JP2017059916A - Content output device, content output method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable output of a content that can attract the interest of people.SOLUTION: In a digital signage device 1, a control part 23 executes human detection processing on a photographed image acquired by an imaging part 31. When a person is detected through the human detection processing, the control part 23 executes face recognition processing on the photographed image acquired by the imaging part 31, and determines whether the reaction of the detected person corresponds to a predetermined condition on the basis of a recognized face image. When determining that the reaction corresponds to the predetermined condition, the control part 23 causes a voice output part 33 to output a voice content 331 with the details different from that of a display content 271 output from an image forming part 27.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a content output device, a content output method, and a program.

  2. Description of the Related Art Conventionally, there is known a video output device-equipped device that projects content onto a screen formed in a contour shape of a person or the like appearing in the content (see, for example, Patent Document 1).

JP 2011-150221 A

  However, the content output device such as a device described in Patent Document 1 only broadcasts predetermined content regularly or repeatedly. For this reason, it has been difficult to attract people's interests, and there have been problems such as being passed through even if a person comes in front of the content output device, or being immediately away.

  An object of the present invention is to enable content output that can attract people's interest.

In order to solve the above-mentioned problem, the content output device of the invention according to claim 1 provides:
First output means for outputting content;
Second output means for outputting content in an output format different from the first output means;
A person detecting means for detecting a person;
Control means for causing the second output means to output content having a content different from the content output by the first output means based on the detection result by the human detection means;
Is provided.

  According to the present invention, it is possible to output content that can attract people's interest.

It is a block diagram which shows the functional structure of the digital signage apparatus in this embodiment. It is a figure which shows schematic structure of the screen part of FIG. (A) is a figure which shows an example of basic utterance sentence data, (b) is a figure which shows an example of a word error conversion table, (c) is a figure which shows an example of a word definition table. It is a flowchart which shows the content output process performed by the control part of FIG. (A) is a figure which shows an example of the normal content output by step S5 of FIG. 4, (b) is a figure which shows an example of the content which produced the typographical error output by step S6 of FIG. . It is a figure which shows the example of the utterance sentence of the content which produced the normal content and the mistake.

  Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following embodiment, a case where the digital signage apparatus 1 is applied as a content output apparatus according to the present invention will be described as an example. The present invention is not limited to the illustrated example.

[Configuration of Digital Signage Device 1]
FIG. 1 is a block diagram showing a main control configuration of the digital signage apparatus 1 in the present embodiment. FIG. 2 is a front view illustrating a schematic configuration of the screen unit 22. The digital signage apparatus 1 is an apparatus that is installed in, for example, a store or the like and outputs content describing a product.

  As shown in FIG. 1, the digital signage apparatus 1 includes a projection unit 21 that irradiates content image light, and a screen unit 22 that receives the image light emitted from the projection unit 21 at the back and projects it onto the front. Yes.

First, the projection unit 21 will be described.
The projection unit 21 includes a control unit 23, a projector 24, a storage unit 25, and a communication unit 26. The projector 24, the storage unit 25, and the communication unit 26 are connected to the control unit 23 as shown in FIG.

  The control unit 23 includes a CPU (Central Processing Unit) that executes various programs stored in the storage unit 25 to perform predetermined calculations and control of each unit, and a memory that is a work area when the program is executed. (Both not shown). The control unit 23 functions as a control unit in cooperation with a program stored in the program storage unit 251 of the storage unit 25. Further, the control unit 23 functions as a human detection unit in cooperation with the imaging unit 31.

The projector 24 is a projection device that converts the image data output from the control unit 23 into image light and irradiates the image data toward the screen unit 22. For example, the projector 24 performs a display operation by individually turning on / off each tilt angle of a plurality of micromirrors arranged in an array (in the case of XGA, horizontal 1024 pixels × vertical 768 pixels) at high speed. A DLP (Digital Light Processing) (registered trademark) projector using a DMD (digital micromirror device), which is a display element that forms a light image with the reflected light, is applicable.
The projector 24 together with the image forming unit 27 constitutes a first output unit.

