JP2018107538A - Information processing device, control method of information processing device, and control program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To register a registration target person and image in association with each other without a user input.SOLUTION: An information processing device (1) provided with output units (14, 15) and an imaging unit (16) includes: an output control unit (22) that makes the output units output a message prompting a registration target person to perform a predetermined operation; an image acquisition unit (24) that makes the imaging unit pick up an image after the message is output; and a registration unit (25) that when a person having performed the operation is included in the picked-up image, registers the image of the person as an image of the registration target person.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus including an output unit that outputs information and an imaging unit.

  A technique for recognizing a person in a captured image and registering the identification information of the person in association with the image has been developed. For example, Patent Document 1 discloses a digital camera that recognizes a person in an image captured by an image processing system and records the name of the person on the image.

JP 2004-62868 A (published February 26, 2004)

  However, the conventional technology as described above has a problem that the user has to input identification information to be associated with the image in order to associate the identification information of the person with the image, and the operation is troublesome for the user. For example, when a digital camera is installed away from the user or when shooting is performed automatically by moving the shooting site, it is even more troublesome for the user to input the input. In this case, the problem becomes even more serious.

  An object of one embodiment of the present invention is to provide an information processing apparatus or the like that can register a registration target person and an image of the registration target person in association with each other without input by a user.

  In order to solve the above-described problem, an information processing apparatus according to an aspect of the present invention is an information processing apparatus including an output unit and an imaging unit, and prompts a registration target person to perform a predetermined operation. Are output to the output unit, the output control unit outputs the message, the image acquisition unit causes the imaging unit to capture an image, and the image captured by the imaging unit includes the predetermined image. And a registration unit that registers an image of the person as an image of the person to be registered when the person who performed the operation is included.

  In order to solve the above-described problem, a method for controlling an information processing device according to one aspect of the present invention is a method for controlling an information processing device including an output unit and an imaging unit. An output control step for causing the output unit to output a message prompting the user to perform the image, an image acquisition step for causing the imaging unit to capture an image after outputting the message in the output control step, and the imaging unit A registration step of registering an image of the person as an image of the person to be registered when the captured image includes a person who has performed the predetermined operation.

  According to an aspect of the present invention, there is an effect that a registration target person and an image of the registration target person can be registered in association with each other without input by a user.

It is a figure which shows the principal part structure of the dialogue robot which concerns on one Embodiment of this invention. It is a figure which shows one specific example of the various data memorize | stored in the memory | storage part of a dialogue robot. It is a flowchart which shows the flow of a process of a dialogue robot. 6 is a flowchart showing a flow of processing of the interactive robot according to the second embodiment.

Embodiment 1
Hereinafter, embodiments of the present invention will be described in detail. In one embodiment of the present invention, the information processing apparatus is applied to the interactive robot 1. However, the present invention is not limited to this, and the information processing apparatus of the present invention can be connected to a handheld or movable head, such as a digital camera and a digital video camera, and a mobile terminal such as a smartphone provided with an imaging unit. Etc. are applicable. When the information processing apparatus of the present invention is applied to the portable terminal, for example, it is conceivable to install and use the portable terminal on a movable charging stand.

  In the present embodiment, the dialogue robot 1 is a robot that can interact with a person based on a known voice recognition technology, and is a robot having an imaging mechanism such as a camera. Also, as an example, the dialogue robot 1 is a robot that has a moving mechanism such as a movable part, and can automatically move the position and orientation of its own device and the position and orientation of the camera.

  In the present embodiment, the dialogue robot 1 arbitrarily moves in a shooting site (a party venue, a lecture hall, etc.) where a plurality of persons are present, takes a picture with the camera directed at the people who are the shooting target, and records an image. To do. Further, the dialogue robot 1 has a function of learning and identifying each person present at the shooting site. Then, the dialogue robot 1 registers a person image in its own device for the learning. Hereinafter, an operation in which the dialogue robot 1 captures people for recording (for example, an operation for taking a commemorative photo) is referred to as recording, and a still image obtained by recording is referred to as a recorded image. In addition, an operation in which the interactive robot 1 captures an image of a person (particularly a face image) for learning is referred to as registered imaging, and a still image acquired by registered imaging is referred to as a registered image.

(Configuration of interactive robot)
FIG. 1 is a block diagram showing a main configuration of an interactive robot 1 according to an embodiment of the present invention. The interactive robot 1 includes, for example, a control unit 10, a storage unit 11, a voice input unit 12, a communication unit 13, a display unit 14, a voice output unit 15, and an imaging unit 16. The dialogue robot 1 may include other mechanisms (not shown) for functioning as the dialogue robot 1. For example, the dialogue robot 1 includes an operation unit such as a servo that moves a movable unit such as an arm or a leg, a sensor unit such as an infrared sensor, an illumination unit such as an LED, a projection unit such as a projector, and an operation unit such as a switch or button. May be provided.

