JP6730953B2 - Terminal position estimating apparatus, program and method in consideration of moving object recognition information - Google Patents

Description

The present invention relates to a technique for estimating the position of a terminal based on the reception status of radio waves at the terminal.

Conventionally, a technique for estimating the position of a receiving terminal using a plurality of received wireless signals (radio waves) has been widely used. For example, a positioning technology using a GPS (Global Positioning System) outdoors, a wireless LAN (Local Area Network) indoors, or the like is currently widely used.

In such a positioning technique using radio waves, whether or not there is an object that affects the propagation of radio waves between a terminal and a radio wave transmission source (radio wave source) such as a satellite, a base station or an access point, Positioning results are greatly affected. For example, when there is a shield that blocks radio waves, the received signal strength at the terminal is lower than when the radio waves reach the terminal directly, and the distance between the radio wave source and the terminal is estimated to be larger than it actually is. The position estimation error increases.

For such a problem, the system disclosed in Non-Patent Document 1 is different from the radio wave attenuation model used when a static shield whose position is fixed exists between the transmitting and receiving nodes and when it does not exist. By using the model, the accuracy of position estimation is improved. In addition, by predicting the position estimation error by radio wave simulation that considers the effect of the obstacle, and determining the position of the transmitting node so that the expected error is small, the optimal transmitting node arrangement according to the obstacle can be determined. I'm going to get it.

Further, in Patent Document 1, when an obstacle for radio wave transmission exists between radio wave transmitters/receivers, a radio signal between the radio transmitter/receiver and not a radio characteristic parameter between the radio transmitter/receiver and a wireless terminal is used. Disclosed is a technique for estimating the position of a wireless terminal from the detection result of a change in the radio wave propagation environment due to communication. In this technology, when radio waves are blocked, a priority (likelihood) used for position estimation is set for each transmitter.

JP, 2011-203129, A

Kaito Oka, Masaki Igarashi, Hideaki Uchiyama, Takashi Shimada, Hajime Nagahara, Rinichiro Taniguchi, "Anchor Node Placement Considering Shielding in Wireless Position Estimation", Multimedia, Distributed, Cooperative and Mobile (DICOMO 2015) Symposium, 2015 , Pages 799-802

In the conventional techniques including the technique described above, although the object that affects the propagation of radio waves is considered, the considered object is a static shield/obstacle whose position is fixed. .. However, in the actual site of terminal position estimation, there are many cases in which a person cannot be ignored as an object that interferes with the propagation of radio waves (radio signals).

For example, at present, in stores in various fields, there is an increasing need for accurately grasping the flow line of a visitor or a store clerk who possesses a terminal. In this case, it is general to arrange a plurality of beacon transmission sources (hereinafter abbreviated as beacons) in the store to estimate the terminal position. Here, the person moving in the store naturally has a very large influence on the terminal position estimation by these beacons.

However, in the related art including the above-described technology, such a person cannot be considered as an object that affects the propagation of radio waves. As a result, an increase in error in the estimation result of the terminal position becomes a problem. Thus, although the influence of a movable object including a person on radio wave propagation is great, it has not been taken into consideration in the past.

Therefore, an object of the present invention is to provide a device, a program, and a method capable of more accurately estimating the position of a terminal that has received a radio wave from a radio wave source in consideration of a movable object.

According to the present invention, a terminal position estimation device that estimates the position of the terminal by acquiring the received radio wave information in the terminal that is carried by a movable object and that has received the radio wave from the radio wave source,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. At least one movable object and an object distribution determining means for determining an object distribution which is a distribution of the previously installed object;
A radio wave simulation is performed on the determined object distribution to estimate the position of the terminal from among a plurality of pre-arranged radio wave sources that are not carried by the at least one movable object. Radio source selection means for selecting a suitable radio source suitable for
There is provided a terminal position estimation device having a terminal position determining means for determining the position of the terminal by using information regarding a plurality of the selected suitable radio wave sources out of the acquired received radio wave information.

As one embodiment of the terminal position estimation device according to the present invention, the radio wave source selection means is such that the object distribution at one time relating to position estimation has not changed by a predetermined amount or more as compared with the object distribution at the previous time. In this case, it is also preferable to set the suitable radio wave source selected at the previous time as the suitable radio wave source at this one time.

In addition, as another embodiment of the terminal position estimation device according to the present invention, a radio wave simulation for performing an electric wave simulation on at least an object arrangement relating to arrangement information of an object installed in advance to minimize an error in an estimated position of the terminal. It is also preferable to further include a radio wave source arranging means for deciding an arrangement and deciding an arrangement position for arranging a plurality of arrangement radio wave sources in advance from candidate positions in which the radio wave sources can be installed based on the decided arrangement. ..

Further, as still another embodiment of the terminal position estimating device according to the present invention, the radio wave source selecting means is configured to provide a plurality of radio wave sources when the at least one movable object does not exist at one time relating to position estimation. It is also preferable to set all of the above as suitable radio wave sources at this one time.