  The storage unit 25 is configured by an HDD (Hard Disk Drive), a nonvolatile semiconductor memory, or the like. As shown in FIG. 1, the storage unit 25 includes a program storage unit 251 and a content storage unit 252.

  The program storage unit 251 stores a system program executed by the control unit 23, various processing programs, data necessary for executing these programs, and the like.

  The content storage unit 252 stores information for outputting content. In the present embodiment, the content is composed of content in two different output formats, display content 271 and audio content 331. Specifically, the content storage unit 252 defines moving image data composed of a plurality of frame images for outputting the display content 271 and text data for outputting the audio content 331 corresponding to each frame image. Information (basic utterance sentence data 252a shown in FIG. 3 (a), an error conversion table 252b shown in FIG. 3 (b), and a word definition table 252c shown in FIG. 3 (c)) is stored. The audio content 331 is content that becomes speech voice of the character C included in the display content 271 (see FIGS. 5A and 5B).

  The basic utterance sentence data 252a is information for specifying the text data of the basic utterance sentence of the audio content 331, as shown in FIG. The basic utterance sentence data 252a includes the change part A including the words (#SENDEN_, #SHOUHIN_) defined in the word definition table 252c, as shown in the record of number 0 in the error word conversion table 252b of FIG. , B are included.

  The word error conversion table 252b is a table in which a condition for generating a word error and a word to be changed when the condition is met are stored in association with each other. As shown in FIG. 3B, the error conversion table 252b is composed of items of “number”, “condition”, “change location A”, and “change location B”. “Condition” is information that defines a condition that causes an error in content output. “Change location A” and “change location B” are information indicating how to change the change location A and the change location B of the basic utterance sentence data 252a when the “condition” is met. In a state (number 0) that does not correspond to the conditions of numbers 1 to 4 in the wrong word conversion table 252b, text data for voice output is generated based on the basic utterance sentence data 252a. When any of the conditions of Nos. 1 to 4 is satisfied, text data for voice output is generated in which the changed words A and B of the basic utterance sentence data 252a are changed based on the wrong word conversion table 252b. In the wrong word conversion table 252b, number 0 has the lowest priority, but numbers 1 to 4 have a higher priority as the number is smaller.

  The word definition table 252c is a table that defines common words used in the basic utterance sentence data 252a and the mistaken word conversion table 252b.

  The communication unit 26 includes a modem, a router, a network card, and the like, and performs communication with an external device.

Next, the screen unit 22 will be described.
As shown in FIG. 2, the screen unit 22 includes an image forming unit 27 and a pedestal 28 that supports the image forming unit 27.

  The image forming unit 27 is for rear projection in which a film-shaped Fresnel lens is laminated on a single translucent plate 29 such as an acrylic plate, which is arranged so as to be substantially orthogonal to the irradiation direction of the image light. It is a screen configured by attaching a film screen.

The pedestal 28 is provided with an imaging unit 31, a button-type operation unit 32, and an audio output unit 33.
The imaging unit 31 captures an image of a space facing the image forming unit 27 and generates a captured image.
Although not shown, the imaging unit 31 includes a camera including an optical system and an imaging element, and an imaging control unit that controls the camera. The optical system of the camera is directed in a direction in which a person in front of the image forming unit 27 can be photographed. The image pickup device is an image sensor such as a charge coupled device (CCD) or a complementary metal-oxide semiconductor (CMOS), and converts an optical image that has passed through the optical system into a two-dimensional image signal.

The audio output unit 33 includes a speaker or the like, and outputs audio content 331 according to control from the control unit 23. The audio output unit 33 functions as a second output unit.
The imaging unit 31, the operation unit 32, and the audio output unit 33 are connected to the control unit 23 as shown in FIG.

[Operation of Digital Signage Device 1]
Next, the operation of the digital signage apparatus 1 will be described.
FIG. 4 shows a flowchart of content output processing executed in the digital signage apparatus 1. The content output process is executed in cooperation with the control unit 23 and the program stored in the program storage unit 251.

  First, the control part 23 performs a person detection process (step S1). In step S <b> 1, for example, the control unit 23 causes the imaging unit 31 to perform imaging, and performs a human detection process on the obtained captured image. As human detection processing, for example, a known image processing technique such as a method of detecting a person by taking a difference between a background image prepared in advance and a captured image, a method of detecting a person shape by pattern recognition, or the like is used. Can do.