  The voice input unit 12 is a device for acquiring voice generated in the field, such as conversations of people who are present at the venue, as sound data that can be processed by the control unit 10, and includes a microphone or the like. For example, the dialogue robot 1 may acquire information related to the participants in the venue from the voice of the conversation input via the voice input unit 12. The communication unit 13 communicates with an external device via a communication network according to a predetermined communication method. The communication line, the communication method, or the communication medium are not limited as long as an essential function for realizing communication with the external device is provided. For example, the dialogue robot 1 may acquire information related to the participants in the venue via the communication unit 13. That is, the voice input unit 12 and the communication unit 13 are input units having a function of inputting information relating to the participant to the control unit 10.

  The display unit 14 displays various types of information processed by the control unit 10 or stored in the storage unit 11 so that a person can visually recognize the information. For example, the display unit 14 includes a display device such as an LCD (liquid crystal display). Is done. The sound output unit 15 is a device for outputting the sound data processed by the control unit 10 as sound, sound effects, music, or the like, and includes a speaker or the like. Thereby, the dialogue robot 1 can output a response with an auditory effect to a person. That is, the display unit 14 and the audio output unit 15 are output units having a function of outputting information to a person (for example, a participant in the venue).

  The imaging unit 16 is a device that captures a subject and inputs an image, and includes a camera or the like. The imaging unit 16 may be a digital camera that captures a still image of a subject, or may be a digital video that can capture the motion of the subject or the background.

  The storage unit 11 includes a volatile or non-volatile storage device such as a random access memory (RAM), a read only memory (ROM), a non-volatile random access memory (NVRAM), and a flash memory. Various information to be stored is stored. Specifically, the storage unit 11 includes a registration target person list 40, a shooting target person list 41, a shooting condition 42, and a recorded image database (DB) 43, which will be described later.

  The control unit 10 comprehensively controls various functions of the interactive robot 1. The control unit 10 includes at least a video processing unit 21, an output control unit 22, an image acquisition unit 24, and a face image registration unit 25 (registration unit) as functional blocks. As necessary, the control unit 10 may further include a list management unit 20, a shooting necessity determination unit 23 (shooting control unit), and a photo storage unit 26 as functional blocks.

  The list management unit 20 manages the registration target person list 40 based on the photographing target person list 41. The photographic subject list 41 is a list of photographic subjects who are persons who should be subjects in recording photography. The shooting target person list 41 is referred to at least when identifying the person from the identification information for uniquely identifying the person and the live view video (video) or still image (image) acquired by the imaging unit 16. The registered image is stored in association with each other.

  FIG. 2 is a diagram showing a specific example of the photographing subject list 41. In the example shown in FIG. 2, the photographing subject list 41 includes a column for storing the name of the photographing subject as identification information and a column for storing a face image as a registered image of the photographing subject. The face image may be registered in advance by a user (for example, a person who intends to record and shoot the venue using the interactive robot 1), or an unlearned person who the interactive robot 1 is present at the venue. Alternatively, registration may be performed by performing registered shooting.

  The list management unit 20 recognizes a person who has identification information (name) in the shooting target person list 41 but whose registered image (face image) is not yet registered, that is, an unlearned person, as a registration target person. A list of registration subject names is extracted as a registration subject list 40 from the photographing subject list 41.

  In the storage unit 11 of the interactive robot 1, the photographing subject list 41 with or without a face image may be registered in advance by the user. For example, when the shooting site is a wedding reception hall or the like, a dialogue robot 1 is installed for each guest table, and each dialogue robot 1 is provided with a guest identification information (name) based on a predetermined seating table. If it can be obtained in advance, a registered image (face image) can be registered.

  Alternatively, the list management unit 20 may include an interpretation unit 32. In the first embodiment, the interpretation unit 32 analyzes transmission / reception information collected in advance via the communication unit 13. The transmission / reception information is information exchanged before the date of the event between the participants of the event held at the shooting site, for example, an e-mail address, title or text, or SNS (Social Networking Service). ) Transmission / reception history, telephone conversation history, and the like. The interpretation unit 32 may extract the names of the participants of the event from the transmission / reception information. The list management unit 20 may automatically create the photographing subject list 41 and the registration subject list 40 based on the names of the participants extracted by the interpretation unit 32.

  The video processing unit 21 controls the imaging unit 16 to start a shooting mode, and processes a video that is a live view video acquired by the imaging unit 16 thereby. Specifically, the video processing unit 21 includes an identification unit 30 and a detection unit 31.