According to the present invention, there is also provided a terminal position estimation device that estimates the position of a terminal that is carried by a movable object and that receives received radio wave information from a terminal that receives a radio wave from a radio wave source. ,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. At least one movable object and an object distribution determining means for determining an object distribution which is a distribution of the previously installed object;
A radio wave simulation is performed on the determined object distribution to calculate an estimated probability of the estimated position of the terminal, and a cost function related to the calculated estimated probability and the distance between the estimated position and the true position is generated. Then, the placement of the radio wave source that minimizes the generated cost function is determined, and based on the determined placement, it is suitable for the position estimation of the terminal from among the plurality of placement radio wave sources that are placed in advance. Radio source selection means for selecting a suitable radio source ,
Of the acquired received radio wave information, a terminal position determining means for determining the position of the terminal by using information related to a plurality of the selected suitable radio wave sources.
There is provided a terminal position estimation device having:

Further, as still another embodiment of the terminal position estimating device according to the present invention, the terminal position determining means further selects three of the selected suitable radio wave sources in order from the highest received radio wave intensity, It is also preferable to determine the position of the terminal by three-point positioning using three radio wave sources. Alternatively, the terminal position determination means preferably determines the position of the terminal by maximum likelihood estimation by a plurality of the selected suitable radio wave sources.

It is also preferable that the object recognizing unit generate the object recognizing information based on the photographing or measurement information from at least one of the camera, the omnidirectional camera, the depth camera, the laser positioning unit, and the thermography unit.

According to the present invention, there is also provided a computer mounted on an apparatus for estimating the position of a terminal which is carried by a movable object and which receives radio wave information from a terminal which has received radio waves from a radio wave source. A program that works,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. At least one movable object and an object distribution determining means for determining an object distribution which is a distribution of the previously installed object;
A radio wave simulation is performed on the determined object distribution to estimate the position of the terminal from among a plurality of pre-arranged radio wave sources that are not carried by the at least one movable object. Radio source selection means for selecting a suitable radio source suitable for
A terminal position estimation program that causes a computer to function as terminal position determination means that determines the position of the terminal using information related to a plurality of the selected suitable radio wave sources out of the acquired received radio wave information is provided. To be done.

According to the present invention, a computer mounted on a device that acquires received radio wave information at a terminal that is carried by a movable object and has received a radio wave from a radio wave source to estimate the position of the terminal is further provided. A terminal location estimation method,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. Determining an object distribution that is a distribution of at least one movable object and the pre-installed object;
A radio wave simulation is performed on the determined object distribution to estimate the position of the terminal from among a plurality of pre-arranged radio wave sources that are not carried by the at least one movable object. A step of selecting a suitable radio wave source suitable for
A terminal position estimation method is provided, which includes a step of determining the position of the terminal by using information related to a plurality of the selected suitable radio wave sources out of the acquired received radio wave information.

According to the terminal position estimation device, program, and method of the present invention, it is possible to more accurately estimate the position of a terminal that has received a radio wave from a radio wave source in consideration of a movable object.

1 is a schematic diagram showing an embodiment of a terminal position estimation system including a terminal position estimation device according to the present invention. It is a functional block diagram which shows the functional structure in one Embodiment of the terminal position estimation apparatus by this invention. It is a flow chart which shows one embodiment of terminal position presumption processing in a radio wave source selection part and a terminal position determination part. It is a flow chart which shows one embodiment of suitable radio wave source selection processing in a radio wave source selection part.

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

[Terminal position estimation system]
FIG. 1 is a schematic diagram showing an embodiment of a terminal position estimation system including a terminal position estimation device according to the present invention.

The terminal position estimation system of the present embodiment shown in FIG. 1 estimates a momentary position in one store in at least one terminal 3 possessed by a store clerk, a visitor or the like, and a store clerk who possesses the terminal 3 concerned. It is possible to grasp the flow line in the store such as a customer.

Specifically, this terminal position estimation system is
(A) Beacons 2 which are installed at a plurality of positions in the store and which transmit radio waves in all directions at predetermined time intervals,
(B) one or a plurality of cameras 4 capable of capturing a movable object such as a person and transmitting the captured image information in time series via a wireless or wired communication network;
(C) “Object recognition information” is generated from a time-series image group acquired from the camera 4 via the communication network, and further directly from the terminal 3 via the wireless communication network (or via a relay device such as an access point). ) "Received radio wave information" is acquired, and the terminal position estimation device 1 that estimates the momentary position of the terminal 3 based on the generated and acquired information and determines the flow line in the store is provided.

