JP6268722B2 - Display device, display method, and program - Google Patents

Description

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

  Patent Document 1 discloses a digital signage system.

  Patent Document 2 discloses a comment layout device that arranges a comment image (balloon image) for displaying a comment arbitrarily determined by a user on a target image having a human face as a subject. The comment layout device includes an image data acquisition unit that acquires image data of a target image, an image region recognition unit that analyzes the image data and recognizes an image region of a person's face in the target image, and an image of the person's face A feature estimator that analyzes image data corresponding to the region and estimates a facial feature of the person, and a form determiner that determines the form of the comment image (speech image) using the feature estimation result; The comment that arranges the comment image (balloon image) having the above form in association with the target image includes a part.

JP 2012-2226017 A JP 2007-122533 A

  The inventor of the present application examined a technique for displaying a photographed person (passerby or the like) on a display of digital signage. If the scenery of you and where you are at that time is displayed on digital signage, people are likely to have a strong interest in it. However, if the captured image is simply displayed on the display, it is immediately lost. Also, the degree to which people are interested is relatively low.

  Patent Document 1 does not disclose such usage, problems, and solutions. Patent Document 2 is not a technique related to digital signage.

  This invention makes it a subject to provide the technique for raising the human interest degree with respect to the digital signage which displays the imaged person on a display.

According to the present invention,
An imaging device;
Person extraction means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determination means to the person in the image;
Display means for displaying the processed image on a display;
I have a,
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
A display device is provided in which the display is installed near the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction .

Moreover, according to the present invention,
Computer
Person extracting means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determining means to the person in the image;
Display means for displaying the processed image on a display;
Function as
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display is provided with a program installed near the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction .

Moreover, according to the present invention,
Computer
A person extracting step of extracting a person from the image captured by the imaging device;
A person attribute estimation step of estimating the attribute of the person extracted in the person extraction step using the image;
Using the attribute estimated in the person attribute estimation step, a line determination step for determining a line to be given to the person of the attribute;
An image processing step for generating a processed image for giving the line determined in the line determination step to the person in the image;
A display step of displaying the processed image on a display;
Run
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
There is provided a display method in which the display is installed in the vicinity of the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction.

  ADVANTAGE OF THE INVENTION According to this invention, it becomes possible to raise a person's interest degree with respect to the digital signage which displays the imaged person on a display.

It is a figure which shows an example of the functional block diagram of the display apparatus of this embodiment. It is a flowchart which shows an example of the flow of a process of the display method of this embodiment. It is a figure which shows an example of the image which the imaging device of this embodiment imaged. It is a figure which shows an example in which the display part of this embodiment displayed the process image. It is a figure which shows an example of the utilization scene of the display apparatus of this embodiment. It is a figure which shows an example of the utilization scene of the display apparatus of this embodiment. It is a figure which shows an example of the utilization scene of the display apparatus of this embodiment. It is a figure which shows an example of the functional block diagram of the display apparatus of this embodiment. It is a figure which shows an example of the information which the dialogue information storage part of this embodiment memorize | stores. It is a figure which shows an example of the information which the dialogue information storage part of this embodiment memorize | stores. It is a figure which shows an example of the information which the dialog determination part of this embodiment can memorize | store. It is a figure which shows an example of the information which the dialog determination part of this embodiment can memorize | store. It is a figure which shows an example of the information which the dialog determination part of this embodiment can memorize | store. It is a figure which shows an example of the functional block diagram of the display apparatus of this embodiment. It is a figure which shows an example of the information which the dialogue information storage part of this embodiment memorize | stores. It is a figure which shows an example of the information which the dialogue information storage part of this embodiment memorize | stores. It is a flowchart which shows an example of the flow of a process of the display method of this embodiment. It is a figure which shows an example of the image which the imaging device of this embodiment imaged. It is a figure which shows an example in which the display part of this embodiment displayed the process image. It is a figure which shows an example of the functional block diagram of the display apparatus of this embodiment. It is a figure which shows an example of the information which the process information storage part of this embodiment memorize | stores. It is a figure which shows an example in which the display part of this embodiment displayed the process image.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  The apparatus according to the present embodiment includes an arbitrary computer CPU, memory, and a program loaded in the memory (a program stored in the memory in advance from the stage of shipping the apparatus, a storage medium such as a CD, and the like on the Internet). And a storage unit such as a hard disk for storing the program, and a network connection interface, and any combination of hardware and software. It will be understood by those skilled in the art that there are various modifications to the implementation method and apparatus.

  In addition, the functional block diagram used in the description of the present embodiment shows a functional unit block, not a hardware unit configuration. In these drawings, each device is described as being realized by one device, but the means for realizing it is not limited to this. That is, it may be a physically separated configuration or a logically separated configuration.

<First Embodiment>
First, an outline of the present embodiment will be described.
The display device of this embodiment can be used as a digital signage that displays a captured person (passerby or the like) on a display. The display device according to the present embodiment does not display the captured image as it is when the captured person is displayed on the display, but a processed image in which a predetermined dialogue is given to the person in the image (the person seems to speak) Display). As a result, the degree of interest of the person with respect to the display image can be increased, and if the comment content is devised, it can be used as an advertising medium. However, if the dialogue given to a person is always the same, the degree of interest of the person with respect to the display image cannot be sufficient.

  Therefore, the display device according to the present embodiment estimates the attributes (gender, age group, race, facial expression, etc.) of the imaged person (the person existing in the image), and displays the dialogue according to the estimated attribute. To grant. According to such a display device of the present embodiment, the dialogue given to each person changes according to the attribute of the person displayed on the display. As a result, it is expected that the degree of human interest in the display image is improved.

Hereinafter, the configuration of the display device of the present embodiment will be described in detail.
FIG. 1 shows an example of a functional block diagram of the display device 1 of the present embodiment. As illustrated, the display device 1 includes an imaging device 10, a person extraction unit 11, a person attribute estimation unit 12, a dialogue determination unit 13, an image processing unit 14, and a display unit 15.

  The imaging device 10 captures a moving image and / or a still image. The imaging device 10 is installed at a predetermined location, and captures an image in the predetermined area continuously or at a predetermined timing (for example, at a predetermined time, when a person is detected in the imaging area). The installation location is not particularly limited, and may be a public area such as a station or an airport, or may be a supermarket, a shopping mall, an entertainment facility, or the like.

  The person extraction unit 11 extracts a person from the image captured by the imaging device 10. The person attribute estimation unit 12 estimates an attribute of the person (eg, at least one of sex, age group, race, facial expression, etc.) extracted by the person extraction unit 11 using an image. Means for realizing these processes by the person extraction unit 11 and the person attribute estimation unit 12 are not particularly limited, but may be realized by using, for example, a well-known face recognition technique. Such a technique is disclosed in, for example, Japanese Patent Application Laid-Open No. 2007-880057. In addition, the structure of the person extraction part 11 and the person attribute estimation part 12 is not limited to what is described in the said literature.