  The identification unit 30 identifies a person included in the video. If the person included in the video has been learned, that is, if the face image is registered in the subject list 41, the identification unit 30 transmits the identification result of the person to each downstream unit that performs recording. . On the other hand, the identification unit 30 indicates that the person is unlearned, that is, if the face image is not registered in the shooting target person list 41, the downstream unit for performing registered shooting (not shown) Specifically, it is transmitted to the output control unit 22 and the detection unit 31).

  The output control unit 22 controls the output unit to output a message that prompts an unlearned person (registration target person) to perform a predetermined operation. Specifically, the output control unit 22 reads the name of the registration target person from the registration target person list 40 and causes the voice output unit 15 to output the name as a voice. It is preferable that the output control unit 22 not only calls a name to an unlearned person, but also causes the voice output unit 15 to output a message requesting to perform a predetermined operation. As a result, it is possible to perform a special operation only on the person corresponding to the name more reliably, and it becomes easier to specify the person. For example, the output control unit 22 creates a message that combines a name and a predetermined action such as “Look at Mr. Yamada, look at me”, “Mr. You may make it output from the audio | voice output part 15. FIG. Further, the output control unit 22 may cause the display unit 14 to display the message.

  The detection unit 31 of the video processing unit 21 detects a predetermined operation specified by the message from the video acquired via the imaging unit 16 after the message is output by the output control unit 22. As a technique for detecting a specific operation from a video as a live view video, an existing gesture recognition technique can be adopted. When the detection unit 31 detects that the predetermined operation has been performed by an unlearned person, the detection unit 31 instructs the image acquisition unit 24 to photograph the person who has performed the predetermined operation.

  The image acquisition unit 24 controls the imaging unit 16 to acquire an image that is a still image. The image acquisition unit 24 may change the angle of view of the lens so that, for example, one or a plurality of persons can be clearly seen in a certain size depending on the purpose of shooting, that is, when recording shooting is performed and when registered shooting is performed. , Direction, aperture, etc. may be controlled. For example, the image acquisition unit 24 may acquire a registered image of the person by controlling the imaging unit 16 to capture the face of the person who has performed the predetermined operation in accordance with an instruction from the detection unit 31. it can.

  The face image registration unit 25 registers the registered image acquired by the image acquisition unit 24 in the shooting target person list 41. The face image registration unit 25 associates the registered image with the name output by the output control unit 22 and registers the name in the photographing subject list 41. Immediately after the message designating the name and the predetermined action is output, the fact that the predetermined action is detected in the video indicates that the person of that name has performed the predetermined action and has been acquired. The registered image is a photograph of a person who has performed the predetermined operation. From this, the face image registration unit 25 can be used for the person without requiring input from the user based on the content of the message output immediately before the predetermined operation is performed and the registered image acquired immediately after. Can be associated with a face image.

  The shooting necessity determination unit 23 determines whether or not recording shooting is necessary for the person identified by the identification unit 30. Specifically, the shooting necessity determination unit 23 acquires, as a photo number ratio, the number of photos in which the person is present among all the recorded images (photos) recorded in the recorded image DB 43. To do. Then, the recorded image of the person is photographed according to whether or not the ratio of the number of photographs of the person is equal to or greater than the ratio of the number of photographs of the photographing condition 42 as compared with the ratio of the number of photographs set in advance as the photographing condition 42. It is determined whether or not. In the first embodiment, the ratio of the number of photos set as the shooting condition 42 is a default value and is, for example, “33%”.

  In this case, if the ratio of the number of photographs of the person is 33% or more, the photographing necessity determination unit 23 determines that the photograph of the person is sufficiently recorded and does not need to be photographed. The number of photographs of the person is determined as needing to be photographed because the target is not reached.

  The image acquisition unit 24 acquires a recorded image of the person when the shooting necessity determination unit 23 determines that shooting is necessary when the shooting necessity determination unit 23 is provided. To do. Thereby, recording photography is performed with respect to each photographing subject so that the ratio of the number of photographing subjects is equal to the value set in the photographing condition 42. As a result, it is possible to shoot all the participants in the venue without any bias, including a person whose face image is not registered in advance.

  The photo storage unit 26 stores the recording image acquired by the image acquisition unit 24 in the recording image DB 43. In the recorded image DB 43, in addition to the recorded images taken so far, the number of photographs for each person or the ratio of the number of photographs may be recorded. When the recorded image is newly stored, the photo storage unit 26 may also update the number of photos or the photo number ratio.

