Patent Application
20190205903
The present invention relates to analysis of data, and particularly to an information-processing device analyzing, a data analysis method, and a recording medium which analyze behavior information of a person.
Recently, to grasp a purchasing trend of customers or examine efficiency improvement of employee's work, an information-processing device that analyzes behavior information of a person has been used. The information-processing device analyzing the behavior information, for example, uses image information of a monitoring camera, information from a radio frequency identification (RFID) tag, and information (e.g., the number) of a subscriber identity module (SIM) card of a cellular phone. Based on these pieces of information, the information-processing device calculates behavior trajectory information of a person (e.g., refer to PTL 1). The calculated person behavior trajectory information is used in analysis of behavior of the person in an area in a store or a warehouse, for example. An analysis person who analyzes behavior can grasp, based on the person behavior trajectory information, information effective in purchasing behavior or work efficiency improvement.
In the future, data concerning a person will further expand (become big data). Such a social environment is creating an increasing demand for the provision of behavior analysis information.
However, a customer in a store not only looks at a product while moving. For example, a customer stops to check a product. In other words, a person not only moves, but may also stop (or stay).
A behavior analysis system described in PTL 1 however, displays analyzed trajectory data of a person at the time of displaying an analyzed result of person's behavior in a target area. For this reason, there is a problem in that the behavior analysis system described in PTL 1 cannot appropriately display a result of behavior analysis of a person in the entire target area.
An object of the present invention is to provide an information-processing device, a data analysis method, and a recording medium, which can solve the above-described problem.
An information-processing device according one aspect of the present invention includes: a person detection and tracking unit that receives analysis information including information related to positions of persons included in a target area, and calculates first person's-tracking-information that is time series information of the positions of the persons based on the analysis information; a same person detection unit that specifies the persons related to the first person's-tracking-information, classifies the first person's-tracking-information for each of the persons, and calculates second person's-tracking-information that is time series information of a position of each of the persons; a direction calculation unit that calculates movement direction information of each of the persons based on the second person's-tracking-information;
a staying time calculation unit that calculates staying-place information and staying-time information of each of the persons based on the second person's-tracking-information; and
a processing unit that calculates trajectory information and staying information of one or more of the persons based on the movement direction information, the staying-place information, and the staying-time information, and displays the trajectory information and the staying information so as to overlap an image of the target area.
A data analysis method according to one aspect of the present invention includes: receiving analysis information including information related to positions of persons included in a target area, and calculating first person's-tracking-information that is time series information of the positions of the persons based on the analysis information; specifying the persons related to the first person's-tracking-information, classifying the first person's-tracking-information for each of the persons, and calculating second person's-tracking-information that is time series information of a position of each of the persons; calculating movement direction information of each of the persons based on the second person's-tracking-information; calculating staying-place information and staying-time information of each of the persons based on the second person's-tracking-information; and calculating trajectory information and staying information of one or more of the persons based on the movement direction information, the staying-place information, and the staying-time information, and displaying the trajectory information and the staying information so as to overlap an image of the target area.
A computer readable non-transitory recording medium one aspect of the present invention embodying a program, the program causing a computer to perform: a method, the method comprising receiving analysis information including information related to positions of persons included in a target area, and calculating first person's-tracking-information that is time series information of the positions of the persons based on the analysis information; specifying the persons related to the first person's-tracking-information, classifying the first person's-tracking-information for each of the persons, and calculating second person's-tracking-information that is time series information of a position of each of the persons; calculating movement direction information of each of the persons based on the second person's-tracking-information; calculating staying-place information and staying-time information of each of the persons based on the second person's-tracking-information; and calculating trajectory information and staying information of one or more of the persons based on the movement direction information, the staying-place information, and the staying-time information, and displaying the trajectory information and the staying information so as to overlap an image of the target area.
According to the present invention, it is possible to produce an advantageous effect in that a result of behavior analysis in an entire target area is appropriately displayed.
Next, exemplary embodiments of the present invention are described with reference to the drawings.
The respective drawings illustrate the exemplary embodiments of the present invention. The present invention is, however, not limited to the illustrations of the respective drawings. The same number is allocated to the same configurations in the respective drawings, and their repeated description may be omitted.
In the drawings used in the following description, a configuration of a part not related to the description of the present invention is omitted and may not be depicted in the drawings.
The person detection and tracking unit 100 receives analysis information used in analysis of behavior in a target area. The analysis information in the present exemplary embodiment is not particularly limited. The analysis information should include information related to a position. For example, the person detection and tracking unit 100 may receive an image of the floor (hereinafter referred to as “floor image”) from a camera capturing a designated floor that is a target area, as the analysis information. Alternatively, the person detection and tracking unit 100 may receive position information of a RFID tag, as the analysis information. In the following, as one example, description is made by using a floor image.