Here, in the store, objects such as desks, chairs, partitions, exhibition stands, and counters that affect radio wave propagation are arranged. The terminal position estimation device 1 also acquires the placement information (“object placement information”) of such an object previously installed in the store and uses it for the position estimation of the terminal 3. Note that this “object placement information” may also be generated after recognizing the installed object based on the image group from the camera 4. Thereby, for example, even if the layout of the equipment in the store is changed or some of the equipment is temporarily placed temporarily, it is possible to obtain the “object arrangement information” that accurately corresponds to it.

Further, the beacon 2 may be, for example, a BLE (Bluetooth (registered trademark) Low Energy) specification beacon that transmits an advertisement packet in all directions at intervals of 100 to 1000 msec. The beacon 2 is not limited to this, of course. For example, it can be an access point of a wireless LAN such as Wi-Fi (registered trademark), or the terminal 3 can receive radio waves from the access point and generate "received radio wave information". Then, various radio wave sources can be adopted as the beacon 2.

By the way, the installation position of the beacon 2 as shown in FIG. 1 (arrangement of the beacon 2 in the store) is also determined by the terminal position estimating device 1 by using the captured image data from the camera 4, as described in detail later. Good.

Further, in the present embodiment, the terminal 3 is a smartphone, a mobile phone, a tablet computer, a wearable terminal or the like that can be carried by a clerk or a visitor, but other various communication terminals can be carried. Applicable The terminal 3 can simultaneously receive radio waves transmitted from a plurality of (preferably three or more) beacons 2.

Similarly, the terminal position estimation device 1 shown in FIG. 1 is a device that acquires “received radio wave information” in the terminal 3 that receives the radio wave from the beacon 2 that is the radio wave source, and estimates the position of the terminal 3. Specifically, as a feature,
(A) Obtaining "object recognition information" from an object recognition means capable of recognizing a movable object, and based on this "object recognition information" and "object arrangement information" of an object installed in advance, An object distribution determination unit 113 that determines a “object distribution” that is a distribution of a movable object and the previously installed object;
(B) A radio wave simulation is performed on the determined “object distribution” to determine the placement of the radio wave sources that minimizes the error in the estimated position of the terminal 3, and a plurality of pre-placed objects are placed based on the determined placement. A radio wave source selection unit 114b for selecting a "suitable radio wave source (suitable beacon)" suitable for the position estimation of the terminal 3 from among the beacons 2 which are the radio wave sources arranged in
(C) A terminal position determination unit 116 that determines the position of the terminal 3 by using information related to a plurality of selected “suitable radio wave sources (suitable beacons)” in the acquired “received radio wave information”. Have

Here, the “received radio wave information” is, for example, information in which the reception time and the received signal strength indicator (RSSI) in the radio wave received by the terminal 3 from the beacon 2 are associated with the identifier of the beacon 2. You can Further, the “object placement information” may be, for example, the position coordinates or position coordinate range of an object placed in advance. Further, the “object recognition information” can be, for example, the foot position coordinates of the recognized person at each time.

As described above as the configurations (A) to (C), the terminal position estimation device 1 uses the “preferred radio wave source (preferred beacon)” for determining the position of the terminal 3 as the “preferred radio wave source (preferred beacon)” of the previously installed object. The selection is made in consideration of not only "object arrangement information" but also "object recognition information" about a movable object such as a person. As a result, even if a moving person or the like affects the propagation of the radio wave from the beacon 2 to the terminal 3, it is possible to reliably capture the effect and more accurately estimate the position of the terminal 3.

Further, for example, the “object distribution” is determined based on the “object recognition information” and the “object arrangement information” at each time of the position estimation period, and the “suitable radio wave source (suitable beacon)” is selected at each time. As a result, it is possible to estimate the position of the terminal 3 every moment. Thereby, for example, the position of each terminal 3 can be determined with higher accuracy even in a situation where many persons are moving around in the store.

In the present embodiment, the object recognition means in the above configuration (A) acquires captured image data from the camera 4, recognizes a movable object, and generates "object recognition information". It is a part 111. As a modification of this, the object recognition means (object recognition unit 111) may be provided in an external device, and the terminal position estimation device 1 may acquire the "object recognition information" from this device.

In still another embodiment, the object recognition means uses the photographing or measurement information from at least one of a omnidirectional camera (omnidirectional) camera, a depth camera, an infrared camera, an infrared positioning means, a laser positioning means, and a thermography means. The "object recognition information" may be generated based on the above. For example, the depth value information (for each target pixel) generated by the depth camera can be converted into image data and used in the same manner as the image captured by the camera 4. In any case, the terminal position estimation device 1 can acquire the “object recognition information” generated by some means and use it for position estimation of the terminal 3.

Further, the movable object as the recognition target related to the “object recognition information” may be a person, an animal, a vehicle, or any other movable physical object that can be recognized by the object recognition means (for example, captured by the camera 4). Various things apply (if possible). Also, the place to be photographed is not particularly limited, and may be, for example, not only in a store but also in a company, a school, a hall, or inside a house. It may be outdoors where shoppers, workers, pedestrians, runners, etc. can be seen.

