each of the at least one estimation frame, the estimating is based on tracking of a characteristic of the detected region of interest into at least one portion of the estimation frame;
- determine a confidence level of the estimating the motion of the region of interest between at least one pair of frames of the plurality of frames, wherein the at least one estimation frame comprises a number of estimation frames determined based on the confidence level;
- and
- based on the estimated motion, estimate a location of the region of interest in the at least one estimation frame.
Dependencies are inferred from the claim text.