JP2012128700A - Relation estimation device, relation estimation system, relation estimation program and relation estimation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a relationship estimation system 100 having a central control unit 10 with a plurality of LRF 12, in which the LRF 12 is configured to detect, for example, the position of each of persons who pass through the passage of a shopping mole, and especially a place which is much frequented or a place which is crowded with people is set as a specific area SA on this passage, and whether or not each of the positions of a plurality of persons is included in the specific area SA is determined, and the presence/absence of a human relationship is estimated based on the movement orbit data of persons which are not included in the specific area SA by the central control unit 10.SOLUTION: A relation estimation system 100 is configured to estimate a human relationship by excluding such a place where persons who have no relationship frequently come and go or gather. Thus, it is possible to accurately estimate the human relationship of persons.

Description

  The present invention relates to a relationship estimation device, a relationship estimation system, a relationship estimation program, and a relationship estimation method, and more particularly to, for example, a relationship estimation device, a relationship estimation system, a relationship estimation program, and a relationship estimation method that estimate human relationships among a plurality of humans. .

  The relationship detection system disclosed in Patent Document 1 records a behavior history of members in a predetermined area centered on a robot. And the relationship between each member is grasped | ascertained from the way of coexistence with the other of a member based on the action | operation history of a some member.

In addition, in the relationship detection system disclosed in Patent Document 2, a movement trajectory of a person to whom a wireless tag is attached is recorded. Based on the movement trajectories of a plurality of humans, it is possible to grasp the friendly relationship between humans.
JP 2005-131748 A [B25J 13/00, B25J 5/00] JP 2005-327156 A [G06F 19/00, G01V 15/00, G06K 17/00, H04B 5/02]

  However, since the simultaneous existence occurs in the plaza where the gathering occurs regardless of the human relationship, the relationship detection system of Patent Document 1 deteriorates the detection accuracy of the human relationship. In addition, since many movement trajectories are similar in street corners where many people come and go and passages with flows, the relationship detection system of Patent Document 2 may not be able to correctly grasp the friendly relationship.

  Therefore, a main object of the present invention is to provide a novel relationship estimation device, relationship estimation system, relationship estimation program, and relationship estimation method.

  Another object of the present invention is to provide a relationship estimation device, a relationship estimation system, a relationship estimation program, and a relationship estimation method that can accurately estimate human relationships.

  The present invention employs the following configuration in order to solve the above problems. The reference numerals in parentheses, supplementary explanations, and the like indicate the corresponding relationship with the embodiments described in order to help understanding of the present invention, and do not limit the present invention.

  1st invention is a relationship estimation apparatus which has a detection means to detect each position of a plurality of people who exist in space, and judges whether each of a plurality of people's positions is included in a specific field. A relationship estimation apparatus comprising: a determination unit configured to perform estimation; and an estimation unit configured to estimate a human relationship based on positions of at least two humans not included in the specific region.

  In the first invention, in the relationship estimation apparatus (10: reference numerals exemplifying corresponding parts in the embodiment, hereinafter the same), the detection means (12) is, for example, a plurality of LRFs, and irradiation from these LRFs The position of each of a plurality of humans existing in the space is detected by the laser that has been used. In the space, a specific area (SA) is a place where there is a lot of traffic or a place where people are crowded. Furthermore, the determination means (16, S9) determines whether each of the plurality of human positions is included in the specific area. And an estimation means (16, S15) estimates the presence or absence of a human relationship based on the position of two persons who are not included in the specific area, for example.

  According to the first aspect of the present invention, it is possible to estimate human relationships except for places where irrelevant people frequently come and go. Therefore, it becomes possible to accurately estimate the human relationships of people.

  A second invention is a relationship estimation system (100) having detection means (12) for detecting positions of a plurality of persons existing in a space, wherein each of the positions of the plurality of persons is in a specific region. A judging means (16, S9) for judging whether or not it is included, and an estimating means (16, S15) for estimating a human relationship based on the respective positions of at least two or more humans not included in the specific area A relationship estimation system is provided.

