JP7199623B1 - Information processing equipment - Google Patents

Abstract

An information processing device (100a) includes a data acquisition unit (120) that acquires image data, a setting unit (110a) that sets a threshold value, and, if one or more persons are included in the image data, based on the image data. an estimation unit (130a) for estimating at least one of attributes and states of one or more persons and generating estimation information as an estimation result for each person; an information transfer unit (190) that acquires from the first information processing device one or more pieces of first estimation information obtained by estimating at least one of the attributes and states of the generated estimation information and the number of the first estimated information is equal to or greater than a threshold, the data generation unit generates provided information that is privacy-considered information based on the estimated information and the first estimated information. (160a) and a data output unit (170) for outputting provided information.

Description

The present disclosure relates to an information processing device.

2. Description of the Related Art Techniques for analyzing attributes and actions of persons included in images generated by cameras installed in facilities (hereinafter referred to as camera images) are known. For example, there is a system that uses this technology to visualize the line of flow of people and the state of congestion in a facility. In addition, data distribution businesses that utilize information about people, such as their attributes and behaviors, to utilize services are spreading.

On the other hand, the camera image contains information about the person. Therefore, when using information about a person, it is necessary to process the data so that the individual cannot be identified from the viewpoint of privacy protection.

For example, as a human flow line analysis system, a flow line analysis system that generates a flow line analysis image on which flow line information is superimposed has been proposed (see Patent Document 1). Patent Literature 1 discloses superimposing flow line information on a background image generated from a camera image. For privacy protection, the person included in the camera image is excluded when the background image is generated. The flow line information is associated with the attributes of the person included in the camera image (that is, gender, age, generation). Flow line information is extracted according to the specified conditions.

JP 2017-123024 A

In the system of Patent Literature 1, flow line information is extracted even when the number of persons included in the camera image is one. Therefore, for example, if the condition is "male over 100" and there is only one male over 100 in the town where the system is installed, the person can be identified. Therefore, the technique of Patent Document 1 may pose a problem from the viewpoint of privacy protection. Therefore, it becomes difficult to utilize the data.

An object of the present disclosure is to generate privacy-friendly data from information about a person contained in a camera image.

An information processing device according to one aspect of the present disclosure is provided. The information processing device communicates with the first information processing device. The information processing device includes a data acquisition unit that acquires image data, a setting unit that sets a threshold value, and, when one or more persons are included in the image data, determines the one or more persons based on the image data. an estimating unit for estimating at least one of the attributes and states of the person and generating estimation information, which is an estimation result, for each person; an information transfer unit that acquires one or more pieces of first estimation information obtained by estimating one from the first information processing device; the number of pieces of the generated estimation information and the first estimation information; is equal to or greater than the threshold value, a data generating unit that generates provided information that is privacy-considered information based on the estimated information and the first estimated information; and the provided information and a data output unit for outputting

According to the present disclosure, privacy-friendly data can be generated from information about a person included in a camera image.

2 is a block diagram showing functions of the information processing apparatus according to Embodiment 1; FIG. 1 is a diagram showing an example of a system equipped with an information processing device according to a first embodiment; FIG. 4 is a diagram showing an example of a camera image according to Embodiment 1; FIG. 4 is a diagram showing an example of a history information table according to Embodiment 1; FIG. 4 is a diagram showing an example of a summary table according to Embodiment 1; FIG. 4 is a diagram showing an example of an environment information table according to Embodiment 1; FIG. 7 is a flowchart showing an example (part 1) of processing for generating provision information according to Embodiment 1; 7 is a flow chart showing an example (part 2) of processing for generating provision information according to Embodiment 1; 2 illustrates hardware included in the information processing apparatus according to the first embodiment; FIG. 3 is a block diagram showing functions of an information processing apparatus according to a second embodiment; FIG. FIG. 10 is a diagram showing a specific example of installation of a plurality of information processing apparatuses according to the second embodiment; FIG. 10 is a diagram showing an example of an environment information table according to the second embodiment; FIG. FIG. 11 is a flow chart showing an example (part 1) of processing for generating provision information according to the second embodiment; FIG. FIG. 13 is a flow chart showing an example (part 2) of processing for generating provision information according to the second embodiment; FIG. 10A and 10B are diagrams showing a specific example (part 1) of processing executed by the information processing apparatus according to the second embodiment; FIG. 13A and 13B are diagrams showing a specific example (part 2) of processing executed by the information processing apparatus according to the second embodiment; FIG.

Embodiments will be described below with reference to the drawings. The following embodiments are merely examples, and various modifications are possible within the scope of the present disclosure. Note that the dimensions of the device, etc., shown in the drawings are different from the actual dimensions. Therefore, it is necessary to determine the dimensions of the devices and the like shown in the drawings by taking the following description into consideration.

Embodiment 1.
FIG. 1 is a block diagram showing functions of an information processing apparatus according to a first embodiment. Information processing apparatus 100 includes setting unit 110 , data acquisition unit 120 , estimation unit 130 , estimation information storage unit 140 , data acquisition environment storage unit 150 , data generation unit 160 , and data output unit 170 .

Setting section 110 outputs the set threshold to data generating section 160 . The data acquisition unit 120 outputs images acquired from the camera (hereinafter referred to as camera images or image data) to the estimation unit 130 . The estimation unit 130 outputs estimation information for each recognized person to the data generation unit 160 based on the acquired camera image. The data generation unit 160 generates provided information from the estimated information based on the comparison between the total result of the estimated information and the threshold, and outputs the provided information to the data output unit 170 . The data output unit 170 outputs the provided information.

The estimated information storage unit 140 stores estimated information. Also, the estimated information storage unit 140 outputs the estimated information to the setting unit 110 and the data generation unit 160 as history information. The data acquisition environment storage unit 150 stores, as environment information, history information acquisition conditions used when generating provided information.

FIG. 2 is a diagram showing an example of a system equipped with the information processing apparatus according to the first embodiment. FIG. 2 shows a state in which the information processing device 100 is installed inside a train car.
The camera 10, edge terminal 20, and monitor 30 communicate via a network. The network may be a wired network or a wireless network.

FIG. 2 shows a case where the information processing device 100 is incorporated in the camera 10. As shown in FIG. The information processing device 100 may be incorporated into the edge terminal 20 . The information processing device 100 may also be incorporated in a server that communicates with the edge terminal 20 . Note that the illustration of the server is omitted. In the following description, it is assumed that the information processing device 100 is incorporated in the camera 10 .

The camera 10 is installed at a position (for example, near the ceiling) where the situation inside the vehicle A can be photographed. The camera 10 generates provided information based on passenger information included in the camera image, and transmits the provided information to the edge terminal 20 . The edge terminal 20 switches the content displayed on the monitor 30 based on the provided information and the train operation information. Note that the edge terminal 20 is a small PC (Personal Computer) or the like. Also, one vehicle may have a plurality of cameras.

Returning to FIG. 1, functions of the information processing apparatus 100 will be described.
The setting unit 110 sets a threshold, which is an output condition of the provided information, and outputs the threshold to the data generation unit 160 . For example, threshold setting is performed as follows. A threshold setting screen appears on the display. A user inputs an arbitrary threshold through an input device such as a keyboard or mouse. Accordingly, the setting unit 110 sets the threshold. Note that the display and input device may be connected to the camera 10 or the edge terminal 20 .