After receiving the floor image, the person detection and tracking unit 100 detects a position of a person or a plurality of positions of a plurality of persons from the floor image. For example, the person detection and tracking unit 100 may detect the position of the person by using a technique of image recognition (e.g., person image recognition).
Furthermore, the person detection and tracking unit 100 calculates time series information of positions of the persons by tracking positions of the persons among frames of the floor image. In the following, the time series information of positions of the persons calculated by the person detection and tracking unit 100 is referred to as “first person's-tracking-information”. The person detection and tracking unit 100 outputs the first person's-tracking-information to the same person detection unit 101. In the first person's-tracking-information, each person is not specified.
The same person detection unit 101 receives the first person's-tracking-information from the person detection and tracking unit 100. Then, the same person detection unit 101 specifies (detects) all persons included in the first person's-tracking-information. For example, the same person detection unit 101 may use a technique of face recognition for specifying. Furthermore, the same person detection unit 101 classifies the first person's-tracking-information for each of same persons distinguished as the same among the specified persons. In the following, the person's-tracking-information classified for each of the same persons by the same person detection unit 101 is referred to as “second person's-tracking-information”. The same person detection unit 101 detects time series information of positions of the same person, as the second person's-tracking-information. The same person detection unit 101 outputs the second person's-tracking-information to the direction calculation unit 102 and the staying time calculation unit 103. The same person detection unit 101 may specify all persons in a designated area. For example, when behaviors of customers are analyzed, the same person detection unit 101 may specify each customer except employees.
The direction calculation unit 102 receives the second person's-tracking-information from the same person detection unit 101. Then, based on time-sequentially continuous position information (in the person's-tracking-information) of each of the same persons, the direction calculation unit 102 calculates information indicating a movement direction (movement direction information) of the person (same person), as time series data. Then, the direction calculation unit 102 outputs the movement direction information calculated for each person to the processing unit 104.
The staying time calculation unit 103 receives the second person's-tracking-information from the same person detection unit 101. After the reception, based on the second person's-tracking-information, the staying time calculation unit 103 calculates staying-place information concerning a place where the same person stays, and staying-time information corresponding to a staying time length about the same person. Then, the staying time calculation unit 103 outputs the calculated staying-place information and the calculated staying-time information to the processing unit 104.
The processing unit 104 receives the movement direction information from the direction calculation unit 102, and receives the staying-place information and the staying-time information from the staying time calculation unit 103. Then, the processing unit 104 calculates trajectory information and staying information for each person based on the movement direction information, the staying-place information, and the staying-time information. The trajectory information is information concerning change of positions of each person. The staying information is information concerning staying of each person. The trajectory information and the staying information is information that the processing unit 104 uses for display. Thus, the trajectory information and the staying information may include information necessary for display, in addition to the above-described information.
Then, the processing unit 104 superimposes and displays an image of the calculated trajectory information and staying information on an image of the target area.
There are no limits to the number of persons of which information is displayed by the processing unit 104.
For example, the processing unit 104 may display the trajectory information and the staying information of all the persons. In this case, the information-processing device 10 displays the information concerning all the persons in the target area. Thus, a user of the information-processing device 10 can collectively grasp the travel information and the staying information of the persons in the entire target area.
Alternatively, the processing unit 104 may receive information of a target person to be displayed from an input device of a user of the information-processing device 10. In this case, the user of the information-processing device 10 can grasp the travel information and the staying information of the designated person in the entire target area. For example, the information-processing device 10 may display information of the persons whose ages are within a designated range.
There are no particular limits to display means by which the processing unit 104 displays the image. For example, the processing unit 104 may display the image on the display means, not illustrated, of the information-processing device 10. Alternatively, the processing unit 104 may send image information to an external device not illustrated.
In the present exemplary embodiment, there are no particular limits to a displaying form of the processing unit 104.
As a result, the processing unit 104 calculates the trajectory information based on the received movement direction information of the person. Then, the processing unit 104 converts the calculated trajectory information into successive points of coordinates on the image (floor map) of the target area. Then, as illustrated in
Furthermore, the processing unit 104 calculates a staying place on the coordinates in the floor map based on the received staying-place information of the person. In addition, the processing unit 104 calculates a staying time length from the received staying-time information. Then, as illustrated in
The processing unit 104 in the present exemplary embodiment displays the staying information 305 to 308 as diagrams whose sizes are proportional to the staying time lengths. This proportion, however, does not need to be limited to mathematically strict proportion. The processing unit 104 should display diagrams corresponding to the staying time lengths. For example, the diagram of the staying information 306 corresponding to the staying time length of “1s (1 second)” is smaller than the diagram of the staying information 305 corresponding to the staying time length of “10s (10 seconds)”. For easy understanding of display, ratios between sizes of the diagrams and the staying time lengths may vary from a strict ratio.
