Propagation characteristic estimation device, propagation characteristic estimation system, propagation characteristic estimation method, and propagation characteristic estimation program

Abstract

A propagation characteristic estimation device according to one embodiment: generates, for a structure between a transmission station and a reception station, an upper view image showing a cross section viewed from an upper side based on the height of the transmission station and the reception station, and a side view image showing a cross section viewed from the side; extracts a first feature parameter by inputting the upper view image to a convolutional neural network; extracts a second feature parameter by inputting the side view image to a convolutional neural network; and estimates a propagation characteristic by inputting the first feature parameter and the second feature parameter to a fully-connected neural network.

Description

Propagation characteristic estimation device, propagation characteristic estimation system, propagation characteristic estimation method, and propagation characteristic estimation program

[0001] The present invention relates to a technique for estimating propagation characteristics of radio waves between a transmitting station and a receiving station in a wireless communication system.

[0002] In wireless communication systems, there are known techniques for estimating propagation characteristics (propagation loss) of radio waves between a transmitter (Tx) and a receiver (Rx). For example, Patent Literature 1 and Non-Patent Literature 1 disclose estimation models for estimating propagation characteristics of radio waves by inputting feature parameters extracted using two convolutional neural networks (CNNs) into a fully-connected neural network (FNN).

[0003] In addition, in urban macrocell environments, when the Rx is far from the Tx in a non-line-of-sight environment, "over-rooftop propagation," which is radio wave propagation over the roofs of buildings between the Tx and Rx, may become dominant.

[0004] International Publication No. 2023 / 127106

[0005] N. Kuno, M. Inomata, M. Sasaki and W. Yamada, "Deep Learning-Based Path Loss Prediction Using Side-View Images in an UMa Environment", 2022 16th European Conference on Antennas and Propagation (EuCAP), 2022, pp. 1-5

[0006] However, in the past, only the outer surface of the structure between the transmitting station and the receiving station was considered, and the influence on radio waves from inside the structure could not be taken into account, making it difficult to accurately estimate the propagation characteristics of radio waves.

[0007] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a propagation characteristics estimation device, a propagation characteristics estimation system, a propagation characteristics estimation method, and a propagation characteristics estimation program that can accurately estimate the propagation characteristics of radio waves by taking into account the influence on radio waves inside structures between a transmitting station and a receiving station.

[0008] A propagation characteristics estimation device according to one embodiment of the present invention is a propagation characteristics estimation device that estimates propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, and includes a first image generation unit that generates, as top-view images, two-dimensional images showing cross sections of structures between the transmitting station and the receiving station based on heights of the transmitting station and the receiving station, a two-dimensional image showing the distance from the transmitting station as viewed from above, and a two-dimensional image showing the distance from the receiving station as viewed from above; a second image generation unit that generates a two-dimensional image indicating distance as a side-view image; a first CNN unit that extracts a first feature parameter by inputting each of the top-view images generated by the first image generation unit into a convolutional neural network; a second CNN unit that extracts a second feature parameter by inputting each of the side-view images generated by the second image generation unit into a convolutional neural network; and an FNN unit that estimates the propagation characteristics by inputting the first feature parameter extracted by the first CNN unit and the second feature parameter extracted by the second CNN unit into a fully connected neural network.

[0009] Furthermore, a propagation characteristics estimation system according to one embodiment of the present invention is a propagation characteristics estimation system for estimating propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristics estimation system including: a first image generation unit that generates, as top-view images, two-dimensional images showing cross sections of structures between the transmitting station and the receiving station based on heights of the transmitting station and the receiving station, two-dimensional images showing distances from the transmitting station as viewed from above, and two-dimensional images showing distances from the receiving station as viewed from above; a second image generation unit that generates, as side-view images, two-dimensional images showing cross sections of structures between the transmitting station and the receiving station as viewed from the side, two-dimensional images showing distances from the transmitting station as viewed from the side, and two-dimensional images showing distances from the receiving station as viewed from the side; a first CNN unit that extracts first feature parameters by inputting each of the top-view images generated by the first image generation unit to a convolutional neural network; The system is characterized by having a second CNN unit that extracts second feature parameters by inputting each of the side-view images generated by the image generation unit into a convolutional neural network; an FNN unit that estimates the propagation characteristics by inputting the first feature parameters extracted by the first CNN unit and the second feature parameters extracted by the second CNN unit into a fully connected neural network; a memory unit that stores verification data that is regarded as the propagation characteristics of actual radio waves between the transmitting station and the receiving station; an error calculation unit that compares the verification data stored in the memory unit with the propagation characteristics estimated by the FNN unit and calculates an error between the propagation characteristics estimated by the FNN unit and the verification data; and an update unit that updates parameters used by the first CNN unit to extract the first feature parameters and parameters used by the second CNN unit to extract the second feature parameters based on the error calculated by the error calculation unit.