  In the second invention as well, as in the first invention, it is possible to estimate the human relationship except for places where irrelevant people frequently come and go. Therefore, it becomes possible to accurately estimate the human relationships of people.

  According to a third aspect of the present invention, there is provided a processor (16) of the relationship estimation device (10) having detection means (12) for detecting the positions of a plurality of persons existing in the space. Functions as a determination means (S9) for determining whether or not a specific area is included, and an estimation means (S15) for estimating a human relationship based on the positions of at least two persons not included in the specific area This is a relationship estimation program.

  In the third invention as well, as in the first invention, it is possible to estimate the human relationship except for places where irrelevant people frequently come and go. Therefore, it becomes possible to accurately estimate the human relationships of people.

  A fourth invention is a relationship estimation method of a relationship estimation device (10) having detection means (12) for detecting the positions of a plurality of humans existing in a space, and each of the plurality of human positions. Is included in the specific region (S9), and based on the respective positions of at least two persons not included in the specific region, human relationships are estimated (S15). is there.

  In the fourth invention as well, similar to the first invention, it is possible to estimate the human relations except for places where unrelated people frequently come and go. Therefore, it becomes possible to accurately estimate the human relationships of people.

  According to the present invention, since human relationships are estimated except for places where irrelevant people frequently come and go, it is possible to improve the accuracy of human relationship estimation.

  The above object, other objects, features, and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

FIG. 1 is an illustrative view showing an outline of a relationship estimation system according to an embodiment of the present invention. FIG. 2 is a block diagram showing an electrical configuration of the central controller shown in FIG. FIG. 3 is an illustrative view showing a measurement region of the LRF shown in FIGS. 1 and 2. FIG. 4 is an illustrative view showing one example of a movement locus detected by using the LRF shown in FIG. FIG. 5 is an illustrative view showing a map of a certain place where the LRF shown in FIG. 1 is installed. 6 is an illustrative view showing one example of a movement locus table stored in the memory shown in FIG. FIG. 7 is an illustrative view showing one example of a related person table stored in the memory shown in FIG. FIG. 8 is an illustrative view showing one example of a memory map of the memory shown in FIG. FIG. 9 is a flowchart showing the movement trajectory selection processing of the CPU shown in FIG. FIG. 10 is a flowchart showing human relationship estimation processing of the CPU shown in FIG.

  Referring to FIG. 1, a relationship estimation system 100 according to this embodiment includes a central controller 10 having several LRFs including LRFs 12a and 12b. LRF12a, 12b is installed in the place (space or environment) where a human can move arbitrarily. The place where humans act arbitrarily is a company floor, a museum, a shopping mall or an attraction venue, and the LRFs 12a and 12b are installed in various places. In this space, a specific area SA is set by the system administrator. Since the specific area SA will be described later, detailed description thereof is omitted here.

  The central controller 10 detects the position of a human who moves arbitrarily by using the LRFs 12a and 12b every predetermined time (for example, 1 second), and stores data of the detected position. In addition, the central control apparatus 10 estimates the human relationship between at least two persons based on the stored position data.

  In addition, a human ID is assigned to a person whose position is detected in the order of detection. For example, in FIG. 1, human ID “001” is assigned to human A, human ID “002” is assigned to human B, human ID “003” is assigned to human C, and human D is assigned to human D. An ID “004” is assigned, and a person ID “005” is assigned to the person E.

  Although only five people are shown in FIG. 1 for simplicity, the central controller 10 can detect more human position data and movement trajectory data at the same time. In addition, the central control device 10 is sometimes referred to as a relationship estimation device.

  FIG. 2 is a block diagram showing an electrical configuration of the central controller 10. Referring to FIG. 2, central controller 10 includes LRFs 12 a-12 f, CPU 16 and memory 18. The CPU 16 is also called a microcomputer or a processor, and includes an RTC 16a that outputs time information. In addition to LRF 12a and LRF 12b described above, LRF 12c, LRF 12d, LRF 12e, and LRF 12f are also connected to CPU 16. Further, a memory 18 is connected to the CPU 16. In addition, when it is not necessary to distinguish LRF12a-12f, it is called "LRF12."

