TW201944325A - Analysis system - Google Patents

Abstract

Provided is an analysis system (1) that is mounted on a moving body (V) and comprises: a moving-body analysis-data collecting device (10) that collects first analysis data containing first image data indicating an image of the outside of the moving body (V) imaged with movement of the moving body (V) and a first positional data indicating a position at which the image of the outside of the moving body (V) was imaged; and a data analysis device (20) that analyzes, on the basis of the first analysis data collected by the moving-body analysis-data collecting device (10), an attribution of a person contained in the image indicated by the first image data and a flow of the person whose attribution has been identified.

Description

Analysis system

The present invention relates to an analysis system.

As a conventional analysis system, for example, Patent Document 1 discloses a counting device. This counting device detects the number of passersby near the store, the number of people entering the store, and the number of people buying goods in the store based on the image data captured by the first to third photography devices. To the number of people.

[Prior technical literature]
[Patent Literature]
[Patent Document 1] Japanese Patent Laid-Open No. 2007-011723

[Inventive problem solving]
However, the analysis system described above still has room for further improvement in, for example, improving the accuracy of analysis.

The present invention has been made in view of the above circumstances, and aims to provide an analysis system that can improve the accuracy of analysis.

[Means for solving problems]
In order to achieve the above object, the analysis system requested by the present invention is characterized by including: a mobile body analysis data collection device installed on the mobile body, and collecting a first analysis including first image data and first analysis data Data, wherein the first image data indicates an image of the outside of the mobile body that is captured as the mobile body moves, and the first position data indicates the position of the image that is captured outside the mobile body And a data analysis device that analyzes the attributes of the person contained in the image represented by the first image data and the defined attributes based on the first analysis data collected by the mobile body analysis data collection device. Character flow.

In addition, in the analysis system, the data analysis device uses a plurality of images represented by the first image data to extract an image that can define the attributes of the person, including the characteristic points of the person, and according to the The extracted image is used to analyze the attributes of the person contained in the image.

In addition, in the analysis system, the moving body analysis data collection device may further collect second analysis data including second image data and second position data, where the second image data indicates the moving body The second position data indicates the position where the internal image of the moving body was taken; the data analysis device further based on the second analysis data collected by the moving body analysis data collection device, for the second analysis data The attributes of the person contained in the image represented by the second image data and the flow of the persons defined by the attribute are analyzed.

In addition, the analysis system may further include a fixed body analysis data collection device which is installed on the fixed body provided on the road and collects third analysis data including third image data and third position data. The third image data indicates an image of the outside of the fixed body obtained by shooting in a state of being mounted on the fixed body; the third position data indicates the position of an image of the outside of the fixed body, and the The data analysis device further analyzes the attributes of the person contained in the image represented by the third image data according to the third analysis data collected by the fixed analysis data collection device; and the person who defines the attribute Flow.

In addition, in the analysis system, the mobile body can repeatedly walk on a path set in advance.

In addition, in the analysis system, the data analysis device may include a memory section that stores analysis result data, and the analysis result data indicates an analysis result obtained by the data analysis device.

In addition, in the analysis system, the attributes of the person analyzed by the data analysis device may include gender, age, physique, social status, hobbies, or action orientation.

[Effect of the invention]
The analysis system requested by the present invention can analyze the attributes of the characters contained in the image represented by the first image data by the data analysis device according to the first analysis data; and the flow of the characters defined by the attributes. In this case, the analysis system can collect the first image data constituting the first analysis data; and can also collect the first image data according to the moving body analysis data collection device installed on the moving body, as the moving body moves. A location data. As a result, the analysis system can ensure a relatively large amount of first analysis data that can be used for analysis performed by the data analysis device, and thus can improve the accuracy of the analysis.

Hereinafter, embodiments of the present invention will be described in detail based on the drawings. In addition, this embodiment is not intended to limit the present invention. In addition, the constituent elements in the following implementation modes also include those that can be easily replaced by persons with ordinary knowledge in the technical field or are substantially equivalent.

[Implementation Mode 1]
The analysis system 1 of the present embodiment shown in FIG. 1 is a system that provides analysis result data analyzed by the analysis device 20 to the customer terminal CL, and includes a recording device 10 as a collection device of mobile analysis data; And an analysis device 20 as a data analysis device. The analysis device 20 of this embodiment analyzes the attributes of the person and the flow of the person who has defined the attributes based on the images collected by the recording device 10. In addition, in this case, in the analysis system 1, the recording device 10 installed in the moving body V is utilized as a device for collecting analysis data, and the analysis data is used for analysis by the analysis device 20. In this way, the accuracy of the analysis is improved. Hereinafter, the configuration of the analysis system 1 will be described in detail with reference to the drawings.