[0010] A propagation characteristics estimation method according to one embodiment of the present invention is a propagation characteristics estimation method for estimating propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristics estimation method including a first image generation step of generating, as top-view images, two-dimensional images showing cross sections of structures between the transmitting station and the receiving station based on heights of the transmitting station and the receiving station, a two-dimensional image showing a distance from the transmitting station as viewed from above, and a two-dimensional image showing the distance from the receiving station as viewed from above, and a second image generation step of generating, as top-view images, two-dimensional images showing cross sections of structures between the transmitting station and the receiving station as viewed from the side, a two-dimensional image showing the distance from the transmitting station as viewed from the side, and a two-dimensional image showing the distance from the receiving station as viewed from the side, a first CNN step of extracting first feature parameters by inputting each of the side-view images generated by the second image generation step into a convolutional neural network; a second CNN step of extracting second feature parameters by inputting each of the side-view images generated by the second image generation step into a convolutional neural network; and an FNN step of estimating the propagation characteristics by inputting the first feature parameters extracted by the first CNN step and the second feature parameters extracted by the second CNN step into a fully connected neural network.

[0011] A propagation characteristics estimation program according to one embodiment of the present invention is a propagation characteristics estimation program executed by a propagation characteristics estimation device that estimates propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristics estimation program including: a first image generation unit that generates, as top-view images, a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station based on heights of the transmitting station and the receiving station, a two-dimensional image showing a distance from the transmitting station as viewed from above, and a two-dimensional image showing the distance from the receiving station as viewed from above; a first CNN unit that extracts a first feature parameter by inputting each of the side-view images generated by the second image generation unit into a convolutional neural network; a second CNN unit that extracts a second feature parameter by inputting each of the side-view images generated by the second image generation unit into a convolutional neural network; and an FNN unit that estimates the propagation characteristics by inputting the first feature parameter extracted by the first CNN unit and the second feature parameter extracted by the second CNN unit into a fully connected neural network.

[0012] According to the present invention, it is possible to accurately estimate the propagation characteristics of radio waves by taking into account the influence on radio waves within structures between a transmitting station and a receiving station.