(Processing flow)
FIG. 3 is a flowchart showing the flow of processing of the interactive robot 1 according to the first embodiment. Among the steps shown in FIG. 3, S105 to S109 indicate the flow of registered shooting processing, and S110 to S112 indicate the flow of recording shooting processing.

  The list management unit 20 extracts the registration target person list 40 whose face images are not registered based on the photographing target person list 41 registered in advance (S101). For example, in the example illustrated in FIG. 2, the registration target person list 40 including “Yamada XX, Suzuki □□, Sato △△” is extracted.

  The video processing unit 21 controls the imaging unit 16 to start the shooting mode and obtain a live view video (S102). When a person is detected from the video (YES in S103), the identification unit 30 compares the face image registered in the photographed person list 41 to determine whether or not the person has been learned. (S104). If the detected face image of the person is not registered in the photographed person list 41 (NO in S104), the fact that the person has not been learned is transmitted from the identification unit 30 to the output control unit 22 and the detection unit 31. Is done.

  In response to this, the output control unit 22 reads one name from the registration target person list 40 extracted in S101, and sends a message prompting the person with the name to perform a predetermined operation as the voice output unit 15. (S105).

  The detection unit 31 monitors the video obtained from the imaging unit 16 after the message is output. If the detection unit 31 detects that an unlearned person has performed a predetermined operation (YES in S106), the detection unit 31 instructs the image acquisition unit 24 to photograph the person who has performed the predetermined operation. On the other hand, if the predetermined time has elapsed since the message was output without detecting the predetermined operation (NO in S106), the detection unit 31 indicates that the predetermined operation has not been detected. To communicate. In this case, the output control unit 22 may change the name listed next in the registration target person list 40 and output the message via the voice output unit 15. Thereafter, the output control unit 22 repeatedly outputs the names listed in the registration target person list 40 in order until a predetermined operation is not detected.

  The image acquisition unit 24 acquires a registered image of the person who performed the predetermined operation according to the instruction of the detection unit 31 (S107). The face image registration unit 25 associates the registered name acquired in S107 with the latest name output in S105 and registers it in the subject list 41 (S108). Note that the image acquisition unit 24 may adjust the composition of the registered image so that the face of the person who has performed the predetermined operation is clearly enlarged by controlling the lens direction, the angle of view, the aperture, the focus, and the like. Good. Alternatively, the face image registration unit 25 trims the registered image so as to leave the face portion of the person who has performed the predetermined operation when another person or a background is reflected in the registered image. The person's face image may be obtained.

  When the face image is registered in the shooting target person list 41 in S108, the list management unit 20 deletes the name of the person in which the face image is registered from the registration target person list 40 (S109).

  The control unit 10 moves the interactive robot 1 or changes the direction of the lens of the imaging unit 16 to change the imaging range (S113), and repeats the processing after S103.

  On the other hand, in S104, when the identification unit 30 has registered the face image of the person detected from the video in the shooting target person list 41 and can identify the person (YES in S104), the identification unit 30 The name of the person as the identification result is transmitted to the photographing necessity determination unit 23.

  The photographing necessity determining unit 23 reads the photograph number ratio of the identified person from the recorded image DB 43 and compares it with the photograph number ratio set as the photographing condition 42 (S110). When the ratio of the number of photographs of the person is equal to or greater than the ratio of the number of photographs in the photographing condition 42 and the target is achieved (YES in S110), the photographing necessity determination unit 23 does not need to record and photograph the person. judge. In this case, the control unit 10 changes the shooting range (S113) and repeats the processes after S103.

  On the other hand, when the ratio of the number of photographs of the person is less than the ratio of the number of photographs in the photographing condition 42 (NO in S110), the photographing necessity determination unit 23 determines that the recording of the person is necessary. In this case, the image acquisition unit 24 captures the person and acquires a recorded image in which the person is captured (S111). The photo storage unit 26 stores the recording image acquired by the image acquisition unit 24 in the recording image DB 43 (S112). Along with the storage, the photo storage unit 26 may further update the total number of photos, the number of photos for each person, the number of photos for each person, and the like stored in the recording image DB 43. Thereafter, the control unit 10 changes the shooting range (S113), and repeats the processes after S103.

  Note that if no person is detected in S103 (NO in S103), if the interactive robot 1 is programmed in advance to shoot only a person, the control unit 10 changes the shooting range (S113) and S103. The subsequent processing is repeated. The interactive robot 1 may be programmed to photograph a subject other than a person based on a predetermined program. Further, the shooting mode started in S102 may be ended based on a predetermined operation or a predetermined program. For example, it is assumed that the user presses a button (operation unit), touches the touch panel (operation unit), or the user sets an end timing (such as time or condition) in advance.

