Apparatus, system, and method of image processing, and recording medium storing image processing control program

摘要

An image processing apparatus receives sound signals that are respectively output by a plurality of microphones, and detects a sound arrival direction from which sounds of the sound signals are traveled. The image processing apparatus calculates a sound level of sounds output from the sound arrival direction, and causes an image that reflects the sound level of sounds output from the sound arrival direction to be displayed in vicinity of an image of a user who is outputting the sounds from the sound arrival direction.

主权项

1. An image processing apparatus, comprising:
an image capturing device to capture an image of users into a captured image; a plurality of microphones that are disposed side by side; and a processor to:
receive sound signals that are respectively output by the plurality of the microphones, the sound signals representing a sound at the plurality of the microphones;detect a sound source direction of a source of the received sound signals, based on time difference data, the time difference data indicating a difference in time at which the sound is received from one of the plurality of the microphones with respect to a time at which the sound is received from the other one of the plurality of the microphones;calculate a sound level of the received sound signals of the sound output from the detected sound source direction;detect, from among the users, a speaker who is generating the sound based on position information of the speaker and the detected sound source direction; anddisplay a sound level image indicating the calculated sound level in a vicinity of an image of the speaker in the captured image by using the detected sound source direction and the calculated sound level,wherein a position of the sound level image with respect to the image of the speaker in the captured image is determined based on:
a x coordinate value of a left corner of the image of the speaker in the captured image;x and y coordinate values of an upper corner of the image of the speaker in the captured image;a size of the sound level image to be displayed in the captured image when the calculated sound level reaches a maximum sound level, anda distance between the image of the speaker and the sound level image in the captured image.