| 摘要 |
An electronic device can include a display and a controller. The controller identifies a location within a displayable area of video frames which has movement, and controls panning/zooming of a sub-area within the video frames that is displayed on the display in response to the identified location of the movement. Some configurations of the controller detect movement of a person's mouth within the video frames while the person is speaking, identifies the associated location of the person speaking, identifies characteristics of voice in the video frames that is concurrently occurring with the detected movement of the person's mouth, and correlates the identified voice characteristics with the identified location of the person speaking. The controller then detects subsequent occurrence of voice in the video frames having the identified voice characteristics of the person and, responsive thereto, pans a sub-area within the video frames displayed on the display toward the identified location of the person and/or zooms-in to increase size of the person speaking by decreasing size of a sub-area within the video frames at the location of the speaker that is fit to the display.
|