The recording device 10 is used to collect the first analysis data, which is used for analysis by the analysis device 20. The first analysis data includes the following data: first image data, which indicates an image, and first position data, which indicates a position where the image was captured. The recording device 10 according to this embodiment is mounted on the moving body V. The moving body V installed in the recording device 10 is typically a vehicle walking on the road, for example, any one of a private car, a rental car, a shared car, a shared car, a bus, a taxi, a truck, a transporter, a work vehicle, and the like. . The recording device 10 is typically mounted on a plurality of moving bodies V in a typical manner. That is, the analysis system 1 according to this embodiment includes a plurality of recording devices 10 respectively installed on the plurality of moving bodies V, and the plurality of recording devices 10 can collect analysis data. Preferably, at least a part of the plurality of recording devices 10 is mounted on a vehicle that repeatedly travels a predetermined path, such as a shuttle bus or a long-distance transportation truck. In addition, the recording device 10 collects the first image data and the first position data as the first analysis data, where the first image data indicates an image taken outside the moving body V as the moving body V moves ; The first position data indicates a position where an image of the outside of the moving body V is taken. The recording device 10 can use, for example, an in-vehicle device such as a so-called driving recorder mounted on the moving body V, but is not limited thereto.

Specifically, the recording device 10 includes an external camera 11, a position information measuring device 12, a data input / output unit 13, and a control unit 14.

The external camera 11 is an external imaging device that captures an image of the outside of the moving body V. The external camera 11 captures an image of the outside of the moving body V as the moving body V moves to collect first image data representing an image of the outside of the moving body V. The external camera 11 typically captures a moving image of the outside of the moving body V. The external camera 11 is installed on the moving body V from the perspective of a person who can capture a person who is an analysis target of the analysis system 1-here, a person located on the road outside the moving body V. The external camera 11 may be provided in a plurality of places such as a front portion, a side portion, a rear portion, and a top portion of the moving body V, so as to facilitate photographing a person on the road from the moving body V. The external camera 11 may be a monocular camera or a stereo camera. In addition, the image captured by the external camera 11 may be black and white or color. The external camera 11 is communicably connected to the control section 14 and outputs the collected first image data to the control section 14.

The position information measuring device 12 is a measuring device that measures the current position of the moving body V. As the position information measuring device 12, for example, a GPS receiver that receives transmitted radio waves from a GPS (Global Positioning System) satellite can be used. The position information measuring device 12 receives GPS information (latitude and longitude coordinates) as information indicating the current position of the mobile body V by receiving radio waves transmitted by GPS satellites, and collects information indicating that the image of the outside of the mobile body V is captured. First position information. The position information measuring device 12 is communicably connected to the control section 14 and outputs the collected first position data to the control section 14.

The data input / output unit 13 is used to input / output various data between the recording device 10 and a device different from the recording device 10. The data input / output unit 13 of this embodiment can input / output the first analysis data to the analysis device 20 of a device different from the recording device 10. The input / output unit 13 may be configured to perform input / output of data between the recording device 10 and different devices through communication (either wired or wireless) through a network. In addition, the data input / output unit 13 may have, for example, a slot unit, and a configuration in which data is input / output between the recording device 10 and different devices through a recording medium inserted in the slot unit. Here, the recording medium may be, for example, a memory (removable medium) removed from the recording device 10 through the slot portion. The recording medium may be, for example, a memory card in various forms, such as an SD card, but is not limited thereto.

The control unit 14 controls the components of the recording apparatus 10 in an integrated manner. The control unit 14 executes various calculation processes for collecting the first analysis data. The control unit 14 is configured as an electronic circuit including a central processing unit such as a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and a conventional microcomputer including an interface. The control unit 14 is communicably connected to various components such as the external camera 11, the position information measuring device 12, and the data input / output 13, and can exchange various signals and data with each component.

More specifically, the control unit 14 is configured to include a storage unit 14A and a processing unit 14B. The storage unit 14A and the processing unit 14B can exchange various signals and data between the components. The storage unit 14A stores: conditions and information required for performing various processes in the processing unit 14B; various programs or software executed by the control unit 14, control data, and the like. The storage unit 14A may store first analysis data, collected time, and the like. In other words, the first analysis data includes time data indicating the time when the data was collected, or other data. The storage unit 14A may temporarily store, for example, various data generated during the processing performed by the processing unit 14B. The storage unit 14A can read out such data as necessary through the processing unit 14B, the data input / output unit 13, and the like. The storage unit 14A may also be a relatively large-capacity storage device such as a hard disk, an SSD (Solid State Drive), or an optical disk, or a storage device such as RAM, flash memory, or NVSRAM (Non Volatile Static Random Access Memory, Non-volatile static random memory) and other rewritable semiconductor memory. The processing unit 14B executes various programs stored in the storage unit 14A according to various input signals and the like, executes various processes, and outputs the output signals to each unit by the operation of the programs to realize various functions. The processing unit 14B controls the operations of the external camera 11 and the position information measuring device 12 to perform processing for collecting first analysis data, the first analysis data including first image data and first position data. In addition, the processing section 14B executes processing on data input / output performed by the data input / output section 13. For example, the processing unit 14B may execute the process of outputting the first analysis data to the analysis device 20 through the data input / output unit 13.

The analysis device 20 is configured to analyze the collected first analysis data by the recording device 10 and provide the analysis result data indicating the analysis result to the customer terminal CL. The analysis device 20 and the customer terminal CL may constitute a so-called cloud service type device (cloud server) installed on the network, or may be constituted as a so-called stand-alone device separated from the network. The analysis device 20 analyzes the attribute of the person and the flow of the person who defines the attribute according to the first analysis data collected by the recording device 10, wherein the character is included in In the image represented by the first image material constituting the first analysis material. The analysis device 20 of the present embodiment generates: character attribute data, which represents the attributes of the characters; attributes distinguishes the person's flow data, which indicates the flows of the characters defined by the attributes. In addition, the analysis device 20 provides analysis result data including character attribute data and attribute-differentiated character flow data to the customer terminal CL.

