JP2019062322A - Audio control console controllable by camera - Google Patents

Abstract

To provide an audio control console that automatically switches microphone audio based on a face image captured by a camera.SOLUTION: A face image recognition unit 22 takes in images of cameras C1 to C3 and recognizes face images included in the images. A person's name and its face image are registered in a database 23. Person's names are assigned to audio adjustment faders 131 to 133. A person's name specification unit 24 specifies person's names of face images captured by the cameras C1 to C3 based on the face image input from the face image recognition unit 22 and the information registered in the database 23. A fader control unit 14 turns on the faders 131 to 133 to which the person's name specified by the person's name specification unit 24 is assigned.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an audio control console capable of controlling audio output based on an image captured by a camera.

  In a voice control system of a television station, microphone sound to be used is frequently switched as the program to be broadcast or recorded advances. The microphone sound is a sound obtained by inputting a sound emitted by an announcer or a performer to a microphone. For example, when the performer switches from scene 1 to scene 2 in the studio, the microphone sound used by the performer is switched at the timing when the performer changes. Also, the microphone sound to be used may be switched at the timing when the announcer switches when switching from the studio to the relay image.

  In normal operation, all the microphone voices used during the program are input to the voice control console, and the microphone voices used are switched by manually operating the operation unit called a fader according to the program progress. Such an audio control console is described, for example, in the following patent documents.

JP, 2015-213246, A JP, 2015-95127, A JP, 2014-93665, A

  However, when the faders of the audio control console are manually operated as in the prior art, switching of the microphone audio is not performed due to an erroneous operation such as forgetting to raise or forget to lower the audio, or unnecessary audio is output. I have a problem. Also, if all the faders used are kept ON, unnecessary audio may be output, or noise picked up by all the microphones will be added to cause a drop in the S / N ratio of the broadcast audio. I will.

  An object of the present invention is to switch a microphone voice by recognizing a face of a person who is a target of switching a microphone voice by a camera and controlling a fader of a voice control console registered with the face image to automatically adjust the volume. It is to provide an audio control console that can be reliably performed.

The camera-controllable audio control console of the present invention is characterized by having the following configuration.
(1) A face image recognition unit that captures an image of a camera and recognizes a face image included in the image.
(2) A database in which personal names and their face images are registered.
(3) Faders for audio adjustment to which personal names are assigned.
(4) A personal name specifying unit for specifying a personal name of a face image captured by a camera based on the face image input from the face image recognition unit and the information registered in the database.
(5) A fader control unit for turning on a fader to which the personal name specified by the personal name specifying unit is assigned.

The present invention also includes the following embodiments.
(6) The face image recognition unit takes in the images of a plurality of cameras, recognizes the face image contained in the images of each camera for each of the plurality of cameras, and the personal name identification unit is identical to the plurality of cameras. When it is determined that the face image of the face image is captured, the fader control unit turns on the volume of the fader to which the name of the face image captured in any one of the plurality of cameras is assigned. Do.
(7) A spectator fader is provided to increase or decrease the volume of a spectator microphone, the face image recognition unit further includes a part determination unit that determines a plurality of types of human face parts, and the fader control unit is the part Control is performed to turn on the spectator fader when the number of parts recognized by the determination unit exceeds a threshold.
(8) The fader control unit includes a circuit that determines an input of a tally signal indicating a camera that is on air or recording, and the image is displayed on the active camera based on information from the camera determined to be active by the tally signal. Control to turn on the microphone fader corresponding to the person's name.

  According to the present invention, it is possible to perform face recognition from an image captured by a camera and to automatically perform on / off control of a fader, thereby preventing manual erroneous operation and reducing microphone sound collection noise.

FIG. 1 is a functional block diagram showing a first embodiment of the present invention. The functional block diagram which shows 2nd Embodiment of this invention. The figure which shows the state of the switch of the camera in other embodiment of this invention.

  Hereinafter, embodiments of the present invention will be specifically described with reference to the drawings. In the present embodiment, the configuration relating to the functions originally provided for the camera and the audio control console will be omitted, and the functions and configurations relating to the microphone to be switched on / off and the fader for adjusting the volume will be described. Although three cameras and microphones are described in the present embodiment, the number of these is merely an example and is not limited.