  The LRF 12 measures the distance to the object from the time it takes to irradiate the laser, reflect off the object (including a human being), and return. For example, a laser beam emitted from a transmitter (not shown) is reflected by a rotating mirror (not shown), and the front is scanned in a fan shape by a certain angle (for example, 0.5 degrees). Here, as the LRF 12, a laser range finder (model LMS200) manufactured by SICK can be used. When this laser range finder is used, a distance of 8 m can be measured with an error of about ± 15 mm.

  The memory 18 includes a ROM, an HDD, and a RAM (not shown). In the ROM and the HDD, a control program for controlling the operation of the central controller 10 is stored in advance. The RAM is used as a work memory or buffer memory for the CPU 16.

  The detected human position is associated with time information output from the RTC 16a when stored as position data.

  Next, the LRF 12 will be described in detail. Referring to FIG. 3, the measurement range of LRF 12 is indicated by a semicircular shape (fan shape) having a radius r (r≈8 m). That is, the LRF 12 can measure the direction of 90 degrees left and right within a predetermined distance (r) when the front direction is the center.

  The laser used is a class 1 laser in Japanese Industrial Standard JIS C 6802 “Safety Standard for Laser Products”, which is a safe level that does not affect human eyes. In this embodiment, the sampling rate of the LRF 12 is 37 Hz. This is because the position of a person who moves by walking or the like is continuously detected.

  Further, each of the LRFs 12 is arranged so that the measurement ranges overlap, and although not shown, it is fixed at a height of about 90 cm from the floor surface. This height is for enabling detection of the body and arms (both arms) of the subject, and is calculated from, for example, the average height of Japanese adults. Therefore, the height at which the LRF 12 is fixed may be appropriately changed according to the location (region or country) where the central controller 10 is provided and the age or age of the subject (for example, children, adults). In this embodiment, six LRFs 12 are set, but any number of LRFs 12 may be installed as long as the number is two or more.

  In the central controller 10 having such a configuration, the CPU 16 estimates a change in the current position of the human using a particle filter based on the output (distance data) from the LRF 12. Then, the estimated change in position is recorded as a movement trajectory.

  For example, referring to FIG. 4, LRFs 12 a and 12 b are installed facing each other, and a range where the measurement ranges of LRFs 12 a and 12 b overlap is indicated by hatching. A hatched range is a detection area E, and the position of the person is continuously detected in the detection area E. And the change of the position detected continuously becomes the movement locus T. That is, the movement trajectory data is composed of a plurality of position data. Note that XY coordinates are set in the detection area E, and human position data can be indicated by coordinates (X, Y).

  FIG. 5A is an illustrative view showing a map showing a place where the LRF 12 is installed. Referring to FIG. 5 (A), a place corresponding to the map is a shopping mall. In addition, a store is shown on the lower left side of the map, and a guide map for guiding the inside of the shopping mall is shown near the center of the upper right. There is a rest space at the bottom right of the map. In addition, in the map of FIG. Then, in the detection area E (passage), an area with a lot of traffic is set as the specific area SA.

  Referring to FIG. 5B, human A and human B have a human relationship, and both of them are moving from the store to a rest space. In addition, each of the human C, the human D, and the human E has no human relationship, and the three persons move along the passage with different purposes. The purpose of human C is to find a guide map, the purpose of human D is to go through the passage, and the purpose of human E is to go to the store. However, since the human C, the human D, and the human E are in the detection area E almost at the same time, the movement trajectory of these three persons has a similar shape for a while after entering the shopping mall passage.

  Here, when the human relationship is estimated based on the similarity of all the movement trajectories detected in the detection region E, not only the human relationship with the human A and the human B is estimated, but also the human C, It is presumed that there is also a human relationship with the human D and the human E.