[0013] 1 is a diagram illustrating an example of the configuration of a propagation characteristic estimation system in a learning stage according to an embodiment; FIG. 1(a) is a diagram schematically illustrating a state in which a transmitting station and a receiving station are connected by a straight line; FIG. 1(b) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as viewed from a side is acquired; FIG. 1(c) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as viewed from above is acquired; FIG. 1(a) is a diagram illustrating an example of a top-view image showing a cross section as viewed from above based on the heights of the transmitting station and the receiving station; FIG. 1(b) is a diagram illustrating an example of a top-view image showing the distance from the transmitting station as viewed from above; FIG. 1(c) is a diagram illustrating an example of a top-view image showing the distance from the receiving station as viewed from above; FIG. 1(a) is a diagram illustrating an example of a side-view image showing a cross section of a structure between the transmitting station and the receiving station as viewed from a side. 1(b) is a diagram illustrating a side-view image showing the distance from the transmitting station as viewed from the side. FIG. 1(c) is a diagram illustrating a side-view image showing the distance from the receiving station as viewed from the side. FIG. 1(a) is a diagram schematically illustrating a state in which a transmitting station and a receiving station are connected by a straight line. FIG. 1(b) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross-section of a structure between the transmitting station and the receiving station as viewed from the side is acquired. FIG. 1(c) is a diagram illustrating a height at which a cross-section of a structure as viewed from above is acquired. FIG. 1(d) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross-section of a structure between the transmitting station and the receiving station as viewed from above is acquired. FIG. 1(a) is a diagram schematically illustrating a state in which a transmitting station and a receiving station are connected by a straight line. FIG. 1(b) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross-section of a structure between the transmitting station and the receiving station as viewed from the side is acquired. 10(c) is a diagram illustrating a process of determining a height at which a cross section of a structure viewed from above is acquired. FIG. 10(d) is a diagram schematically illustrating a state in which a two-dimensional image showing a plurality of cross sections of a structure viewed from above between a transmitting station and a receiving station is acquired. FIG. 10(c) is a diagram illustrating a process of determining a height at which a cross section of a structure viewed from above is acquired. FIG. 10(d) is a diagram schematically illustrating a third example of a procedure in which an input image generation unit generates a cross section of a structure as an image. FIG. 10(c) is a diagram illustrating a process of determining a height at which a cross section of a structure viewed from above is acquired. FIG. 10(d) is a diagram schematically illustrating a1 is a diagram illustrating an example of the inside of a structure (indoor environment) for estimating radio wave propagation characteristics using a propagation characteristics estimation system; (a) is a diagram illustrating an example of a two-dimensional image showing a cross section viewed from the side of the inside of the structure generated by a propagation characteristics estimation device; (b) is a diagram illustrating an example of a two-dimensional image showing a cross section viewed from above of the inside of the structure generated by a propagation characteristics estimation device; and (c) is a diagram illustrating an example of a path in a rectangular parallelepiped room.

[0014] A propagation characteristics estimation system according to an embodiment will be described below with reference to the drawings. The propagation characteristics estimation system according to an embodiment has a neural network that performs machine learning, and is used in both a learning stage in which radio wave propagation characteristics are learned and an estimation stage in which radio wave propagation characteristics are estimated. The propagation characteristics estimation system according to an embodiment may have the same configuration or different configurations in the learning stage and the estimation stage.

[0015] 1 is a diagram illustrating an example of the configuration of a learning-stage propagation characteristics estimation system 1 according to one embodiment. The learning-stage propagation characteristics estimation system 1 according to one embodiment includes a propagation characteristics estimation device 2 that estimates propagation characteristics of radio waves between, for example, a transmitting station and a receiving station that perform wireless communication, and storage devices (storage units) 3, 4-1, and 4-2.

[0016] The storage device 4-1 is a database that stores data on structures and the like located between the transmitting station and the receiving station. For example, the storage device 4-1 stores a BIM (Building Information Modeling) model. The storage device 4-1 may also store LOD (Level of Details: LOD2, LOD3, LOD4, etc.), which indicates the level of detail of features included in the 3D city model.

[0017] The storage device 4-2 is a database that stores transmitting and receiving positions that indicate the respective positions of transmitting and receiving stations.

[0018] The storage device 3 is a database that stores verification data that is considered to be the propagation characteristics of actual radio waves between a transmitting station and a receiving station. For example, the storage device 3 stores, as verification data, measurement data (such as the received power of the receiving station) that is actually measured to measure the propagation characteristics of radio waves between a transmitting station and a receiving station, or simulation data.

[0019] The propagation characteristics estimation device 2 includes, for example, an input image generation unit 20, a model unit 22, an estimated data storage unit 24, an error calculation unit 26, and an update unit 28.

[0020] The input image generation unit 20 includes, for example, a first image generation unit 200 and a second image generation unit 202 .

[0021] The first image generation unit 200 generates top-view images of structures between the transmitting station and the receiving station, including a two-dimensional image showing a cross section from above based on the height of the transmitting station and the receiving station, a two-dimensional image showing the distance from the transmitting station from above, and a two-dimensional image showing the distance from the receiving station from above, and outputs these to the model unit 22. For example, the first image generation unit 200 generates top-view images using data on structures (such as BIM) and transmitting / receiving positions stored in the storage devices 4-1 and 4-2. The top-view images showing the distance from the transmitting station and the top-view images showing the distance from the receiving station are used to specify the position and coordinates of the structures. The top-view images can also be considered bird's-eye views.