  The line determination unit 13 determines a line to be given to a person with the attribute using the attribute estimated by the person attribute estimation unit 12 (eg, at least one of gender, age group, race, facial expression, etc.). To do. The line determination unit 13 can determine different lines for persons having different attributes. That is, the dialogue determination unit 13 can determine dialogues having various contents according to the attributes.

  For example, the line determination unit 13 can make a line given to a person with a certain attribute content that does not feel uncomfortable as a statement of the person with that attribute. As an example, it can be a speech line that matches the attributes of a person. If you want to promote a certain product “Orangesas”, you ’ll decide on a man ’s tone “Orange Jesus”! ~! "Etc. may be determined. In addition, it is possible to determine the gender, age group, race, tone of the person's expression at that time and / or dialogue of the content.

  As another example, the line determination unit 13 can set a line to be given to a person with a certain attribute as a content in which the person with that attribute is interested. A person is considered interested in a display image on which he is displayed. For this reason, it is expected that a processed image in which a dialogue is given to a certain person is viewed by the person with a high probability. If the dialogue given to the person makes the person interested, it is considered that the person's interest in the display image is further increased. Since the line determination unit 13 can determine the line to be given to the person based on the estimated attribute of the person (eg, at least one of gender, age group, race, facial expression, etc.), a high probability Thus, it can be made contents that the person of the attribute is interested in. For example, “Golf shop A is on sale!” May be determined for middle-aged men.

  The image processing unit 14 generates a processed image that gives the person in the image the line determined by the line determination unit 13. For example, the image processing unit 14 stores in advance data (hereinafter, “line-granted image data”) of an image (hereinafter, “line-granted image data”) used to give a line such as a speech balloon image, Using the dialogue giving image data, it is possible to generate a processed image that gives a predetermined dialogue in an image captured by the imaging device 10. The processed image data is image data different from the image data captured by the imaging device 10 and is data for displaying a dialogue-giving image and dialogue on the display so as to overlap the image captured by the imaging device 10. May be. Alternatively, the processed image data may be image data that has been modified so that a part of the image data captured by the imaging device 10 is partially modified so that the dialogue-given image and dialogue are displayed at predetermined positions in the image. Good.

  The position where the in-image dialogue-added image is arranged in the image captured by the imaging device 10 can be determined based on the position of the person's face in the image specified by a known face recognition technique.

  The display unit 15 displays the processed image generated by the image processing unit 14 on the display. When the processed image data and the image data captured by the imaging device 10 are different image data, the display unit 15 uses both of these data and places the processed image data at a predetermined position on the image captured by the imaging device 10. The dialogue application image included in the processed image and the image on which the dialogue is superimposed are displayed on the display. When the processed image data is image data that has been modified so that a part of the data of the image captured by the imaging device 10 is corrected and the dialogue-given image and dialogue are displayed at a predetermined position in the image, The display unit 15 displays an image on the display using the image data. The display unit 15 may display a still image on the display as a processed image, or may display a moving image on the display.

FIG. 2 is a flowchart showing an example of the processing flow of the display method of the present embodiment.
For example, when the imaging device 10 captures (acquires) the image shown in FIG. 3 (S1), the person extraction unit 11 extracts a person from the image captured by the imaging device (S2). Thereafter, the person attribute estimation unit 12 estimates the attribute of the person extracted by the person extraction unit 11 using an image (S3). Next, the line determination unit 13 determines a line to be given to the person with the attribute using the attribute estimated by the person attribute estimation unit 12 (S4). Thereafter, the image processing unit 14 generates a processed image that gives the person in the image the line determined by the line determination unit 13 (S5). Then, the display unit 15 displays the processed image generated by the image processing unit 14 on the display (S6). FIG. 4 shows an example of an image displayed on the display 300 by the display unit 15. When the configuration is realized by a moving image, the position in the person image extracted in S2 is tracked, and the position of the dialogue is changed in accordance with the movement of the person position.

  According to the display device of the present embodiment described above, the dialogue to be given to the person can be determined according to the attribute of the person displayed in the image. That is, dialogues with various contents according to the attributes of the person can be displayed. For this reason, the line given to a person does not become the same every time. According to such a display device of the present embodiment, it is possible to increase the degree of human interest in the displayed image.

  Further, according to the display device of the present embodiment, the dialogue given to a person with a certain attribute can be made uncomfortable as the content of the remark of the person with that attribute. For example, a man's dialogue can be determined for men and a woman's dialogue for women. In addition, it is possible to determine the speech of the age group, race, tone and / or content according to the facial expression of the person at that time.

  In addition, according to the display device of the present embodiment, the dialogue to be given to a person with a certain attribute can be content that the person with that attribute is interested in. A person is considered interested in a display image on which he is displayed. For this reason, it is expected that a processed image in which a dialogue is given to a certain person is viewed by the person with a high probability. If the dialogue given to the person in the image makes the person interested, it is expected that the degree of interest of the person will further increase.

<Second Embodiment>
In this embodiment, an example of an application scene of the display device 1 of the first embodiment is shown.

<Application example 1>
In this application example, the display device of the first embodiment is used by installing the imaging device 10 and the display unit 15 in the vicinity of a transportation means for transporting a person in one direction.

  An example is shown in FIG. In this example, the imaging device 100 (imaging device 10) and the display 300 (display unit 15) are installed in the vicinity of an escalator 400 that moves a person in one direction toward the end point. The imaging apparatus 100 is installed at a position where a person who is moving by the escalator 400 can be imaged. The display 300 is installed near the end point of the escalator 400. Note that the installation position of the display 300 is not necessarily near the end point of the escalator 400, and can be installed at an arbitrary position downstream of the position captured by the imaging apparatus 100 in the moving direction of the escalator 400. Specific installation positions and installation methods of the imaging apparatus 100 and the display 300 are design matters.

  The imaging device 100, the control device 200, and the display 300 are connected to each other by wire and / or wireless, and an image captured by the imaging device 100 and a processed image generated by the image processing unit 14 can be displayed on the display 300. . The control device 200 includes a person extraction unit 11, a person attribute estimation unit 12, a line determination unit 13, and an image processing unit 14. Note that the control device 200 and the display 300 may be provided in the same casing.