The analysis device 20 performs various arithmetic processes, and the purpose of the arithmetic process is to analyze the attributes of the person and the flow of the person based on the first analysis data. The analysis device 20 is configured to include an electronic circuit mainly composed of a central processing unit such as a CPU, a ROM, a RAM, and a conventional microcomputer including an interface. The aspect of the analysis device 20 may also be constructed by installing software that can implement various processes described below in a known computer system such as a PC or a workstation.

Specifically, the analysis device 20 includes a data input / output unit 21, a storage unit 22, and a processing unit 23. The data input / output unit 21, the storage unit 22, and the processing unit 23 can exchange various signals and data with each other.

The data input / output unit 21 is used to input / output various data between the analysis device 20 and a device different from the analysis device 20. The data input / output unit 21 of this embodiment can input the first analysis data from the recording device 10 which is a device different from the analysis device 20. In addition, the data input / output unit 21 of this embodiment can output analysis result data to a client terminal CL, which is a device different from the analysis device 20. The data input / output unit 21 may be configured similarly to the data input / output unit 13 to perform input / output of data between devices other than the analysis device 20 based on communication (either wired or wireless) via a network. Similarly, the data input / output unit 21 may have a configuration in which, for example, a slot unit is provided and data is input / output between devices different from the analysis device 20 through a recording medium inserted in the slot unit.

The storage unit 22 stores: conditions and information required for performing various processes in the processing unit 23; various programs or software executed by the processing unit 23, control data, and the like. The storage unit 22 can store the first analysis data input by the data input / output unit 21. The storage unit 22 may be, for example, temporarily storing various data generated during the processing performed by the processing unit 23. The storage unit 22 can read out such data as needed through the data input / output unit 21, the processing unit 23, and the like. The storage unit 22 may also be a relatively large-capacity storage device such as a hard disk, an SSD, an optical disk, or a rewritable semiconductor memory such as a RAM, a flash memory, or an NVSRAM.

More specifically, the storage unit 22 is structured to include conceptually a function: an analysis target database (hereinafter referred to as "analysis target DB") 22A; an analysis reference database (hereinafter referred to as "analysis reference DB") 22B; And analysis result database (hereinafter referred to as "analysis result DB" 22C).

The analysis target DB 22A is a part that stores, stores, and stores the first analysis data (first image data, first position data, time data, etc.) that is the analysis target data processed by the processing unit 23. The first analysis data input from the recording device 10 to the data input / output unit 21 is stored in the analysis target DB 22A.

The analysis reference DB 22B is a part that accumulates the analysis reference data that is referenced by the first analysis data processed by the processing unit 23 during analysis, and stores and stores the database. The analytical reference materials include, for example, map reference materials, attribute prediction reference materials, and the like. The map reference data indicates data of a map that is used to define the position of the moving body V based on the first position data or the like, in other words, when the position of the image of the outside of the moving body V is captured. The attribute prediction reference material is data that is referred to when estimating the attributes and the like of a person contained in an image shown in the first image data. The reference material for attribute prediction will be explained in detail later. The analysis reference data is used as a reference when analyzing the first analysis data by the processing unit 23.

The analysis result DB22C is a part that accumulates the analysis result data and stores it in a database. The analysis result data indicates the analysis result of the first analysis data processed by the processing unit 23. The analysis result data includes, for example, person attribute data and attribute distinguishing character flow data, etc., where the character attribute data represents the attribute of the person contained in the image shown in the first image data; the attribute distinguishing character flow data represents the attribute attribute Define the flow of characters. The analysis result data is processed into a required form by the processing unit 23, and is output by the data input / output unit 21 and provided to the customer terminal CL.

In addition, various data stored in the analysis target DB22A, the analysis reference DB22B, and the analysis result DBC can be utilized as so-called big data.

The processing unit 23 executes various programs stored in the storage unit 22 based on various input / output signals and the like, and executes various processes for analyzing the data for the first analysis by the operation of the programs. The processing unit 23 performs processing for processing the analysis result into a desired format. In addition, the processing unit 23 performs processing related to data input / output performed by the data input / output unit 21. For example, the processing unit 23 processes the analysis result data into a required form, and executes processing for outputting to the customer terminal CL through the data input / output unit 21.

More specifically, the processing unit 23 may be configured to include conceptually a data pre-processing unit 23A, a data analysis processing unit 23B, and a data processing processing unit 23C.

The data pre-processing section 23A is a section that performs various pre-processings on the first analysis data that is the analysis target data. For example, as pre-processing, the data pre-processing unit 23A reads the first analysis data as the analysis target data from the analysis target DB 22A, and executes the dynamics shown by the first image data included in the first analysis data. Image cut out processing of still images. In addition, for example, as the pre-processing, the data pre-processing section 23A performs processing to associate the following two: one is the cut-out still image; the other is contained in the first analysis data as the analysis target data. The location shown in the first position profile. In addition, as the pre-processing, the data pre-processing section 23A uses various known image processing techniques to detect and extract people from the cut still images. In addition, the material pre-processing section 23A performs a process of extracting an image including feature points of a person from among a plurality of images shown in the first image data. Here, the feature point of a person refers to a part of the person included in the image where the attribute of the person can be specified. Characteristic points about a person may be, for example, a face on which the character's expression appears, a limb on which a gesture appears, an easy-to-wear accessory location, and the like. Since the first image data of this embodiment is collected according to the movement of the moving body V according to the recording device 10 installed on the moving body V, it contains a lot of data about the same person from different angles. The likelihood of a captured image is high. Using this, the data pre-processing unit 23A extracts display images of characteristic points of the person that can be used to define the attributes of the person from a plurality of images taken from different angles as the moving body V moves, thereby In order to ensure as much information as possible to define the attributes of the character.