[0022] The second image generation unit 202 generates side-view images of structures between the transmitting station and the receiving station, including a two-dimensional image showing a cross section as viewed from the side, a two-dimensional image showing the distance from the transmitting station as viewed from the side, and a two-dimensional image showing the distance from the receiving station as viewed from the side, and outputs these images to the model unit 22. For example, the second image generation unit 202 generates side-view images using data (such as BIM) of structures and transmitting / receiving positions stored in the storage devices 4-1 and 4-2. The side-view images showing the distance from the transmitting station and the side-view images showing the distance from the receiving station are used to specify the position and coordinates of the structures. The side-view images can also be referred to as side images.

[0023] Here, a first example of a procedure in which the input image generating unit 20 (first image generating unit 200 and second image generating unit 202) generates an image of a cross section of a structure will be described with reference to FIGS.

[0024] 2A and 2B are diagrams showing a first example of a procedure in which the input image generation unit 20 generates an image of a cross section of a structure. FIG. 2A is a diagram showing a state in which a transmitting station and a receiving station are connected by a straight line. FIG. 2B is a diagram showing a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as seen from the side is acquired. FIG. 2C is a diagram showing a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as seen from above is acquired. FIG. 3 is a diagram showing a first example of a procedure in which the input image generation unit 20 generates an image of a cross section of a structure.

[0025] First, the input image generating unit 20 connects the transmitting and receiving points (the transmitting station and the receiving station) with a straight line (FIG. 2(a), FIG. 3, S100).

[0026] Next, the input image generation unit 20 acquires an image of a cross section perpendicular to the line (FIG. 2B, S102 in FIG. 3). Specifically, the second image generation unit 202 generates a side-view image showing a cross section of the structure between the transmitting station and the receiving station as seen from the side.

[0027] Next, the input image generation unit 20 acquires an image of a plane rotated 90 degrees around the axis of the straight line connecting the transmitting and receiving points with respect to the acquired cross section (FIG. 2(c), FIG. 3S104). Specifically, the first image generation unit 200 generates a top-view image showing a cross section as seen from above based on the heights of the transmitting station and the receiving station. Note that the input image generation unit 20 may acquire cross sections at multiple heights.

[0028] Then, the input image generation unit 20 uses the acquired images as input data for machine learning in the first image generation unit 200 and the second image generation unit 202, respectively (FIG. 3, S106).

[0029] 4A and 4B are diagrams illustrating top-view images generated by the first image generation unit 200. Fig. 4A is a diagram illustrating a top-view image showing a cross section viewed from above based on the heights of the transmitting station and the receiving station. Fig. 4B is a diagram illustrating a top-view image showing the distance from the transmitting station viewed from above. Fig. 4C is a diagram illustrating a top-view image showing the distance from the receiving station viewed from above.

[0030] 4A to 4C, the first image generator 200 generates, for example, three types of top-view images. The top-view images are two-dimensional images covering, for example, a rectangular area of ​​128 m x 128 m, and the rectangular area is divided into 2 m x 2 m meshes, resulting in a 64 x 64 mesh configuration.

[0031] 5A and 5B are diagrams illustrating side-view images generated by the second image generation unit 202. Fig. 5A is a diagram illustrating a side-view image showing a cross section of a structure between a transmitting station and a receiving station as viewed from the side. Fig. 5B is a diagram illustrating a side-view image showing the distance from the transmitting station as viewed from the side. Fig. 5C is a diagram illustrating a side-view image showing the distance from the receiving station as viewed from the side.

[0032] The xy plane defining the side-view image is perpendicular to the horizontal plane. The x direction is the horizontal direction from the transmitting station to the receiving station. The y direction is the vertical direction perpendicular to the x direction. In other words, the side-view image is, for example, an image of a predetermined rectangular area.

[0033] Alternatively, the input image generating unit 20 may generate an image of the cross section of a structure by another procedure. Here, a second example of the procedure by which the input image generating unit 20 (the first image generating unit 200 and the second image generating unit 202) generates an image of the cross section of a structure will be described with reference to FIGS.

[0034] FIG. 6 is a diagram schematically illustrating a second example of a procedure in which the input image generation unit 20 generates an image of a cross section of a structure. FIG. 6( a) is a diagram schematically illustrating a state in which a transmitting station and a receiving station are connected by a straight line. FIG. 6( b) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as seen from the side is acquired. FIG. 6( c) is a diagram illustrating an example of a height at which a cross section of a structure as seen from above is acquired. FIG. 6( d) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as seen from above is acquired. FIG. 7 is a diagram illustrating a second example of a procedure in which the input image generation unit 20 generates an image of a cross section of a structure.