  In the case of this application example, when an image captured by the image capturing apparatus 100 is displayed on the display 300 in real time, the captured person cannot view the image. Therefore, in this application example, the image captured by the imaging apparatus 100 is not displayed on the display 300 in real time, but is displayed on the display 300 after a predetermined time (eg, 3 seconds, 5 seconds, 10 seconds, etc.) has elapsed since the time of imaging. can do. The predetermined time can be an estimated time required for the person imaged by the imaging apparatus 100 to move to the vicinity of the display 300. This estimated time can be determined based on the moving speed of the escalator 400, the distance between the imaging device 100 and the display 300, and the like.

  According to this application example, it is possible to achieve the same effect as that of the first embodiment. In addition, it is possible to increase the probability that the processed person can view the processed image.

<Application example 2>
In this application example, the display of the imaging device 10 and the display unit 15 is installed in the vicinity of the transportation means for transporting a person in one direction, and the display device of the first embodiment is used.

  An example is shown in FIG. In this example, the imaging device 100 (imaging device 10) and the display 300 (display unit 15) are installed in the vicinity of a moving sidewalk 500 that moves a person in one direction toward the end point. The imaging apparatus 100 is installed at a position where a moving person can be imaged by a moving sidewalk 500. The display 300 is installed near the end point of the moving sidewalk 500. Note that the installation position of the display 300 is not necessarily near the end point of the moving sidewalk 500, and may be installed at an arbitrary position downstream of the position captured by the imaging device 100 in the moving direction of the moving sidewalk 500. it can. Specific installation positions and installation methods of the imaging apparatus 100 and the display 300 are design matters.

  The imaging device 100, the control device 200, and the display 300 are connected to each other by wire and / or wireless, and an image captured by the imaging device 100 and a processed image generated by the image processing unit 14 can be displayed on the display 300. . The control device 200 includes a person extraction unit 11, a person attribute estimation unit 12, a line determination unit 13, and an image processing unit 14. Note that the control device 200 and the display 300 may be provided in the same casing.

  In the case of this application example, when an image captured by the image capturing apparatus 100 is displayed on the display 300 in real time, the captured person cannot view the image. Therefore, in this application example, the image captured by the imaging apparatus 100 is not displayed on the display 300 in real time, but is displayed on the display 300 after a predetermined time (eg, 3 seconds, 5 seconds, 10 seconds, etc.) has elapsed since the time of imaging. can do. The predetermined time can be an estimated time required for the person imaged by the imaging apparatus 100 to move to the vicinity of the display 300. The predicted time can be determined based on the moving speed of the moving sidewalk 500, the distance between the imaging device 100 and the display, and the like.

  According to this application example, it is possible to achieve the same effect as that of the first embodiment. In addition, it is possible to increase the probability that the processed person can view the processed image.

<Application example 3>
In this application example, the display device of the first embodiment is used by installing the display of the imaging device 10 and the display unit 15 in a store or facility that provides a place where a customer stays for a certain time, such as a restaurant or a coffee shop.

  An example is shown in FIG. In this example, a display 300 (display unit 15) is installed on a table at a box seat in a restaurant. The imaging device 100 (imaging device 10) is an external space of a restaurant and is installed at a position where a space that can be viewed through a window from the box seat can be imaged. In the example of the present embodiment, the target for viewing the processed image is not the person who captured the image but a customer such as a store or a facility. Specific installation positions and installation methods of the imaging apparatus 100 and the display 300 are design matters.

  The imaging device 100, the control device 200, and the display 300 are connected to each other by wire and / or wireless, and an image captured by the imaging device 100 and a processed image generated by the image processing unit 14 can be displayed on the display 300. . The control device 200 includes a person extraction unit 11, a person attribute estimation unit 12, a line determination unit 13, and an image processing unit 14. Note that the control device 200 and the display 300 may be provided in the same casing.

  An image captured by the imaging apparatus 100 may be displayed on the display 300 in real time, or may be displayed on the display 300 after a predetermined time (eg, 3 seconds, 5 seconds, 10 seconds, etc.) has elapsed since the time of imaging.

  According to this application example, it is possible to achieve the same effect as that of the first embodiment. In addition, it is possible to provide a new and unprecedented entertainment for a person browsing the display 300. In the case of the example of FIG. 7, a customer relaxing at a box seat in a restaurant has a realistic sight that can be seen through a window, and an entertaining image in which a predetermined dialogue is given to a person existing in the sight (on the display 300). It is possible to have a good time while comparing with the displayed image. That is, according to this application example, the degree of interest of the customer with respect to the image displayed on the display 300 can be increased.

  In addition, the illustration here is an example to the last, and the application scene of the display apparatus 1 is not limited to these. For example, you may install the imaging device 100 so that the person in front of the display 300 may be imaged. Then, a processed image created using the captured image (moving image or still image) may be displayed on the display 300 in real time. When configured in this way, it is possible to allow a person included in the processed image to view an image in which he is displayed.

<Third Embodiment>
The display device 1 of the present embodiment has a dialogue storage unit 17 that stores dialogue in association with the attributes of a person, and the dialogue determination unit 13 decides dialogue using information stored in the dialogue storage unit 17. This is different from the first and second embodiments. Other configurations can be the same as those in the first and second embodiments.

  FIG. 8 shows an example of a functional block diagram of the display device 1 of the present embodiment. As illustrated, the display device 1 includes an imaging device 10, a person extraction unit 11, a person attribute estimation unit 12, a line determination unit 13, an image processing unit 14, a display unit 15, and a line storage unit 17. Have. The configurations of the imaging device 10, the person extraction unit 11, the person attribute estimation unit 12, the image processing unit 14, and the display unit 15 are the same as those in the first and second embodiments. Hereinafter, configurations of the dialogue storage unit 17 and the dialogue determination unit 13 will be described.

  The dialogue storage unit 17 stores dialogue information in which a person attribute is associated with a dialogue. FIG. 9 shows an example of dialogue information stored in the dialogue storage unit 17. In the illustrated dialogue information, dialogue is associated with each combination of gender and age group. The dialogue is for the purpose of promoting a product "Orange Jesus". For this reason, the word “Orange Jesus” is included in any dialogue. The content of dialogue is a design matter. Moreover, although the dialogue information of the example shown in FIG. 9 associates dialogue with each combination of gender and age group, as another example, dialogue may be associated with each attribute, or other plural Dialogue may be associated with each combination of attributes.

  The line determination unit 13 acquires the line associated with the attribute estimated by the person attribute estimation unit 12 from the line storage unit 17 and determines the acquired line as a line to be given to the person with the attribute.

  As a modification of the present embodiment, the dialogue storage unit 17 may store dialogue information in which a person attribute, a time zone, and a dialogue are associated with each other. FIG. 10 shows an example of dialogue information stored in the dialogue storage unit 17. The dialogue information shown in the figure associates a time zone and dialogue for each combination of gender and age group. The dialogue is for the purpose of promoting a certain product “Orange Jesus” and has contents suitable for the associated time zone. The content of dialogue is a design matter. Moreover, although the dialogue information in the example shown in FIG. 10 associates dialogue with each combination of gender and age group, as another example, dialogue may be associated with each attribute, or other plural Dialogue may be associated with each combination of attributes.

