Optical flow and sensor input based background subtraction in video content

An image-processing system, comprising:

• one or more processors in an imaging device configured to:
• compute a plurality of first motion vector values for a plurality of pixels in a current image frame with respect to a previous image frame using an optical flow map;
• compute a plurality of second motion vector values for said plurality of pixels in said current image frame based on an input received from a sensor provided in said imaging device;
• determine a confidence score for said plurality of first motion vector values based on a set of defined parameters;
• extract one or more background regions from said current image frame based on said determined confidence score and a similarity parameter between said plurality of first motion vector values and said plurality of second motion vector values;
• and
• detect one or more objects-of-interest in said current image frame based on said extracted one or more background regions.

A method for image processing, said method comprising:

• in an apparatus that is configured to handle a sequence of image frames:
• computing a plurality of first motion vector values for a plurality of pixels in a current image frame with respect to a previous image frame using an optical flow map;
• computing a plurality of second motion vector values for said plurality of pixels in said current image frame based on an input received from a sensor;
• determining a confidence score for said plurality of first motion vector values based on a set of defined parameters;
• and
• extracting one or more background regions in said current image frame based on said determined confidence score and a similarity parameter between said plurality of first motion vector values and said plurality of second motion vector values.