[0035] First, the input image generating unit 20 connects the transmitting and receiving points (the transmitting station and the receiving station) with a straight line (FIG. 6(a), FIG. 7, S200).

[0036] Next, the input image generation unit 20 acquires an image of a cross section perpendicular to the line (FIG. 6B, S202 in FIG. 7). Specifically, the second image generation unit 202 generates a side-view image showing a cross section of the structure between the transmitting station and the receiving station as seen from the side.

[0037] Next, the input image generating unit 20 calculates the average height of the transmitting and receiving points (S204 in FIG. 7), and calculates the average height of the transmitting and receiving points (FIG. 6(c), S206 in FIG. 7).

[0038] Then, the input image generation unit 20 acquires an image of a horizontal cross section at the calculated average height of the transmitting and receiving points (FIG. 6(d), FIG. 7S208). Specifically, the first image generation unit 200 generates an upper-view image showing a cross section as seen from above based on the heights of the transmitting station and the receiving station.

[0039] Furthermore, the input image generating unit 20 (the first image generating unit 200 and the second image generating unit 202) may generate an image of a cross section of a structure according to the procedures shown in FIGS.

[0040] FIG. 8 is a diagram schematically illustrating a third example of a procedure in which the input image generation unit 20 generates an image of a cross section of a structure. FIG. 8( a) is a diagram schematically illustrating a state in which a transmitting station and a receiving station are connected by a straight line. FIG. 8( b) is a diagram schematically illustrating a state in which a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as seen from the side is acquired. FIG. 8( c) is a diagram illustrating a process of determining a height at which a cross section of a structure as seen from above is acquired. FIG. 8( d) is a diagram schematically illustrating a state in which a two-dimensional image showing multiple cross sections of a structure between the transmitting station and the receiving station as seen from above is acquired. FIG. 9 is a diagram illustrating a third example of a procedure in which the input image generation unit 20 generates an image of a cross section of a structure.

[0041] First, the input image generating unit 20 connects the transmitting and receiving points (the transmitting station and the receiving station) with a straight line (FIG. 8(a), FIG. 9, S300).

[0042] Next, the input image generation unit 20 acquires an image of a cross section perpendicular to the line (FIG. 8B, S302 in FIG. 9). Specifically, the second image generation unit 202 generates a side-view image showing a cross section of the structure between the transmitting station and the receiving station as seen from the side.

[0043] Next, the input image generating unit 20 calculates the average height of the transmitting and receiving points (FIG. 8(c), FIG. 9, S304).

[0044] Then, the input image generation unit 20 acquires images of horizontal cross sections at the calculated average heights of the transmitting and receiving points (transmission height and reception height) (FIG. 8(d), FIG. 9S306). Specifically, the first image generation unit 200 generates an upper-view image showing a cross section as seen from above based on the heights of the transmitting station and the receiving station.

[0045] The model unit 22 (FIG. 1) includes, for example, a first CNN unit 220, a second CNN unit 222, and an FNN unit 224, and is configured with a CNN part that uses CNN and an FNN part that uses FNN. FIG. 10 is a diagram schematically illustrating the functions of the model unit 22.

[0046] The first CNN unit 220 has an internal CNN, and inputs each of the top-view images generated by the first image generation unit 200 into a convolutional neural network to extract first feature parameters and output them to the FNN unit 224.

[0047] The second CNN unit 222 has an internal CNN, and inputs each of the side view images generated by the second image generation unit 202 into a convolutional neural network to extract second feature parameters and output them to the FNN unit 224.

[0048] The FNN unit 224 has an internal FNN, and inputs the first feature parameters extracted by the first CNN unit 220 and the second feature parameters extracted by the second CNN unit 222 into a fully connected neural network to estimate the propagation characteristics (propagation loss L) of radio waves between the transmitting station and the receiving station, and outputs the estimated data to the estimated data storage unit 24.