The data analysis processing unit 23B is based on the first analysis data pre-processed by the data pre-processing unit 23A, based on the attributes of the person contained in the image shown in the first image data, and the attributes of the person defined by the attribute. The part that flows for analysis. Here, the data analysis processing unit 23B is configured to execute the following processing: using, for example, various conventional artificial intelligence technology or deep learning technology to analyze the image data shown in the first image data Contains the attributes of the character and the flow of the character defined by the attribute.

The data analysis processing unit 23B of this embodiment uses the data pre-processing unit 23A to analyze the attributes of the person included in the image based on the image including the feature points of the person extracted from the first image data. For example, the data analysis processing unit 23B may analyze the attributes of the person according to the attribute prediction reference (analysis reference) and the feature points of the character, and the attribute prediction reference is stored in the analysis reference DB22; the character includes An image extracted from the first image data by the data pre-processing unit 23A. Here, the attribute prediction reference data reflects the information of the following: by using various methods of artificial intelligence technology or deep learning technology, the attributes of the person can be estimated based on the feature points of the person included in the image. The result of learning. In other words, the attribute prediction reference data is a database that uses various methods using artificial intelligence technology or deep learning technology to estimate the attributes of a person based on the feature points of the person included in the image. This attribute prediction reference can be updated in turn. For example, the attribute prediction reference data may also be data for the purpose of learning analysis result data (person attribute data) itself, where the analysis result data represents the analysis result made by the data analysis processing section 23B.

As attributes of a person analyzed by the data analysis processing unit 23B, typically, items that can be analyzed by the appearance feature points of the character include, for example, the character's gender, age, physique, social status, hobbies, or action orientation. Here, gender refers to the attribute that distinguishes between men and women. Age is an attribute indicating the length of the year and month from birth to the present (at this time). Physique refers to attributes that indicate height, weight, and various sizes. Social status refers to attributes that indicate occupations (self-employed, businessmen, police, students, job hunting, part-time employment), annual income, status, peers, etc. Hobbies refer to attributes such as clothing, possessions, and dress styles (casual, elegant, brand, high-end, fast-fashion), and interests (sports / subculture / outdoor / beauty, etc.). Action-oriented refers to attributes that indicate the mood, the direction of the heart (what you want to do, where you want to go), etc. at that time. That is, here, the data analysis processing unit 23B estimates the sex, age, physique, social status, hobbies, and action orientation of a character as attributes of the character.

The data analysis processing unit 23B refers to the attribute prediction reference data to extract the attributes (gender, age, physique, social status, hobbies, or action orientation) of the characteristic points of the person contained in the image, and estimates the extracted attributes to be displayed Attribute of the person in the image. For example, the data analysis processing unit 23B may predict the reference data based on the facial expressions, the postures of the limbs, the worn accessories or dresses, etc. of the person's feature points included in the image, and match the feature points that match the feature points. Attributes to estimate the character ’s gender, age, physique, social status, hobbies, and action orientation.

In addition, the data analysis processing unit 23B further performs a flow motion analysis process on the person based on the position data, and the position data is assigned to the image data that defines the attributes of the person. For example, the data analysis processing unit 23B can read the first position data from the analysis target DB 22A, where the first position data is assigned to the first image data that defines the attributes of the person. In addition, the data analysis processing unit 23B analyzes the flow of the people defined by the attributes according to the following two: one is the map reference (analysis reference), which is stored in the analysis reference DB22B; the second is the first position read out data. For example, the data analysis processing unit 23B may refer to the map reference data and define the position of the captured image according to the first position data. In addition, the data analysis processing unit 23B defines the positions of the persons defined by the attributes based on the positions shown in the first position data, and arranges them in order in time to define the flow of the characters. The flow of a person analyzed by the data analysis processing unit 23B is typically expressed by a distribution, a moving direction, a moving speed, a start point and an end point of the character in each time zone of the character. That is, here, the data analysis processing unit 23B estimates the distribution, moving direction, moving speed, starting point and ending point of the movement among the time zones of the character as the flow of the person with the specified attribute.

The data analysis processing section 23B generates character attribute data and attribute distinguishing character flow data as analysis result data for analyzing the first analysis data, wherein the character attribute data is the attribute of the character analyzed as described above; and the attribute distinguishes the flow data It refers to the flow of characters of a specific attribute. In addition, the data analysis processing section 23B accumulates the analysis result data including the generated character attribute data and attribute distinguishing character flow data in the analysis result DB22C, and stores its database into storage.