Furthermore, as still another embodiment, the terminal 3 has the configurations (A) to (C) described above, and functions as a terminal position estimation device that estimates the position of itself and the positions of other terminals 3 in the vicinity. You may. In this case, for example, it is possible to generate the "object recognition information" by using the camera (in which the position is determined every moment) built in the terminal 3.

[Device configuration, terminal position estimation method]
FIG. 2 is a functional block diagram showing a functional configuration in one embodiment of the terminal position estimating device according to the present invention.

According to FIG. 2, the terminal position estimation device 1 includes a communication interface 101 capable of communication connection with the camera 4, the terminal 3, and the like, a received radio wave information storage unit 102, an object recognition information storage unit 103, and an object placement information storage unit. 104, a terminal flow line information storage unit 105, a display/keyboard (DP/KB) 106, and a processor/memory. Here, the processor memory realizes the terminal position estimating function by executing a program that causes the computer of the terminal position estimating device 1 to function.

Further, the processor/memory includes a function recognizing unit including an object recognizing unit 111, an object recognizing information managing unit 112, an object distribution determining unit 113, a radio wave source arrangement deciding unit 114a, and a radio wave source selecting unit 114b. It has a unit 114, a received radio wave information management unit 115, a terminal position determination unit 116, a terminal flow line information management unit 117, a communication control unit 118, and an input/output control unit 119. The process flow shown by connecting the functional components of the terminal position estimating apparatus 1 in FIG. 2 with arrows is understood as an embodiment of the terminal position estimating method according to the present invention.

Similarly, in FIG. 2, the camera 4 is a visible light, near-infrared, or infrared imaging device including a solid-state imaging device such as a CCD image sensor or a CMOS image sensor. Further, the camera 4 or a camera control device (not shown) generates captured image data including an image of the object captured by the camera 4, and transmits the information to the object tracking device 1 in time series or in batch. Have a function.

The communication interface 101 receives captured image data, which is a time-series image group, from the camera 4 or the camera control device via a wired or wireless communication network. The acquired captured image data (image file) is output to the object recognition unit 111. Further, the communication interface 101 receives the received radio wave information from the terminal 3 directly (or via a relay device such as an access point) via the wireless communication network. Alternatively, the received radio wave information may be received after being wire-connected to the terminal 3 via a USB (Universal Serial Bus) or the like. Furthermore, the communication interface 101 may transmit the flow line information generated as a result of the terminal position estimation to an external information processing device. Note that the communication control unit 118 controls the transmission/reception of the information in the communication interface 101, and the information is transmitted/received at an appropriate timing.

In the present embodiment, the object recognition unit 111 recognizes a person staying or moving in the store based on the captured image data of the image captured by the camera 4, and generates object (person) recognition information. Here, the generated object (person) recognition information may include the two-dimensional (or three-dimensional) coordinate value of the foot position of the recognized one or more persons at each time of the recognition process. Good. Note that the object (person) recognition processing in the object recognition unit 111 can be implemented by adopting various known methods.

For example, when an omnidirectional camera is used as the camera 4, a non-patent document Tatsuya Kobayashi, Haruhisa Kato, Masaru Kanno, “Proposal of a person trajectory tracking method that is robust against occlusion using a monocular omnidirectional camera”, Object (person) recognition information can be generated using the method described in Technical Report, vol.116, no.411, PRMU2016-146, 2017, p. 321 to 326.

Specifically, in this method, person detection processing and person tracking processing are executed for each image frame, the position of each person at each time is estimated, and the person is tracked. In the person detection process, the area extracted using the background subtraction technique is matched with a 3D person model prepared in advance, and the person area in the image is detected. Here, the human model is arranged in advance at various foot positions where a person can exist, and the corresponding foot position is detected as the person position by searching the contour having the highest similarity to the foreground area.

Further, in the person tracking process, the person ID being tracked is assigned to the detected person area by associating the person being tracked with the above detection result, and the element having the maximum matching score by one-to-one person matching is determined. select. Then, based on the result of this person matching, the tracking position of each person is estimated using a particle filter.

Incidentally, the apparatus 1 may not have the object recognition unit 111, and the object recognition information management unit 112 may take an embodiment in which the object recognition information is acquired and managed from an external object recognition unit. In any case, the object recognition information management unit 112 appropriately outputs the acquired object recognition information to the object distribution determination unit 113 while storing it in the object identification information storage unit 103.

The object distribution determination unit 113, based on the input object recognition information and the same input object arrangement information, the position distribution of a movable object (for example, a person) and a previously installed object (for example, equipment in a store) Determines the object distribution that is

Here, the object arrangement information is information including a coordinate value or a coordinate value range of an arrangement position of an object such as a desk, a chair, a partition, an exhibition stand, or a counter in a store that influences radio wave propagation, and from the keyboard 106. It is also preferable that the data is input, recorded in the object arrangement information storage unit 104 via the input/output control unit 119, and output to the object distribution determination unit 113. It is also preferable that the object placement information further includes information on the size (horizontal and vertical) of the floor in the store where the position is estimated. Note that, as a modification, this object placement information may also be generated by the object recognition unit 111 recognizing an installed object in the store based on the captured image data of the image captured by the camera 4.