  Therefore, in the present embodiment, human relations are not estimated for humans existing in the specific area SA where there are many people. Specifically, when all human positions in the detection area E are detected, if the detected human positions are not included in the specific area SA, the human position data is recorded in the movement trajectory table. The Further, if the human position is included in the specific area SA, the human position data is not recorded in the movement trajectory table. Then, the central control apparatus 10 estimates the human relationship between at least two persons based on the movement trajectory data recorded in the movement trajectory table. That is, since the position data is not recorded for the person existing in the specific area SA, the human relation is not estimated.

  For example, since the positions of the person A and the person B in FIG. 5B are not included in the specific area SA, the movement locus data of the two persons is recorded in the movement locus table shown in FIG. Referring to FIG. 6, this movement trajectory table is composed of columns of human IDs and movement trajectory data. In the human ID column, a human ID “001”, a human ID “002”, and the like are recorded. In the column of movement trajectory data, coordinates representing position data detected continuously every predetermined time are recorded corresponding to the human ID column. For example, “(Xa1, Ya1), (Xa2, Ya2),...” Is recorded in the movement locus data column corresponding to the human ID “001 (human A)”. Corresponding to the human ID “002 (human B)”, “(Xb1, Yb1), (Xb2, Yb2),. In the movement trajectory table, a plurality of position (coordinate) data recorded for each line represents the movement trajectory data.

  In this embodiment, DP matching is used to estimate the human relationship from the movement trajectory data recorded in the movement trajectory table. In this case, first, all the movement trajectory data is converted into a state string. Next, the similarity is calculated for each converted state sequence by DP matching. When there is a combination of state sequences in which the calculated similarity is greater than the threshold, it is estimated that there is a human relationship with the two persons corresponding to the combination. Note that a method for comparing movement trajectories using DP matching is disclosed in the co-pending Japanese Patent Application Laid-Open No. 2010-231470 relating to the same applicant's application, and thus detailed description thereof is omitted.

  If it is estimated that there is a human relationship, the estimated human ID is stored in the related human table as an estimation result. Referring to FIG. 7, when it is estimated that there is a human relationship between human A and human B shown in FIG. 5B, two human IDs “001” and “002” are stored in the related human table. The

  Here, only two human IDs are recorded, but if it is estimated that there are one human relationship among three or more people, one column of the related human table contains three or more human IDs. The human ID is recorded. For example, when it is estimated that there is a human relationship with three families, the three human IDs are recorded in one column in the related human table. The related person table may record the similarity calculated together with the human ID.

  As described above, in this embodiment, an area where there is a lot of traffic on a daily basis or where people are likely to gather is set as the specific area SA, and human relations can be prevented from being estimated for humans existing in the specific area SA. . Therefore, it is possible to improve human relationship estimation accuracy.

  FIG. 8 is an illustrative view showing one example of a memory map 300 of the memory 18 in the central controller 10 shown in FIG. As shown in FIG. 8, the memory 18 includes a program storage area 302 and a data storage area 304. The program storage area 302 stores a movement trajectory selection program 310, a human relationship estimation program 312 and the like as programs for operating the central controller 10.

  The movement trajectory selection program 310 is a program for selecting position data continuously recorded, that is, a movement trajectory. The human relationship estimation program 312 is a program for estimating a human relationship of a human whose detected position is not included in the specific area based on the movement trajectory recorded in the movement trajectory table.

  Although illustration is omitted, the program for operating the central controller 10 includes a program for converting the position obtained by the LRF 12 into position data.

  In the data storage area 304, a position buffer 330 and a similarity buffer 332 are provided. The data storage area 304 stores movement locus table data 334, related person table data 336, map data 338, and specific area coordinate data 340.

  The position buffer 330 temporarily stores the position data of each person. The similarity buffer 332 temporarily stores the similarity of movement trajectory data calculated using DP matching or the like.

  The movement trajectory table data 334 is table data configured as shown in FIG. The related person table data 336 is table data configured as shown in FIG. The map data 338 is map data indicating the detection area E. The specific area coordinate data 340 is data composed of coordinates indicating the specific area SA shown in FIGS. 5 (A) and 5 (B).

