Methods and systems for auto-zoom based adaptive video streaming

An apparatus comprising:

• a memory configured to store video data;
• and
• a processor configured to:
• obtain a tracking video stream, the tracking video stream having a first resolution, wherein the tracking video stream is used to define one or more regions of interest for one or more frames of the tracking video stream;
• obtain a target video stream, the target video stream having a second resolution, wherein the second resolution is a higher resolution than the first resolution;
• process the target video stream to generate a zoomed-in region of one or more frames of the target video stream, wherein the zoomed-in region corresponds to a region of interest defined using the tracking video stream;
• and
• provide the zoomed-in region of the one or more frames of the target video stream for display.

A computer readable medium having stored thereon instructions that when executed by a processor perform a method, comprising:

• obtaining a tracking video stream, the tracking video stream having a first resolution, wherein the tracking video stream is used to define one or more regions of interest for one or more frames of the tracking video stream;
• obtaining a target video stream, the target video stream having a second resolution, wherein the second resolution is a higher resolution than the first resolution;
• processing the target video stream to generate a zoomed-in region of one or more frames of the target video stream, wherein the zoomed-in region corresponds to a region of interest defined using the tracking video stream;
• and
• providing the zoomed-in region of the one or more frames of the target video stream for display.