Similarly, in FIG. 2, the radio wave source arrangement deciding unit 114a of the radio wave source deciding unit 114 decides an arrangement position where the beacon 2 is actually arranged in advance from among the candidate positions where the beacon 2 can be arranged in the store. The pre-arrangement position determination process of the beacon 2 will be described in detail later. As a modification, the device 1 does not have the radio wave source arrangement determining unit 114a, and the arrangement information of the beacon 2 which is considered appropriate from an experience sense or in the past results is input/output from the keyboard 106. It may be input to the power supply determination unit 114 via the control unit 119.

On the other hand, the radio wave source selection unit 114b of the radio wave source determination unit 114, as will be described later in detail with reference to FIGS.
(A) For the object distribution input from the object distribution determination unit 113, a radio wave simulation using maximum likelihood estimation is performed for each placement pattern (set of placement positions) A of a plurality of beacons 2 (placement radio sources) that are placed in advance. And calculate the estimated probability of the estimated position e of the terminal 3,
(B) Generate a cost function C(A) related to the calculated estimated probability and the distance between the estimated position e and the true position u,
(C) Determine the placement A _opt of the beacon 2 that minimizes the generated cost function C(A),
(D) Based on the determined placement A _opt , a suitable beacon 2 (suitable radio source) suitable for position estimation of the terminal 3 is selected from among a plurality of beacons 2 (placed radio sources) that are placed in advance.

The received radio wave information management unit 115 inputs the received radio wave information acquired from the terminal 3, stores the received radio wave information in the received radio wave information storage unit 102, manages the received radio wave information, and outputs the received radio wave information to the terminal position determination unit 116 as appropriate. Here, the received radio wave information can be information in which the reception time, the RSSI, and the identifier of the beacon 2 are associated with each beacon 2 that is the source of the radio wave received by the terminal 3.

The terminal position determination unit 116 determines the position of the terminal 3 by using information related to a plurality of the suitable beacons 2 (suitable radio wave sources) selected by the radio wave source selection unit 114b among the acquired received radio wave information. To do. In particular,
(A) Of the selected suitable beacons 2, three may be further selected in order from the highest RSSI, and the position of the terminal 3 may be determined by three-point positioning by these three beacons 2, or
(B) The position of the terminal 3 may be determined by maximum likelihood estimation by a plurality of the selected suitable beacons 2.

FIG. 3 is a flowchart showing an embodiment of the terminal position estimation processing in the radio wave source selection unit 114b and the terminal position determination unit 116.

(S101) Object placement information (for example, installation position coordinates in facilities and the like in a store) is acquired.
(S102) The beacon arrangement information including the arrangement A _set of n beacons 2 arranged in advance and the number m of the suitable beacons 2 to be selected is acquired.

Next, the loop (steps S103 to S111) of the suitable beacon selection process and the terminal position determination process at each time of the position estimation period is entered. That is, the processing of steps S103 to S111 is executed at each time. As a result, the position of the terminal 3 is determined (estimated) every moment.

(S103) Object (person) recognition information is acquired.
(S104) Object distribution information is generated from the object arrangement information and the object (person) recognition information.
(S105) It is determined whether or not there is a moving or movable object (person). Here, when a false determination (determination that it does not exist) is made, the process proceeds to step S107b.

(S107b) All of the n beacons 2 (placed radio wave sources) installed in advance are set as the suitable beacons 2 (preferable radio wave sources) at this time. This is particularly effective when the arrangement of these n beacons 2 is suitably determined in advance by the radio wave source arrangement determining unit 114a based on the object arrangement information. Note that, as another flow mode, it is also possible to cancel this step S107b and, if a false determination is made in step S105, move to step S107a described later.

(S106) On the other hand, if the true determination (determination of existence) is made in step S105, then whether or not the position of the moving or movable object (person) has changed, or It is determined whether the determined object distribution has changed.

Here, the change of the position means, for example, that the position is separated from the position at the previous time by a predetermined distance or more, or a predetermined range including the position at the previous time. You may be out. In addition, the fact that the object distribution is changing means that the position of at least one object forming the object distribution is separated from the position at the previous time by a predetermined distance or more, or one position before. It may be outside the predetermined range including the position at the time.

When a false determination (determination that there is no change) is made in step S106, the process proceeds to step S107c.
(S107c) The suitable beacon 2 (preferred radio wave source) selected at the immediately preceding time is set as the suitable beacon 2 (preferred radio wave source) at this time. If the preferred beacon 2 selected at the immediately preceding time does not exist, the process proceeds to step S107a regardless of the determination result of step S106.