For example, the threshold is the number of people with the same attribute obtained from the camera image. The threshold may change depending on the output conditions of the provided information. Also, the threshold is set to a value that is larger than a predetermined provision allowable threshold. For example, the offer acceptance threshold is one.

Also, the setting of the threshold is performed by the user's operation. Therefore, an appropriate threshold may not be set. If the appropriate threshold is not set, no provision information will be generated. For example, if the threshold is set to a value clearly larger than the number of passengers, the provided information is not generated because the provided information output condition is not satisfied. Therefore, when a certain number of pieces of history information are stored in the estimated information storage unit 140, the setting unit 110 calculates the average number of people for each time period based on the certain number of pieces of history information. is presented to the user. A user can set an appropriate threshold value by visually recognizing the average value. A method of calculating the average value for each time period will be described later in detail.

The data acquisition unit 120 acquires camera images from an external terminal such as a surveillance camera, and outputs the camera images to the estimation unit 130 . When the information processing apparatus 100 is incorporated in the camera 10 , the data acquisition section 120 acquires a camera image captured by the imaging section of the camera 10 . The data acquisition unit 120 acquires camera images at a predetermined frame rate. Further, the camera 10 may acquire the image capturing timing from an external terminal connected to the camera 10 and output the camera image obtained by capturing the image at the image capturing timing to the data acquisition unit 120 . For example, the camera 10 acquires train operation information from the edge terminal 20 and captures images at the timing of the running state of the train (for example, while the train is stopped, while it is running between stations, and before stopping at the next station). The image is output to the data acquisition unit 120 .

The estimation unit 130 recognizes a person included in the camera image, and estimates attributes and states of the recognized person as estimation information. For example, the attributes of a person are the person's age, gender, height, and the like. The state of a person is the position, action, vehicle, belongings, and the like of the person. The estimation unit 130 outputs estimation information to the estimation information storage unit 140 and the data generation unit 160 .

Here, the estimation unit 130 estimates the attribute and state of the person using a known image recognition technology. A person's position in the camera image is represented by (x, y). Also, the lower left corner of the camera image is set as the starting point (x0, y0). The horizontal axis is the x-axis, and the vertical axis is the y-axis.

For example, the action of a person is "stand", "sit", and the like. The estimation unit 130 may estimate what the person is looking at. For example, the objects are "in-vehicle advertisement", "destination guide", "portable terminal", "book", "person", and the like. The estimation unit 130 may estimate a state in which the person's eyes are closed.

For example, a vehicle is a "chair", a "stroller", or the like. Also, the estimation unit 130 may estimate a state in which the person is not in the vehicle. Also, when the camera is installed outside, the estimation unit 130 may estimate “bicycle”.

For example, belongings are a "suitcase", a "stroller", a "bag", and the like. The estimation unit 130 may estimate "no belongings".

The estimation unit 130 may estimate other than the example of the attribute and the example of the state of the person. Also, the estimation unit 130 may estimate only what the user needs. For example, when the camera image shows the situation inside the train car, the estimation unit 130 does not estimate the vehicle. Also, for example, when the camera image shows the situation inside a vehicle such as a taxi or a bus, the estimation unit 130 does not estimate the vehicle. Also, the estimation unit 130 may estimate a vehicle (for example, a bicycle) when the camera 10 is installed in the city.

3 is a diagram showing an example of a camera image according to Embodiment 1. FIG. A person 1a included in the camera image 1 is a 40-year-old man. Person 1a has a suitcase. A person 1a is sitting on a seat. Also, the person 1b is a 30-year-old male. A person 1b is standing without holding an item.

The estimation unit 130 recognizes a person included in the camera image and estimates attributes and states of the recognized person. For example, the person 1a is estimated to be "(age, sex, position, action, belongings)=(40, male, (x1, y1), sit down, suitcase)". Also, the person 1b is estimated to be "(age, sex, position, behavior, belongings)=(30, male, (x2, y2), standing, none)". Thus, the estimation unit 130 generates estimation information for each person included in the camera image. Also, the number of people who have been recognized can be obtained by aggregating the estimated information.

Also, the estimation unit 130 may acquire the number of persons included in the camera image using a known person detection technique. Here, the number of people may be the number of people whose attributes or states match each other. For example, if there are three people included in the camera image, and the sexes of the people included in the camera image are "male, male, female," the number of persons is "(male, female)=(2, 1)." becomes. In the following description, the number of people is the number of people whose attributes or states match each other.

After the estimation is done, the camera images are discarded. Also, the camera image may be stored in the storage unit. Furthermore, camera images may be stored in the edge terminal 20 . When the camera image is stored in the storage unit, or when the camera image is stored in the edge terminal 20, the stored camera image is desirably encrypted.

The estimated information storage unit 140 stores estimated information as history information. In addition, estimated information storage section 140 outputs history information to setting section 110 or data generation section 160 in response to a request.

FIG. 4 is a diagram showing an example of a history information table according to the first embodiment. The history information table is stored in the estimation information storage unit 140. FIG.
The history information table has items of time and estimated information. The time is the time when the camera image was acquired. Estimated information is registered in the history information table in order of time when the camera image was acquired. For example, when the camera image 1 in FIG. 3 was acquired at “2019/12/17 8:00”, the estimated information shown in FIG. 4 is registered in the history information table. The time display format may be a display format other than the display format shown in FIG.

A case where estimated information storage section 140 outputs history information to setting section 110 will be described. When a certain number of pieces of history information are stored in the estimated information storage unit 140 (for example, when one week's worth of history information is stored in the estimated information storage unit 140), the estimated information storage unit 140 stores the setting unit 110 history information to the setting unit 110 in response to the request.

Next, return to the description of the setting unit 110 . The setting unit 110 calculates the average number of people based on the history information. First, the setting unit 110 aggregates the number of people included in the history information acquired from the estimated information storage unit 140 for each hour. Here, in the following description, the time is set to 1 hour. Also, the time may be a time other than one hour.

FIG. 5 is a diagram showing an example of a summary table according to the first embodiment. The tabulation table in FIG. 5 is a table in which the number of persons included in the history information is tabulated for each hour. FIG. 5 shows the number of people totaled for each day in the time period from 5:00 to 10:00. For example, from 5:00 to 6:00 on December 10th, the number of persons recognized from the camera image is zero. That is, the camera image does not include a person. From 5:00 to 6:00 on December 16th, one person was recognized from the camera image. Therefore, the camera image includes one person.

Next, the setting unit 110 sums up the aggregated results for each time period to calculate an average value. For example, the counting result from 7:00 to 8:00 from December 10th to December 16th is "8, 4, 7, 7, 6, 5, 5". The setting unit 110 calculates an average value of 6 people (=(8+4+7+7+6+5+5)/7) using the counted result. The setting unit 110 provides the average value to the user. The user sets the threshold with reference to the average value. For example, the user sets the threshold to the provided average value. Also, for example, the user sets the threshold value to be slightly smaller than the provided average value.

Also, the total result from 5:00 to 6:00 from December 10th to December 16th is "0, 0, 1, 0, 0, 1, 1". The setting unit 110 calculates the average value of 3/7 people using the aggregated result. 3/7 people are less than 1. The setting unit 110 provides the average value to the user. Here, the fact that the average value is less than one person means that the camera image often includes only one person. Therefore, when the average value is less than 1 person, there is a high possibility that a person is identified. Therefore, the user to whom the average value is provided recognizes that the person will be identified when the provided information is generated based on the information from 5:00 to 6:00. Therefore, based on the information from 5:00 to 6:00, the user determines that it is better not to generate the provided information.
Also, when the average value includes a decimal point, the setting unit 110 may truncate the decimal point.