  According to the above configuration and method, the interactive robot 1 includes the output control unit 22 and the face image registration unit 25, so that even an unlearned participant whose face image is not registered in advance can be displayed as a video. The captured person can be learned and identified as a person to be photographed, and a recorded image (photograph) can be left. Furthermore, when the photographing necessity determination unit 23 is provided, it is possible to perform recording photographing without bias for all photographing subjects including unlearned persons. The numerical value “33%” of the number of photographs as the photographing condition 42 is an example, and other numerical values may be used.

[Embodiment 2]
The following will describe another embodiment of the present invention with reference to FIGS. For convenience of explanation, members having the same functions as those described in the embodiment are given the same reference numerals, and descriptions thereof are omitted.

  In the second embodiment, the dialogue robot 1 specifies the name of the person to be photographed based on the contents of the conversations of the participants present at the photographing site, and the photographing subject list 41 and the registration subject list 40 are obtained. Shooting can be generated dynamically.

(Configuration of interactive robot)
In the second embodiment, the interpretation unit 32 processes the speech recognition result (text data) of the conversations of the people present at the venue, which are input via the voice input unit 12, and interprets the semantic content of the conversation.

  Between the speech input unit 12 and the interpretation unit 32, a speech recognition unit (not shown) that converts speech into text using an existing speech recognition technology is provided. The text data of the conversations of the participants in the venue obtained by the voice recognition unit is once stored in the storage unit 11 and read by the interpretation unit 32 to be supplied to the interpretation unit 32.

  In particular, the interpretation unit 32 detects a person's name if it is included in the conversation. Then, it is determined from the context of the conversation whether or not the detected person is a participant present at the actual shooting site.

(Processing flow)
FIG. 4 is a flowchart showing the flow of processing of the interactive robot 1 according to the second embodiment. The steps shown in FIG. 4 are performed simultaneously while the steps shown in FIG. 3 are being executed. That is, when the registration target person list 40 and the photographing target person list 41 are updated by executing each step shown in FIG. 4, the registered photographing or the recording photographing is performed based on each updated list.

  A voice recognition unit (not shown) of the control unit 10 recognizes the voice input via the voice input unit 12 (S201). When the interpretation unit 32 detects the name of a person in the conversation (YES in S202), the interpretation unit 32 determines based on the conversation context whether or not the person with the name is a participant present at the shooting site (S203). ). For example, the interpretation unit 32 determines that “Mr. XX” is not a participant from the statement “Mr. XX, I am sorry that I cannot come”. In addition, it is determined that “Mr. □□ is a participant” from the remarks “Mr.

  When the interpretation unit 32 determines that the person with the name detected from the conversation is a participant (YES in S203), the list management unit 20 determines that the name of the person determined to be a participant is the subject list. It is determined whether it is registered in 41 (S204).

  When the name of the person is not registered in the shooting target person list 41, the list management unit 20 adds a record of the person name to the shooting target person list 41, and adds the name of the person to the registration target person list. 40 is also added (S205).

  After S205, the control unit 10 repeats the processes after S201. If the name of the person is not detected in the text data of the speech recognition result (NO in S202), and even if it is detected, the person with that name is not a participant (NO in S203), In addition, even when the person is a participant, if the name is already registered in the shooting target person list 41 (YES in S204), the control unit 10 does not need to update the shooting target person list 41. The process returns to S201 and the subsequent processing is repeated.

  According to the configuration and method, the dialogue robot 1 includes the list management unit 20 and the interpretation unit 32, thereby recognizing the name of the participant from the contents of real-time conversation by the people present at the shooting site. Thus, the photographing subject list 41 and the registration subject list 40 can be dynamically created even during an event. Thereby, for example, even when a person other than the participant who has been grasped in advance based on the transmission / reception information or the user's input participates in a jump-in, the presence of the person is recognized from the conversation in the venue and the face image is obtained. Can learn. It is possible to leave a recorded image of the person.

[Embodiment 3]
Another embodiment of the present invention will be described below with reference to FIGS. For convenience of explanation, members having the same functions as those described in the embodiment are given the same reference numerals, and descriptions thereof are omitted.

  In the third embodiment, the storage unit 11 stores the shooting conditions 42 illustrated in FIG. Unlike the shooting condition 42 of the first embodiment, the ratio of the number of photos as the shooting condition is set for each shooting target person. This setting can be performed in advance by the user, for example. For example, it is assumed that the dialogue robot 1 is used for photographing at an event such as a wedding reception hall or a birthday party hall. In this case, the user sets their photo ratio high so that many recorded images of the protagonist or host of the event (such as a bride or groom or a person celebrating a birthday) are taken, and other participation The ratio of the number of photographers can be set low.