(S107a) On the other hand, when the true determination (determination that it has changed) is made in step S106, the maximum likelihood estimation method is used to find m preferred beacons 2 from the n beacons 2 arranged in advance. select. This is a process of excluding the beacon 2 that is more strongly affected by the blocking or the like by the moving or movable object (person). This suitable beacon selection process will be described later in detail with reference to FIG.

(S108) Received radio wave information is acquired from the terminal 3.
(S109) Of the selected suitable beacons 2 (suitable radio wave sources), three are further selected in order from the highest RSSI.

(S110) The position of the terminal 3 is determined by three-point positioning using these three beacons 2. Specifically, the distance distance from each beacon 2 of the terminal 3 is calculated by the following equation (1) distance=10^((TxPower-RSSI)/10d) (unit is meter (m))
It is also possible to perform three-point positioning using the calculated three distance distances. In the above equation (1), RSSI is the strength (RSSI) of the radio wave received from the beacon 2, and the unit is dBm. Further, TxPower is RSSI measured at a position separated from the beacon 2 by a distance of 1 m, and d is a constant representing the degree of attenuation of radio waves.
(S111) The terminal position estimation result including the (two-dimensional or three-dimensional) estimated position coordinates of the terminal 3 is output.

By performing the processing of steps S103 to S111 described above at each time during the position estimation period, the terminal position determination unit 116 can form time-series information of estimated position coordinates of the terminal 3. ..

FIG. 4 is a flowchart showing an embodiment of a suitable radio wave source selection process in the radio wave source selection unit 114b. The flow shown in the figure corresponds to the processing in step S107a in FIG.

In the radio wave source selection unit 114b, first, object distribution information and beacon arrangement information (n beacon arrangements A _set , the number m of suitable beacons to be selected) are set. In addition, an arrangement pattern in which the beacons 2 are installed one by one in the arrangement pattern A _set of a plurality of beacons 2 (arranged radio wave sources) arranged in advance is defined as A _i (A _i ⊂A _set , A ₀ =φ). .. That is, the arrangement pattern A _p (p=1, 2,..., M) is the arrangement of the beacon 2 whose position is determined up to the p-th beacon. Hereinafter, the loop of steps S201 to S204 is repeated until the parameter i is incremented from zero by 1 and reaches m-1.

Further, among these steps, step S201 is repeated as a process in a loop (incrementing k by 1) for _k of the estimated position e _k of the terminal 3 that can be taken in the position estimation range, and further, this step S201 and step are repeated. S202 is repeated as a process in a loop (incrementing j by 1) for _j of the true position u _j of the terminal 3 that can be in the position estimation range.

(S201) With respect to the _set object distribution, the beacon 2 having the arrangement pattern A _i (⊂A _set ) and the terminal 3 having the true position u _j (j=0, 1,..., U _j εS) A radio wave simulation using the maximum likelihood estimation method is performed between the probability P(A _i , u _j , e _k ) at which the estimated position is e _k (k=0, 1,..., E _k ∈ S). calculate. Here, S(⊂R ² ) is a set of all coordinates of the position estimation range.

By the way, in this maximum likelihood estimation, the above probability P(A _i , u _j , e _k ) is taken as a normal distribution with mean μ and variance σ ² , and the likelihood function L is calculated, and μ which maximizes this L and This probability P(A _i , u _j , e _k ) can be determined by determining the variance σ ² . Also, in the above radio wave simulation, the radio wave attenuation of an object distributed according to the object distribution information, which is used when determining the radio wave intensity, uses a preset value according to the assumed object (for example, human body). You may. In addition, the transmission radio wave characteristics such as the transmission radio wave intensity in each beacon 2 of the arrangement pattern A _set may be uniformly set to a predetermined one that is normally used, or according to the characteristics of the beacon actually installed. It is also preferable to set it.

(S202) Next, after the loop process for k including step S201 is completed, the following equation (2) E(A _i , u _j )=Σ _ekεR |u _j −e _k |*P( A _i ,u _j ,e _k )
The expected value E(A _i ,u _j ) of the distance (that is, the estimation error of the estimated position) between the estimated position e _k and the true position u _j defined by is calculated. In the above equation (2), Σ _{ek εR} is the summation of all the estimated positions e _k of the terminal 3 that can be taken in the position estimation range.

(S203) Next, after the loop process for j including step S202 is completed, the cost function C(A _i ) is further calculated by the following equation (3) C(A _i )=Σ _ujεS E( A _i ,u _j )
Then, the cost function C(A _i ) for the arrangement pattern A _i is calculated. In the above equation (3), Σ _ujεS is the sum of all the true positions u _j of the terminal 3 that can be taken in the position estimation range. That is, the cost function C(A _i ) defined here is the sum of expected values of the position estimation error in the entire position estimation range.