[1. First embodiment]
(1) Configuration As shown in FIG. 1, the audio control console of the present embodiment is reflected in the audio control unit 10 for a plurality of microphones M1 to M3 provided in a known audio control console and cameras C1 to C3. And a face information analysis unit 20 for specifying a person's name. The voice control unit 10 and the face information analysis unit 20 are respectively provided with communication units 11 and 21. The name of the person specified in the face information analysis unit 20 via the communication units 11 and 21, the number of parts in the camera image, etc. Data is communicated.

  The audio control unit 10 has input units 121 to 123 for independently receiving audio signals from a plurality of microphones M1 to M3 connected to the audio control console, and a plurality of audio signals input to the input units 121 to 123. A plurality of faders 131 to 133 are provided to independently turn on / off and adjust the volume. The volume of each of the plurality of faders 131 to 133 is controlled separately or in synchronization by a computer program which is manually or preset as in the conventional audio control console. The names of persons wearing the microphones M1 to M3 controlled by the faders are assigned to the respective faders 131 to 133.

  The audio control unit 10 is provided with a fader control unit 14 that performs on / off control of the faders 131 to 133 according to the information from the face information analysis unit 20, separately from the control of the fader according to the conventional technology as described above. . The fader control unit 14 is configured by a CPU and an FPGA (programmable logic device) as hardware. The fader control unit 14 turns on the faders 131 to 133 of the microphones M1 to M3 assigned to the person's name when the face information analysis unit 20 inputs the name of a person appearing in the cameras C1 to C3. At the same time, when there is no input of a personal name from the face information analysis unit 20, the faders 131 to 133 of the microphones M1 to M3 assigned to the personal name are turned off.

  When the same person's name is input from any one of the plurality of cameras C1 to C3 connected to the audio control console, the fader control unit 14 faders 131 of the microphones M1 to M3 assigned to the person's name. An OR circuit is provided to turn on. That is, as long as a specific personal name is input from any one of the cameras C1 to C3, the fader control unit 14 maintains the on state of the faders 131 to 133 of the microphones M1 to M3 corresponding to the personal name.

  The face information analysis unit 20 is provided with a face image recognition unit 22, a database 23, and a personal name identification unit 24. These units are configured by hardware and recording means such as a CPU and a memory. The face image recognition unit 22 captures an image of one or more cameras C1 to C3 connected to the audio control console, and recognizes a face image included in the image. That is, the face image recognition unit 22 takes in the video captured to each of the cameras C1 to C3 and determines whether or not a face image exists. If a face image exists, the face image and the camera C1 are determined. It outputs to the personal name identification part 24 in the state matched with ID of -C3. The database 23 associates a personal name with its face image and is registered in advance in the recording means. The personal name specification unit 24 specifies the personal name of the face image captured by the cameras C1 to C3 by comparing the face image input from the face image recognition unit 22 with the face image registered in the database 23.

  The personal name identification unit 24 is connected to the fader control unit 14 of the audio control unit 10 via the communication units 11 and 21 and the IDs of the cameras C1 to C3 and the personal names of face images displayed on the cameras C1 to C3 are displayed. It is output to the fader control unit 14.

(2) Operation In the present embodiment, when an image of a person wearing the microphones M1 to M3 is taken out to one of the cameras C1 to C3 connected to the face information analysis unit 20, the image is a face image It is input to the recognition unit 22. The face image recognition unit 22 determines whether or not a face image is included in the images from the cameras C1 to C3. If the face image is included, the image data corresponding to the face image is identified by the person name identification unit 24. Output to The personal name specifying unit 24 compares the input face image with the face image registered in advance in the database 23, and when there is the same face image, specifies the name of the person shown on the cameras C1 to C3. .

  After identifying the names of the persons copied to the cameras C1 to C3, the personal name identification unit 24 associates the IDs of the cameras C1 to C3 with the names of the persons extracted there and outputs them to the fader control unit 14. Even when the same person or different people are shown in a plurality of cameras C1 to C3, the personal name specifying unit 24 outputs the ID of each camera C1 to C3 to the fader control unit 14 in association with the names of the persons photographed there. Do.

  The fader control unit 14 having received the IDs of the cameras C1 to C3 and the corresponding personal names turns on the volume of the faders 131 to 133 corresponding to the personal names. When different personal names are input to the fader control unit 14 from the plurality of cameras C1 to C3, the volume of all the corresponding faders 131 to 133 is turned on.

