System and method of predicting field of view for immersive video streaming

Abstract

Aspects of the subject disclosure may include, for example, a process that analyzes image content of an immersive video frame and identifies a first group of segments of the immersive video frame based on the analysis. The segments collectively span an entire space portrayed by the immersive video frame and the first group of segments spans less than the entire space. A size of a display region of an immersive video viewer is determined that spans less than the entire space and a second group of segments is determined based on the first group of segments and the size of the display region. Transport of the second group of segments, spanning less than the entire space, is facilitated via a communication network to the immersive video viewer for presentation, without requiring transmission of all of the segments. Other embodiments are disclosed.

What is claimed is: 
     
         1 . A device, comprising:
 a processing system including a processor; and   a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:   predicting a future field-of-view of an immersive video viewer at a future time, wherein the future field-of-view spans less than an entire image space portrayed by an immersive video frame of a sequence of immersive video frames;   identifying a first group of segments of a plurality of segments of the sequence of immersive video frames, the first group of segments being predicted to be at least partially in the future field-of-view, wherein the first group of segments span less than the entire image space portrayed by the immersive video frame;   identifying a second group of segments of the plurality of segments of the sequence of immersive video frames, the second group of segments being predicted to be at least partially outside the future field-of-view, wherein the second group of segments span less than the entire image space portrayed by the immersive video frame; and   facilitating, via a communication network, transport of the first group of segments to the immersive video viewer at a first quality and transport of the second group of segments to the immersive video viewer at a second quality, wherein the second quality is less than the first quality.   
     
     
         2 . The device of  claim 1 , wherein the operations further comprise:
 applying image processing to image content of the plurality of segments; and   identifying, by the processing system, an object portrayed in the image content based on the image processing.   
     
     
         3 . The device of  claim 2 , wherein the identifying the first group of segments comprises identifying the first group of segments as segments of the plurality of segments that include a portion of the object. 
     
     
         4 . The device of  claim 1 , wherein the operations further comprise:
 obtaining heat-map data indicating viewing frequencies of sub-regions of the sequence of immersive video frames.   
     
     
         5 . The device of  claim 4 , wherein the predicting the future field-of-view comprises predicting the future field-of-view within the sequence of immersive video frames based on the heat-map data. 
     
     
         6 . The device of  claim 1 , wherein the identifying the first group of segments further comprises:
 determining an overlap of the future field-of-view and the first group of segments, wherein the first group of segments spans the future field-of-view in its entirety, while spanning less than the entire image space portrayed by the sequence of immersive video frames.   
     
     
         7 . The device of  claim 1 , wherein the first group of segments and the second group of segments are non-overlapping. 
     
     
         8 . The device of  claim 1 , wherein the first group of segments and the second group of segments are overlapping. 
     
     
         9 . The device of  claim 1 , wherein the future field-of-view is based on an estimate of an orientation of the immersive video viewer, and wherein the operations further comprise:
 predicting the orientation of the immersive video viewer to obtain a prediction, wherein the estimate of the orientation of the immersive video viewer is based on the prediction of the orientation of the immersive video viewer.   
     
     
         10 . The device of  claim 1 , wherein the operations further comprise:
 identifying an identity of a user of the immersive video viewer; and   determining a viewer characteristic based on the identity of the user of the immersive video viewer, wherein the identifying the first group of segments is further based on the viewer characteristic.   
     
     
         11 . The device of  claim 10 , wherein the determining of the future field-of-view is based on the viewer characteristic. 
     
     
         12 . The device of  claim 10 , wherein the determining of the viewer characteristic further comprises: accessing a user profile associated with the identity of the user. 
     
     
         13 . A non-transitory, machine-readable storage medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
 predicting a future field-of-view of an immersive video viewer at a future time, wherein the future field-of-view spans less than an entire image space portrayed by an immersive video frame of a sequence of immersive video frames;   identifying a first group of segments of a plurality of segments of the sequence of immersive video frames, the first group of segments being predicted to be at least partially in the future field-of-view, wherein the first group of segments span less than the entire image space portrayed by the immersive video frame;   identifying a second group of segments of the plurality of segments of the sequence of immersive video frames, the second group of segments being predicted to be at least partially outside the future field-of-view, wherein the second group of segments span less than the entire image space portrayed by the immersive video frame; and   facilitating, via a communication network, transport of the first group of segments to the immersive video viewer at a first quality and transport of the second group of segments to the immersive video viewer at a second quality, wherein the second quality is less than the first quality.   
     
     
         14 . The non-transitory, machine-readable storage medium of  claim 13 , wherein the operations further comprise:
 applying image processing to image content of the plurality of segments; and   identifying, by the processing system, an object portrayed in the image content based on the image processing.   
     
     
         15 . The non-transitory, machine-readable storage medium of  claim 14 , wherein the identifying the first group of segments comprises identifying the first group of segments as segments of the plurality of segments that include a portion of the object. 
     
     
         16 . The non-transitory, machine-readable storage medium of  claim 13 , wherein the operations further comprise:
 obtaining heat-map data indicating viewing frequencies of sub-regions of the sequence of immersive video frames.   
     
     
         17 . The non-transitory, machine-readable storage medium of  claim 16 , wherein the predicting the future field-of-view comprises predicting the future field-of-view within the sequence of immersive video frames based on the heat-map data. 
     
     
         18 . A method, comprising:
 predicting, by a processing system including a processor, a future field-of-view of an immersive video viewer at a future time, wherein the future field-of-view spans less than an entire image space portrayed by an immersive video frame of a sequence of immersive video frames;   identifying, by the processing system, a first group of segments of a plurality of segments of the sequence of immersive video frames, the first group of segments being predicted to be at least partially in the future field-of-view, wherein the first group of segments span less than the entire image space portrayed by the immersive video frame;   identifying, by the processing system, a second group of segments of the plurality of segments of the sequence of immersive video frames, the second group of segments being predicted to be at least partially outside the future field-of-view, wherein the second group of segments span less than the entire image space portrayed by the immersive video frame; and   facilitating, by the processing system, via a communication network, transport of the first group of segments to the immersive video viewer at a first quality and transport of the second group of segments to the immersive video viewer at a second quality, wherein the second quality is less than the first quality.   
     
     
         19 . The method of  claim 18 , further comprising:
 applying, by the processing system, image processing to image content of the sequence of immersive video frames; and   identifying, by the processing system, an object portrayed in the image content based on the image processing.   
     
     
         20 . The method of  claim 19 , wherein the identifying of the first group of segments further comprises: determining a portion of the object is portrayed.