  Next, the control unit 23 determines whether a person is detected as a result of the person detection process (step S2). When it is determined that no person is detected (step S2; NO), the control unit 23 proceeds to step S5.

  On the other hand, when it is determined that a person has been detected (step S2; YES), the control unit 23 performs a face recognition process on the captured image acquired in step S1 (step S3). For the face recognition processing, for example, a known image processing technique can be used as described in JP-A-2006-202049.

Next, the control unit 23 determines whether or not the person detected in step S1 satisfies a predetermined condition (predetermined condition) based on the face image recognized by the face recognition process (step S4). ).
The predetermined condition used in step S4 is a condition that serves as a trigger for generating an error, and includes the following conditions (1) to (4).
(1) A person is in front of the digital signage device 1 for m seconds (for example, m = 5) or more (2) A person in front of the digital signage device 1 is not smiling (3) A person is in front of the digital signage device 1 (4) N or more people (for example, n = 100) have passed in front of the digital signage device 1. Here, (3) indicates that a person away from the digital signage device 1 This is a condition indicating that there are many.
Note that the predetermined condition used in step S4 indicates that a person in front of the digital signage apparatus 1 has a reaction that it is determined that it is preferable to change the content so as to attract people's interest. If it is the conditions which are estimated, it will not specifically limit.

For example, the control unit 23 stores the face image recognized from the captured image acquired in the immediately preceding m seconds in the memory, and compares the face image recognized in step S3 with the face image stored in the memory. By doing so, it is determined whether or not the same person is in front of the digital signage apparatus 1 for m seconds or more.
Further, for example, the control unit 23 determines whether or not the person in front of the digital signage device 1 is smiling based on the face eyes and mouth shape recognized in step S3.
Further, for example, the control unit 23 performs gender identification processing on the face image recognized in step S3, and among the number of people detected in step S1, the ratio of the number of genders identified in the gender identification processing (gender identification rate) ) Is calculated. Then, based on the comparison between the calculated gender identification rate and a predetermined threshold, it is determined whether or not the gender identification rate of the person in front of the digital signage apparatus 1 is lower than the predetermined threshold.
For example, the control unit 23 counts the number of persons who have passed in front of the digital signage device 1 based on a comparison between the face image recognized in the previous face recognition process and the face image recognized in the current face recognition process. Then, it is added to the counter in the memory, and it is recognized whether or not a predetermined number or more (for example, 100 or more people) have passed in front of the digital signage device 1 based on the counter value after the addition.

  If it is determined in step S4 that the person detected in step S1 does not meet the predetermined condition (step S4; NO), the control unit 23 outputs the normal content (step S5), and the process proceeds to step S7. To do. That is, the control unit 23 reads the image data of the display content 271 from the content storage unit 252, sequentially outputs the frame images to the projector 24, and causes the projector 24 to project the image forming unit 27. Further, text data of the basic utterance sentence is generated based on the basic utterance sentence data 252a and the word definition table 252c corresponding to the frame image stored in the content storage unit 252, and the voice is synthesized based on the generated text data. Then, the voice output unit 33 outputs the voice content 331 of the basic utterance sentence.

  FIG. 5A shows an example of normal content output in step S5. In the present embodiment, the display content 271 includes the character C, and the audio content 331 is the speech voice of the character C. In the normal content, the contents of the display content 271 and the audio content 331 are the same. That is, as shown in FIG. 5A, the display content 271 of the normal content is a content for promoting meat buns, and the audio content 331 of the normal content is, for example, “This is the meat bun recommended for our shop” It is the sound of the content that promotes meat buns.

On the other hand, if it is determined in step S4 that the person detected in step S1 satisfies the predetermined condition (step S4; YES), the control unit 23 makes an error in accordance with the corresponding condition. The generated content is output (step S6), and the process proceeds to step S7.
In step S <b> 6, the control unit 23 reads the image data of the display content 271 from the content storage unit 252, sequentially outputs the frame images to the projector 24, and causes the projector 24 to project the image forming unit 27. Also, the text for voice output in which the wording of the changed portions A and B of the basic utterance sentence data 252a corresponding to the output frame image is changed based on the word error conversion table 252b stored in the content storage unit 252. Generate data. Then, the voice is synthesized based on the generated text data, and the voice output unit 33 outputs the voice content 331 in which an error has occurred.