The data processing and processing unit 23C is a part that executes the following processing: processing the analysis result data obtained by the data analysis and processing unit 23B into a required form. The data processing processing unit 23C processes the character attribute data and the attribute distinguishing character flow data included in the analysis result data into a desired form. For example, as shown in FIG. 2, the data processing processing unit 23C processes the analysis result data including character attribute data, attribute classification (attribute type) character flow data, and other data into a map to draw when and what There are several people, such as people, and various attributes, or various charts and line charts. In addition, the processing unit 23 performs the following processing: The analysis result data processed by the data processing processing unit 23C into a required form is output to the customer terminal CL through the data input / output unit 21. The customer terminal CL is a terminal that can use the analysis result data provided by the analysis device 20 for various purposes such as business district surveys, marketing, advertising, disaster prevention, and urban planning. The customer terminal CL may be configured as, for example, a notebook PC, a desktop PC, a tablet PC, a smart phone, a portable terminal, or the like.

Next, an example of processing in the analysis system 1 will be described with reference to a flowchart of FIG. 3.

First, the recording device 10 collects first analysis data including a first image data and a first position data as the moving body V moves (step S1).

Next, the recording device 10 outputs the collected first analysis data through the data input / output section 13 and inputs the collected first analysis data to the analysis device 20 through the data input / output section 21 of the analysis device 20 (step S2). The first analysis data input to the analysis device 20 is stored in the analysis target DB 22A.

Next, the data pre-processing unit 23A of the analysis device 20 performs various pre-processing as described above on the first analysis data stored in the analysis target DB 22A (step S3).

Next, the data analysis processing unit 23B of the analysis device 20 analyzes the attributes of the person included in the image shown in the first image data, and the data based on the first analysis data obtained by performing the preprocessing by the data preprocessing unit 23A. The flow of characters defining this attribute is determined (step S4).

Next, the data analysis processing unit 23B generates character attribute data and attribute distinguishing character flow data as analysis result data, stores them in the analysis result DB 22C, and stores them in a database (step S5).

Next, the data processing unit 23C of the analysis device 20 processes the analysis result data (character attribute data, attribute distinguishing character flow data) stored in the analysis result DB 22C according to a request from the customer terminal CL or the like, and processes it into the example illustrated in FIG. General desired form (step S6).

Next, the processing unit 23 of the analysis device 20 processes the analysis result data obtained by the data processing and processing unit 23C into a required form, and outputs and provides (step S7) to the customer terminal CL through the data input / output unit 21 to end a series of deal with.

In the analysis system 1 described above, based on the first analysis data, the analysis device 20 can analyze the attributes of the person contained in the image shown in the first image data and the flow of the person with the defined attributes. In this case, the analysis system 1 can collect the first image data and the first position data constituting the first analysis data by the recording device 10 installed in the mobile body V and as the mobile body V moves. With this configuration, in this analysis system 1, the recording device 10 moves along the road with the moving body V and collects the first analysis data, and the data collection device fixed on the road collects the first analysis data, for example. In comparison, the analysis system 1 can significantly ensure that a larger amount of first analysis data is collected. In addition, in the analysis system 1, since the first image data is collected by the recording device 10 as the moving body V moves, it is possible to collect many images taken from different angles of the same person The first image data of the image. As a result, since the analysis system 1 can secure a relatively large amount of first analysis data that can be used for analysis by the analysis device 20, the accuracy of analysis can be improved.

In addition, as compared with the case where the analysis data is collected using, for example, specific software, fill-in questionnaires, data organized by a specific person, and the like, the analysis system 1 is capable of extracting data from persons who actually exist in the data collection target area. Randomly collected first analysis data with few attribute deviations. In this regard, the analysis system 1 can also improve the accuracy of the analysis. In addition, as compared with a case where the analysis data is directly collected from, for example, a personal-owned portable terminal, the analysis system 1 can collect the first analysis data with relatively high anonymity. According to this, the analysis system 1 can obtain analysis result data with relatively high anonymity from the viewpoint of protecting personal information.

In the analysis system 1 described above, among the plurality of images taken from different angles with the movement of the moving body V by the recording device 10, those that can be used to define the attributes of the person are extracted, including the characteristic points of the person. Images to ensure as much information as possible to define the attributes of the person. As a result, the analysis system 1 can further improve the accuracy of analysis.

In addition, in the analysis system 1 described above, it is preferable to include a thing repeatedly walking on a predetermined path as a moving body in which the recording device 10 is installed. In this case, the analysis system 1 can efficiently collect a large amount of first analysis data for different time zones in the same area by the recording device 10 installed on the moving body V repeatedly walking on a predetermined path. This point can also improve the accuracy of analysis.

The analysis system 1 described above is configured to include a storage unit 22 (analysis result DB 22C) that stores analysis result data, and therefore the analysis result data can be easily used as big data.

As an example, the analysis system 1 described above estimates gender, age, physique, social status, hobbies, action orientation, etc. as attributes of the person included in the image represented by the first image data. The analysis result data is used for various purposes such as business district surveys, marketing, advertising, disaster prevention, and urban planning.

[Implementation Mode 2]
The analysis system in the implementation mode 2 is different from the implementation mode 1 in that it analyzes the data for the second analysis. In the following, common component symbols are marked with the same constituent elements as the above-mentioned embodiment, and repeated descriptions of the common constituents, functions, and effects are omitted as much as possible (the same applies hereinafter).