[0049] The FNN unit 224 may input system parameters related to the wireless communication system to the FNN together with the first and second characteristic parameters. The system parameters include, for example, the frequency used by the wireless communication system, the height of the Tx antenna, the height of the Rx antenna, etc.

[0050] The estimated data storage unit 24 is a storage unit that stores the propagation characteristics of radio waves estimated by the FNN unit 224 .

[0051] The error calculation unit 26 compares the verification data stored in the memory device 3 with the propagation characteristics stored in the estimated data storage unit 24, calculates the error between the propagation characteristics estimated by the FNN unit 224 and the verification data, and outputs the error to the update unit 28.

[0052] The update unit 28 updates the parameters used by the first CNN unit 220 to extract the first feature parameter and the parameters used by the second CNN unit 222 to extract the second feature parameter, based on the error calculated by the error calculation unit 26. For example, the update unit 28 updates the parameters until the error calculated by the error calculation unit 26 converges to a predetermined level or less. The update unit 28 may also update the parameters used by the FNN unit 224.

[0053] That is, the propagation characteristics estimation system 1 trains the model unit 22 using the training data, checks the convergence of the error using the verification data, and ends the training when the error has converged.

[0054] Next, a configuration example of a propagation characteristics estimation system 1 at an estimation stage according to an embodiment will be described. Fig. 11 is a diagram showing a configuration example of the propagation characteristics estimation system 1 at an estimation stage according to an embodiment. In the configuration example of the propagation characteristics estimation system 1 at an estimation stage shown in Fig. 11, components that are substantially the same as those of the propagation characteristics estimation system 1 at a learning stage shown in Fig. 1 are assigned the same reference numerals.

[0055] The propagation characteristics estimation system 1 in the estimation stage includes a propagation characteristics estimation device 2 and storage devices 4-1 and 4-2. Here, the propagation characteristics estimation device 2 includes an input image generation unit 20, a model unit 22, an estimated data storage unit 24, and an output unit 29, and estimates the propagation characteristics (propagation loss L) of radio waves using a trained model.

[0056] The output unit 29 outputs the propagation characteristics of the radio waves stored in the estimated data storage unit 24, for example, by displaying them.

[0057] In this way, the propagation characteristic estimation system 1 according to one embodiment generates a two-dimensional image showing a cross section of a structure between the transmitting station and the receiving station as viewed from above and a two-dimensional image showing a cross section as viewed from the side, and estimates the propagation characteristics of radio waves. This makes it possible to accurately estimate the propagation characteristics of radio waves by taking into account the influence on radio waves inside the structure between the transmitting station and the receiving station.

[0058] Note that each function of the propagation characteristics estimation device 2 may be partially or entirely configured by hardware such as a programmable logic device (PLD) or a field programmable gate array (FPGA), or may be configured as a program executed by a processor such as a CPU.

[0059] For example, the propagation characteristics estimation device 2 can be realized using a computer and a program, and the program can be recorded on a storage medium or provided via a network.

[0060] Fig. 12 is a diagram illustrating an example of a hardware configuration of a propagation characteristics estimation device 2 according to an embodiment. As illustrated in Fig. 12, the propagation characteristics estimation device 2 has, for example, an input unit 50, an output unit 51, a communication unit 52, a CPU 53, a memory 54, and an HDD 55 connected via a bus 56, and functions as a computer. The propagation characteristics estimation device 2 is also configured to input and output data to and from a computer-readable storage medium 57.

[0061] The input unit 50 is, for example, a keyboard and a mouse. The output unit 51 is, for example, a display device such as a display that outputs images. The communication unit 52 is, for example, a wired or wireless network interface, and may have a function as an output unit that outputs data to the outside.

[0062] As described above, the CPU 53 controls each component of the propagation characteristics estimation device 2 and performs predetermined processing, etc. The memory 54 and HDD 55 are storage units that store data, etc.

[0063] The storage medium 57 is capable of storing programs and the like that cause the functions of the propagation characteristics estimation apparatus 2 to be executed. Note that the architecture that constitutes the propagation characteristics estimation apparatus 2 is not limited to the example shown in FIG.

[0064] Next, an example will be described in which the propagation characteristics of radio waves are estimated inside a structure (indoor environment) using the propagation characteristics estimation system 1. Fig. 13 is a diagram illustrating the inside of a structure (indoor environment) in which the propagation characteristics of radio waves are estimated using the propagation characteristics estimation system 1.