The setting unit 110 may calculate the average value using the aggregated results for the same time slot on the same day of the week. The reason for using this method is as follows. For example, if the camera image is an image showing the inside of a train, there are many passengers such as commuters and students on weekdays. On the other hand, on holidays, many passengers go to shopping and leisure facilities. As described above, the types of customers differ depending on the day of the week, so the setting unit 110 calculates the average value for each day of the week. The user can set a threshold according to the application by being provided with the average value.
The data acquisition environment storage unit 150 stores history information acquisition conditions as environment information. The history information acquisition condition indicates the time of history information to be acquired from the estimated information storage unit 140 .

FIG. 6 is a diagram showing an example of an environment information table according to the first embodiment. The environment information table is stored in the data acquisition environment storage unit 150. FIG. FIG. 6 shows cameras AD. Any one of cameras AD may be considered camera 10 .

The history information acquisition condition for camera A is "one hour". For example, when the current time is 10:00, the history information acquisition condition “1 hour” means that history information from 9:00 to 10:00 is acquired from the estimated information storage unit 140 .
Also, the history information acquisition condition of camera D is "-". The history information acquisition condition "-" means that the history information currently existing in the estimated information storage unit 140 can be acquired without limitation.

The data acquisition environment storage unit 150 stores environment information in advance. Further, for example, the history information acquisition condition, which is the environment information, may be the traveling time between specific stations. By setting the history information acquisition condition to the travel time, information on passengers boarding a train traveling between specific stations is acquired as history information. Also, for example, if the history information acquisition condition is "-" and it is desired to obtain information on passengers on a train traveling from station B to station D, a camera image showing the inside of the train before arriving at station B may be used.

The environment information table shows the correspondence between cameras and time. The environment information table may indicate the correspondence relationship between position information and sections. For example, the environment information table shows the correspondence relationship between the position information of the moving object when the camera image was acquired and the section from A station to C station. Then, when the information processing device 100 is mounted on a moving object (that is, a train), history information from station A to station C is acquired from the estimated information storage unit 140 .

The data generator 160 generates provision information based on the threshold, estimated information, history information, and environment information. The provided information is information in consideration of privacy. Data generator 160 outputs the provided information to data output unit 170 . Also, when the provided information is generated for each camera image, the data generation unit 160 generates the provided information without using the environment information.

Examples of methods for generating offer information are described. Assume that the estimated information of the person 1a is "(age, sex, position, behavior, belongings)=(40, male, (x1, y1), sits, suitcase)". Assume that the estimated information of the person 1b is "(age, sex, position, behavior, belongings)=(30, male, (x2, y2), standing, none)". Also, the threshold is assumed to be "2".

If the condition is "30 to 40 years old", there are two people between 30 and 40 years old, so the number of people is the same as the threshold. The data generation unit 160 generates “(age, gender, position, action, belongings)=(30-40, male, (x1, y1), sitting, suitcase)” and “(age, gender, position, action, belongings)=(30-40, male, (x2, y2), standing, none)” is generated as the provided information. Here, "30-40" means an estimated age range from 30 to 40 years old.

A different example will also be described. The threshold is set to "2". If the current time is 7:00, history information from 6:00 to 7:00 is acquired. Specifically, the history information of the person 1c is "(age, sex, position, behavior, belongings)=(20, female, (x6, y6), sitting, no belongings)". The history information of the person 1d is "(age, sex, position, action, belongings)=(60, male, (x7, y7), sit, none)". In addition, estimation information of the person 1e is obtained from the camera image. The estimated information of the person 1e is "(age, gender, position, behavior, belongings)=(20, female, (x3, y3), sitting, none)". Presumed information of the person 1f is obtained from the camera image. The estimated information of the person 1f is "(age, gender, position, behavior, belongings)=(40, female, (x4, y4), sitting, none)". Presumed information of the person 1g is obtained from the camera image. The estimated information of the person 1g is "(age, sex, position, action, belongings)=(40, male, (x5, y5), standing, suitcase)".

If the conditions are "male" and "40 to 60 years old", there are two people between the ages of 40 and 60 (i.e., person 1d and person 1g), so the number is the same as the threshold. . The data generation unit 160 generates “(age, gender, position, action, belongings)=(40-60, male, (x5, y5), standing, suitcase)” and “(age, gender, position, action, belongings)=(40-60, male, (x7, y7), sitting, none)” is generated as the provided information.

Also, when the conditions are "female" and "20 to 40 years old", there are three persons aged 20 to 40 (that is, person 1c, person 1e, and person 1f). Therefore, in the case of this condition, the number of people is equal to or greater than the threshold. The data generation unit 160 generates "(20-40, female, (x3, y3), sitting, none)" and "(age, sex, position, behavior, belongings) = (20-40, female, (x4, y4), sitting, none)” and “(age, sex, position, behavior, belongings)=(20-40, female, (x6, y6), sitting, none)” are generated as the provided information.

In this way, when the number of people of the estimated age for the sex is less than the threshold, the age range is widened and the number of people is aggregated. As a result, the number of people becomes equal to or greater than the threshold, and the provision information is generated based on the number of people, thereby reducing the possibility that an individual can be identified and generating the provision information in consideration of privacy.

In the above, the case of widening the age range has been described. Other methods may be used to secure the number of people. For example, by increasing the number of pieces of history information to be acquired, the number of people who are equal to or greater than the threshold may be secured. When the number of people is secured by this method, the generated provision information may include time information.

The data output unit 170 outputs the provided information to the outside. When the information processing device 100 is incorporated in the camera 10 , the data output unit 170 outputs the provided information to the edge terminal 20 .

The edge terminal 20 switches content to be displayed on the monitor 30 using the provided information acquired from the camera 10 . When there is content with a clear target, such as advertisement content for cosmetics or travel tour advertisement content for middle-aged people, the edge terminal 20 switches the content based on the provided information. This improves advertising efficiency.

Next, the flow of operations of the information processing apparatus 100 will be described.
First, after power-on of the information processing apparatus 100, the setting unit 110 sets a threshold value. The threshold may be a preset threshold or a threshold set by the user. Alternatively, the setting unit 110 may set the threshold to a value obtained by subtracting a predetermined number from the average value calculated based on the history information. For example, let the average value be 20. The predetermined number is 3. The setting unit 110 may set 17 (=20-3) as the threshold. It should be noted that the threshold is preferably set to a value greater than 1 in order to lower the probability that an individual will be identified.

After the threshold is set, the data acquisition unit 120 starts acquiring camera images. Data acquisition section 120 outputs the acquired camera image to estimation section 130 .
The estimation unit 130 recognizes a person included in the camera image and estimates attributes and states of the recognized person. Estimation section 130 outputs estimation information, which is an estimation result, to estimation information storage section 140 and data generation section 160 . The estimation unit 130 may output the number of persons included in the camera image to the data generation unit 160 .
The estimated information storage unit 140 registers estimated information in the history information table. The estimated information may be registered in descending order or may be registered in ascending order.