  FIG. 5B shows an example of content in which an error is output in step S6. FIG. 5B is an example of content output when the above conditions (1) and (2) are met. As shown in FIG. 5B, in the content output when the above conditions (1) and (2) are met, the display content 271 is the same as the content of the normal content, but the audio content 331 is the normal content. It differs from the content. That is, the content of the display content 271 and the content of the audio content 331 are different. For example, as shown in FIG. 5 (b), the audio content 331 is “This is our recommended dumpling, not meat bun (sweat)” for the display content 271 that displays the meat bun advertisement. In this way, it is possible to draw people's interest by mistakenly saying the contents different from the display contents 271 on purpose.

  FIG. 6 shows the utterance sentence of the audio content 331 (Normal) and the utterance sentence of the audio content 331 when the above conditions (1) to (4) are satisfied. As shown in FIG. 6, the audio content 331 of the content output in step S6 when the conditions (1) to (4) are met, the character C of the display content 271 makes a mistake or forgets to speak Content that is more humane, such as giving a special feeling to viewers. Therefore, it becomes possible to attract people's interest in the output content.

  In step S7, the control unit 23 determines whether or not the operation unit 32 has instructed termination (power OFF) (step S7). When it is determined that the termination is not instructed (step S7; NO), the control unit 23 returns to step S1. When it is determined that the end is instructed (step S7; YES), the control unit 23 ends the content output process.

As described above, according to the digital signage apparatus 1, the control unit 23 performs a person detection process on the captured image acquired by the imaging unit 31. When a person is detected by the person detection process, the control unit 23 performs a face recognition process on the photographed image acquired by the imaging unit 31, and based on the recognized face image, a reaction of the detected person is predetermined. It is determined whether or not this condition is met. If it is determined that the predetermined condition is satisfied, the control unit 23 causes the audio output unit 33 to output audio content 331 having a content different from the display content 271 output by the image forming unit 27. Specifically, the audio output unit 33 outputs the audio content 331 in which a part of the utterance sentence of the audio content 331 corresponding to the display content 271 is changed and an error is generated.
Accordingly, it is possible to output content that is more human and can attract people's interest.

  In addition, the description content in the said embodiment is a suitable example of the digital signage apparatus which concerns on this invention, and is not limited to this.

  For example, in the above-described embodiment, when a person is detected, it is determined whether the detected person (detected person's reaction) meets a predetermined condition, and the predetermined condition is met. In addition, the content in which a mistake has been made is output, but the present invention is not limited to this. For example, when a person is detected, content in which an error has occurred may be output. Thereby, when a person is detected, it is possible to output content that can attract the person's interest.

In the above embodiment, the content output control is performed by the digital signage device 1 alone, but the present invention is not limited to this example.
For example, information specifying moving image data for outputting the display content 271 to a server device (not shown) connected to the digital signage device 1 via a communication network and information specifying the text data of the audio content 331 corresponding to each frame image are stored. It is good to keep it. And the picked-up image acquired by the imaging part 31 is transmitted to a server apparatus via the communication part 26, the process of step S1-step S4 is performed by a server apparatus, and display content is displayed by a server apparatus based on the determination result of step S4. The video data of 271 is read, and the text data of the audio content 331 of the normal content or the content in which the error is generated is generated and transmitted to the digital signage device 1, and the digital signage device 1 receives it from the server device The content may be output in real time based on the data.

  Further, in the above embodiment, the case where the character C is included in the display content 271 and the audio content 331 is output as the speech voice of the character C has been described as an example, but a person may be used instead of the character C.

  In the above embodiment, the case where the present invention is applied to a digital signage apparatus that displays an image by projecting an image from a projector onto a screen has been described as an example. Even when applied to a content reproduction apparatus including the display device, the same effect can be obtained, and the present invention is not limited to this example.

