Patent attributes
This disclosure is directed to methods, apparatuses, and systems for facilitating video communications between users in environments including a plurality of imaging devices. For example, an environment can include first and second imaging devices having associated fields of view providing multiple perspectives of a user. Upon initiating a video communication session, a network device can receive image data from the imaging devices to determine an identity of a user. A user profile of the user can include preferences for the communication, such as device selection, zoom selection, audio selection, subject framing, and the like. Further, the network device can utilize machine learned algorithms to determine an optimal view of the user for the video communication based on the fields of view associated with each imaging device. The network device can intelligently add users to a communication session and provide output to devices to provide a seamless videoconferencing experience.