  Although not shown, the data storage area 304 is provided with a buffer for temporarily storing the results of various calculations and other counters and flags necessary for the operation of the central controller 10. It is done.

  Hereinafter, a program executed by the CPU 16 of the central controller 10 will be described. The flowchart in FIG. 9 shows processing by the movement trajectory selection program 310, and the flowchart in FIG. 10 shows processing by the human relationship estimation program 312.

  FIG. 9 is a flowchart of the movement trajectory selection process. When the central controller 10 is turned on, the CPU 16 of the central controller 10 determines whether or not the end operation is performed in step S1. For example, it is determined whether or not an operation for turning off the power of the central control device 10 has been performed. If “NO” in the step S1, that is, if the operation for turning off the power of the central control apparatus 10 is not performed, the position data of N persons in the detection region E is acquired in a step S3. For example, as shown in FIG. 5B, if there are five people in the detection area E, the variable E is “5”, and the position data of the person A-human E is acquired from the position buffer 330. The Subsequently, in step S5, the variable i is initialized. The variable i is a variable for designating a human ID. Therefore, in the process of step S5, “1” is set to the variable i in order to designate the first human ID “001”.

Subsequently, in step S7, it is determined whether or not the variable i is larger than the variable N. That is, it is determined whether or not the processing of steps S9 to S13 has been performed for each movement locus corresponding to each of all human IDs. If “NO” in the step S7, that is, if the processing of the steps S9 to S13 is not performed on the movement trajectory corresponding to all the human IDs, the human position of the human ID _i is determined in the specific area SA in the step S9. It is judged whether it is included in. For example, if the variable i is “1”, it is determined whether or not the position of the human ID “001 (human A)” is included in the specific area SA. As a specific process, the CPU 16 determines whether or not the position data of the person A stored in the position buffer 330 is included in the coordinate range indicated by the specific area coordinate data 340. In addition, CPU16 which performs the process of step S9 functions as a determination means.

If “YES” in the step S9, for example, if the variable i is “3”, the position of the person C (human ID “003”) is included in the specific area SA as shown in FIG. Therefore, the process proceeds to step S13. If “NO” in the step S9, for example, if the variable i is “1”, the position of the person A is not included in the specific area SA as shown in FIG. The position of the person with human ID _i is added to the movement trajectory table. That is, as shown in FIG. 6, the position data of the person A is recorded in the movement trajectory table.

  Subsequently, in step S13, the variable i is incremented. For example, if the variable i is “1”, the variable i is set to “2” when the process of step S13 is executed. Then, the CPU 16 can designate the next human ID by incrementing the variable i. When the process of step S13 is completed, the process returns to step S7.

  If “YES” in the step S7, that is, if it is determined whether each of a plurality of human positions is included in the specific area SA, a human relationship estimation process is executed in a step S15. The human relationship estimation processing will be described in detail with reference to the flowchart shown in FIG. 10, and thus detailed description thereof is omitted here. Moreover, CPU16 which performs the process of step S15 functions as an estimation means.

  When the process of step S15 ends, the process returns to step S1. If “YES” in the step S1, for example, when the central control device 10 is turned off, the movement trajectory selection process is ended.

  FIG. 10 is a flowchart of human relationship estimation processing. When the process of step S15 is executed in FIG. 9, the CPU 16 sets the number of rows in the movement locus table to a variable L in step S31. For example, if the movement trajectory table has three rows, “3” is set in the variable L. Subsequently, in step S33, “1” is set to the variable k. The variable k is a variable for designating a line of the movement trajectory table. Then, in order to start the process from the first line of the movement trajectory table, “1” is set to the variable k in step S33. Subsequently, in step S35, “k + 1” is set to the variable m. For example, if the variable k is “1”, “2” is set to the variable m. That is, the variable m is a variable for designating the next line with respect to the line designated by the variable k.