FIG. 7 is a flowchart illustrating an example (part 1) of processing for generating provision information according to the first embodiment.
(Step S<b>101 ) The data generation unit 160 acquires estimation information and the number of people from the estimation unit 130 . Further, the data generation unit 160 may obtain the number of people by counting the number of estimation information.
(Step S<b>102 ) The data generation unit 160 acquires a threshold from the setting unit 110 .
(Step S<b>103 ) The data generation unit 160 acquires environment information from the data acquisition environment storage unit 150 .
The execution order of steps S101 to S103 is not limited to that shown in FIG. Also, steps S101-103 may be executed in parallel.

(Step S104) The data generator 160 determines whether or not the number of people is equal to or greater than a threshold. If the number of people is greater than or equal to the threshold, the process proceeds to step S105. If the number of people is smaller than the threshold, the process proceeds to step S106.
(Step S105) The data generator 160 generates provision information based on the estimated information.

FIG. 8 is a flowchart illustrating an example (part 2) of processing for generating provision information according to the first embodiment.
(Step S106) The data generation unit 160 determines whether or not the history information acquisition condition, which is environment information, is satisfied. In other words, the data generation unit 160 determines whether history information can be acquired. If the history information acquisition condition is satisfied, the process proceeds to step S107. If the history information acquisition condition is not satisfied, the process ends.

(Step S107) The data generator 160 acquires the number of pieces of history information that satisfy the condition for acquiring history information. For example, if the history information acquisition condition is one hour and the camera image acquisition time is 7:00, the data generator 160 acquires history information from 6:00 to 7:00.
(Step S108) The data generator 160 adds the number of history information to the number of people. For example, the data generator 160 adds the number of history information from 6:00 to 7:00 (for example, 10) to the number of people acquired in step S101.

(Step S109) The data generator 160 determines whether or not the number of people obtained by the addition is equal to or greater than a threshold. If the number of people is greater than or equal to the threshold, the process proceeds to step S110. If the number of people is smaller than the threshold, the process proceeds to step S111.
(Step S110) The data generator 160 generates provided information based on the estimated information and the history information. The process then ends.
(Step S111) The data generation unit 160 changes the time zone so as to acquire past history information rather than previously acquired history information. For example, when history information from 6:00 to 7:00 was obtained last time, the data generator 160 changes the time period so that history information from 5:00 to 6:00 is obtained. Then, the process proceeds to step S106.

Next, hardware included in the information processing apparatus 100 will be described.
FIG. 9 illustrates hardware included in the information processing apparatus according to the first embodiment. The information processing apparatus 100 has a processor 201 , a memory 202 , a key input/output interface (hereinafter referred to as I/F) 203 , a data input/output I/F 204 and a display output I/F 205 .

For example, the processor 201 is a CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), or the like. Processor 201 may be a multiprocessor. Further, the information processing device 100 may have a processing circuit.
For example, the memory 202 is RAM (Random Access Memory).

A key input/output I/F 203 is connected to a keyboard, a touch key device, and the like.
A data input/output I/F 204 is connected to the camera 10 . Also, for example, the data input/output I/F 204 may acquire threshold values, history information, and environment information stored in an external storage device.
The display output I/F 205 may provide the average value to the user. The display output I/F 205 outputs the provided information. For example, the display output I/F 205 outputs the provided information to the edge terminal 20 .

Here, the estimated information storage unit 140 and the data acquisition environment storage unit 150 may be implemented as storage areas secured in the memory 202 .
A part or all of the setting unit 110, the data acquiring unit 120, the estimating unit 130, the data generating unit 160, and the data output unit 170 may be implemented by a processing circuit. Also, some or all of the setting unit 110 , the data acquisition unit 120 , the estimation unit 130 , the data generation unit 160 , and the data output unit 170 may be implemented as modules of a program executed by the processor 201 .

According to Embodiment 1, the information processing apparatus 100 can generate privacy-friendly data based on information about a person included in a camera image. The information processing apparatus 100 also provides the user with a value recommended as the threshold. Therefore, the information processing apparatus 100 can allow the user to set an appropriate threshold when generating the provided information.

Furthermore, the information processing apparatus 100 can generate provision information according to the situation in which the camera 10 is installed by using the history information acquisition condition.
In the above description, the control when the camera 10 is installed in the vehicle A has been described for easy understanding of the description. However, similar effects can be obtained even when the camera 10 is installed outside the vehicle.

Embodiment 2.
Next, Embodiment 2 will be described. In Embodiment 2, mainly matters different from Embodiment 1 will be described. In the second embodiment, descriptions of items common to the first embodiment are omitted.

FIG. 10 is a block diagram showing functions of the information processing apparatus according to the second embodiment. 10 that are the same as those shown in FIG. 1 are assigned the same reference numerals as those shown in FIG.
The information processing device 100a includes a setting unit 110a, an estimation unit 130a, an estimation information storage unit 140a, a data acquisition environment storage unit 150a, a data generation unit 160a, an other device estimation information storage unit 180, and an information transfer unit 190.

The estimation information storage unit 140 a , the data acquisition environment storage unit 150 a , and the other device estimation information storage unit 180 may be implemented as storage areas secured in the memory 202 .
A part or all of the setting unit 110a, the estimation unit 130a, the data generation unit 160a, and the information transfer unit 190 may be realized by a processing circuit. Also, part or all of the setting unit 110a, the estimation unit 130a, the data generation unit 160a, and the information transfer unit 190 may be implemented as modules of a program executed by the processor 201. FIG.

Before describing the functions of the information processing device 100a, a specific example of installation of a plurality of information processing devices will be shown.
FIG. 11 is a diagram showing a specific example of installation of a plurality of information processing apparatuses according to the second embodiment. The cameras 10a-10d, edge terminals 20a and 20b, and monitors 30a-30d communicate via a network. The network may be a wired network or a wireless network.

The cameras 10a-10d incorporate information processing devices 100a-100d. Information processing apparatuses 100a to 100d may be incorporated in edge terminals 20a and 20b. Also, the information processing apparatuses 100a to 100d may be incorporated in a server that communicates with the edge terminals 20a and 20b. In the following description, it is assumed that the information processing apparatuses 100a-100d are incorporated in the cameras 10a-10d. When the information processing apparatuses 100a to 100d are incorporated in the edge terminals 20a, 20b or servers, a plurality of cameras may be connected to the edge terminals 20a, 20b or servers.

FIG. 11 shows that the cameras 10a and 10b are installed on the vehicle A. FIG. Moreover, FIG. 11 shows that the cameras 10c and 10d are installed in the vehicle B. As shown in FIG. The cameras 10a and 10b are installed at positions (for example, near the ceiling) where the situation inside the vehicle A can be photographed. The cameras 10a and 10b generate provided information based on passenger information included in camera images, and transmit the provided information to the edge terminal 20a. The cameras 10c and 10d are installed at positions (for example, near the ceiling) where the situation inside the vehicle B can be photographed. The cameras 10c and 10d generate provided information based on passenger information included in camera images, and transmit the provided information to the edge terminal 20b. The edge terminals 20a and 20b switch the content displayed on the monitor based on the provided information and the train operation information.

As described above, the information processing device 100a communicates with the information processing devices 100b to 100d. Here, the information processing apparatuses 100b to 100d are also referred to as a plurality of first information processing apparatuses. Therefore, one of the information processing apparatuses 100b to 100d is also called a first information processing apparatus.