  The dialogue determination unit 13 of the modification example acquires information indicating the attribute estimated by the person attribute estimation unit 12 and also acquires time information. The time specified by the time information may be a time around the process of determining the dialogue, and it is a design matter to determine the timing of the time. The line determination unit 13 acquires information indicating the current time at a predetermined timing (design matter) from, for example, a clock unit present in the display device 1. Then, the line determination unit 13 acquires the line associated with the attribute estimated by the person attribute estimation unit 12 and the time zone including the acquired time information from the line storage unit 17, and acquires the acquired line. It is determined as a dialogue to be given to a person with that attribute.

  According to the present embodiment, it is possible to achieve the same effects as those of the first and second embodiments. Further, by devising the content of the dialogue information stored in the dialogue storage unit 17, the display device 1 of the present embodiment can be used as an announcement medium for a specific product or service. It can also be used as an entertainment device for providing entertainment to customers. In such a case, the display device 1 is expected to attract customers to the area.

<Fourth Embodiment>
The display device 1 of the present embodiment is the first in that a plurality of users acquire a predetermined comment from a registration server that registers a comment together with their own attribute information for information transmission, and determine the acquired comment as a dialogue. Or different from the third embodiment. Other configurations can be the same as those of the first to third embodiments.

  An example of a functional block diagram of the display device 1 of the present embodiment is shown in FIG. The configurations of the imaging device 10, the person extraction unit 11, the person attribute estimation unit 12, the image processing unit 14, and the display unit 15 are the same as those in the first to third embodiments. Hereinafter, the configuration of the dialogue determination unit 13 will be described.

  The dialogue determination unit 13 receives a comment from a user whose registered attribute matches the attribute estimated by the person attribute estimation unit 12 from a registration server in which a plurality of users have registered comments together with their own attribute information for information transmission. And the acquired comment is determined as a dialogue to be given to the person with the attribute.

  The registration server is a server included in a so-called social media system. In this system, a plurality of users register comments with their attribute information in the server for information transmission. These comments are open to the public through the Internet.

  Means for realizing the above configuration of the line determination unit 13 is not particularly limited, and can be realized using any conventional technique. An example will be described below, but the present invention is not limited to this.

  For example, one or more search servers capable of searching in one or more registration servers are provided on a network such as the Internet. Then, the line determination unit 13 holds in advance address information of one or a plurality of search servers.

  When the line determination unit 13 acquires the attribute estimated by the person attribute estimation unit 12, the line determination unit 13 transmits a user comment request matching the attribute to the search server via a network such as the Internet. When the search server obtains the comment request, it searches the registration server using the attribute included therein as a key, and identifies a user that matches the key. Next, an arbitrary comment is acquired from the comments registered by the identified user. Then, the search server returns the acquired comment to the line determination unit 13. Note that, when there are a plurality of hit comments as a search result, which one to select is a design matter. For example, the one with the latest registration time in the registration server may be selected.

  As a modification of the present embodiment, the line determination unit 13 includes a comment including a predetermined keyword among user comments in which the registered attribute matches the attribute estimated by the person attribute estimation unit 12 from the registration server. (One sentence) may be acquired, and the acquired comment may be determined as a dialogue to be given to the person with the attribute.

  The line determination unit 13 may hold a predetermined keyword in advance. The predetermined keyword may be, for example, the name of a product for the purpose of promoting a product “Orange Jesus”.

  The predetermined keyword is determined by the dialogue determination unit 13 based on at least one of the attribute estimated by the person attribute estimation unit 12 and an arbitrary time (design matter) when a comment is acquired from the registration server. May be. In this way, the keyword can be changed according to the attribute and time of the person in the image. As a result, the dialogue variations displayed on the screen increase.

  The line determination unit 13 may hold information as illustrated in FIG. 11, for example, and may determine a predetermined keyword using the information. The information shown in FIG. 11 associates keywords for each combination of gender and age group. The keyword has a content that is considered to be generally interesting to a person with each attribute. The content of the keyword is a design matter. Moreover, although the information of the example shown in FIG. 11 associates a keyword for each combination of gender and age group, as another example, a keyword may be associated with each attribute, A keyword may be associated with each combination of attributes.

  When the line determination unit 13 acquires the attribute estimated by the person attribute estimation unit 12, the line determination unit 13 searches for information as illustrated in FIG. 11 using the attribute as a key, and acquires a keyword associated with the attribute. In the case of the example shown in FIG. 11, a plurality of keywords are associated with each combination of gender and age group. Which one is selected is a design matter, for example, one is randomly selected. You may choose.

  As another example, the line determination unit 13 may store information as illustrated in FIG. 12 and determine a predetermined keyword using the information. The information shown in FIG. 12 associates keywords for each predetermined time zone. The keyword has contents suitable for each time zone. The content of the keyword is a design matter.

  In the case of the modification, the line determination unit 13 acquires time information when determining a predetermined keyword. The time specified by the time information may be a time around a process for determining a predetermined keyword, and the timing of the time is a design matter. When the line determination unit 13 acquires time information, the line search unit 13 searches for information such as shown in FIG. 12 using the time as a key, and acquires a keyword associated with a time zone including the time specified by the time information. To do. In the case of the example shown in FIG. 12, a plurality of keywords are associated with each predetermined time period. Which one is selected is a design matter, for example, one is selected at random. May be.

  As another example, the line determination unit 13 may store information as illustrated in FIG. 13, for example, and may determine a predetermined keyword using the information. The information shown in FIG. 13 associates a predetermined time zone with a keyword for each combination of gender and age group. The keyword has a content that a person of each attribute is considered to be interested in that time zone. The content of the keyword is a design matter. Moreover, although the information of the example shown in FIG. 13 associates a keyword for each combination of gender and age group, as another example, a keyword may be associated for each attribute, A keyword may be associated with each combination of attributes.

  The line determination unit 13 acquires time information when determining a predetermined keyword. The time specified by the time information may be a time around a process for determining a predetermined keyword, and the timing of the time is a design matter. When the line determination unit 13 obtains the time information, the line determination unit 13 searches for information as shown in FIG. 13 using the time and the attribute estimated by the person attribute estimation unit 12 as a key, and specifies the attribute and the time information. A keyword associated with a time zone including the time to be acquired is acquired.

  As other modified examples, the dialog determination unit 13 has been based on the premise that the comment of the user that matches the attribute of the person estimated by the person attribute estimation unit 12 is acquired from the registration server. It can also be.