  When the same person's name is input from a plurality of cameras C1 to C3, the fader control unit 14 follows the OR circuit provided there, and as long as the same person appears on any of the cameras C1 to C3, the person's name The on-states of the faders 131 to 133 of the microphones M1 to M3 corresponding to V.

  On the other hand, a person who is not shown in any of the cameras C1 to C3 despite wearing the microphones M1 to M3 does not have a person name specified in the face image recognition unit 22 and the person name specification unit 24. Therefore, the personal name corresponding to the ID of the cameras C1 to C3 is not output from the personal name specifying unit 24 to the fader control unit 14. As a result, since the fader control unit 14 can not turn on the faders 131 to 133 corresponding to personal names, the faders 131 to 133 are turned off, and the audio signals input from the microphones M1 to M3 are output from the audio control console I have not.

  This means that when a person wearing the microphones M1 to M3 is shown on the cameras C1 to C3 and the faders 131 to 133 are turned on, the camera C1 to C3 or a person on the camera C1 moves. The same is true when face image recognition can not be performed during the video of ~ C3. When the face image can not be recognized from the images of the cameras C1 to C3 and the identification of the person's name becomes impossible, the fader control unit 14 turns off the fader corresponding to the person's name. The volume of the microphones M1 to M3 is turned off.

(3) Effects According to the present embodiment, the following effects are exhibited.
(A) Since it becomes possible to turn on only the faders 131 to 133 of the microphones M1 to M3 worn by the people photographed on the cameras C1 to C3, the microphones M1 of the people not photographed on the cameras C1 to C3 The noise input from ~ M3 is not output from the audio control console.

(B) It is automatically judged by the face image whether a person wearing the microphones M1 to M3 appears in the camera, and a person's name is determined based on the face image. ~ 133 can also be turned on and off automatically. As a result, there is no operation error as in the case where the faders 131 to 133 are manually turned on and off, and the burden on the operator of the audio control console is also greatly reduced.

(C) Even if different cameras C1 to C3 recognize face images of the same person by the OR circuit provided in the fader control unit 14, a person who can specify a person's name appears in any of the cameras C1 to C3 As long as it is, it is possible to keep the faders 131 to 133 of the microphones M1 to M3 corresponding to the person's name on.

(D) When there are a plurality of cameras, one of them is activated by the tally signal, and only the video taken by the camera may be broadcast or recorded. In this embodiment, the tally signal is used. Regardless of the above, there is an advantage that the fader of the microphone corresponding to the person's name is controlled to be on when the person's name shown in any camera is identified.

[2. Second embodiment]
FIG. 2 shows a second embodiment of the present invention. In the second embodiment, a microphone used by a person whose name is unknown, such as a spectator, is on / off controlled by an image of a camera, not a microphone whose name is known in advance. Therefore, in addition to the microphones M1 and M2 whose names are known, the audio control console of the second embodiment is provided with a microphone M4 for the audience and a fader 134 for the audience to increase / decrease the volume. In addition, an image of the camera C4 that captures a person to whom the audience microphone M4 is directed is input to the face image recognition unit 22. The face image recognition unit 22 includes, in addition to the part performing the face image recognition processing of the first embodiment, a parts determination unit 25 that determines a plurality of types of parts of a human face.

  In the part determination unit 25, when the personal name identification unit 24 accesses the database 23 and the personal name corresponding to the face image from the camera C 4 is not registered in the database 23, the personal name identification unit 24 recognizes the face image recognition unit 22. There is a face image from, but there is no registration on the database 23 and there is a mismatch, and it is not possible to specify a person's name, and as a result the fader control unit 14 performs on / off control for any fader. Can not. In the second embodiment, it is possible to perform processing so that the audience fader 134 is turned on in response to the mismatch in this case.

  That is, when the personal name identification unit 24 in which the face image is input can not identify the personal name based on the face image, the personal name identification unit 24 determines the audience based on the information from the parts determination unit 25. Control the on / off control of the fader 134 for The judgment criteria of the on / off control unit of the audience fader 134 uses the number of recognized face parts (eyes, eyebrows, nose, mouth, ears, head, etc.).