  Subsequently, in step S37, the similarity of the movement track data between the k-th row and the m-th row in the movement track table is calculated. For example, if the variable k is “1” and the variable m is “2”, the movement trajectory between the human A and the human B shown in the first and second rows in the movement trajectory table shown in FIG. Data similarity is calculated using DP matching. The calculated similarity is stored in the similarity buffer 332. Subsequently, in step S39, it is determined whether or not the calculated similarity is greater than a threshold value. For example, it is determined whether the similarity of the movement trajectory data between the person A and the person B is greater than a threshold value. If “NO” in the step S39, that is, if the similarity is equal to or less than the threshold value, the process proceeds to a step S43. On the other hand, if “YES” in the step S39, if the similarity is larger than the threshold value, the human ID corresponding to the movement trajectory data of the k-th row and the m-th row is recorded in the related human table in a step S41. For example, if the variable k is “1” and the variable m is “2”, the human ID “001” and the human ID “002” are recorded as in the related person table shown in FIG.

  Subsequently, in step S43, the variable m is incremented. For example, if the variable k before the process of step S43 is “1” and the variable m is “2”, the movement trajectory data on the first line and the movement trajectory data on the third and subsequent lines In order to calculate the similarity, the variable m is incremented.

  Subsequently, in step S45, it is determined whether the variable m is larger than the variable L. That is, it is determined whether all the similarities between the movement trajectory data on the kth row and the movement trajectory data on the “k + 1” th and subsequent rows have been calculated. If “NO” in the step S45, that is, if the similarity between the movement trajectory data in the k-th row and the movement trajectory data in the “k + 1” -th and subsequent rows has not been calculated, the process returns to the step S37.

  If “YES” in the step S45, that is, if the similarity between the movement locus data in the k-th row and the movement locus data in the “k + 1” -th and subsequent rows is calculated, the variable k is incremented in a step S47. For example, if the variable k is “1”, the variable k is incremented to calculate the similarity between the movement trajectory data in the second row and the movement trajectory data in the third and subsequent rows.

  Subsequently, in step S49, it is determined whether or not the variable k matches the variable L. For example, when the similarity calculation is completed for all the row combinations, the values of the variable k and the variable L match. Therefore, in step S49, it is determined whether or not similarity calculation has been completed for all combinations of rows. If “NO” in the step S49, that is, if the calculation of the similarity is not completed for all combinations of rows, the process returns to the step S35. On the other hand, if “YES” in the step S49, if the calculation of the similarity is completed for all the row combinations, the human relationship estimation process is ended, and the process returns to the movement trajectory selection process.

  When calculating the similarity, there may be only one position data constituting the movement trajectory data. In this case, the human relationship is estimated based on the distance between the two people. Specifically, in step S37 of the human relationship estimation process, a distance value between two people is calculated as the similarity. In step S39, if the calculated distance value is smaller than the threshold value, “YES” is determined. That is, when the human relation is estimated based on the distance between the two persons, if the distance between the two persons is shorter than the threshold, it is determined that there is a human relation.

  As can be seen from the above description, the relationship estimation system 100 includes the central control device 10 including a plurality of LRFs 12. The LRF 12 detects, for example, the positions of people passing through a shopping mall aisle. In this passage, a place where there is a particularly heavy traffic and a place where people gather is set as the specific area SA. Then, it is determined whether each of a plurality of human positions is included in the specific area SA, and the central controller 10 determines whether or not there is a human relationship based on the movement trajectory data of the human that is not included in the specific area SA. Is estimated.

  Therefore, the relationship estimation system 100 can estimate human relationships except for places where irrelevant people frequently come and go. Therefore, it becomes possible to accurately estimate the human relationships of people.

  In the human relationship estimation process according to the present embodiment, the human relationship is estimated at every predetermined time. As a result, the estimated human relationship may change over time. For example, immediately after the system is started up, the accumulated position data is small, so it may be estimated that there is a human relationship even though there is actually no human relationship. However, since the accumulated position data increases as the operating time of the system increases, human relations are correctly estimated.