  For example, the line determination unit 13 acquires a comment including a predetermined keyword determined based on the attribute of the person estimated by the person attribute estimation unit 12 from the registration server, and uses the acquired comment as a person with the attribute. You may decide as a line to give. In the case of this example, the line determination unit 13 can acquire a user comment that does not match the attribute estimated by the person attribute estimation unit 12 from the registration server.

  The line determination unit 13 may determine part of the comment so that the content does not completely match and determine the modified comment as a line, instead of directly determining the comment acquired from the registration server as a line. .

  According to the present embodiment, it is possible to achieve the same operational effects as the first to third embodiments. Further, in the case of the present embodiment, the dialogue given to the person changes depending on not only the attribute of the person included in the captured image but also the timing of obtaining a comment from the registration server. For this reason, the probability that exactly the same dialogue is displayed can be further reduced. As a result, it is possible to further increase the degree of human interest in the display device 1 of the present embodiment. In the case of the present embodiment, the dialogue can be determined using the comments registered in the registration server, so the administrator of the display device 1 does not need to prepare and register dialogue beforehand. . As a result, it is possible to save the administrator and the like.

<Fifth Embodiment>
The display device 1 of this embodiment is a case where there are a plurality of persons in the image captured by the image capturing apparatus 10, and when the plurality of persons satisfy a predetermined relationship, the persons are grouped. And it differs from the 1st thru / or a 4th embodiment by the point which gives dialogue style dialogue to a plurality of people who belong to the same group. Other configurations can be the same as those of the first to fourth embodiments.

  FIG. 14 shows an example of a functional block diagram of the display device 1 of the present embodiment. As illustrated, the display device 1 includes an imaging device 10, a person extraction unit 11, a person attribute estimation unit 12, a dialogue determination unit 13, an image processing unit 14, a display unit 15, and a grouping unit 16. Have. Although not shown, the dialogue storage unit 17 may be included. Hereinafter, each part will be described.

  The configurations of the imaging device 10 and the display unit 15 are the same as those in the first to fourth embodiments.

  The person extraction unit 11 extracts a person from an image captured by the imaging device. Note that when a plurality of persons are present in one image, the person extracting unit 11 extracts a plurality of persons. Predetermined identification information (hereinafter, “in-image person identification information”) is assigned to each of the plurality of extracted persons. The person identification information in the image is associated with information indicating the position of each face on the image.

  The person attribute estimation unit 12 estimates an attribute of each of a plurality of persons extracted by the person extraction unit 11 using an image captured by the imaging device 10. The estimated attributes of the plurality of persons are associated with the in-image person identification information.

  When a plurality of persons are extracted from an image captured by the imaging device 10, the grouping unit 16 generates a group including two or more persons using the image.

  For example, the grouping unit 16 checks whether or not there is a combination that satisfies a predetermined relationship among the plurality of extracted persons, and if there is, sets that combination as one group. The grouping unit 16 can hold information indicating the predetermined relationship in advance.

  Hereinafter, an example of the predetermined relationship will be described. The purpose of grouping here is to group friends existing in the image. For this reason, the said predetermined relationship shall be estimated with friends.

  For example, a predetermined relationship may be defined by the size of a person's face on the image and the distance from each other. Specifically, the predetermined relationship is that the difference between the sizes of the faces on the image is equal to or smaller than a predetermined threshold (design item), and the distance between the faces on the image is a predetermined threshold (designed). Matter) It may be as follows. It is considered that the distance between such persons in the real space is close enough to be estimated to be friends.

  As another example, a predetermined relationship may be defined by the orientation of a person's face. Specifically, the predetermined relationship may be that face orientations are substantially the same (difference in orientation is within a predetermined angle), or may be facing each other. In the former case, it is considered that such persons are facing the same direction and having a conversation about the target while looking at the same target. In the latter case, it is considered that such persons are talking while looking at each other's faces. That is, such persons can be estimated as friends.

  The means for specifying the orientation of the person's face is not particularly limited, and any conventional technique can be adopted. Such a technique is disclosed in, for example, Japanese Patent Application Laid-Open No. 2008-148988. Note that the means for specifying the face orientation of the person employed in the present embodiment is not limited to that described in the document. In addition, there is no particular means for identifying the relationship that faces each other. For example, a pair of faces that face each other ahead of each other (may have a predetermined angle spread) face each other. You may specify that

  As another example, a predetermined relationship may be specified by the size of a person's face on the image, the distance from each other, and the orientation of the face. For example, the predetermined relationship is that the difference in the size of each other's faces on the image is equal to or less than a predetermined threshold (design item), and the distance between the faces on the image is equal to or less than a predetermined threshold (design item). And the face orientations may be substantially the same (or face each other).

  The grouping unit 16 can generate one or a plurality of groups from one image. When the grouping unit 16 generates a group, the grouping unit 16 can manage the persons included in each group using the person identification information in the image. For example, information indicating belonging to the same group can be associated with all the person identification information in the image of persons belonging to the same group.

  The line determination unit 13 determines a conversational line as a line to be given to two or more persons belonging to the same group. Hereinafter, an example of a process for determining conversational dialogue will be described.

  For example, the dialogue storage unit 17 may store dialogue information in which each person's attribute and dialogue are associated with each group.

  An example is shown in FIG. The dialogue information shown in FIG. 15 is dialogue information for the case where there are two persons belonging to the group. In the dialogue information, the attribute of the first person (attribute 1), the attribute of the second person (attribute 2), the dialogue of the first person, and the dialogue of the second person are associated with each other. . The dialogue of the first person and the dialogue of the second person are conversational dialogue.

  FIG. 16 shows another example. The dialogue information shown in FIG. 16 is dialogue information for the case where there are three persons belonging to the group. In the dialogue information, the attribute of the first person (attribute 1), the attribute of the second person (attribute 2), the attribute of the third person (attribute 2), the dialogue of the first person, The dialogue of the second person and the dialogue of the third person are associated with each other. The lines of the first to third persons are conversational lines.

  The dialogue information in both FIG. 15 and FIG. 16 is the content for the purpose of promoting a certain product “Orange Jesus”. For this reason, the word “Orange Jesus” is included in any conversation. The content of dialogue is a design matter. In addition, the dialogue information in the examples shown in FIGS. 15 and 16 associates dialogue with each combination of gender and age group, but as another example, dialogue may be associated with each attribute. Dialogue may be associated with each combination of a plurality of attributes.

  When the display device 1 has such a dialogue storage unit 17, the dialogue determination unit 13 uses the number of persons belonging to the group generated by the grouping unit 16 and the attributes of the persons belonging to the group as a key. 17 can be searched, and the dialogue-style dialogue associated with the key can be acquired. When the dialogue determination unit 13 acquires a plurality of dialogue-style dialogues, each dialogue is associated with identification information in the image of the person to whom the dialogue is given.