(S204) The placement pattern A _i is evaluated based on the calculated value of the cost function C(A _i ). Specifically, under the placement pattern A _i , the placement position of the beacon 2 to be placed (i+1)th is set to a _i+1 , and the following equation (4) a _i+1 =arg min C(A _i ∪{ a})
Is used to determine the arrangement position a _i+1 . In the above equation (4), arg min is calculated for all possible placement positions a (εA _set ). Using this arrangement position a _i+1 , the arrangement A _i+1 can be _calculated by the following equation (5) A _i+1 =A _i ∪{a _i+1 }.
Required by.

(S205) In this way, the arrangement position a of the beacon 2 that minimizes the defined cost function C(A _i ) is sequentially determined for all parameters i, and finally, the arrangement positions a _{1 to} a a _m m pieces of suitable beacon placement a _opt (= a _m) is determined. Next, based on this suitable beacon arrangement A _opt , the suitable beacon 2 is selected from among the plurality of beacons 2 arranged in advance.

As described above, in the radio wave source selection unit 114b, the one that is more strongly affected by the obstruction by the moving or movable object (person) from the n beacons 2 arranged in advance. Excluded. As a result, after this, the terminal position determination unit 116 can determine the position of the terminal 3 using the suitable beacon 2 that is more suitable for position determination, and as a result, the conventional method that does not consider the influence of occlusion by a moving object. Therefore, the terminal position estimation accuracy is considerably improved as compared with.

Returning to FIG. 2, the radio wave source arrangement determining unit 114a of the radio wave source determining unit 114 performs the same process as the process in the radio wave source selecting unit 114b described above with reference to FIG. The position where the beacon 2 is actually arranged in advance is determined from among the candidate positions where can be installed. Here, the candidate position in the store may be, for example, a position on the wall surface in the store, a position on equipment such as a desk or a chair, and may not be set on the floor surface.

Specifically, the radio wave source arrangement determination unit 114a sets all the arrangements that can be set for the n beacons 2 as A _all (⊂S), and then
(A) A radio wave simulation using maximum likelihood estimation is performed for each placement pattern A (⊂A _all ) of candidate positions where the beacon 2 can be installed in the store, and the estimated probability P(A of the estimated position e of the terminal 3 is P(A , u, e) is calculated,
(B) Generate a cost function C(A) related to the calculated distance between the estimated position e and the true position u,
(C) The arrangement A _set (⊂A _all ) of the n beacons 2 that minimizes the generated cost function C(A) is determined.

As a result, an appropriate arrangement of the beacons 2 is determined in consideration of the arrangement of pre-installed objects, which is a prerequisite for the suitable beacon selection process in the radio wave source selection unit 114b. The processing of the above radio wave source arrangement determination unit 114a is similar to the processing in the radio sources selected portion 114b, without the A _opt set of beacon arrangement candidate point input for processing, A _all The difference is that

Similarly, in FIG. 2, the terminal flow line information management unit 117 collects the estimated position coordinates of the terminal 3 determined by the terminal position determination unit 116 for each time during the position estimation period, and the terminal 3 (the user who owns it). The flow line information in which the collected time series information of the estimated position coordinates is associated with each identifier ID is generated. In addition, the terminal flow line information management unit 117 may store the generated flow line information in the terminal flow line information storage unit 105, and it is preferable to display the generated flow line information on the display 106 via the input/output control unit 119. It may be transmitted to an external information processing device via the control unit 118 and the communication interface 101.

As described above in detail, according to the present invention, the suitable radio wave source for determining the position of the terminal is not only the object placement information of the object installed in advance but also the object of the movable object such as a person. Selection is also made in consideration of recognition information. As a result, even if a moving person or the like influences the propagation of the radio wave from the radio wave source to the terminal, the influence can be surely taken in and the position of the terminal can be estimated more accurately.

Further, for example, the position of the terminal is estimated every moment by determining the object distribution based on the object recognition information and the object arrangement information at each time of the position estimation period and selecting the suitable radio wave source at each time. You can Therefore, for example, the position of each terminal can be determined with higher accuracy even when many people are moving around.

By the way, the configuration and method of the present invention can be applied to, for example, a monitoring system for monitoring a place where a large number of people move/stay, enter/exit, a store, a commercial/service facility, and even a store. It can be applied to various systems, such as a marketing research system for investigating the situation of people entering and leaving a store, taking a break, watching a game, participating in an event, or moving on the streets of a city.

In the various embodiments of the present invention described above, various changes, modifications and omissions of the technical idea and scope of the present invention can be easily made by those skilled in the art. The above description is merely an example and is not intended to be limiting. The invention is limited only by the claims and equivalents thereof.