The analysis system 201 of this embodiment shown in FIG. 4 is different from the analysis system 1 in that it includes a recording device 210 as a moving body analysis data collection device instead of the recording device 10. The other configurations of the analysis system 201 are substantially the same as those of the analysis system 1. The recording device 201 is different from the above-mentioned recording device 10 in that it includes an external camera 11, a position information measuring device 12, a data input / output section 13, and a control section 14, as well as an internal camera 215. The other structures of the recording device 210 are substantially the same as those of the recording device 10.

The recording device 210 of the present embodiment collects the second analysis data in addition to the first analysis data used for analysis by the analysis device 20. The second analysis data includes: a second image data showing an image of the inside of the moving body V; and a second position data showing a position where the image of the inside of the moving body V is taken. The recording device 210 collects the second image data and the second position data as the second analysis data. The second image data is collected by the internal camera 215.

The internal camera 215 is an internal photographing device that captures the inside of the moving body V, that is, an image in the car. The internal camera 215 captures an image of the inside of the moving body V, and collects second image data representing an image of the inside of the moving body V. The internal camera 215 typically captures a moving image of the inside of the moving body V. The internal camera 215 is installed on the moving body V from the perspective of a passenger or the like in the vehicle of the moving body V, which can capture an analysis target person of the analysis system 201. A plurality of internal cameras 215 may also be provided on the top of the inside of the moving body V, so as to be more convenient for shooting people inside the moving body V. The internal camera 215 may be a monocular camera or a stereo camera. In addition, the image captured by the internal camera 215 may be black and white or color. The control unit 14 is communicably connected to the internal camera 215 so that it can exchange various signals and data with each other. The internal camera 215 outputs the collected second image data to the control section 14.

In addition, the position information measuring device 12 collects second position data in addition to the first position data, which indicates a position where an image of the inside of the moving body V is captured. In addition to the first position data, the position information measuring device 12 also outputs the collected second position data to the control unit 14.

The processing unit 14B, in addition to performing the process of collecting the first analysis data, also controls the operation of the internal camera 215 and the position information measuring device 12, and collects the second analysis data including the second image data and the second position data. Its processing. In addition, the storage unit 14A may also store the collected time for the second analysis data. In other words, the second analysis data includes the data indicating the time when the data was collected or other data similarly to the first analysis data. The data input / output unit 13 may output the second analysis data in addition to the first analysis data to the analysis device 20. The processing unit 14B executes a process of outputting the second analysis data to the analysis device 20 through the data input / output unit 13.

In addition, the analysis device 20 of this embodiment analyzes the second analysis data in addition to the first analysis data collected by the recording device 210, and provides the analysis result data indicating the analysis result to the customer terminal CL.

The data input / output unit 21 may input the second analysis data in addition to the first analysis data from the recording device 210. In addition to the first analysis data, the analysis target DB 22A also accumulates and analyzes the second analysis data (second image data, second position data, time data, etc.) of the analysis target data of the processing unit 23. The library turns into storage. The second analysis data input to the data input / output unit 21 by the recording device 210 is stored in the analysis target DB 22A. In addition, the analysis reference data stored in the analysis reference DB 22B is also used as a reference in the analysis of the second analysis data performed by the processing unit 23.

The data pre-processing unit 23A applies various pre-processing to the second analysis data which is the analysis target data, as the first analysis data. In addition, the data analysis processing unit 23B analyzes the attributes of the person contained in the image shown in the second image data and the defined attributes based on the second analysis data obtained by the preprocessing performed by the data preprocessing unit 23A. Character flow. The data analysis processing unit 23B performs analysis of the second analysis data, which is the same as the analysis of the first analysis data, and generates character attribute data and attribute distinguishing character flow data as analysis result data. Among them, the character attribute The data indicates the attribute of the person contained in the image shown in the two image data; this attribute distinguishes the flow of the character. The data indicates the flow of the character of the defined attribute. Similar to the analysis result data representing the analysis result of the first analysis data, the analysis result DB 22C also accumulates and stores the analysis result data representing the analysis result of the second analysis data made by the data analysis processing unit 23B. The analysis result data includes person attribute data and attribute distinguishing person mobility data, etc., where the character attribute data represents the attributes of the person contained in the image indicated by the second image data; attribute distinguishing person mobility data represents the character of the defined attribute. flow. In addition, the data processing unit 23C processes the person attribute data and the attribute distinguishing character flow data included in the analysis result data in the same format as described above. In addition, the processing unit 23 uses the data processing processing unit 23C to process the analysis result data that has been processed into a desired form, and outputs the data to the customer terminal CL through the data input / output unit 21.

The analysis system 201 described above is similar to the analysis system 1 in that a relatively large amount of first analysis data that can be used for analysis performed by the analysis device 20 can be ensured, and thus the accuracy of analysis can be improved.

In addition, the analysis system 201 described above can also collect second analysis data by the recording device 210, which includes: second image data, which represents an image inside the moving body V; and the second Location data, which corresponds to the second image data. As a result, not only the characters on the road where the moving body V is walking, the analysis result data that can be obtained by the analysis system 201 also involves the attributes of the characters (passengers) inside the moving body V or the flow of the people, thereby further improving the accuracy of the analysis. degree. In this way, the analysis system 201 can also use the analysis result data for the attributes of the passengers of the bus or taxi, the boarding and alighting position, the analysis of the flow of people before and after getting on and off, or the efficiency of the operation of the bus, taxi, and car allocation.