  When the person captured in the video is identified in S104 shown in FIG. 3 (YES in S104), the shooting necessity determination unit 23 according to the third embodiment first determines the ratio of the number of photographs of the identified person. Reading is performed from the imaging condition 42 shown in FIG. The photographing necessity determining unit 23 compares the photograph number ratio of the person stored in the recorded image DB 43 with the read photograph number ratio (S110). Thereafter, the recording and photographing process is executed as in the first embodiment.

  According to the above configuration and method, for example, it is possible to respond to a desire to leave a large number of recorded images of a specific subject, such as a leading role or a presidency of an event.

[Modification]
The identification information is not limited to a person's name, and may be a nickname, a handle name, a membership number, an ID, or the like. In addition, in the subject list 41, in addition to a name, nickname, or handle name that can be identified by a person, a code for the controller 10 of the interactive robot 1 to identify each person is stored in association with each other. Also good.

  In this specification, the person to be imaged is expressed as “person”, but this is not intended to limit the object to be imaged by the interactive robot 1 to a person. In the image recognition technology mounted on the interactive robot 1, the interactive robot 1 can target subjects other than humans (for example, animals, still lifes, etc.) as long as the subjects to be imaged can be individually identified.

  The interactive robot 1 can record a moving image as a recorded image. In this case, the shooting necessity determination unit 23 of the interactive robot 1 may refer to, for example, the length of time during which a person is captured in the moving image as the shooting condition 42 instead of the number-of-photograph ratio.

  The photographing necessity determination unit 23 may refer to the number of photographs as the photographing condition 42 in addition to or instead of the photograph number ratio.

[Example of software implementation]
Control blocks of the interactive robot 1 (particularly, a list management unit 20, a video processing unit 21, an output control unit 22, a shooting necessity determination unit 23, an image acquisition unit 24, a face image registration unit 25, a photo storage unit 26, and an identification unit 30) The detection unit 31 and the interpretation unit 32) may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be realized by software using a CPU (Central Processing Unit). Also good.

  In the latter case, the interactive robot 1 includes a CPU that executes instructions of a program that is software that implements each function, a ROM (Read Only Memory) in which the program and various data are recorded so as to be readable by a computer (or CPU), or A storage device (these are referred to as “recording media”), a RAM (Random Access Memory) for expanding the program, and the like are provided. Then, the computer (or CPU) reads the program from the recording medium and executes it to achieve the object of the present invention. As the recording medium, a “non-temporary tangible medium” such as a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. The program may be supplied to the computer via an arbitrary transmission medium (such as a communication network or a broadcast wave) that can transmit the program. Note that one aspect of the present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission.

[Summary]
An information processing apparatus (dialogue robot 1) according to aspect 1 of the present invention is an information processing apparatus including an output unit (display unit 14, audio output unit 15) and an imaging unit (16). An output control unit (22) that causes the output unit to output a message that prompts the user to perform a predetermined operation, and an image acquisition unit that causes the imaging unit to capture an image after the output control unit outputs the message. 24) and a registration unit (face image registration unit) that registers an image of the person as an image of the person to be registered when the image captured by the imaging unit includes a person who has performed the predetermined operation. 25).

  According to the above configuration, the output control unit causes the output unit to output a message that prompts the person to be registered to perform a predetermined operation. After the message is output, the image acquisition unit controls the imaging unit to acquire a person image. When the person performs a predetermined action when prompted by the message, an image of the person who has performed the predetermined action is acquired. And based on being a person who performed predetermined operation | movement, a registration part can specify that the said person is the said registration subject to whom the said message was addressed. Therefore, the registration unit can register the image acquired by the image acquisition unit after outputting the message as the image of the person to be registered.

  As a result, the information processing apparatus can grasp which person the captured image is without having the user specify it. As a result, it is possible to realize an information processing apparatus capable of registering a registration target person and an image of the registration target person in association with each other without input by the user.

  In the information processing apparatus according to aspect 2 of the present invention, in the aspect 1, the output control unit is configured to identify one identification information (name) read from a registration target person list (40) including identification information of one or more registration target persons. ) As at least a part of the message, and the information processing apparatus further outputs the message from the live view video acquired by the imaging unit after the output control unit outputs the message. A detection unit (31) for detecting a person who has performed the operation, wherein the image acquisition unit acquires the image of the person detected by the detection unit by the imaging unit, and the registration unit includes: The image (registered image, face image) may be registered by associating the image acquired by the image acquisition unit with the identification information output by the output control unit.