DESCRIPTION OF SYMBOLS 1 Terminal position estimation device 101 Communication interface 102 Received radio wave information storage unit 103 Object recognition information storage unit 104 Object placement information storage unit 105 Terminal flow line information storage unit 106 Display/keyboard (DP/KB)
111 object recognition unit 112 object recognition information management unit 113 object distribution determination unit 114 radio wave source determination unit 114a radio wave source arrangement determination unit 114b radio wave source selection unit 115 received radio wave information management unit 116 terminal position determination unit 117 terminal flow line information management unit 118 Communication control unit 119 Input/output control unit 2 Beacon (radio wave source)
3 terminal 4 camera

Claims (10)

A terminal position estimation device that estimates the position of a terminal that is carried by a movable object and that acquires received radio wave information at a terminal that has received radio waves from a radio wave source,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. At least one movable object and an object distribution determining means for determining an object distribution which is a distribution of the previously installed object;
A radio wave simulation is performed on the determined object distribution to estimate the position of the terminal from among a plurality of pre-arranged radio wave sources that are not carried by the at least one movable object. Radio source selection means for selecting a suitable radio source suitable for
A terminal position estimating device comprising: a terminal position determining unit that determines the position of the terminal by using information related to a plurality of the selected suitable radio wave sources from the acquired received radio wave information. .. A terminal position estimation device that estimates the position of a terminal that is carried by a movable object and that acquires received radio wave information at a terminal that has received radio waves from a radio wave source,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. At least one movable object and an object distribution determining means for determining an object distribution which is a distribution of the previously installed object;
A radio wave simulation is performed on the determined object distribution to calculate an estimated probability of the estimated position of the terminal, and a cost function related to the calculated estimated probability and the distance between the estimated position and the true position is generated. Then, the placement of the radio wave source that minimizes the generated cost function is determined, and based on the determined placement, it is suitable for the position estimation of the terminal from among the plurality of placement radio wave sources that are placed in advance. Radio source selection means for selecting a suitable radio source ,
Of the acquired received radio wave information, a terminal position determining means for determining the position of the terminal by using information related to a plurality of the selected suitable radio wave sources.
A terminal position estimation device having: The radio wave source selecting means selects the suitable radio wave source selected at the previous time when the object distribution at one time relating to position estimation has not changed by a predetermined amount or more as compared with the object distribution at the previous time. The terminal position estimation device according to claim 1 or 2 , wherein is set as a suitable radio wave source at the one time. A radio wave simulation is performed on at least the object placement related to the placement information of the previously installed object to determine the placement of the radio wave source that minimizes the error in the estimated position of the terminal, and based on the determined placement, the radio wave The radio wave source arranging means for deciding an arrangement position for preliminarily arranging the plurality of arranged radio wave sources from among candidate positions where a source can be installed, according to any one of claims 1 to 3. Terminal position estimation device. When the at least one movable object does not exist at one time relating to position estimation, the radio wave source selecting means sets all of the plurality of arranged radio wave sources as suitable radio wave sources at the one time. The terminal position estimation device according to any one of claims 1 to 4 . The terminal position determining means further selects three of the selected suitable radio wave sources in order from the highest received radio wave intensity, and determines the position of the terminal by three-point positioning by the three radio wave sources. The terminal position estimation device according to claim 1, wherein The terminal position determining means determines the position of the terminal by maximum likelihood estimation by a plurality of the selected suitable radio wave sources, and the terminal position according to any one of claims 1 to 5. Estimator. The object recognition means, based on the imaging or measurement information from at least one of a camera, a spherical camera, a depth camera, an infrared camera, an infrared positioning means, a laser positioning means, and a thermography means, the object recognition information. It produces|generates, The terminal position estimation apparatus of any one of Claim 1 to 7 characterized by the above-mentioned. A program that causes a computer installed in a device that estimates the position of a terminal that is a terminal carried by a movable object and that receives radio wave information at a terminal that receives radio waves from a radio wave source,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. At least one movable object and an object distribution determining means for determining an object distribution which is a distribution of the previously installed object;
A radio wave simulation is performed on the determined object distribution to estimate the position of the terminal from among a plurality of pre-arranged radio wave sources that are not carried by the at least one movable object. Radio source selection means for selecting a suitable radio source suitable for
A terminal characterized by causing a computer to function as terminal position determining means for determining the position of the terminal using information on a plurality of the selected suitable radio wave sources from the acquired received radio wave information. Location estimation program. A terminal position estimation method by a computer mounted on a device that acquires the received radio wave information at a terminal that is a terminal carried by a movable object and has received a radio wave from a radio wave source, and estimates the position of the terminal,
Object recognition information is acquired from an object recognition means capable of recognizing at least one movable object including the movable object, and the object recognition information is acquired based on the object recognition information and the placement information of the object installed in advance. Determining an object distribution that is a distribution of at least one movable object and the pre-installed object;
A radio wave simulation is performed on the determined object distribution to estimate the position of the terminal from among a plurality of pre-arranged radio wave sources that are not carried by the at least one movable object. A step of selecting a suitable radio wave source suitable for
And a step of determining the position of the terminal by using information on a plurality of the selected suitable radio wave sources among the acquired received radio wave information.

Images