[0065] In the propagation characteristic estimation system 1, the propagation characteristic estimation device 2 generates a two-dimensional image showing a cross section of a structure between a transmitting station and a receiving station as viewed from above, and a two-dimensional image showing a cross section as viewed from the side.

[0066] Fig. 14 is a diagram illustrating two-dimensional images showing a cross section generated by the propagation characteristics estimation device 2 for the interior of the structure (indoor environment) shown in Fig. 13. Fig. 14(a) is a diagram illustrating a two-dimensional image showing a cross section generated by the propagation characteristics estimation device 2 for the interior of the structure as viewed from the side. Fig. 14(b) is a diagram illustrating a two-dimensional image generated by the propagation characteristics estimation device 2 for a cross section generated by the interior of the structure as viewed from above. In Figs. 14(a) and 14(b), for example, the shaded portions are used as images showing the cross sections.

[0067] Note that the structures between the transmitting point and the receiving point include structures through which paths calculated by, for example, ray tracing simulation pass. Specifically, as shown in Fig. 15 , paths in a rectangular parallelepiped room include paths reflected by the ceiling and floor, as well as paths reflected by the walls.

[0068] That is, in a rectangular parallelepiped room, the vertical plane path (dashed line) and the horizontal plane path (chain line) are the dominant paths for radio wave propagation between the transmitting and receiving points.

[0069] Furthermore, the propagation characteristic estimation system 1 generates a two-dimensional image showing a cross section of the structure between the transmitting and receiving points as seen from above and a two-dimensional image showing a cross section as seen from the side, even for the inside of a structure (indoor environment), and estimates the propagation characteristics of radio waves.Therefore, it is possible to accurately estimate the propagation characteristics of radio waves by taking into account the influence of the structures between the transmitting and receiving points on the radio waves.

[0070] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general purpose processors, application specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions.

[0071] A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may be a programmed processor that executes programs stored in memory.

[0072] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0073] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0074] 1... Propagation characteristic estimation system, 2... Propagation characteristic estimation device, 3... Storage device, 4-1, 4-2... Storage device, 20... Input image generation unit, 22... Model unit, 24... Estimated data storage unit, 26... Error calculation unit, 28... Update unit, 29... Output unit, 50... Input unit, 51... Output unit, 52... Communication unit, 53... CPU, 54... Memory, 55... HDD, 56... Bus, 57... Storage medium, 200... First image generation unit, 202... Second image generation unit, 220... First CNN unit, 222... Second CNN unit, 224... FNN unit

Claims

1. A propagation characteristics estimation device that estimates propagation characteristics of radio waves between a transmitting station and a receiving station that communicate wirelessly, comprising: a first image generation unit that generates, as top-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from above based on the heights of the transmitting station and the receiving station, a two-dimensional image that shows the distance from the transmitting station viewed from above, and a two-dimensional image that shows the distance from the receiving station viewed from above; a second image generation unit that generates, as side-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from the side, a two-dimensional image that shows the distance from the transmitting station viewed from the side, and a two-dimensional image that shows the distance from the receiving station viewed from the side; and a first CNN unit that extracts first feature parameters by inputting each of the top-view images generated by the first image generation unit into a convolutional neural network; a second CNN unit that extracts second feature parameters by inputting each of the side view images generated by the second image generation unit into a convolutional neural network; and an FNN unit that estimates the propagation characteristics by inputting the first feature parameters extracted by the first CNN unit and the second feature parameters extracted by the second CNN unit into a fully connected neural network.

2. The propagation characteristics estimation device according to claim 1, further comprising: an error calculation unit that compares verification data considered to be the propagation characteristics of actual radio waves between the transmitting station and the receiving station with the propagation characteristics estimated by the FNN unit, and calculates an error between the propagation characteristics estimated by the FNN unit and the verification data; and an update unit that updates parameters used by the first CNN unit to extract a first feature parameter and parameters used by the second CNN unit to extract a second feature parameter based on the error calculated by the error calculation unit.

