Target number estimation system, target number estimation method, and program

Abstract

To provide a target number estimation system capable of more accurately estimating the number of staying persons.SOLUTION: A target number estimation system comprises a first target number estimation section, a radio propagation path acquisition section, and a second target number estimation section. The first target number estimation section estimates the number of targets staying in a first area on the basis of radio information, excluding radio propagation path information, or image information relating to the first area. The radio propagation path acquisition section acquires radio propagation path information based on a radio signal transmitted from a radio within the first area. The second target number estimation section performs a final target number estimation through machine learning by using a result estimated by the first target number estimation section and the radio propagation path information acquired by the radio propagation path acquisition section as input information. The second target number estimation section selects a model to be used for the estimation by the machine learning on the basis of the result estimated by the first target number estimation section.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to a target number estimation system, a target number estimation method, and a program. [Background technology]

[0002] As part of research into people flow estimation, a people flow estimation device has been proposed that acquires signals transmitted from terminals and estimates the number of people using identifiers in the signals (see, for example, Patent Document 1).

[0003] Also, a CSI (Channel Status Information) information processing method for accurately estimating the number of people using radio propagation path information is known (see, for example, Non-Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-128599 [Non-patent literature]

[0005] [Non-Patent Document 1] H.ZOU, Y.ZHOU, J.YANG, W.GU, L.XIE AND C.SPANOS,“FREECOUNT:DEVICE-FREE CROWD COUNTING WITH COMMODITY WIFI” GLOBECOM 2017-2017 IEEE GLOBAL COMMUNICATIONS CONFERENCE,SINGAPORE,2017,PP.1-6,DOI:10.1109 / GLOCOM.2017.8255034. Summary of the Invention [Problem to be solved by the invention]

[0006] The method of Patent Document 1 is a method for estimating the number of people using only signal ID information such as MAC addresses, while the method of Non-Patent Document 1 is a method for estimating the number of people using only CSI information.

[0007] In other words, both the methods of Patent Document 1 and Non-Patent Document 1 rely solely on estimation using signal ID information or CSI information, and therefore have the problem that further improvement in accuracy cannot be expected.

[0008] The embodiments of the present invention provide a target number estimation system, a target number estimation method, and a program that can estimate the number of people present with higher accuracy. [Means for solving the problem]

[0009] According to an embodiment, the object number estimation system includes a first object number estimation unit, a wireless propagation path acquisition unit, and a second object number estimation unit. The first object number estimation unit estimates the number of objects present in the first area based on wireless information, excluding wireless propagation path information, or image information related to the first area. The wireless propagation path acquisition unit acquires wireless propagation path information based on wireless signals transmitted from wireless devices in the first area. The second object number estimation unit estimates the final number of objects through machine learning using the estimation results from the first object number estimation unit and the wireless propagation path information acquired by the wireless propagation path acquisition unit as input information. The second object number estimation unit selects a model to be used in the machine learning estimation based on the estimation results from the first object number estimation unit. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a target number estimation system according to an embodiment. [Figure 2] FIG. 1 is a diagram for explaining an overview of target number determination using CSI in the target number estimation system according to the embodiment. [Figure 3] 3A and 3B are diagrams for explaining an overall model and a plurality of partial models in the object number estimation system according to the embodiment; [Figure 4]FIG. 10 is a diagram for further explaining a plurality of partial models in the target number estimation system according to the embodiment. [Figure 5] FIG. 10 is a diagram for explaining a method for selecting an appropriate model in the target number estimation system according to the embodiment. [Figure 6] 10 is a flowchart showing the procedure of a process for estimating the number of people present in the target number estimation system according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments will be described with reference to the drawings.

[0012] FIG. 1 is a diagram showing an example of the configuration of a target number estimation system 1 according to an embodiment.

[0013] In recent years, people flow estimation has been studied as part of building solutions, and people flow estimation using camera footage has been considered, but from the perspective of the cost of the installed equipment, blind spots, security, etc., people flow estimation using non-video systems is also being considered.

[0014] Wireless LAN (Local Area Network) is likely already installed as building equipment, and since sensing is possible without installing new equipment, it is expected to be one of the sensing information sources for non-visual estimation. Basically, the number of users present in the area covered by each access point (AP) that forms the service area of ​​the wireless network is counted as the number of devices connected to that access point. However, there are also users who do not own a device, and users who own multiple devices, making it difficult to accurately estimate the number of users present based on connection count information alone.