[Implementation Mode 3]
The analysis system of the implementation form 3 is different from the implementation form 2 in that it analyzes the data for the third analysis.

The analysis system 301 of this embodiment shown in FIG. 5 includes a recording device 310 as a fixed body analysis data collection device installed on the fixed body F in addition to the recording device 210 installed on the moving body V. It differs from the analysis system 201 in a point. The other configurations of the analysis system 301 are substantially the same as those of the analysis system 201.

The recording device 310 of this embodiment is installed on a fixed body F installed on a road, and the installation object is the fixed body F, which is different from the recording device 10 (refer to FIG. 1) or the recording device 210 in this regard. Since the configuration of this recording device 310 is substantially the same as that of the recording device 10, its description is omitted. Therefore, regarding the following configurations of the recording device 310, the configuration of the recording device 10 of FIG. 1 may be appropriately referred to as appropriate.

Here, the fixed body F installed in the recording device 310 of this embodiment is installed and fixed on the road. The fixed body F may be, for example, a bus stop, a digital signage board, a vending machine, a sign, a telephone pole, or the like, or may be a dedicated structure provided for installing the recording device 310.

In addition, the recording device 310 of the present embodiment collects third analysis data in addition to analysis data used for analysis performed by the analysis device 20. The third analysis data includes a third image data and a third position data, wherein the third image data represents an image of the outside of the fixed body F, which is captured by being mounted on the fixed body F; the third position The data indicates a position where an image of the outside of the fixed body F is taken. The recording device 310 collects the third image data and the third position data as the third analysis data. The third image data is collected by the external camera 11 (refer to FIG. 1).

In this case, the external camera 11 is set to the fixed body F with the perspective of a person who can photograph the analysis target of the analysis system 1, and here refers to the perspective of the person located on the road outside the moving body V. A plurality of external cameras 11 may also be provided, which is more advantageous for photographing people on the road outside the fixed body F. The external camera 11 outputs the collected third image data to the control section 14.

In addition, the position information measuring device 12 (refer to FIG. 1) collects third position data indicating a position where an image of the outside of the fixed body F is captured. The position information measuring device 12 outputs the collected third position data to the control unit 14.

The processing unit 14B (refer to FIG. 1) controls the operations of the external camera 11 and the position information measuring device 12, and executes processing for collecting third analysis data including third image data and third position data. The storage unit 14A (see FIG. 1) also stores the content such as the time when the third analysis data was collected. In other words, like the first analysis data, the third analysis data also includes time data or other data indicating the time when the data was collected. The data input / output unit 13 (see FIG. 1) can output the third analysis data to the analysis device 20. The processing unit 14B executes processing for outputting the third analysis data to the analysis device 20 through the data input / output unit 13.

In addition, the analysis device 20 of this embodiment analyzes the third analysis data collected by the recording device 310 in addition to the first analysis data and the second analysis data collected by the recording device 210, and The analysis result data representing the analysis result is provided to the customer terminal CL.

The data input / output unit 21 may input the third analysis data from the recording device 310 in addition to the first analysis data and the second analysis data. In addition, the analysis target DB 22A includes, in addition to the first analysis data and the second analysis data, the analysis target data of the processing unit 23, that is, the third analysis data (third image data, third position data, and time data). Etc.) to accumulate and store the database into storage. The third analysis data input to the data input / output unit 21 by the recording device 310 is stored in this analysis target DB 22A. The analysis reference data stored in the analysis reference DB 22B is also used as a reference during the analysis of the third analysis data performed by the processing unit 23.

The data pre-processing unit 23A performs the same various pre-processing on the third analysis data as the analysis target data, as the first analysis data and the second analysis data. In addition, the data analysis processing unit 23B analyzes the attributes of the person contained in the image represented by the third image data based on the third analysis data obtained by the pre-processing performed by the data pre-processing unit 23A; and the defined attributes Character flow. The data analysis processing unit 23B analyzes the third analysis data in the same manner as the analysis for the first analysis data and the second analysis data, and generates the following data: character attribute data, which represents the third image data The attribute of the person contained in the represented image; the attribute distinguishes the character flow data, which represents the flow of the character defined by the attribute, and uses this data as the analysis result data. The analysis result DB22C is similar to the analysis result data indicating the analysis results of the first analysis data and the second analysis data, and the analysis result data indicating the analysis results of the third analysis data made by the data analysis processing unit 23B is also accumulated. And store it in a database. The analysis result data includes character attribute data and attribute distinguishing character flow data, etc., where the character attribute data represents the attribute of the person contained in the image represented by the third image data; the attribute distinguishing character flow data represents the defined attribute Character flow. In addition, the data processing unit 23C processes the person attribute data and the attribute-differentiated person flow data included in the analysis result data into a desired format in the same manner as described above. In addition, the processing unit 23 processes the analysis result data processed into the required format by the data processing processing unit 23C, and outputs the data to the customer terminal CL through the data input / output unit 21.

Similar to the analysis systems 1 and 201, the analysis system 301 described above can relatively secure a large amount of first analysis data that can be used for analysis by the analysis device 20, and thus can improve analysis accuracy.

In addition, the analysis system 301 described above is the same as the analysis system 201, and the analysis result data that can be obtained are not only characters walking on the road, but also the attributes or characters of the characters (passengers) inside the moving body V, To improve the resolution accuracy.