  In addition, the detailed configuration and detailed operation of each device constituting the digital signage device can be changed as appropriate without departing from the spirit of the invention.

Although several embodiments of the present invention have been described, the scope of the present invention is not limited to the above-described embodiments, but includes the scope of the invention described in the claims and equivalents thereof.
The invention described in the scope of claims attached to the application of this application will be added below. The item numbers of the claims described in the appendix are as set forth in the claims attached to the application of this application.
[Appendix]
<Claim 1>
First output means for outputting content;
Second output means for outputting content in an output format different from the first output means;
A person detecting means for detecting a person;
Control means for causing the second output means to output content having a content different from the content output by the first output means based on the detection result by the human detection means;
A content output device comprising:
<Claim 2>
The content output apparatus according to claim 1, wherein the content output by the first output means is display content, and the content output by the second output means is audio content.
<Claim 3>
The display content and the audio content are content representing contents corresponding to each other,
The control unit changes a part of the audio content corresponding to the display content output by the first output unit based on the detection result by the human detection unit, and causes the second output unit to output it. The content output device according to claim 2.
<Claim 4>
The control means, based on the detection result by the person detection means, outputs the audio content in which an error has occurred in the utterance sentence of the audio content corresponding to the display content output by the first output means. The content output device according to claim 3, wherein the output unit outputs the content.
<Claim 5>
The control means recognizes a reaction of the detected person when the person is detected by the person detection means, and when the recognized reaction meets a predetermined condition, the first output means The content output device according to any one of claims 1 to 4, wherein the second output unit outputs a content having a content different from the content output by the first output unit.
<Claim 6>
Outputting the content by the first output means;
Outputting a content in an output format different from that of the first output means by a second output means;
Detecting a person by means of human detection means;
A step of causing the second output means to output a content having a content different from the content output by the first output means based on a detection result by the human detection means;
Content output method.
<Claim 7>
Used in a content output apparatus comprising: first output means for outputting content; second output means for outputting content in an output format different from that of the first output means; and human detection means for detecting a person Computer
Control means for causing the second output means to output content having a content different from the content output by the first output means, based on the detection result by the human detection means;
Program to function as.

DESCRIPTION OF SYMBOLS 1 Digital signage apparatus 21 Projection part 22 Screen part 23 Control part 24 Projector 25 Storage part 251 Program storage part 252 Content storage part 26 Communication part 27 Image formation part 271 Display content 28 Base 29 Translucent board 31 Imaging part 32 Operation part 33 Sound Output unit 331 Audio content

Claims (7)

First output means for outputting content;
Second output means for outputting content in an output format different from the first output means;
A person detecting means for detecting a person;
Control means for causing the second output means to output content having a content different from the content output by the first output means based on the detection result by the human detection means;
A content output device comprising:   The content output apparatus according to claim 1, wherein the content output by the first output means is display content, and the content output by the second output means is audio content. The display content and the audio content are content representing contents corresponding to each other,
The control unit changes a part of the audio content corresponding to the display content output by the first output unit based on the detection result by the human detection unit, and causes the second output unit to output it. The content output device according to claim 2.   The control means, based on the detection result by the person detection means, outputs the audio content in which an error has occurred in the utterance sentence of the audio content corresponding to the display content output by the first output means. The content output device according to claim 3, wherein the output unit outputs the content.   The control means recognizes a reaction of the detected person when the person is detected by the person detection means, and when the recognized reaction meets a predetermined condition, the first output means The content output device according to any one of claims 1 to 4, wherein the second output unit outputs a content having a content different from the content output by the first output unit. Outputting the content by the first output means;
Outputting a content in an output format different from that of the first output means by a second output means;
Detecting a person by means of human detection means;
A step of causing the second output means to output a content having a content different from the content output by the first output means based on a detection result by the human detection means;
Content output method. Used in a content output apparatus comprising: first output means for outputting content; second output means for outputting content in an output format different from that of the first output means; and human detection means for detecting a person Computer
Control means for causing the second output means to output content having a content different from the content output by the first output means, based on the detection result by the human detection means;
Program to function as.

Images