  The image processing unit 14 generates a processed image by using the dialogue associated with each piece of identification information in the image and information indicating the position of each face on the image.

FIG. 17 is a flowchart illustrating an example of a processing flow of the display method of the present embodiment.
For example, when the imaging device 10 captures (acquires) the image illustrated in FIG. 18 (S10), the person extraction unit 11 extracts a plurality of persons from the image captured by the imaging device (S11). Thereafter, the person attribute estimation unit 12 estimates the attributes of each of the plurality of persons extracted by the person extraction unit 11 using an image (S12). Next, the grouping unit 16 generates a group including two or more persons using the image (S13). Here, a group including all three persons in the image is generated. Then, the line determination unit 13 determines a conversational line as a line to be given to two or more persons (here, 3 persons) belonging to the same group (S14). Thereafter, the image processing unit 14 generates a processed image that gives the person in the image the dialogue-style dialogue determined by the dialogue determination unit 13 (S15). Then, the display unit 15 displays the processed image generated by the image processing unit 14 on the display (S16). FIG. 19 shows an example of an image displayed on the display 300 by the display unit 15.

  According to the present embodiment, it is possible to achieve the same operational effects as those of the first to fourth embodiments. Moreover, it is possible to further increase the degree of interest of a person with respect to the display device 1 of the present embodiment by grouping friends existing in the image and giving a conversational dialogue.

<Sixth Embodiment>
The display device 1 according to the present embodiment is different from the first to fifth embodiments in that the face of a person in an image captured by the imaging device 10 is processed and a line is added to the processed image for display. . Other configurations can be the same as those of the first to fifth embodiments. According to such this embodiment, the interestingness of a processed image can be increased, and a person's interest level can be raised more. In addition, by processing to a state where a person cannot be specified, the privacy of the person can be protected.

  FIG. 20 shows an example of a functional block diagram of the display device 1 of the present embodiment. As illustrated, the display device 1 includes an imaging device 10, a person extraction unit 11, a person attribute estimation unit 12, a dialogue determination unit 13, an image processing unit 14, a display unit 15, and a processing information storage unit 18. Have Although not shown, at least one of the grouping unit 16 and the dialogue storage unit 17 may be further included. The configurations of the imaging device 10, the person extraction unit 11, the person attribute estimation unit 12, the dialogue determination unit 13, the display unit 15, the grouping unit 16, and the dialogue storage unit 17 are the same as those in the first to fifth embodiments. The configuration of the image processing unit 14 and the processing information storage unit 18 will be described.

  The image processing unit 14 adds a dialogue to the person in the image captured by the imaging device 10 and generates a processed image that processes the face of the person in the image. For example, the image processing unit 14 may generate a processed image for displaying the face of an animal or character at the position of a person's face. The image processing unit 14 can determine the processing content to be performed on each person's face using the attribute estimated by the person attribute estimation unit 12, and can execute the determined processing.

  For example, the processing information storage unit 18 stores processing information in which a person attribute is associated with a replacement image (eg, an animal or character face) displayed at the position of the person's face in the processing image. (See FIG. 21). The processing information storage unit 18 stores replacement image data. The content of the replacement image is a design matter. The processing information in the example illustrated in FIG. 21 associates a replacement image for each combination of gender and age group. However, as another example, a replacement image may be associated with each attribute. A replacement image may be associated with each combination of a plurality of attributes.

  When the display device 1 has such a processing information storage unit 18, the image processing unit 14 generates a processing image using the processing information and replacement image data stored in the processing information storage unit 18. Can do. Specifically, the image processing unit 14 acquires a replacement image associated with the attribute estimated by the person attribute estimation unit 12 from the processing information storage unit 18, and the acquired replacement image is obtained when the face of the person with the attribute is displayed. A processed image to be displayed at the displayed position may be generated.

  The processed image data may be data that is different from the image data captured by the imaging device 10 and that is used to display a replacement image on the display so as to overlap the image captured by the imaging device 10. Alternatively, the processed image data may be image data that is modified so that a part of the image data captured by the imaging device 10 is corrected and a replacement image is displayed at a predetermined position in the image.

  An example is shown. FIG. 3 is an image captured by the imaging apparatus 10. FIG. 22 shows a display of a processed image generated by the image processing unit 14 based on the image. In the case of FIG. 22, it can be seen that the dialogue is given and the face of the person is processed.

  In addition, the image processing unit 14 may perform other processing such as black and white processing, sepia processing, and processing that makes the image appear like a sketch on the image captured by the imaging device 10.

  According to the present embodiment, it is possible to achieve the same operational effects as those of the first to fifth embodiments. In addition, by processing the face of a person in the image and adding a dialogue to the processed image for display, the interest of the processed image can be increased, and the degree of interest of the person can be further increased. In addition, by processing to a state where a person cannot be specified, the privacy of the person can be protected.