Next, returning to FIG. 10, the functions of the information processing device 100a will be described.
The setting unit 110a sets a threshold. The setting unit 110a outputs the threshold to the data generation unit 160a. The threshold setting method is the same as in the first embodiment. Therefore, the description is omitted.

The setting unit 110a calculates the average number of people for each time slot based on the history information stored in the other device estimation information storage unit 180. FIG. Here, the other device estimation information storage unit 180 stores history information of the information processing devices 100b to 100d. The setting unit 110a outputs an average value for each time period. Thereby, the user can set the threshold by referring not only to the average value obtained from the information processing device 100a but also to the average values obtained from the information processing devices 100b to 100d.

The data acquisition unit 120 acquires camera images. For example, a camera image contains one or more people.

The estimation unit 130a performs estimation based on the camera image. For example, the estimation unit 130a estimates at least one of attributes and states of one or more persons based on camera images. When one or more persons are included in the camera image, the estimation unit 130a generates estimation information, which is an estimation result, for each person.
The estimation unit 130a outputs estimation information to the data generation unit 160a and the estimation information storage unit 140a. Estimating section 130 a also outputs estimation information to information transferring section 190 upon receiving a request from information transferring section 190 . The estimated information is the same as in the first embodiment. Therefore, the description is omitted.

The estimated information storage unit 140a stores estimated information as history information. History information may be expressed as follows. History information is estimation information generated before estimation information is generated by estimation section 130a. In addition, when receiving a request from the setting unit 110a, the data generation unit 160a, or the information transfer unit 190, the estimated information storage unit 140a outputs history information to the setting unit 110a, the data generation unit 160a, or the information transfer unit 190. . The history information table stored in estimated information storage unit 140a is the same as in the first embodiment. Therefore, the description is omitted.

The other device estimation information storage unit 180 stores history information of other information processing devices received by the information transfer unit 190 . Further, when receiving a request from the setting unit 110a or the data generation unit 160a, the other device estimation information storage unit 180 outputs the history information of the other information processing device to the setting unit 110a or the data generation unit 160a. The history information may be expressed as follows. The history information is information obtained by estimation by another information processing apparatus and is information generated before the estimation information is generated. The history information is also called first history information.

When the information transfer unit 190 receives a request from the data generation unit 160a or the setting unit 110a, the information transfer unit 190 receives history information from another information processing device based on the environment information in the data acquisition environment storage unit 150a. Information transfer section 190 stores the received history information in other device estimation information storage section 180 . The information transfer unit 190 receives estimation information from another information processing device when receiving a request from the data generation unit 160a. The information transfer unit 190 outputs the received estimation information to the data generation unit 160a. Further, when receiving a request from another information processing device, the information transfer unit 190 transmits the estimation information or history information to the other information processing device.
The information transfer section 190 may also acquire information from a storage medium.

As described above, the information transfer unit 190 acquires estimation information or history information from another information processing device. The estimated information is one or more pieces of information obtained by estimating at least one of attributes and states of one or more persons by the other information processing apparatus. Moreover, the said estimation information is also called 1st estimation information. The information transfer unit 190 also acquires estimated information or history information from other information processing devices. Therefore, each of the information processing apparatuses 100b to 100d stores estimation information or history information.

The data acquisition environment storage unit 150a stores history information acquisition conditions as environment information. Also, the environment information may be expressed as information indicating history information acquisition conditions. A history information acquisition condition will be described.

FIG. 12 is a diagram showing an example of an environment information table according to the second embodiment. The environment information table is stored in the data acquisition environment storage unit 150a.
The information processing device A in FIG. 12 is assumed to be an information processing device 100a. The information processing device B is assumed to be an information processing device 100b. The information processing device C is assumed to be an information processing device 100c. The information processing device D is assumed to be an information processing device 100d.
Also, the camera A in FIG. 12 is assumed to be a camera 10a. The camera B is assumed to be a camera 10b. The camera C is assumed to be a camera 10c. The camera D is assumed to be a camera 10d.

The time of the history information acquisition condition is the same as in the first embodiment. The time may be travel time between specific stations. The history information acquisition condition may indicate position information instead of the time. Historical information may not be used. When history information is not used, "estimation information only" is registered in the environment information table. Also, the conditions for acquiring the history information stored by the information processing device 100a and the history information stored by the information processing devices 100b to 100d may be different.

The item "another information processing apparatus" in the history information acquisition condition will be described. Priority is set for other information processing devices. That is, a priority is set for each information processing device. Items of other information processing apparatuses may include the same priority. Also, FIG. 12 shows the relationship between the information processing device and the camera. For example, “information processing device B-camera B” means that estimation information and history information generated based on camera images generated by camera 10b are stored in information processing device 100b.

Here, priority setting will be described. First, it is assumed that the information processing device 100a is included in a camera. Note that the camera is also called an imaging device. Information processing apparatuses 100b to 100d are assumed to be included in a plurality of cameras. A plurality of cameras are installed near the camera including the information processing device 100a. The priority may be set in order of proximity from the camera including the information processing device 100a.

Also, the time indicated by the history information acquisition condition may be set as follows. First, it is assumed that the information processing device 100a is included in a camera. It is assumed that one of the information processing devices 100b to 100d is included in the camera. The camera is also called a first imaging device. The one information processing device is also referred to as a first information processing device. The camera including the first information processing device is installed near the camera including the information processing device 100a. The time indicated by the history information acquisition condition is set based on the distance between the camera including the information processing device 100a and the camera including the first information processing device.

The information transfer unit 190 determines an information processing device that receives the estimation information and the history information based on the priority. Further, when the information transfer unit 190 does not receive the estimation information or the history information, "none" is registered in the item of the other information processing device. Furthermore, the relationship between the information processing device and the camera may be represented by an IP address, PORT number, or the like.

Next, return to the description of the setting unit 110a. The setting unit 110a calculates the average value of the number of people from the history information of the estimation information storage unit 140a and the other device estimation information storage unit 180. FIG. The method of calculating the average value and the method of presenting the average value are the same as in the first embodiment. Therefore, the description is omitted.

The setting unit 110a presents an average value when receiving a request from a user to present an average value based on history information stored in another information processing apparatus. The processing will be explained in detail. Upon receiving the user's request, the setting unit 110a requests the information transfer unit 190 to transmit the specified date and time of the history information used for calculating the average value. The information transfer unit 190 refers to the environment information table and identifies the target information processing apparatus. The information transfer unit 190 transmits an instruction to transmit the history information of the specified date and time to the specified information processing device. The specified information processing device transmits the history information of the designated date and time to the information processing device 100a. The information transfer unit 190 stores the history information of the designated date and time in the other device estimation information storage unit 180 . Other device estimation information storage section 180 outputs the stored history information to setting section 110a. The setting unit 110a calculates the average value based on the history information output by the other device estimation information storage unit 180. FIG. The method for calculating the average value is the same as the method for calculating the average value based on the history information of the estimated information storage unit 140a. Accordingly, the information processing device 100a can present an average value based on history information of other information processing devices. From the viewpoint of privacy protection, it is desirable that the information stored in the other device estimation information storage unit 180 be discarded after the average value is calculated.