Display by the processing unit 104 in the exemplary embodiment does not need to be limited to the display in
Thus, the processing unit 104 in the present exemplary embodiment displays the staying information 305 to 308 indicating the staying places and the staying time lengths, in addition to the trajectory information 301 to 304 based on the movement information.
Next, advantageous effects of the present exemplary embodiment are described.
The advantageous effect obtained from the present exemplary embodiment is that a result of analysis of behavior in an entire target area is appropriately displayed.
The reason for it is as follows.
The person detection and tracking unit 100 in the present exemplary embodiment calculates the first person's-tracking-information by detecting positions of persons based on the analysis information. Then, the same person detection unit 101 classifies the first person's-tracking-information into each person. Then, the direction calculation unit 102 outputs the movement direction information for each of the classified persons. Meanwhile, the staying time calculation unit 103 outputs the staying-place information and the staying-time information. Then, the processing unit 104 can display the staying information based on the staying-place information and the staying-time information, as well as the trajectory information based on the movement direction information.
In other words, the present exemplary embodiment displays the trajectory information indicating the movement of the person, and the staying information indicating the staying of the person. Accordingly, an analyst who uses the information-processing device 10 of the present exemplary embodiment can simultaneously grasp the staying position and the staying time length as well as the movement of the person. For this reason, the analyst can perform more appropriate analysis.
Furthermore, in addition to the above-described advantageous effect, the advantageous effect that more detailed analysis of behavior of the person in the target area is appropriately displayed can be obtained from the exemplary embodiment.
This is because the processing unit 104 displays the trajectory information and the staying information of all or part of persons.
A store is used above for describing the present exemplary embodiment. Nevertheless, the present exemplary embodiment can be applied not only to a store, but also to an indoor floor such as a warehouse or an office, and an outdoor floor such as an amusement place.
The above-described information-processing device 10 is configured as follows.
For example, each configuration unit of the information-processing device 10 may be configured by a hardware circuit.
The information-processing device 10 may be configured as a plurality of information-processing devices which are connected to each other via a network or a bus.
The information-processing device 10 may configure a plurality of units as one hardware.
The information-processing device 10 may be implemented as a computer device including a central processing unit (CPU), a read only memory (ROM), and a random access memory (RAM). The information-processing unit 10 may be configured as a computer device further including an input output circuit (IOC) and a network interface circuit (NIC) in addition to the above configuration.
The information-processing device 60 includes a CPU 610, a ROM 620, a RAM 630, an internal storage device 640, an IOC 650, and an NIC 680 to constitute a computer.
The CPU 610 reads a program from the ROM 620. Then, based on the read program, the CPU 610 controls the RAM 630, the internal storage device 640, the IOC 650, and the NIC 680. Then, the computer including the CPU 610 controls these configurations to implement respective functions as the information-processing unit 10, illustrated in
The CPU 610 may use a storage medium reading device not illustrated, to read the program included in a computer readable storage medium 700 storing the program. Alternatively, the CPU 610 may receive the program from an external device, not illustrated, via the NIC 680. Further, the CPU 610 may store the read program or the received program in the RAM 630 to operate based on the stored program.
The ROM 620 stores the program executed by the CPU 610, and fixed data. The ROM 620 is a programmable-ROM (P-ROM) or a flash ROM, for example.
The RAM 630 temporarily stores the program executed by the CPU 610, and the data. The RAM 630 is a dynamic-RAM (D-RAM), for example.
The internal storage device 640 stores data and the program that the information-processing device 60 saves for a long period. The internal storage device 640 may operate as a temporary storage device of the CPU 610. The internal storage device 640 is a hard disk device, a magneto-optical disk device, a solid state drive (SSD), or a disk array device, for example.
The ROM 620 and the internal storage device 640 are non-transitory storage media. Meanwhile, the RAM 630 is a transitory storage medium. Then, the CPU 610 can operate based on the program stored in the ROM 620, the internal storage device 640, or the RAM 630. In other words, the CPU 610 can operate by using the non-transitory storage medium or the transitory storage medium.
The IOC 650 mediates data between the CPU 610 and an input device 660 and between the CPU 610 and a display device 670. The IOC 650 is an IO interface card or a universal serial bus (USB) card, for example.
The input device 660 is a device receiving input commands from an operator of the information-processing device 60. The input device 660 is a keyboard, a mouse, or a touch panel, for example. The input device 660 includes a camera outputting a floor image.