3. A propagation characteristic estimation system for estimating propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, comprising: a first image generation unit that generates, as top-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from above based on the heights of the transmitting station and the receiving station, a two-dimensional image that shows the distance from the transmitting station viewed from above, and a two-dimensional image that shows the distance from the receiving station viewed from above; a second image generation unit that generates, as side-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from the side, a two-dimensional image that shows the distance from the transmitting station viewed from the side, and a two-dimensional image that shows the distance from the receiving station viewed from the side; and a first CNN unit that extracts first feature parameters by inputting each of the top-view images generated by the first image generation unit into a convolutional neural network; a second CNN unit that extracts second feature parameters by inputting each of the side view images generated by the second image generation unit into a convolutional neural network; an FNN unit that estimates the propagation characteristics by inputting the first feature parameters extracted by the first CNN unit and the second feature parameters extracted by the second CNN unit into a fully connected neural network; a memory unit that stores verification data that is considered to be the propagation characteristics of actual radio waves between the transmitting station and the receiving station; an error calculation unit that compares the verification data stored in the memory unit with the propagation characteristics estimated by the FNN unit and calculates an error between the propagation characteristics estimated by the FNN unit and the verification data; and an update unit that updates parameters used by the first CNN unit to extract the first feature parameters and parameters used by the second CNN unit to extract the second feature parameters, based on the error calculated by the error calculation unit.

4. A propagation characteristic estimation method for estimating propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, comprising: a first image generation step of generating, as top-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from above based on the heights of the transmitting station and the receiving station, a two-dimensional image that shows the distance from the transmitting station viewed from above, and a two-dimensional image that shows the distance from the receiving station viewed from above; a second image generation step of generating, as side-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from the side, a two-dimensional image that shows the distance from the transmitting station viewed from the side, and a two-dimensional image that shows the distance from the receiving station viewed from the side; and a first CNN step of extracting first feature parameters by inputting each of the top-view images generated by the first image generation step into a convolutional neural network; a second CNN step of extracting second feature parameters by inputting each of the side-view images generated by the second image generation step into a convolutional neural network; and an FNN step of estimating the propagation characteristics by inputting the first feature parameters extracted by the first CNN step and the second feature parameters extracted by the second CNN step into a fully connected neural network.

5. The propagation characteristics estimation method according to claim 4, further comprising: an error calculation step of comparing verification data considered to be the propagation characteristics of actual radio waves between the transmitting station and the receiving station with the propagation characteristics estimated by the FNN step, and calculating an error between the propagation characteristics estimated by the FNN step and the verification data; and an updating step of updating parameters used to extract a first feature parameter by the first CNN step and parameters used to extract a second feature parameter by the second CNN step, based on the error calculated by the error calculation step.

6. A propagation characteristic estimation program executed by a propagation characteristic estimation device that estimates propagation characteristics of radio waves between a transmitting station and a receiving station that perform wireless communication, comprising: a first image generation unit that generates, as top-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from above based on the heights of the transmitting station and the receiving station, a two-dimensional image that shows the distance from the transmitting station viewed from above, and a two-dimensional image that shows the distance from the receiving station viewed from above; a second image generation unit that generates, as side-view images, two-dimensional images of structures between the transmitting station and the receiving station that show a cross section viewed from the side, a two-dimensional image that shows the distance from the transmitting station viewed from the side, and a two-dimensional image that shows the distance from the receiving station viewed from the side; and a first CNN unit that extracts first feature parameters by inputting each of the top-view images generated by the first image generation unit into a convolutional neural network; a second CNN unit that extracts second feature parameters by inputting each of the side-view images generated by the second image generation unit into a convolutional neural network; and an FNN unit that estimates the propagation characteristics by inputting the first feature parameters extracted by the first CNN unit and the second feature parameters extracted by the second CNN unit into a fully connected neural network.

7. The propagation characteristics estimation program according to claim 6, wherein the propagation characteristics estimation device further comprises: an error calculation unit that compares verification data considered to be the propagation characteristics of actual radio waves between the transmitting station and the receiving station with the propagation characteristics estimated by the FNN unit, and calculates an error between the propagation characteristics estimated by the FNN unit and the verification data; and an update unit that updates parameters used by the first CNN unit to extract a first feature parameter and parameters used by the second CNN unit to extract a second feature parameter, based on the error calculated by the error calculation unit.

Images