  According to the above configuration, the output control unit grasps the identification information of the registration target person to register the image in the registration target person list, and outputs the identification information as at least a part of the message. After the message is output, the image acquisition unit controls the imaging unit to acquire a live view video of the person. When the person performs a predetermined action when prompted by the message, the person who has performed the predetermined action is captured in the live view video. When the detection unit detects a person who has performed the predetermined operation from the live view video, the image acquisition unit acquires an image of the person detected by the detection unit. That is, an image of the person who has performed a predetermined operation is acquired. Since the message includes identification information, based on the fact that the person who performed the predetermined operation is the person to be registered to which the message is addressed, the registration unit It can be accurately identified. Therefore, the registration unit can register the image acquired by the image acquisition unit after outputting the message as the image of the person to be registered.

  As a result, it is possible to realize an information processing apparatus capable of registering a registration target person and an image of the registration target person in association with each other without input by the user.

  In the information processing apparatus according to aspect 3 of the present invention, in the aspect 2, the speech input unit (12) that acquires sound and the speech recognition result of the acquired sound are interpreted, and the identification information of the person to be registered is obtained. You may provide the interpretation part (32) to acquire, and the list management part (20) which adds the acquired said identification information to the said registration object person list.

  According to the above configuration, the registration target person list for grasping the registration target persons who must register the image is dynamically generated based on the contents of the voice acquired through the voice input unit. . That is, even if a person who has not been grasped in advance as a person to be registered is present at the shooting site, from the content of the sound generated at the shooting site (for example, conversation between the persons present at the shooting site), The presence of a person can be recognized, and the person can be grasped as a person to be registered. As a result, even if there is no input by the user, it is possible to recognize a person who is present at the shooting site as a registration target person and register an image.

  In the information processing apparatus according to aspect 4 of the present invention, in the aspect 3, when the image associated with the acquired identification information is not registered, the list management unit stores the identification information in the registration You may add to a subject list. According to the said structure, there exists an effect similar to the said aspect 3.

  In the information processing apparatus according to aspect 5 of the present invention, in the above aspects 1 to 4, the image acquisition unit includes a person of the image registered by the registration unit in the live view video acquired by the imaging unit. The image of the person is acquired as a recorded image, and the information processing apparatus further includes a recorded image database (43) for storing the recorded image acquired by the image acquiring unit, The recorded image is acquired so that the number of recorded images stored in a recorded image database (hereinafter referred to as DB) with each person as a subject is a predetermined ratio (photograph ratio) for each person. You may provide the imaging | photography control part (imaging necessity determination part 23) which controls an image acquisition part.

  According to the above configuration, when the images of the people who are present at the shooting site are learned based on the configurations of the aspects 1 to 4, each person is identified based on the learned images, and the image acquisition unit A recorded image of each person is acquired and stored in the recorded image DB. Since each person is learned based on the registered image as described above, it is possible to grasp which person is reflected in which recorded image in the recorded image DB.

  Therefore, the shooting control unit sets the image acquisition unit so as to acquire the recorded images so that the number of recorded images that are stored in the recorded image DB is set to a predetermined ratio for each person. Control. In this way, the image acquisition unit manages the number of shot images while controlling the number of shot images so that the number of recorded images of each person as a subject is a predetermined ratio for each person under the control of the shooting control unit. get. In this way, shooting for recording is performed while adjusting the number of recorded images so that the ratio of the number of recorded images of each person in the recorded image DB is a predetermined ratio for each person. It becomes possible. As a result, it is possible to avoid the problem that the number of recorded images in which a certain person is photographed is less than the desired number, so that convenience during recording and shooting is improved.

  In the information processing apparatus according to aspect 6 of the present invention, in the aspect 5, the imaging control unit controls the image acquisition unit so that the number of the recorded images is a constant ratio for each person. Also good.

  According to the above configuration, the image acquisition unit manages the number of shots so that the number of recorded images with each person as a subject is uniformly a predetermined ratio under the control of the shooting control unit. The recorded image is acquired. As a result, each recorded image is accumulated in the recorded image DB so that the ratio of the number of recorded images in which each person is photographed is approximately the same. Therefore, a recorded image is left unbiased with respect to all persons present at the shooting site including unlearned persons. As a result, it is possible to avoid the problem that the number of recorded images in which a certain person is photographed is less than the desired number, so that convenience during recording and shooting is improved.

  In the information processing apparatus according to aspect 7 of the present invention, in the aspect 5, the imaging control unit controls the image acquisition unit so that the number of the recorded images is a ratio predetermined for each person. May be.