In addition, the analysis system 301 described above can also collect third analysis data including third image data and third position data, where the third image data indicates that the image of the fixed body F is captured by the recording device 310 and An external image; the third position data corresponds to the third image data and can be used for analysis by the analysis device 20. As a result, the analysis system 301 can add the third analysis data collected by the recording device 310 installed in the fixed body F as analysis data for analyzing people on the road. Therefore, the analysis system 301 can further improve the accuracy of the analysis.

In addition, the analysis system in the above-mentioned embodiment of the present invention is not limited to the above-mentioned embodiment, and various changes can be made within the scope described in the scope of the invention application patent. The analysis system in this embodiment may be configured by appropriately combining the constituent elements of the above-mentioned embodiments and modifications.

As analysis data for analysis, the analysis systems 1, 201, and 301 described above may further use data collected by means of specific software, fill-in coupons, and data organized by specific persons.

In the control unit 14 and the analysis device 20 described above, each component may be separately configured, and each component may be configured to exchange various electronic signals with each other, and some functions may be implemented by other control devices. In addition, the programs, software, various data, and the like described above may be appropriately updated, and the analysis systems 1, 201, and 301 may be stored in a connected server through an arbitrary network. The programs, software, and various materials described above, for example, can be downloaded in whole or in part as needed. In addition, for example, all or any part of the processing functions provided by the control unit 14 and the analysis device 20 may be implemented by, for example, a CPU or the like and a program executed by the CPU or the like as a transliteration execution. In addition, the processing function may also be based on wired logic. Into hardware.

1‧‧‧ Analysis System

10‧‧‧Recording device

11‧‧‧External Camera

12‧‧‧Position information measuring device

13‧‧‧Data input and output department

14‧‧‧Control Department

14A‧‧‧Storage Department

14B‧‧‧Processing Department

20‧‧‧ Resolution Device

21‧‧‧I / O Department

22‧‧‧Storage Department

22A‧‧‧Analysis target database (analysis target DB)

22B‧‧‧Analysis Reference Database (Analysis Reference DB)

22C‧‧‧Analysis result database (analysis result DB)

23‧‧‧Treatment Department

23A‧‧‧Data pre-processing department

23B‧‧‧Data Analysis and Processing Department

23C‧‧‧Data Processing Department

201‧‧‧Analysis system

210‧‧‧Recording device

215‧‧‧Internal camera

301‧‧‧Analysis system

310‧‧‧Recording device

CL‧‧‧Customer Terminal

F‧‧‧Fixed body

S1 ～ S7‧‧‧‧Steps

V‧‧‧ Mobile

[Fig. 1] Fig. 1 is a block diagram showing a schematic configuration of an analysis system in Embodiment 1. [Fig.

[Fig. 2] It is a schematic diagram showing an example of analysis result data that is analyzed and processed in the analysis system in the implementation mode 1.

[Fig. 3] A flowchart showing an example of processing in the analysis system in the implementation mode 1. [Fig.

[Fig. 4] A block diagram showing a schematic configuration of an analysis system in Embodiment 2. [Fig.

[FIG. 5] A block diagram showing a schematic configuration of an analysis system in Embodiment 3. [FIG.

Claims (7)

An analysis system, which is characterized by: Mobile body analysis data collection device, which is installed on a mobile body and collects first analysis data including first image data and first analysis data, wherein the first image data indicates that the mobile body is accompanied by the mobile body. An image of the outside of the moving body that is captured while moving, the first position data indicates a position of an image of the outside of the moving body that was captured; and A data analysis device that analyzes the attributes of the person contained in the image represented by the first image data and the flow of the persons defined by the first analysis data collected by the mobile body analysis data collection device. . The analysis system according to claim 1, wherein the data analysis device extracts, from the plurality of images represented by the first image data, an image of the feature points of the character that can define the attributes of the character, And the attributes of the person contained in the image are analyzed based on the extracted image. The analysis system according to claim 1 or 2, wherein the mobile body analysis data collection device further collects second analysis data including second image data and second position data, wherein the second image The data indicates the image of the interior of the moving body; the second position data indicates the position of the image of the interior of the moving body; The data analysis device further based on the second analysis data collected by the mobile body analysis data collection device, for the attributes of the person contained in the image represented by the second image data and the characteristics of the person defined by the attribute. flow. The analysis system according to any one of claims 1-3, comprising: The fixed body analysis data collection device is installed on a fixed body provided on the road, and collects third analysis data including third image data and third position data. The third image data indicates that it is installed in An image of the outside of the fixed body obtained by shooting in the state of the fixed body; the third position data indicates a position where an image of the outside of the fixed body is taken, and The data analysis device further analyzes the attributes of the person contained in the image represented by the third image data according to the third analysis data collected by the fixed analysis data collection device; Character flow. The analysis system according to any one of claims 1-4, wherein the moving system repeatedly walks a path set in advance. The analysis system according to any one of claims 1-5, wherein the data analysis device includes a memory unit that stores analysis result data, and the analysis result data is obtained by analyzing by the data analysis device. Parse results. The analysis system according to any one of claims 1-6, wherein the attributes of the person analyzed by the data analysis device include gender, age, physique, social status, hobbies, or action orientation.