[0015] On the other hand, population estimation using CSI has also attracted attention, and many studies have been conducted on this topic, but there is still room for improvement in the accuracy of the estimation.

[0016] The target number estimation system 1 of the embodiment realizes a mechanism for improving the accuracy of people number estimation using wireless propagation path information by using information on the number of terminals connected to APs, which will be described in detail below. Note that this mechanism is not limited to non-video-based people flow estimation, and can also be realized by, for example, utilizing already installed cameras and combining them with video-based people flow estimation.

[0017] 1, the object number estimation system 1 includes a first object estimation unit 11, a wireless propagation path acquisition unit 12, and a second object estimation unit 13. The first object estimation unit 11, the wireless propagation path acquisition unit 12, and the second object estimation unit 13 may be configured by a central processing unit (CPU) executing a program, or may be configured as hardware such as an electrical circuit. Furthermore, the first object estimation unit 11, the wireless propagation path acquisition unit 12, and the second object estimation unit 13 may be configured within the same hardware, or may be configured on separate hardware and exchange information via an interface such as an Ethernet (registered trademark) cable.

[0018] The first target estimation unit 11 estimates the number of targets present in the target area, for example, using wireless information about terminals connected to APs covering the target area, more specifically, identifiers such as MAC addresses in signals transmitted from the terminals, or image information of images captured of the target area.

[0019] The first object estimation unit 11 can use various known methods to estimate the number of objects. If the information about the target area is wireless information, the first object estimation unit 11 detects, for example, the number of terminals connected to the AP. If the information about the target area is image information, the first object estimation unit 11 analyzes the images to detect the number of subject images that appear to be objects. The object number estimation system 1 of the embodiment treats the result of estimation by the first object estimation unit 11, i.e., the estimated number of objects, as a provisional estimated number of objects (primary estimation result).

[0020] The wireless propagation path acquisition unit 12 acquires CSI from a signal transmitted from a terminal connected to the AP. Note that, although it is assumed here that the wireless propagation path acquisition unit 12 receives a signal from a terminal connected to the AP and acquires CSI from the received signal, this is not the only method, and for example, a method in which another device or system receives a signal transmitted from a terminal connected to the AP and acquires CSI from the received signal, and the wireless propagation path acquisition unit 12 receives CSI from the other device or system, may also be applied.

[0021] Second target estimation unit 13 estimates the final number of targets (obtains a secondary estimation result) through machine learning using the result of estimation by first target estimation unit 11 and the CSI acquired by wireless propagation path acquisition unit 12 as input information. At this time, second target estimation unit 13 selects a model to be used in the estimation by machine learning, based on the result of estimation by first target estimation unit 11.

[0022] Thus, in the object number estimation system 1 of the embodiment, compared to when the second object estimation unit 13 uses one large overall model including the number of objects provisionally estimated by the first object estimation unit 11 to estimate the final number of objects, multiple partial models with a limited number of objects are prepared, and the second object estimation unit 13 selects and uses a partial model to use from among them based on the number of objects provisionally estimated by the first object estimation unit 11 to estimate the final number of objects, thereby making it possible to estimate the number of objects from models with a narrowed-down list of candidates, and therefore improving estimation accuracy can be expected. The overall model and multiple partial models will be described later.

[0023] Here, an overview of determining the number of objects using CSI will be described with reference to FIG.

[0024] In supervised learning, a model (DNN, CNN, etc.) is given the data to be judged and its label, and trained to select the desired label when given unknown data. In this embodiment, the input data is CSI data, and the data is obtained when there are X people (or X pieces) of the target object in the target range (area).

[0025] As an example, Figure 2 shows the behavior when the target object is a human and 11 types of data are prepared, ranging from a state where there are no humans in the target range (0 people) to a state where there are 10 people in the target range.

[0026] As shown in Figure 2(A), during training, 11 types of data are input and processed so that labels corresponding to the input data are obtained through the model. Meanwhile, as shown in Figure 2(B), during operation, actually obtained CSI data is input and an estimated number of people X is output. Since training was performed using data from 0 to 10 people, the estimated output X generally takes a value between 0 and 10.

[0027] Next, the overall model and the multiple partial models will be described.

[0028] As an example, consider continuing to estimate the number of people in a target area where there are potentially between 0 and 10 people.

[0029] First, Fig. 3(A) shows an overall model with 11 types of input CSI data. As in Fig. 2, this model uses all types of acquired CSI data for learning, and when unknown CSI data is input, it determines whether the estimated number of people is between 0 and 10.