The display device 670 is a device displaying information to an operator of the information-processing device 60. The display device 670 is a liquid crystal display, for example. The CPU 610 may display on the display device 670 an image displayed by the processing unit 104. In this case, the display device 670 may be included in the processing unit 104.
The NIC 680 relays data communication with an external device, not illustrated, via a network. The NIC 680 is a local area network (LAN) card, for example.
The same advantageous effect as that of the information-processing device 10 can be obtained from the thus-configured information-processing device 60.
This is because the CPU 610 of the information-processing device 60 can implement the same functions as those of the information-processing device 10, based on the program.
Next, the exemplary embodiment 2 of the present invention is described with reference to the drawings.
Since the person detection and tracking unit 100, the same person detection unit 101, the direction calculation unit 102, and the staying time calculation unit 103 are the same as those in the first exemplary embodiment, the detailed description is omitted. The following mainly describes the configuration and operation peculiar to the present exemplary embodiment.
The data accumulation unit 201 receives the movement direction information from the direction calculation unit 102, and receives the staying-place information and the staying-time information from the staying time calculation unit 103. Then, the data accumulation unit 201 accumulates the generated number of the persons of the movement direction information (trajectory data) of the same movement direction in the same section. Furthermore, the data accumulation unit 201 accumulates the generated number of the persons of the same staying place. The data accumulation unit 201 may hold, in advance, information of the section for which the number of the persons in the target area is accumulated. Alternatively, the data accumulation unit 201 may set the section for the accumulation, based on the staying-place information.
The data accumulation unit 201 outputs, to the processing unit 202, the accumulated number of the persons of the trajectory data of the same movement direction in the same section, and the accumulated number of the persons of the same staying place.
The processing unit 202 receives the accumulated number of the persons of the trajectory data of the same movement direction in the same section, and the accumulated number of the persons of the same staying place. Based on the received accumulated number of the persons of the trajectory data and the received accumulated number of the persons of the same staying place, the processing unit 202 superimposes and displays the trajectory information and the staying information on the image of the target area. In other words, the processing unit 202 displays the trajectory information and the staying information corresponding to the accumulated numbers of the persons.
The data accumulation unit 201 may accumulate one of the accumulated number of the persons of the trajectory data of the same movement direction in the same section and the accumulated number of the persons of the same staying place. In this case, the processing unit 202 may perform displaying based on the information accumulated by the data accumulation unit 201.
There are no particular limits to a displaying form of the processing unit 202.
For example, the processing unit 202 displays as the displaying of the trajectory information the arrows whose thicknesses (widths) are proportional to the accumulated numbers of the persons. In
In addition, the processing unit 202 displays as the displaying of the staying information the diagrams whose sizes are proportional to the accumulated number of the persons of the same staying place. In
The proportion does not, however, need to be limited to mathematically strict proportion also in the present exemplary embodiment.
The display illustrated in
For example, in
The processing unit 202 may receive the movement direction information, the staying-place information, and the staying-time information in the same manner as the processing unit 104 of the first exemplary embodiment does, and display the same information that the processing unit 104 displays. In other words, the processing unit 202 may include the function of the processing unit 104. For example, the processing unit 202 may display information equivalent to the trajectory information 301 to 304 and the staying information 305 to 306, in addition to the trajectory information 401 to 404 and the staying information 405 to 406 corresponding to the accumulated numbers of the persons.
Next, advantageous effects of the present exemplary embodiments are described.
In addition to the advantageous effects of the first exemplary embodiment, the advantageous effect that the number of the persons related to the trajectory information and the staying information are clarified can be obtained.
The reason for it is as follows.
The data accumulation unit 201 of the present exemplary embodiment calculates the accumulated number of the persons of the trajectory data of the same direction in the same section and the accumulated number of the persons of the same staying place. Then, the processing unit 202 displays the trajectory information and the staying information corresponding to the accumulated numbers of the persons.
While the invention has been particularly shown and described with reference to exemplary embodiments thereof, the invention is not limited to these embodiments. It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the claims.
This application is based upon and claims the benefit of priority from Japanese patent application No. 2014-034036, filed on Feb. 25, 2014, the disclosure of which is incorporated herein in its entirety by reference.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2014-034036 | Feb 2014 | JP | national |
The present application is a Continuation application of Ser. No. 15/119,460 filed on Aug. 17, 2016, which is a National Stage Entry of PCT/JP2015/000779 filed on Feb. 19, 2015, which claims priority from Japanese Patent Application 2014-034036 filed on Feb. 25, 2014, the contents of all of which are incorporated herein by reference, in their entirety.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 15119460 | Aug 2016 | US |
| Child | 16297942 | US |