<Appendix>
Hereinafter, examples of the reference form will be added.
1. An imaging device;
Person extraction means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determination means to the person in the image;
Display means for displaying the processed image on a display;
A display device.
2. In the display device according to 1,
The line determining means is a display device for determining different lines for persons having different attributes.
3. In the display device according to 1 or 2,
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display is a display device installed near the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction.
4). In the display device according to any one of 1 to 3,
When a plurality of persons are extracted from the image, the image processing apparatus further includes a grouping unit that generates a group including two or more persons using the image.
The line determining means is a display device for determining a dialogue type line as the line to be given to two or more persons belonging to the same group.
5). 4, the display device according to
The grouping means is a display device that generates the group based on at least one of a human face orientation, face size, and mutual face distance.
6). In the display device according to any one of 1 to 5,
Further comprising dialogue storage means for storing dialogue information in which attributes of the person and dialogue are associated with each other;
The line determination unit acquires a line associated with the attribute estimated by the person attribute estimation unit from the line storage unit, and determines the acquired line as a line to be given to the person of the attribute .
7). In the display device according to any one of 1 to 5,
The dialogue determining means is a registration server in which a plurality of users register comments together with their own attribute information for information transmission, and the registered attributes coincide with the attributes estimated by the person attribute estimating means. A display device that acquires the comment and determines the acquired comment as a line to be given to a person with the attribute.
8). In the display device according to 7,
The line determination unit acquires the comment including a predetermined keyword among the comments of the user whose registered attribute matches the attribute estimated by the person attribute estimation unit from the registration server, A display device that determines the acquired comment as a dialogue to be given to a person with the attribute.
9. 8. The display device according to 8,
The display device in which the line determination unit determines the predetermined keyword based on at least one of an attribute estimated by the person attribute estimation unit and a time when the comment is acquired from the registration server.
10. In the display device according to any one of 1 to 5,
The line determination means includes a comment including a predetermined keyword determined based on the attribute estimated by the person attribute estimation means from a registration server in which a plurality of users have registered comments together with their own attribute information for information transmission. , And the obtained comment is determined as a dialogue to be given to the person with the attribute.
11. In the display device according to any one of 1 to 10,
The image processing means is a display device that gives the dialogue to the person in the image and generates the processed image that processes the face of the person in the image.
12 11. The display device according to 11,
The image processing means is a display device that uses the attribute estimated by the person attribute estimation means to determine the processing content to be performed on each person's face and performs the determined processing.
13. 12. The display device according to 12,
Processing information storage means for storing processing information in which a person attribute is associated with a replacement image displayed at the position of the person's face in the processing image;
The image processing unit acquires the replacement image associated with the attribute estimated by the person attribute estimation unit from the processing information storage unit, and the acquired replacement image is displayed with the face of the person with that attribute. A display device that generates the processed image to be displayed at a position.
14 Computer
Imaging means,
Person extracting means for extracting a person from the image captured by the imaging means;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determining means to the person in the image;
Display means for displaying the processed image on a display;
Program to function as.
14-2. 14 program,
A program for causing the line determination means to determine different lines for persons having different attributes.
14-3. In the program described in 14 or 14-2,
The imaging means is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display is a program installed near the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction.
14-4. In the program according to any one of 14 to 14-3,
When a plurality of persons are extracted from the image, the computer further functions as a grouping unit that generates a group including two or more persons using the image,
A program for causing the dialogue determining means to determine a dialogue-type dialogue as the dialogue to be given to two or more persons belonging to the same group.
14-5. In the program described in 14-4,
The program which makes the said grouping means produce | generate the said group based on at least 1 in the direction of a person's face, the size of a face, and the distance of each other's face.
14-6. In the program according to any one of 14 to 14-5,
Further causing the computer to function as dialogue storage means for storing dialogue information in which attributes of a person and dialogue are associated with each other;
A program for causing the line determination unit to acquire a line associated with the attribute estimated by the person attribute estimation unit from the line storage unit, and to determine the acquired line as a line to be given to the person with the attribute.
14-7. In the program according to any one of 14 to 14-5,
From the registration server in which a plurality of users registered comments together with their own attribute information for information transmission, the registered attribute matches the attribute estimated by the person attribute estimation unit. A program for acquiring the comment and determining the acquired comment as a line to be given to a person having the attribute.
14-8. In the program described in 14-7,
Causing the line determination means to acquire, from the registration server, the comment including a predetermined keyword among the comments of the user whose registered attribute matches the attribute estimated by the person attribute estimation means; The program which determines the acquired said comment as a dialog given to the person of the attribute.
14-9. In the program described in 14-8,
A program that causes the line determination unit to determine the predetermined keyword based on at least one of the attribute estimated by the person attribute estimation unit and the time when the comment is acquired from the registration server.
14-10. In the program according to any one of 14 to 14-5,
A comment including a predetermined keyword determined based on the attribute estimated by the person attribute estimation unit from a registration server in which a plurality of users registered comments together with their own attribute information for information transmission in the dialogue determination unit A program that causes the acquired comment to be determined as a dialogue to be given to the person with the attribute.
14-11. In the program according to any one of 14 to 14-10,
A program for causing the image processing means to generate the processed image by giving the dialogue to the person in the image and processing the face of the person in the image.
14-12. In the program described in 14-11,
A program for causing the image processing means to determine the processing content to be performed on each person's face using the attribute estimated by the person attribute estimating means and to perform the determined processing.
14-13. In the program described in 14-12,
The computer,
Further functioning as processing information storage means for storing processing information that associates the attributes of the person with the replacement image displayed at the position of the face of the person in the processed image;
The image processing unit is caused to acquire the replacement image associated with the attribute estimated by the person attribute estimation unit from the processing information storage unit, and the acquired replacement image is displayed with the face of the person with the attribute. A program for generating the processed image to be displayed at a position.
15. Computer
A person extracting step of extracting a person from the image captured by the imaging device;
A person attribute estimation step of estimating the attribute of the person extracted in the person extraction step using the image;
Using the attribute estimated in the person attribute estimation step, a line determination step for determining a line to be given to the person of the attribute;
An image processing step for generating a processed image for giving the line determined in the line determination step to the person in the image;
A display step of displaying the processed image on a display;
Display method to execute.
15-2. 15. The display method according to 15,
A display method for determining different dialogues for persons having different attributes in the dialogue determination step.
15-3. In the display method according to 15 or 15-2,
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display method is a display method in which the display is installed near the end point of the transportation means or on the downstream side of the position captured by the imaging device in the one direction.
15-4. In the display method according to any one of 15 to 15-3,
The computer further executes a grouping step of generating a group including two or more persons using the image when a plurality of persons are extracted from the image,
A display method for determining a dialogue-type dialogue as the dialogue to be given to two or more persons belonging to the same group in the dialogue determination step.
15-5. In the display method described in 15-4,
In the grouping step, a display method for generating the group based on at least one of a human face orientation, a face size, and a mutual face distance.
15-6. In the display method according to any one of 15 to 15-5,
The computer stores line information in which attributes of persons are associated with lines,
A display method in which in the speech determination step, the speech associated with the attribute estimated in the human attribute estimation step is acquired from the speech information, and the acquired speech is determined as a speech to be given to the person with the attribute.
15-7. In the display method according to any one of 15 to 15-5,
In the dialogue determination step, from a registration server in which a plurality of users have registered comments together with their own attribute information for information transmission, the registered attributes match those estimated in the person attribute estimation step. A display method of acquiring the comment and determining the acquired comment as a dialogue to be given to a person with the attribute.
15-8. In the display method according to 15-7,
In the dialogue determination step, the comment including a predetermined keyword in the comment of the user in which the registered attribute matches the attribute estimated in the person attribute estimation step is acquired from the registration server, The display method which determines the acquired said comment as a dialog given to the person of the attribute.
15-9. In the display method according to 15-8,
The display method in which the predetermined keyword is determined in the dialogue determination step based on at least one of an attribute estimated by the person attribute estimation unit and a time when the comment is acquired from the registration server.
15-10. In the display method according to any one of 15 to 15-5,
In the dialogue determination step, a comment including a predetermined keyword determined based on the attribute estimated in the person attribute estimation step from a registration server in which a plurality of users registered comments together with their own attribute information for information transmission The display method of determining the acquired comment and determining the acquired comment as a dialogue to be given to the person with the attribute.
15-11. In the display method according to any one of 15 to 15-10,
In the image processing step, the dialogue is given to the person in the image and the processed image for processing the face of the person in the image is generated.
15-12. In the display method according to 15-11,
A display method in which, in the image processing step, processing content to be performed on each person's face is determined using the attribute estimated in the person attribute estimation step, and the determined processing is performed.
15-13. In the display method according to 15-12,
The computer stores processing information in which a person attribute is associated with a replacement image displayed at the position of the person's face in the processed image,
In the image processing step, the replacement image associated with the attribute estimated in the person attribute estimation step is acquired from the processing information, and the acquired replacement image is displayed with the face of a person with that attribute. A display method for generating the processed image to be displayed at a position.