[0030] Secondly, Fig. 3(B) shows a partial model in which input data is limited and data on only 2 to 6 people is input. Since this partial model has only learned data on 2 to 6 people, it is generally used as a model for determining which of the 2 to 6 people the input CSI data corresponds to.

[0031] Comparing the two models in Figure 3(A) and Figure 3(B), if the number of subjects to be estimated is assumed to be between 2 and 6, the partial model in Figure 3(B) will provide higher estimation accuracy because it narrows down the candidates.

[0032] Next, the plurality of partial models will be further described with reference to Fig. 4. As in Fig. 3(B), partial models with five types of input CSI data are listed in Fig. 4.

[0033] In the case of estimating the number of subjects up to 10, as in this case, up to seven partial models can be created by inputting five consecutive types of CSI data and training them. Here, the CSI data for a single subject is included in both the top and second partial models, and in this way, different models may include the same data set as input. Furthermore, partial models are not limited to five consecutive types, and it is also possible to create partial models using three consecutive types or six consecutive types.

[0034] The target number estimation system 1 according to the embodiment can estimate the number of people present with higher accuracy by selecting an appropriate model from a plurality of models that are a collection of such partial models, for example.

[0035] Next, a method for selecting an appropriate model will be described.

[0036] In the object number estimation system 1 according to the embodiment, it is desirable to select a supervised learning model that includes the number of objects estimated by the first object estimation unit 11 as an input label. For example, if the number of objects estimated by the first object estimation unit 11 is four, it is desirable to perform estimation using the partial model shown in FIG. 3(B) that includes CSI data for four people (the third partial model among the seven partial models shown in FIG. 4). If the partial model shown in FIG. 3(B) is used even though the number of objects estimated by the first object estimation unit 11 is eight, the estimation result of the second object estimation unit 13 will be between two and six people, regardless of the input data, and there is a high possibility that the correct result will not be obtained.

[0037] In other words, the embodiment of the target number estimation system 1 can improve the accuracy of the target number secondary estimation result (estimation result of the second target estimation unit 13) by appropriately utilizing the target number primary estimation result (estimation result of the first target estimation unit 11).

[0038] When the number of subjects estimated by the first subject estimation unit is eight, it is desirable to use the bottom-most partial model among the seven partial models in FIG.

[0039] In addition, the object number estimation system 1 of the embodiment may select a model using, in addition to the object number estimated by the first object estimation unit 11, information on the likelihood of the object number (accuracy / error / reliability / distribution, etc.) as further input data.

[0040] Suppose that the accuracy of the estimation result of first object estimation unit 11 is very high, and for example, when the estimated number of people result is N, it is known that the possible error is ±1. In this case, as shown in FIG. 5, if a partial model is trained using CSI data of ±1 centered around N, and three types of training data are used, the second object estimation unit 13 can obtain the most accurate secondary estimation result.

[0041] On the other hand, if the accuracy of the estimation result of the first target estimation unit 11 is low, the primary estimation result is N, and the possible error is ±3, a model with seven types of training data trained using CSI data of ±3 centered around N should be used.

[0042] If a model with three types of training data trained using training data ±1 centered around N is used, a correct result will never be obtained if the true number is N+2 or greater or N-2. Therefore, as described above, by determining the size of the partial model to be selected depending on the likelihood, the subject number estimation system 1 of the embodiment can make more accurate estimations.

[0043] FIG. 6 is a flowchart showing the procedure of the number of people present estimation process in the target number estimation system 1 of the embodiment.

[0044] After the start of estimating the number of people present, the first object estimation unit 11 performs a primary estimation of the number of people (S101). From this primary estimation, a primary object number estimation result is obtained. Using this primary object number estimation result, the object number estimation system 1 selects a model to be used in the second object estimation unit 13 (S102).

[0045] In parallel with the processing of steps S101 and S102, the wireless propagation path acquisition unit 12 acquires wireless propagation path information (S103).

[0046] Then, by inputting the wireless propagation path information obtained in S103 into the model selected in S102, a secondary estimation result of the number of objects is obtained from the second object estimation unit 13 (S104), and the number of people present estimation process is completed.

[0047] As described above, in the object number estimation system 1 of the embodiment, the estimation accuracy of the second object estimation unit 13 can be improved by using the primary estimation result to select a model to be used in the second object estimation unit 13.