The data generation unit 160a generates provision information based on thresholds, estimation information, history information, environment information, and estimation information and history information of other information processing devices. The data generator 160 a outputs the provided information to the data output unit 170 . Note that when the provided information is generated for each camera image, the data generation unit 160a generates only the estimated information stored by the information processing device 100a, or the estimated information stored by the information processing device 100a and the estimated information of other information processing devices. Generate offer information based on the information.

The data generator 160a generates provision information. In generating the provided information, the data generation unit 160a attempts to generate the provided information based on the time indicated by the environment information table, estimated information stored by the information processing device 100a, and history information stored by the information processing device 100a. The method of generating provision information based on the estimated information stored by the information processing device 100a and the history information stored by the information processing device 100a is the same as in the first embodiment. Therefore, the description is omitted. Here, when the number of data of the estimated information and the history information is small, or when the information is extremely biased, the provision information may not be generated. Therefore, estimation information or history information stored in another information processing apparatus is acquired. Then, the data generation unit 160a attempts to generate the provision information again.

Here, a case where estimation information or history information stored in another information processing apparatus is acquired will be described. Based on the estimated information stored in the information processing device 100a and the history information stored in the information processing device 100a, the data generation unit 160a, if the provided information could not be generated under the condition of "time = 1 hour", the information A request is output to the transfer unit 190 . The information transfer unit 190 refers to the history information acquisition condition and acquires the history information from the information processing apparatus 100b with priority 1 under the condition of “time=1 hour”. The information transfer section 190 stores the acquired history information in the other device estimation information storage section 180 . The data generation unit 160a generates the provided information again based on the estimation information stored in the information processing device 100a, the history information stored in the information processing device 100a, and the history information stored in the other device estimation information storage unit 180. try. When the provided information is generated, the data generating section 160 a outputs the provided information to the data output section 170 . Note that the history information stored in the other device estimation information storage unit 180 is desirably discarded.

If the provided information is not generated, the information transfer unit 190 determines another information processing apparatus from which history information is to be acquired, according to the priority. Specifically, the information transfer unit 190 refers to the history information acquisition condition and determines the information processing apparatus 100c with priority 2 . Then, the information transfer unit 190 acquires the history information from the information processing device 100c under the condition of "time=1 hour". The information transfer section 190 stores the acquired history information in the other device estimation information storage section 180 . The data generation unit 160a attempts to generate the provided information again based on the estimated information stored in the information processing device 100a, the history information stored in the information processing device 100a, and the history information acquired from the information processing devices 100b and 100c. . The data generator 160a repeats the above process until the provided information is generated. It should be noted that the data generation unit 160a terminates the process when the provision information cannot be generated even by using the history information of the information processing device with the lowest priority. Further, when there are a plurality of information processing apparatuses having the same priority, the information transfer unit 190 may simultaneously acquire history information from the plurality of information processing apparatuses. Then, the data generation unit 160a may attempt to generate the provided information using the history information acquired from the plurality of information processing devices.

In this way, the data generating unit 160a generates the number of pieces of history information (that is, the history information stored in the estimated information storage unit 140a) according to the content indicated by the history information acquisition condition (for example, one hour) and the history information acquisition condition. whether or not the sum of the number of pieces of history information corresponding to the content indicated by (that is, the number of pieces of history information stored by the other device estimation information storage unit 180) and the number of pieces of estimation information acquired from the estimation unit 130a is equal to or greater than the threshold judge. If the total value is equal to or greater than the threshold, the data generation unit 160a generates history information corresponding to the content indicated by the history information acquisition condition (that is, the history information stored in the estimated information storage unit 140a) and the content indicated by the history information acquisition condition. Provided information is generated based on the history information according to (that is, the history information stored in the other device estimation information storage unit 180) and the estimation information acquired from the estimation unit 130a.

Next, a case where "estimation information only" is registered in the time item of the environment information table will be described. Further, the description uses the information processing device 100d. That is, the information processing device 100d is assumed to be included in the camera D. FIG.
The data generation unit of the information processing device 100d outputs a request to the information transfer unit of the information processing device 100d when the provision information cannot be generated based on the estimation information stored in the information processing device 100d. The information transfer unit of the information processing device 100d refers to the environment information table and acquires the estimated information from the information processing device 100c with priority 1 . The information transfer unit of the information processing device 100d outputs the acquired estimation information to the data generation unit of the information processing device 100d. The data generation unit of the information processing device 100d attempts to generate the provision information again based on the estimation information stored in the information processing device 100d and the acquired estimation information. When the provided information is generated, the data generation unit of the information processing device 100d outputs the provided information to the data output unit of the information processing device 100d. If the provided information is not generated, the data generation unit of the information processing device 100d repeats the above process until the provided information is generated. It should be noted that the data generation unit of the information processing device 100d terminates the process when the provision information cannot be generated even by using the estimated information of the information processing device with the lowest priority.

In this way, the information transfer unit of the information processing device 100d determines the target information processing device from which the estimation information or the history information is to be obtained based on the priority, and transmits the estimation information or the history information from the determined information processing device. get.

Further, when estimation information stored by the information processing device 100a, history information stored by the information processing device 100a, and estimation information or history information acquired from another information processing device are used, the imaging regions of a plurality of cameras overlap. Sometimes. When the imaging areas overlap, the same person is included in multiple camera images generated by multiple cameras. If the same person is included, the information is duplicated. Duplicate information should therefore be removed. For example, when the estimated information includes the time and the position of the person, the information processing device 100a transforms the position of the person in each of the plurality of camera images from the camera coordinate system to the world coordinate system. Thereby, the information processing device 100a can obtain a plurality of coordinates corresponding to the plurality of camera images. The information processing apparatus 100a can determine whether or not the person is the same person by comparing the plurality of coordinates. The information processing apparatus 100a deletes redundant information when the same person exists. Further, when the position of the person is not included in the estimation information and when the difference between the items of the estimation information is within the estimation error range, the information processing device 100a may determine that the information is identical. Also, a method for deleting redundant information may be a method other than the above.

In this way, the information processing device 100a can generate information that takes privacy into consideration. That is, the information processing device 100a can generate data that makes it difficult to identify an individual.

Further, the information processing apparatus 100a can flexibly create provision information according to the purpose of use by setting the priority to another information processing apparatus. For example, when it is desired to use history information of nearby cameras, priority is set in the information processing device in order of distance. Furthermore, in a train running between A station and B station, if it is desired to generate provision information from all the cameras arranged in the leading car of each train set, priority 1 is set to the lead car of each train set. It is set in the information processing device corresponding to all cameras.

The function of data output section 170 is the same as in the first embodiment. For example, in FIG. 11, the provided information output by the cameras 10a and 10b is input to the edge terminal 20a. For example, in FIG. 11, the provided information output by the cameras 10c and 10d is input to the edge terminal 20b. Content switching by the edge terminals 20a and 20b is the same as in the first embodiment. Therefore, the description is omitted.

Next, the operation flow of the information processing device 100a will be described.
First, after the information processing apparatus 100a is powered on, the setting unit 110a sets a threshold value. The threshold may be a preset threshold or a threshold set by the user. Further, the setting unit 110a may set the average value calculated based on the history information stored in the information processing device 100a and the history information acquired from other information processing devices as the threshold value. It should be noted that the threshold is preferably set to a value greater than 1 in order to lower the probability that an individual will be identified. In addition, when the average value is presented to the user, the user can set the threshold with reference to the average value.

