Method and apparatus for tracking active subject in video call service

摘要

A method for tracking an active subject in a video call service includes establishing a peer-to-peer connection between a videophone input apparatus and a peer over a wireless connection; receiving information of a first resolution display of an A/V output apparatus of the peer; and generating a local video stream in the videophone apparatus based on a video signal provided by a second resolution camera of the videophone apparatus, the second resolution being greater than the first resolution. The method further includes generating a local audio stream in the videophone input apparatus based on an audio signal provided by a microphone of the videophone input apparatus; determining active subject information of the video call using at least one of the local video stream and the local audio stream; targeting the local video stream towards the active subject by selecting a first resolution view area from the second resolution video signal based on the determined active subject information; and transmitting the first resolution view area for displaying on the first resolution display.

主权项

1. A videophone input apparatus, for tracking an active subject in a video call service, comprising:
a communication interface for communicating with a peer; at least one processor; and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the videophone input apparatus to: establish a peer-to-peer connection between the videophone input apparatus and a peer over a wireless connection; receive information of a first resolution display of an A/V output apparatus of the peer; generate a local video stream in the videophone apparatus based on a video signal provided by a second resolution camera of the videophone apparatus, the second resolution being greater than the first resolution; generate a local audio stream in the videophone input apparatus based on an audio signal provided by a microphone of the videophone input apparatus; determine active subject information of the video call using at least one of the local video stream and the local audio stream; target the local video stream towards the active subject by selecting a first resolution view area from the second resolution video signal based on the determined active subject information; and transmit the first resolution view area for displaying on the first resolution display.