[0048] Furthermore, in the object number estimation system 1 of the embodiment, wireless propagation path information is divided into multiple data sets, multiple models learned in each data set are stored, and the model required to perform the most accurate secondary estimation can be selected based on the estimation result of the first object estimation unit 11.

[0049] Furthermore, in the object number estimation system 1 of the embodiment, by selecting a supervised learning model that includes the object number estimated by the first object estimation unit 11 as an input label, the secondary estimation result obtained from that model contains at least the same result as the primary estimation result. As a result, it is possible to perform a more accurate secondary estimation based on the primary estimation result.

[0050] Furthermore, in the embodiment of the target number estimation system 1, by adding the probability of the primary estimation result as input data and selecting a model, an appropriate model can be selected according to that probability, and more accurate secondary estimation results can be obtained.

[0051] Furthermore, in the object number estimation system 1 of the embodiment, the same labeled radio propagation path information data set can be input even between different models. In other words, by allowing overlapping data sets between different models, the object number estimation system 1 of the embodiment can increase the number of models to choose from, making it possible to select a more appropriate model in more detail depending on the situation, and further improving estimation accuracy.

[0052] The present invention is not limited to the above-described embodiments, and the components can be modified and embodied in practice without departing from the spirit of the invention. Furthermore, various inventions can be created by appropriately combining multiple components disclosed in the above-described embodiments. For example, some components may be omitted from all the components shown in the embodiments. Furthermore, components from different embodiments may be appropriately combined. [Explanation of symbols]

[0053] 1...object number estimation system, 11...first object estimation unit, 12...wireless propagation path acquisition unit, 13...second object estimation unit.

Claims

1. a first object number estimation unit that estimates the number of objects present in the first area based on wireless information, excluding wireless propagation path information, or image information, regarding the first area; a wireless propagation path acquisition unit that acquires wireless propagation path information based on a wireless signal transmitted from a wireless device within the first area; a second object number estimation unit that estimates a final number of objects by machine learning using the result of estimation by the first object number estimation unit and wireless propagation path information acquired by the wireless propagation path acquisition unit as input information; The second target number estimation unit selects a model to be used in the estimation by machine learning based on the result of estimation by the first target number estimation unit. Target population estimation system.

2. The target number estimation system according to claim 1 , wherein the first target number estimation unit estimates the target number based on the number of terminal connections to an access point managed by the access point that forms a wireless network service area in the first area.

3. The object number estimation system according to claim 1 , wherein the first object number estimation unit estimates the number of objects by analyzing an image of the first area.

4. 2. The system for estimating the number of objects according to claim 1, wherein the model to be selected by the second object number estimation unit and used in the machine learning estimation is a plurality of independent models trained by dividing wireless propagation path information labeled with the number of objects in a range up to a maximum expected estimated number of objects into a plurality of data sets and inputting data sets of different combinations from among the plurality of data sets.

5. The object number estimation system according to claim 4 , wherein the second object number estimation unit selects a supervised learning model in which the object number estimated by the first object number estimation unit is included as an input label.

6. The models used in the machine learning estimation are a plurality of independent models trained by inputting a group of datasets containing different numbers of labels, The second object number estimation unit The likelihood of the result estimated by the first object number estimation unit is further used as input information from the first object number estimation unit, a model having a smaller number of labels included in a data set is selected as the likelihood of the estimation result estimated by the first object number estimation unit increases; The system for estimating the number of subjects according to claim 4 .

7. The system for estimating the number of objects according to claim 4 , wherein the plurality of independent models can input data sets of wireless propagation path information that are labeled identically even between different models.

8. provisionally estimating the number of objects present in the first area based on wireless information, excluding wireless propagation path information, or image information, relating to the first area; receiving a radio signal transmitted from a radio device within the first area, and acquiring radio propagation path information from the received signal; using the provisionally estimated result and the acquired wireless propagation path information as input information, and estimating the final number of targets through machine learning; The estimation of the final number of subjects includes selecting a model to be used in the machine learning estimation based on the provisional estimation result. Methods for estimating the number of subjects.

9. Computer, provisionally estimating the number of objects present in the first area based on wireless information, excluding wireless propagation path information, or image information, relating to the first area; receiving a radio signal transmitted from a radio device within the first area, and acquiring radio propagation path information from the received signal; The final number of targets is estimated by machine learning using the provisionally estimated result and the acquired wireless propagation path information as input information. This is a program to make it work like this. The estimation of the final number of subjects includes selecting a model to be used in the machine learning estimation based on the provisional estimation result. program.

Images