Video engagement determination based on statistical positional object tracking

A method, comprising:

• in an electronic device:
• receiving media content including a set of video frames based on a content playability factor;
• applying a first neural network (NN) model on each video frame of the set of video frames;
• detecting a set of objects included in the each video frame of the set of video frames based on the application of the first NN model;
• receiving a set of images of an audience watching the received media content;
• applying a second NN model on each image of the received set of images of the audience;
• estimating gaze co-ordinates associated with the audience based on the application of the second NN model;
• splitting the each video frame of the set of video frames into a set of segments;
• mapping the estimated gaze co-ordinates to the set of segments of the each video frame of the set of video frames;
• determining an engagement score for each object of the detected set of objects based on the mapping of the estimated gaze co-ordinates;
• and
• rendering, on a display device, the determined engagement score for the each object of the detected set of objects.

A non-transitory computer-readable medium having stored thereon, computer-executable instructions that when executed by an electronic device, causes the electronic device to execute operations, the operations comprising:

• receiving media content including a set of video frames based on a content playability factor;
• applying a first neural network (NN) model on each video frame of the set of video frames;
• detecting a set of objects included in the each video frame of the set of video frames based on the application of the first NN model;
• receiving a set of images of an audience watching the received media content;
• applying a second NN model on each image of the received set of images of the audience;
• estimating gaze co-ordinates associated with the audience based on the application of the second NN model;
• splitting the each video frame of the set of video frames into a set of segments;
• mapping the estimated gaze co-ordinates to the set of segments of the each video frame of the set of video frames;
• determining an engagement score for each object of the detected set of objects based on the mapping of the estimated gaze co-ordinates;
• and
• rendering, on a display device, the determined engagement score for the each object of the detected set of objects.