After the threshold is set, the data acquisition unit 120 starts acquiring camera images. The data acquisition unit 120 outputs the acquired camera image to the estimation unit 130a.
The estimation unit 130a recognizes a person included in a camera image and estimates attributes and states of the recognized person. The estimation unit 130a outputs estimation information, which is an estimation result, to the estimation information storage unit 140a and the data generation unit 160a. Estimation section 130 a outputs estimation information to information transfer section 190 when a request is received from information transfer section 190 .
The estimated information storage unit 140a registers the estimated information in the history information table.

FIG. 13 is a flowchart illustrating an example (part 1) of processing for generating provision information according to the second embodiment. The process of FIG. 13 differs from the process of FIG. 8 in that step S106a is executed. Therefore, FIG. 13 demonstrates step S106a. The description of the processes other than step S106a is omitted. Processing other than step S106a is executed by the data generator 160a.

(Step S106a) The data generation unit 160a determines whether or not the history information stored in the estimated information storage unit 140a can be acquired based on the content indicated by the history information acquisition condition, which is the environment information. Note that when the history information cannot be acquired, the history stored in the estimated information storage unit 140a with the content indicated by the history information acquisition condition (for example, one hour) at the time when step S106a is executed after step S104. This is the case when information cannot be obtained. A case where history information cannot be acquired is a case where the number of users satisfying the threshold cannot be secured even if the time slot indicated by the history information acquisition condition (for example, one hour) is changed.
If history information can be acquired, the process proceeds to step S107. If the history information cannot be acquired, the process proceeds to step S112.
Here, the information processing device 100a does not have to execute step S111. If step S111 is not executed and if step S109 is No, the process proceeds to step S106a. Information on whether to execute step S111 may be stored in the memory 202 .

FIG. 14 is a flowchart illustrating an example (part 2) of processing for generating provision information according to the second embodiment.
(Step S112) The data generation unit 160a refers to the environment information table and determines whether or not there is another information processing apparatus that has not been selected. If the condition is satisfied, the process proceeds to step S113. If the condition is not met, the process ends.
(Step S113) The data generation unit 160a refers to the environment information table and selects the information processing apparatus with the highest priority among the other non-selected information processing apparatuses.

(Step S114) The data generation unit 160a transmits a request to acquire the estimated information or the history information corresponding to the content (for example, 1 hour) indicated by the history information acquisition condition from the selected information processing device. Output to unit 190 .
The information transfer unit 190 determines whether or not the estimated information or the history information has been acquired. If the condition is satisfied, the process proceeds to step S115. If the condition is not satisfied, the process proceeds to step S112.

In addition, when the estimation information can be acquired, the information transfer unit 190 outputs the estimation information to the data generation unit 160a. In addition, the said estimation information is one or more estimation information. Moreover, the said estimation information is also called 1st estimation information. Further, when the history information can be acquired, the information transfer section 190 stores the history information in the other device estimation information storage section 180 . Note that the history information is one or more pieces of history information. The history information is also called first history information.

(Step S<b>115 ) The data generation unit 160 a acquires the estimation information or the history information stored in the other device estimation information storage unit 180 .
(Step S116) When the estimation information is acquired, the data generation unit 160a adds the number of estimation information to the number of people. Further, when the history information is acquired, the data generation unit 160a adds the number of history information to the number of people.
(Step S117) The data generator 160a determines whether or not the number of people obtained by the addition is equal to or greater than a threshold. If the number of people is greater than or equal to the threshold, the process proceeds to step S118. If the number of people is smaller than the threshold, the process proceeds to step S112.

(Step S118) The data generator 160a generates provision information.
Specifically, in the case of No in step S106a executed after step S104 and when the estimated information is acquired, the data generation unit 160a transfers the estimated information acquired from the information transfer unit 190 and the estimation unit Provided information is generated based on the estimated information obtained from 130a. In this way, when the sum of the number of estimated information acquired from the information transfer unit 190 and the number of estimated information acquired from the estimation unit 130a is equal to or greater than the threshold, the data generation unit 160a Provided information is generated based on the obtained estimated information and the estimated information obtained from the estimation unit 130a.

Further, in the case of No in step S106a executed after step S104 and when the history information is acquired, the data generation unit 160a stores the history information acquired from the other device estimation information storage unit 180, Provided information is generated based on the estimated information acquired from the estimation unit 130a. In this way, data generating section 160a, when the sum of the number of estimated information acquired from estimating section 130a and the number of history information acquired from other device estimated information storage section 180 is equal to or greater than a threshold, estimates Provided information is generated based on the estimated information acquired from the unit 130 a and the history information acquired from the other device estimated information storage unit 180 .

Further, when step S107 is executed and the estimated information is acquired, the data generating unit 160a generates the estimated information acquired from the information transfer unit 190, the estimated information acquired from the estimating unit 130a, Provided information is generated based on the history information acquired from the estimated information storage unit 140a. In this way, the data generating unit 160a calculates the number of pieces of estimated information acquired from the estimating unit 130a, the number of pieces of history information acquired from the estimated information storage unit 140a, and the number of pieces of estimated information acquired from the information transfer unit 190. If the total value is equal to or greater than the threshold, the provided information is generated based on the estimated information acquired from the estimation unit 130a, the history information acquired from the estimated information storage unit 140a, and the estimated information acquired from the information transfer unit 190. do.

Further, when step S107 is executed and the history information is acquired, the data generation unit 160a stores the history information acquired from the other device estimation information storage unit 180 and the history information acquired from the estimation unit 130a. Provided information is generated based on the estimated information and the history information acquired from the estimated information storage unit 140a. In this way, the data generating unit 160a stores the number of estimated information acquired from the estimating unit 130a, the number of history information acquired from the estimated information storage unit 140a, and the history information acquired from the other device estimation information storage unit 180. is equal to or greater than the threshold, the estimated information acquired from the estimation unit 130a, the history information acquired from the estimated information storage unit 140a, and the history information acquired from the other device estimated information storage unit 180 to generate the provided information.
After the offer information is generated, the process ends.

The number of people compared with the threshold in steps S104, 109, and 117 may be the number of persons whose attributes or states match. For example, in the case where step S106a executed after step S104 is No and the estimated information is acquired from another information processing device, the data generation unit 160a determines that the estimated information acquired from the information transfer unit 190 is If the sum of the number of men indicated and the number of men indicated by the estimation information obtained from the estimation unit 130a is equal to or greater than the threshold (Yes in step S117), the estimation information obtained from the information transfer unit 190 and the number of men indicated by the estimation unit Provided information is generated based on the estimated information acquired from 130a (step S118). Further, for example, when step S106a executed after step S104 is No and history information is acquired from another information processing device, the data generation unit 160a acquires from the other device estimation information storage unit 180 If the sum of the number of women indicated by the history information that has been obtained and the number of women indicated by the estimation information acquired from the estimation unit 130a is equal to or greater than the threshold (Yes in step S117), the estimation information acquired from the estimation unit 130a and the history information acquired from the other device estimation information storage unit 180, the provision information is generated (step S118).

Here, the result of tallying the estimation information acquired from the estimation unit 130a is also referred to as a first tallying result. The result obtained by adding the estimation information acquired from the information transfer unit 190 to the first totalization result is also referred to as the second totalization result. The result obtained by adding the history information acquired from the estimated information storage unit 140a to the second totalization result is also referred to as the third totalization result. The result obtained by adding the history information acquired from the estimated information storage unit 140a and the history information acquired from the information transfer unit 190 to the first totalization result is also referred to as a fourth totalization result.