  According to the above configuration, the image acquisition unit controls the number of shots so that, under the control of the shooting control unit, the number of recorded images with each person as a subject becomes a predetermined ratio designated for each person. Record images while managing them. As a result, each recorded image is stored in the recorded image DB so that the ratio of the number of recorded images in which each person appears is the ratio set for each person. Therefore, it is possible to adjust the number of recording images to be left for each person, such as leaving a large number or a small number of recorded images of a specific person among the people present at the shooting site. As a result, it is possible to avoid the problem that the number of recorded images in which a certain person is photographed is less than the desired number, so that convenience during recording and shooting is improved.

  An information processing apparatus control method according to an aspect 8 of the present invention is an information processing apparatus control method including an output unit and an imaging unit, and a message that prompts a registration target person to perform a predetermined operation, An output control step (S105) to be output to the output unit, an image acquisition step (S107) to cause the image capturing unit to capture an image after outputting the message in the output control step, and an image captured by the image capturing unit A registration step (S108) of registering an image of the person as an image of the person to be registered when the person who has performed the predetermined operation is included in According to the said method, there exists an effect similar to the said aspect 1.

  The information processing apparatus according to each aspect of the present invention may be realized by a computer. In this case, each unit (software element, for example, the output control unit, the image acquisition unit, and the like) included in the information processing apparatus. A control program for the information processing apparatus that causes the information processing apparatus to be realized by a computer by operating as the registration unit) and a computer-readable recording medium that records the control program also fall within the scope of the present invention.

  The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims, and embodiments obtained by appropriately combining technical means disclosed in different embodiments. Is also included in the technical scope of the present invention. Furthermore, a new technical feature can be formed by combining the technical means disclosed in each embodiment.

DESCRIPTION OF SYMBOLS 1 Dialogue robot (information processing apparatus), 10 Control part, 11 Storage part, 12 Voice input part (input part), 13 Communication part (input part), 14 Display part (output part), 15 Voice output part (output part) , 16 Imaging unit, 20 List management unit, 21 Video processing unit, 22 Output control unit, 23 Shooting necessity determination unit (shooting control unit), 24 Image acquisition unit, 25 Face image registration unit (registration unit), 26 Photo storage Part, 30 identification part, 31 detection part, 32 interpretation part, 40 registration subject list, 41 photographing subject list, 42 photographing condition (ratio), 43 recorded image database

Claims (9)

An information processing apparatus including an output unit and an imaging unit,
An output control unit that causes the output unit to output a message prompting the registration target person to perform a predetermined operation;
An image acquisition unit that causes the imaging unit to capture an image after the output control unit outputs the message;
A registration unit that registers an image of the person as an image of the person to be registered when a person who has performed the predetermined operation is included in the image captured by the imaging unit; Information processing apparatus. The output control unit outputs one identification information read from a registration target person list including identification information of one or more registration target persons as at least a part of the message,
The information processing apparatus further includes:
A detection unit for detecting a person who has performed the predetermined operation from a live view image acquired by the imaging unit after the output control unit has output the message;
The image acquisition unit acquires the image of the person detected by the detection unit by causing the imaging unit to capture the image,
The information according to claim 1, wherein the registration unit registers the image by associating the identification information output by the output control unit with the image acquired by the image acquisition unit. Processing equipment. An audio input unit for acquiring audio;
Interpreting the voice recognition result of the acquired voice, and acquiring the identification information of the person to be registered;
The information processing apparatus according to claim 2, further comprising: a list management unit that adds the acquired identification information to the registration target person list.   The list management unit, when an image associated with the acquired identification information is not registered, adds the identification information to the registration target person list. Information processing device. The image acquisition unit is configured to acquire an image of the person as a recorded image when the person of the image registered by the registration unit is included in the live view video acquired by the imaging unit.
The information processing apparatus further includes:
A recorded image database for storing the recorded images acquired by the image acquisition unit;
An imaging control unit that controls the image acquisition unit to acquire the recorded image so that the number of recorded images that are stored in the recorded image database is a predetermined ratio for each person. The information processing apparatus according to claim 1, wherein the information processing apparatus comprises:   The information processing apparatus according to claim 5, wherein the photographing control unit controls the image acquisition unit so that the number of the recorded images is a constant ratio for each person.   The information processing apparatus according to claim 5, wherein the photographing control unit controls the image acquisition unit so that the number of the recorded images is a ratio determined in advance for each person. A method for controlling an information processing apparatus including an output unit and an imaging unit,
An output control step for causing the output unit to output a message prompting the person to be registered to perform a predetermined operation;
An image acquisition step of causing the imaging unit to capture an image after outputting the message in the output control step;
A registration step of registering an image of the person as the image of the person to be registered when the person who has performed the predetermined operation is included in the image captured by the imaging unit. Control method.   A control program for causing a computer to function as the information processing apparatus according to claim 1, wherein the control program causes the computer to function as the output control unit, the image acquisition unit, and the registration unit.

Images