  In another embodiment, in order to prevent the human relationship from changing as described above, the human relationship may not be estimated for a certain period of time after the relationship estimation system 100 is activated. In this case, before step S15 of the movement trajectory determination process is executed, a step of determining whether a certain time has elapsed since the system was started is added.

  In another embodiment, the “attribute” of the estimated human relationship is determined based on the gender and age of the human. The “attribute” of the human relationship includes “family”, “friend”, “couple”, and the like. More specifically, a person who has an RFID tag in which the gender and age of the person are registered in advance is used, and the person who owns the RFID tag and the person who has been detected using the radio wave intensity of the RFID tag. Associate. If the relationship between two men and women is estimated, the attribute of the relationship is determined as “couple”. Also, if the human relationship is estimated for a group of three or more people of the same age, the attribute of the human relationship is determined as “friend”. Furthermore, if the age difference is large among three or more people, the attribute of the human relationship is determined as “family”.

  In still another embodiment, an autonomous mobile robot that performs an information providing service may be arranged in the detection area E. Then, the robot changes the content of the information to be provided to the person whose human relation attribute is determined. For example, a shop for couples and event information are provided to two persons having the attribute of “couple”. Further, a group of three or more people having the attribute of “friends” is provided with information such as restaurants that can accommodate the people who make up the group. The group of three or more persons having the “family” attribute is provided with event information for the youngest person (child) belonging to the group, information on a family store, and the like.

  In another embodiment, a technique different from DP matching may be used as a technique for estimating the human relationship. For example, in the detection area E, an estimation area is further provided separately from the specific area SA. And like patent document 1, based on the action history in the presumed field, human relations may be presumed.

  In this embodiment, the specific area SA is manually set by the system administrator, but may be automatically set in other embodiments. For example, the positions of detected people are accumulated, the occurrence frequency of local behavior and global behavior disclosed in the above-mentioned “Japanese Patent Application Laid-Open No. 2010-231470” is obtained, and there is a region where the occurrence frequency of the local behavior and global behavior is high. Alternatively, the specific area SA may be automatically set. Furthermore, in another embodiment, the specific area SA may change depending on the season, event, and time zone.

  Further, the movement trajectory selection program 310 and the human relationship estimation program 312 may be stored in the HDD of the data distribution server and distributed to a central control device or the like in a system having the same configuration as the present embodiment via the network. . Further, the storage medium may be sold or distributed in a state where these programs are stored in a storage medium such as an optical disk such as a CD, a DVD, or a BD (Blu-ray Disc), a USB memory, and a memory card. When the movement trajectory selection program 310 and the human relationship estimation program 312 downloaded through the above-described server or storage medium are installed in the central controller in the system having the same configuration as that of this embodiment, The same effect can be obtained.

  The specific numerical values such as the number of people, predetermined time, distance, error, radius, angle, and frequency given in this specification are merely examples, and are appropriately changed according to the needs of the product specifications and the like. Is possible.

10 ... Central controller 12a-12f ... LRF
16 ... CPU
18 ... Memory

Claims (4)

A relationship estimation device having detection means for detecting the positions of a plurality of humans existing in space,
A determination means for determining whether each of the plurality of human positions is included in a specific area, and estimating a human relationship based on each position of at least two persons not included in the specific area A relationship estimation device comprising estimation means. A relationship estimation system having detection means for detecting positions of a plurality of humans existing in a space,
A determination means for determining whether each of the plurality of human positions is included in a specific area, and estimating a human relationship based on each position of at least two persons not included in the specific area A relationship estimation system comprising an estimation means. A processor of a relationship estimation device having detection means for detecting the position of each of a plurality of persons existing in space;
A determination means for determining whether each of the plurality of human positions is included in a specific area, and estimating a human relationship based on each position of at least two persons not included in the specific area A relationship estimation program that functions as an estimation means. A relationship estimation method for a relationship estimation device, comprising detection means for detecting the position of each of a plurality of humans existing in space,
Determining whether each of the plurality of human positions is included in a specific area, and estimating a human relation based on each position of at least two persons not included in the specific area Estimation method.

Images