The fader control unit 14 turns on the spectator fader 134 when the number of parts recognized by the parts determination unit 25 exceeds a predetermined threshold (for example, 3). For example, as shown in the left side of the table on the left side of the table below, the control judgment criteria for the spectator fader 134 in the fader control unit 14 turn on the fader when the number of recognized parts exceeds the threshold 3, As indicated by the circle in the table, when the number of recognized parts is equal to or less than the threshold 3, the fader is turned off.

  According to the present embodiment, even when the microphone C4 does not correspond to a specific person's name like the audience microphone M4, when the camera C4 recognizes the face image of the person directed to the audience microphone M4, The fader 134 for controlling the audience microphone M4 can be turned on / off. Moreover, even when it is recognized that a face image is present in the camera image, the audience fader 134 is turned on only when a plurality of parts constituting the face can be clearly determined. The audience microphone M4 can be turned on only when it is clearly shown in the inside.

[3. Other embodiments]
The present invention is not limited to the above embodiment, and includes, for example, the following other embodiments.
(1) In the above embodiments, the case where one face image appears in the image of one camera has been described, but a plurality of face images appear in one camera, and a plurality of names of people are specified. It is also possible to simultaneously control multiple faders with information from one camera.

(2) As in the case where one microphone is shared by a plurality of persons, a plurality of personal names are associated with the fader of one microphone, and the personal name identification unit 24 selects one of the plural personal names in the video of the camera. If one is identified, the microphone associated with that person's name may be turned on.

(3) In general, a tally lamp is mounted in a studio camera system, and the tally lamp is turned on at the time of on-air or at the time of recording so that the subject (performer) can confirm the operation state of the active camera. In such a system, the fader control unit 14 is provided with a circuit for determining the input of a tally signal indicating a camera that is on air or recording, such as detecting lighting and non-lighting of the tally lamp of each camera. Each fader can be controlled based on information from the lighted active camera.

  That is, as shown in FIG. 3A, by setting the camera with the tally lamp activated and setting the unlit camera as the standby, the fader of the microphone corresponding to the name specified by the image from the active camera For the personal name specified by the standby camera only, even if the person wearing the microphone is on the camera, the microphone fader corresponding to the personal name is turned off. Thereafter, as shown in FIG. 3B, when the fader control unit 14 detects that the camera in the on-air state has been switched based on the input of the tally signal, the information from the newly activated camera is used. Then, the fader of the microphone corresponding to the personal name specified by the camera is turned on, and the fader is turned off for the microphone corresponding to the personal name specified by the other standby camera.

C1 to C4: Cameras M1 to M4: Microphone 10: Voice control unit 11: Communication unit 121 to 124: Input unit 131 to 134: Fader 14: Fader control unit 20: Face information analysis unit 21: Communication unit 22: Face image recognition Part 23 ... Database 24 ... Person name identification part 25 ... Parts judgment part

Claims (4)

A face image recognition unit for capturing an image of a camera and recognizing a face image included in the image;
A database in which people's names and their face images are registered,
Voice adjustment faders to which personal names are assigned,
A personal name specifying unit for specifying a personal name of a face image captured by a camera based on the face image input from the face image recognition unit and the information registered in the database;
A fader control unit for turning on a fader to which the personal name specified by the personal name specifying unit is assigned;
An audio control console that can be controlled by a camera equipped with. The face image recognition unit takes in images of a plurality of cameras, and recognizes face images included in the images of each camera for each of the plurality of cameras.
When the personal name specifying unit specifies that face images of the same person are captured by a plurality of cameras, the fader control unit may determine the name of the face image captured in any one of the plurality of cameras. The camera-controllable audio console according to claim 1, wherein the faders assigned are turned on. Has a fader for the audience to increase or decrease the volume of the audience microphone
The face image recognition unit further includes a parts determination unit that determines a plurality of types of parts of a human face,
The audio controllable by the camera according to claim 1 or 2, wherein the fader control unit performs control to turn on the spectator fader when the number of parts recognized by the part determination unit exceeds a threshold. Adjustment table.   The said fader control part is provided with a circuit which determines the input of the tally signal which shows the camera on air or recording, and the person who is reflected to the active camera based on the information from the camera judged to be active by the said tally signal. The camera-controllable voice control console according to any one of claims 1 to 3, which is controlled to turn on a microphone fader corresponding to a person's name.

Images