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 studies 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 estimating the number of people with high accuracy using radio channel information is known (see, for example, Non-Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] 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, whereas 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 involve estimation using either signal ID information or CSI information alone, and therefore there is a problem in 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 capable of estimating 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 by machine learning using the result of estimation by 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 estimation by machine learning based on the result of estimation by the first object number estimation unit. [Brief description 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. [Diagram 2] FIG. 2 is a diagram for explaining an overview of target number determination using CSI in the target number estimation system according to the embodiment. [Diagram 3] 3A and 3B are diagrams for explaining an overall model and a plurality of partial models in the target number estimation system according to the embodiment. [Figure 4]FIG. 4 is a diagram for further explaining a plurality of partial models in the target number estimation system according to the embodiment. [Diagram 5] FIG. 4 is a diagram for explaining a method for selecting an appropriate model in the target number estimation system according to the embodiment. [Figure 6] 1 is a flowchart showing the procedure of a presence number estimation process in the target number estimation system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

[0012] FIG. 1 is a diagram showing an example of a 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 studies are being conducted on people flow estimation using camera footage, etc., but from the standpoint of the cost of the installed equipment, blind spots, security, etc., non-video based people flow estimation methods are also being considered.

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

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

[0016] The target number estimation system 1 of the embodiment realizes a mechanism for improving the accuracy of the number of people estimation using wireless propagation path information by using the information on the number of terminals connected to the AP, and this point 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 combining, for example, a video-based people flow estimation by utilizing an already installed camera.

[0017] As shown in Fig. 1, the target number estimation system 1 has a first target estimation unit 11, a wireless propagation path acquisition unit 12, and a second target estimation unit 13. The first target estimation unit 11, the wireless propagation path acquisition unit 12, and the second target estimation unit 13 may be configured by a CPU (Central Processing Unit) executing a program, or may be configured as hardware such as an electric circuit. In addition, the first target estimation unit 11, the wireless propagation path acquisition unit 12, and the second target estimation unit 13 may be configured in the same hardware, or may be configured on separate hardware and may transfer 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 an AP covering the target area, more specifically, identifiers such as MAC addresses in signals transmitted from the terminals, or image information of images capturing the target area.

[0019] The first object estimation unit 11 can estimate the number of objects using various known methods. When the information on the object area is wireless information, the first object estimation unit 11 detects, for example, the number of terminals connected to an AP. When the information on the object area is image information, the first object estimation unit 11 analyzes 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 by itself 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] The second target estimation unit 13 estimates the final number of targets by machine learning using the result of estimation by the first target estimation unit 11 and the CSI acquired by the wireless propagation path acquisition unit 12 as input information (obtains a secondary estimation result). At that time, the second target estimation unit 13 selects a model to be used in the estimation by machine learning based on the result of estimation by the first target estimation unit 11.

[0022] Thus, in the object number estimation system 1 of the embodiment, compared to a case where the second object estimation unit 13 estimates the final number of objects using one large overall model including the number of objects provisionally estimated by the first object estimation unit 11, 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 be used 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 candidates narrowed down in advance, and thus improving the estimation accuracy can be expected. The overall model and multiple partial models will be described later.

[0023] Here, an overview of target number determination using CSI will be described with reference to FIG.

[0024] In the case of supervised learning, the data to be judged and its label are given to a model (DNN, CNN, etc.), and the model learns to select the desired label when unknown data is given. In the present 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] FIG. 2 shows, as an example, the operation 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 Fig. 2(A), 11 types of data are input during learning, and the model processes the input data so that labels corresponding to the input data are obtained. Meanwhile, as shown in Fig. 2(B), during operation, the actually obtained CSI data is input, and the estimated number of people X is output. Since data from 0 to 10 people was used during learning, 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 where there can be between 0 and 10 humans within the target area.

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

[0030] Secondly, Fig. 3 shows a partial model in which input data is limited and only data of 2 to 6 people is input as Fig. 3(B). Since this partial model learns only data of 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), when the assumption is that the number of subjects to be estimated is between 2 and 6, estimation using the partial model in Figure 3(B) will result in higher estimation accuracy because the candidates are narrowed down.

[0032] Next, the multiple 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 people, as in this case, up to seven types of partial models can be created that are trained by inputting five consecutive types of CSI data. Here, CSI data for a single subject is included in both the top partial model and the second partial model, and in this way, different models may include the same data set as input. Also, partial models are not limited to five consecutive types, and it is also possible to create partial models with three consecutive types or six consecutive types.

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

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

[0036] In the object number estimation system 1 of 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 estimate using the partial model including CSI data of four people in FIG. 3(B) (the third partial model among the seven partial models in FIG. 4). If the partial model in FIG. 3(B) is used even though the number of objects estimated by the first object estimation unit is eight, the estimation result of the second object estimation unit 13 will be either two or 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 bottommost 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 by further using information on the accuracy (precision / error / reliability / distribution, etc.) of the object number estimated by the first object estimation unit 11 as 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 expected error is ±1. In that case, as shown in Fig. 5, if a partial model is trained using CSI data of ±1 centered on N, a secondary estimation result with the highest accuracy can be obtained in second object estimation unit 13 by using a model with three types of training data.

[0041] On the other hand, if the accuracy of the estimation result of the first object 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 centered on N and ±3 should be used.

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

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

[0044] After the in-person number estimation starts, the first object estimation unit 11 performs a primary object number estimation (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 processes 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 object number estimation result 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 according to the embodiment, the estimation accuracy of the second object estimation unit 13 can be improved by selecting a model to be used in the second object estimation unit 13 using the primary estimation result.

[0048] Furthermore, in the target 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 target estimation unit 11.

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

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

[0051] Furthermore, in the target number estimation system 1 of the embodiment, the same labeled radio channel information data set may be input even between different models. In other words, by allowing overlapping of data sets between different models, the target number estimation system 1 of the embodiment can increase the number of model options, and can select a more appropriate model in more detail depending on the situation, thereby improving the estimation accuracy.

[0052] The present invention is not limited to the above-described embodiment, and the components can be modified and embodied in the implementation stage without departing from the gist of the invention. In addition, various inventions can be formed by appropriately combining the multiple components disclosed in the above-described embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, components from different embodiments may be appropriately combined. [Explanation of symbols]

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

Claims

1. a first object number estimation unit that estimates the number of objects present in a first area based on wireless information, excluding wireless propagation path information, or image information, related to the first area; a wireless propagation path acquiring 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 estimating unit that estimates a final number of objects by machine learning using, as input information, a result estimated by the first object number estimating unit and wireless propagation path information acquired by the wireless propagation path acquiring unit, 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 object number estimation system according to claim 1 , wherein the first object number estimation unit estimates the object number based on the number of terminals connected to an access point managed by the access point that forms a service area of ​​a wireless network in the first area.

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

4. 2. The system for estimating the number of targets according to claim 1, wherein the model to be selected by the second target number estimation unit and used in the estimation by machine learning is a plurality of independent models that are trained by dividing wireless propagation path information labeled with the number of targets in a range up to a maximum estimated number of targets into a plurality of data sets, and inputting a group of data sets that are 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 data sets each having a different number of labels included therein, The second target number estimation unit, The likelihood of the result estimated by the first object number estimation unit is further inputted 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 is higher. The subject number estimation system according to claim 4.

7. The target number estimation system according to claim 4 , wherein the independent models can input a data set of wireless channel information that is labeled in the same way even between different models.

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

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

Images