Next, the processing executed by the information processing device 100a will be described using a specific example.
15A and 15B are diagrams illustrating a specific example (part 1) of processing executed by the information processing apparatus according to the second embodiment.
The information processing device 100a acquires the estimation information 41 (step S101). FIG. 15A shows estimated information 41. FIG.

The information processing device 100a acquires a threshold (step S102). A threshold value of 3 is used. Since the number of pieces of estimated information is 1, the information processing apparatus 100a determines that the number of people is smaller than the threshold (No in step S104). It is assumed that the information processing apparatus 100a cannot acquire history information from the estimated information storage unit 140a (No in step S106a).

The information processing device 100a refers to the environment information table and identifies the information processing device 100b with priority 1 . The information processing device 100a acquires the history information 42 from the information processing device 100b (step S115). FIG. 15B shows history information 42 . Further, FIG. 15B shows that the information processing apparatus 100a acquires the estimation information 41 and the history information 42. FIG. Also, the number of people based on the estimation information 41 and the history information 42 is two. The information processing apparatus 100a determines that the number of people is smaller than the threshold (No in step S117).

16A and 16B are diagrams illustrating a specific example (part 2) of processing executed by the information processing apparatus according to the second embodiment.
The information processing device 100a refers to the environment information table and identifies the information processing device 100c with priority 2 . The information processing device 100a acquires the history information 43 from the information processing device 100c (step S115). FIG. 16A shows the history information 43. FIG. FIG. 16A also shows that the information processing apparatus 100a acquires estimated information 41, history information 42, and history information 43. FIG. Also, the number of persons based on the estimation information 41, the history information 42, and the history information 43 is three. The information processing device 100a determines that the number of people is equal to or greater than the threshold (Yes in step S117).

The information processing device 100a generates the provision information 44 based on the estimated information 41, the history information 42, and the history information 43 (step S118). FIG. 16B shows the provided information 44. FIG. For example, the age of the provided information 44 is "20-30". In this way, since privacy is considered, the age is "20-30".

According to the second embodiment, the information processing device 100a can generate privacy-conscious provision information using estimated information or history information stored in another information processing device.
In addition, the information processing apparatus 100a presents the average value to the user, so that the user can set an appropriate threshold as the threshold.

Furthermore, by setting the priority to other information processing apparatuses, the information processing apparatus 100a can generate the provision information according to the situation in which the camera is installed or the purpose of use.
In the above description, the control when the camera is installed in the vehicle has been described in order to make the description easier to understand. However, the same effect can be obtained even when the camera is installed outside the vehicle.

The features of the embodiments described above can be combined as appropriate.

1 camera image 1a person 1b person 10 camera 10a to 10d camera 20 edge terminal 20a, 20b edge terminal 30 monitor 30a to 30d monitor 41 estimated information 42 history information 43 history information 44 provision Information 100 information processing device 100a to 100d information processing device 110 setting unit 110a setting unit 120 data acquisition unit 130 estimation unit 130a estimation unit 140 estimated information storage unit 140a estimated information storage unit 150 data acquisition environment storage unit 150a data acquisition environment storage unit 160 data generation unit 160a data generation unit 170 data output unit 180 other device estimation information storage unit 190 information transfer unit 201 processor 202 memory 203 key input/output I /F, 204 data input/output I/F, 205 display output I/F.

Claims (11)

An information processing device that communicates with a first information processing device,
a data acquisition unit that acquires image data;
a setting unit for setting a threshold;
when one or more persons are included in the image data, at least one of attributes and states of the one or more persons is estimated based on the image data, and estimation information, which is an estimation result, is provided for each person; an estimator that generates in
Acquiring from the first information processing apparatus one or more pieces of first estimation information obtained by the first information processing apparatus estimating at least one of attributes and states of one or more persons an information transfer unit;
When the total value of the number of the generated estimation information and the number of the first estimation information is equal to or greater than the threshold, privacy-conscious information based on the estimation information and the first estimation information a data generation unit that generates provided information that is
a data output unit that outputs the provided information;
Information processing device having further comprising an estimated information storage unit that stores history information, which is estimated information generated before the estimated information is generated;
When the total number of the number of estimation information, the number of history information, and the number of first estimation information is equal to or greater than the threshold value, the data generation unit generates the estimation information, the history information, and the first generating the provided information based on the estimated information of 1;
The information processing device according to claim 1 . The information transfer unit communicates with a plurality of the first information processing devices,
each of the plurality of first information processing devices stores the first estimation information;
A priority is set for each of the plurality of first information processing devices,
The information transfer unit acquires the first estimated information based on the priority.
The information processing apparatus according to claim 1 or 2. The information processing device is included in an imaging device,
The plurality of first information processing devices are included in a plurality of imaging devices,
The plurality of imaging devices are installed near an imaging device including the information processing device,
The priority is set in order of proximity from an imaging device including the information processing device.
The information processing apparatus according to claim 3. Other device estimation information storage unit for storing first history information which is information obtained by estimation of the first information processing device and is information generated before the first estimation information is generated. further having
When the total value of the number of the estimated information and the number of the first history information is equal to or greater than the threshold, the data generation unit performs the provision based on the estimated information and the first history information. generate information,
The information processing device according to claim 1 . an estimated information storage unit that stores history information that is estimated information generated before the estimated information is generated;
Other device estimation information storage unit for storing first history information which is information obtained by estimation of the first information processing device and is information generated before the first estimation information is generated. When,
further having
When the total value of the number of estimated information, the number of history information, and the number of first history information is equal to or greater than the threshold value, the data generation unit generates the estimated information, the history information, and the first generating the provided information based on the history information of 1;
The information processing device according to claim 1 . further comprising a data acquisition environment storage unit that stores environment information indicating history information acquisition conditions;
The data generation unit generates the number of history information according to the content indicated by the history information acquisition condition, the number of first history information according to the content indicated by the history information acquisition condition, and the number of estimated information. is equal to or greater than the threshold value, the history information corresponding to the contents indicated by the history information acquisition condition, the first history information corresponding to the contents indicated by the history information acquisition condition, and the estimated information generating the provided information based on
The information processing device according to claim 6 . The information processing device is included in an imaging device,
The first information processing device is included in a first imaging device,
The first imaging device is installed near an imaging device including the information processing device,
the time indicated by the history information acquisition condition is set based on the distance between the imaging device and the first imaging device;
The information processing apparatus according to claim 7. The information transfer unit communicates with a plurality of the first information processing devices,
each of the plurality of first information processing devices stores the first history information;
A priority is set for each of the plurality of first information processing devices,
the information transfer unit acquires the first history information based on the priority;
The information processing apparatus according to any one of claims 5 to 8. The information processing device is included in an imaging device,
The plurality of first information processing devices are included in a plurality of imaging devices,
The plurality of imaging devices are installed near an imaging device including the information processing device,
The priority is set in order of proximity from an imaging device including the information processing device.
The information processing apparatus according to claim 9 . Other device estimation information storage unit for storing first history information which is information obtained by estimation of the first information processing device and is information generated before the first estimation information is generated. further having
The setting unit calculates an average value of the number of people for each time period based on the first history information, and outputs the average value for each time period.
The information processing device according to claim 1 .

Images