DESCRIPTION OF SYMBOLS 1 Display apparatus 10 Imaging device 11 Person extraction part 12 Person attribute estimation part 13 Dialogue determination part 14 Image processing part 15 Display part 16 Grouping part 17 Dialogue storage part 18 Processing information storage part 100 Imaging apparatus 200 Control apparatus 300 Display 400 Escalator 500 Moving walkway

Claims (14)

An imaging device;
Person extraction means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determination means to the person in the image;
Display means for displaying the processed image on a display;
Have
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display is a display device installed near the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction. An imaging device;
Person extraction means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determination means to the person in the image;
Display means for displaying the processed image on a display;
Grouping means for generating a group including two or more persons using the image when a plurality of persons are extracted from the image;
Have
The line determining means is a display device for determining a dialogue type line as the line to be given to two or more persons belonging to the same group. The display device according to claim 2,
The grouping means is a display device that generates the group based on at least one of a human face orientation, face size, and mutual face distance. An imaging device;
Person extraction means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determination means to the person in the image;
Display means for displaying the processed image on a display;
Have
The dialogue determining means is a registration server in which a plurality of users register comments together with their own attribute information for information transmission, and the registered attributes coincide with the attributes estimated by the person attribute estimating means. A display device that acquires the comment and determines the acquired comment as a line to be given to a person with the attribute. The display device according to claim 4,
The line determination unit acquires the comment including a predetermined keyword among the comments of the user whose registered attribute matches the attribute estimated by the person attribute estimation unit from the registration server, A display device that determines the acquired comment as a dialogue to be given to a person with the attribute. An imaging device;
Person extraction means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determination means to the person in the image;
Display means for displaying the processed image on a display;
Have
The line determination means includes a comment including a predetermined keyword determined based on the attribute estimated by the person attribute estimation means from a registration server in which a plurality of users have registered comments together with their own attribute information for information transmission. , And the obtained comment is determined as a dialogue to be given to the person with the attribute. Computer
Person extracting means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determining means to the person in the image;
Display means for displaying the processed image on a display;
Function as
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display is a program installed near the end point of the transportation means or on the downstream side of the position taken by the imaging device in the one direction. Computer
Person extracting means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determining means to the person in the image;
Display means for displaying the processed image on a display;
Grouping means for generating a group including two or more persons using the image when a plurality of persons are extracted from the image;
Function as
The dialogue determining means determines a dialogue-style dialogue as the dialogue to be given to two or more persons belonging to the same group. Computer
Person extracting means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determining means to the person in the image;
Display means for displaying the processed image on a display;
Function as
The dialogue determining means is a registration server in which a plurality of users register comments together with their own attribute information for information transmission, and the registered attributes coincide with the attributes estimated by the person attribute estimating means. The program which acquires the said comment and determines the acquired said comment as a dialog given to the person of the attribute. Computer
Person extracting means for extracting a person from an image captured by the imaging device;
Person attribute estimation means for estimating the attribute of the person extracted by the person extraction means using the image;
Using the attribute estimated by the person attribute estimating means, a line determining means for determining a line to be given to the person of the attribute;
Image processing means for generating a processed image for giving the line determined by the line determining means to the person in the image;
Display means for displaying the processed image on a display;
Function as
The line determination means includes a comment including a predetermined keyword determined based on the attribute estimated by the person attribute estimation means from a registration server in which a plurality of users have registered comments together with their own attribute information for information transmission. A program that acquires the comment and determines the acquired comment as a line to be given to the person with the attribute. Computer
A person extracting step of extracting a person from the image captured by the imaging device;
A person attribute estimation step of estimating the attribute of the person extracted in the person extraction step using the image;
Using the attribute estimated in the person attribute estimation step, a line determination step for determining a line to be given to the person of the attribute;
An image processing step for generating a processed image for giving the line determined in the line determination step to the person in the image;
A display step of displaying the processed image on a display;
Run
The imaging device is installed at a position where a moving person can be imaged by a transportation means that moves the person in one direction toward the end point,
The display method is a display method in which the display is installed near the end point of the transportation means or on the downstream side of the position captured by the imaging device in the one direction. Computer
A person extracting step of extracting a person from the image captured by the imaging device;
A person attribute estimation step of estimating the attribute of the person extracted in the person extraction step using the image;
Using the attribute estimated in the person attribute estimation step, a line determination step for determining a line to be given to the person of the attribute;
An image processing step for generating a processed image for giving the line determined in the line determination step to the person in the image;
A display step of displaying the processed image on a display;
A grouping step of generating a group including two or more persons using the image when a plurality of persons are extracted from the image;
Run
A display method for determining a dialogue-type dialogue as the dialogue to be given to two or more persons belonging to the same group in the dialogue determination step. Computer
A person extracting step of extracting a person from the image captured by the imaging device;
A person attribute estimation step of estimating the attribute of the person extracted in the person extraction step using the image;
Using the attribute estimated in the person attribute estimation step, a line determination step for determining a line to be given to the person of the attribute;
An image processing step for generating a processed image for giving the line determined in the line determination step to the person in the image;
A display step of displaying the processed image on a display;
Run
In the dialogue determination step, from a registration server in which a plurality of users have registered comments together with their own attribute information for information transmission, the registered attributes match those estimated in the person attribute estimation step. A display method of acquiring the comment and determining the acquired comment as a dialogue to be given to a person with the attribute. Computer
A person extracting step of extracting a person from the image captured by the imaging device;
A person attribute estimation step of estimating the attribute of the person extracted in the person extraction step using the image;
Using the attribute estimated in the person attribute estimation step, a line determination step for determining a line to be given to the person of the attribute;
An image processing step for generating a processed image for giving the line determined in the line determination step to the person in the image;
A display step of displaying the processed image on a display;
Run
In the dialogue determination step, a comment including a predetermined keyword determined based on the attribute estimated in the person attribute estimation step from a registration server in which a plurality of users registered comments together with their own attribute information for information transmission The display method of determining the acquired comment and determining the acquired comment as a dialogue to be given to the person with the attribute.

Images