3D indoor radio map estimation method and system based on 2D deep learning

Abstract

The application discloses a 3D indoor radio map estimation method based on a 2D deep learning radio residual network (R 2 Net), which estimates a 3D indoor radio map according to a building layout map, a furniture layout map and a transmitter position, and considers the influence of indoor transmitters, receivers and obstacles on the radio map. Since the input and output of the 2D deep learning algorithm are both 2D pictures, the application proposes to represent the building, furniture and transmitter height by pixel values, and to generate 3D radio maps with different heights by different output channels. The 3D radio map estimation is converted into a 2D deep learning task, reducing the calculation overhead and memory requirement. The 2D deep learning method R 2 Net proposed in the application has strong generalization ability, and according to the indoor path loss characteristics, the feature extraction is enhanced, and the estimation accuracy and efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the field of wireless communication technology, and in particular relates to a 3D indoor radio map estimation method and system based on 2D deep learning. Background Art

[0002] Radio maps depict the spatial distribution of received signal strength in the form of images. Each pixel in the image corresponds to the physical location of the receiver, and its pixel value represents the path loss value. Radio maps have broad application prospects, such as fingerprint positioning, robot path planning, aerial base station deployment, and interference management. For example, computer vision technology can be used to improve the accuracy and efficiency of fingerprint positioning using radio maps.

[0003] The primary challenge in leveraging radio maps to empower related applications lies in obtaining them. Traditional radio maps are mostly obtained through site surveys, but due to physical limitations, some inaccessible areas exist, resulting in missing radio map data. To complete the radio map, radio map reconstruction, which estimates unmeasured path losses based on measured values, has attracted widespread attention. Site surveys require deployed base stations. However, base stations are not deployed during the network planning phase, and radio maps are also important for optimizing base station deployment locations. Physical simulation methods can search for possible propagation paths between transmitters and receivers based on the provided environmental data without measurements, and calculate path losses based on antenna characteristics, obstacle materials, and scattering and diffraction parameters. However, searching for radio propagation paths requires significant computational overhead, making physical simulations time-consuming. Therefore, efficient radio map estimation methods are urgently in need of research.

[0004] Deep learning-based radio map estimation has attracted widespread attention due to its fast inference speed and high accuracy. Existing deep learning-based indoor radio map estimation methods primarily focus on 2D radio maps, ignoring the influence of transmitter, receiver, and obstacle heights, which must be considered in indoor scenarios. While 3D indoor radio map estimation can be achieved by replacing the 2D operations in existing 2D radio map estimation methods with 3D ones, 3D deep learning algorithms are computationally expensive. Therefore, further research is needed to achieve computationally efficient 3D indoor radio map estimation. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a 3D indoor radio map estimation method and system based on 2D deep learning, which solves the problem of low efficiency and accuracy of 3D indoor radio map estimation in the prior art.

[0006] The present invention adopts the following technical solutions to solve the above technical problems:

[0007] A 3D indoor radio map estimation method based on 2D deep learning includes the following steps:

[0008] Step 1: Construct the inputs and outputs of several 3D radio map estimates obtained in advance through simulation into 2D images containing height information, using pixel values ​​to represent the heights of buildings, furniture, and transmitters. 3D radio maps at different heights are generated using different output channels. The 2D images include a building layout, furniture layout, and transmitter location map.

[0009] Step 2: Build a 2D deep learning estimation model based on the characteristics of the 3D radio map, and divide the 2D images obtained in step 1 into a training set, a cross-validation set, and a test set.

[0010] Step 3: Set the training parameters and loss function of the 2D deep learning method estimation model;

[0011] Step 4: Use the training set to train the 2D deep learning method estimation model, use the cross-validation set for verification, and update the parameters of the 2D deep learning method estimation model in real time until the training is completed. Use the test set to evaluate the estimation accuracy of the model;

[0012] Step 5: Input the environmental parameters into the optimal 2D deep learning method estimation model obtained in step 4 to estimate the 3D indoor radio map.

[0013] The specific architecture of the 2D deep learning method estimation model includes an encoder and a decoder, wherein the encoder includes several cascaded residual modules; the decoder includes several nearest neighbor upsampling modules; and a path loss feature enhancement module is connected between the encoder and the decoder.

[0014] The specific process of building a 2D deep learning method estimation model is as follows:

[0015] Step 2.1: Based on the U-Net encoder and decoder structure model, random dropout layers and cascaded residual modules are used to enhance feature extraction according to the characteristics of path loss.

[0016] Step 2.2: Using the nearest neighbor interpolation algorithm, the decoder restores the features extracted by the encoder to the size of the original image, thereby achieving pixel-level radio map estimation;

[0017] Step 2.3: Use skip connection to pass the features proposed by the encoder to the decoder.

[0018] In step 2.1, for feature maps with relatively low resolution, a random dropout layer is used to enhance generalization; nonlinear feature extraction is enhanced through cascaded residual modules.

[0019] The training parameters in step 3 include the network initial learning rate, the learning rate decay method, and the number of network iterations.

[0020] The loss function selects the mean square error, which is specifically expressed as follows:

[0021]

[0022] in, is the i-th estimated radio map, V(i) is the true value; N train is the number of training samples.

[0023] In step 1, the specific method of using pixel values ​​to represent the height of buildings, furniture, and transmitters is as follows:

[0024] Use pixel value 0 to represent no object, and pixel value 1 to represent the highest object h max , height h env The value of the pixel where the object is located is calculated according to the following formula:

[0025] v env =(h env +ε) / (h max +ε), where ε is a constant set to distinguish objects located on the ground.

[0026] The computer-readable storage medium is characterized in that: the computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, all or part of the steps of the method are called.

[0027] A 3D indoor radio map estimation system based on 2D deep learning includes a processor module, a 3D radio map simulation module, and a memory module. The processor module calls the method to estimate the 3D indoor radio map. The 3D radio map simulation module is used to simulate and obtain the data set required for model training and perform preprocessing. The memory module is used to classify and store the preprocessed data.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. Using the proposed method, all deep learning-based 2D radio map estimation methods can estimate 3D radio maps, reducing computational overhead and memory requirements. The proposed method can also be used for 2D radio map estimation by inputting ambient height information.

[0030] 2. This paper also proposes a 2D deep learning method for 3D indoor radio map estimation R 2 Net (radioresidual network), the proposed method R 2 Net enhances feature extraction based on the path loss characteristics to improve estimation accuracy and achieve faster estimation speed.

[0031] 3. Proposed method R 2 Net also achieves strong generalization ability by randomly dropping layers. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Schematic diagram of the input and output of the 3D indoor radio map estimation of the present invention.

[0033] Figure 2 The 3D indoor radio map estimation method R based on 2D deep learning of the present invention 2 Net structure diagram.

[0034] Figure 3 This is a schematic diagram of the cascaded residual module used in the present invention.

[0035] Figure 4 Schematic diagram of the path loss feature enhancement module proposed in the present invention.

[0036] Figure 5 This is a schematic diagram of the nearest neighbor upsampling module used in the present invention.

[0037] Figure 6 The 0.5m high indoor radio map estimated by the present invention and the comparison algorithm, where a is the true value obtained by simulation, b to e are the radio maps estimated by the comparison algorithm, b to e are all 2D deep learning methods originally used to estimate 2D radio maps, and the 3D radio map is estimated by the method proposed by the present invention, and f is the 2D deep learning method R proposed by the present invention. 2 Net estimated radio map. DETAILED DESCRIPTION

[0038] The structure and working process of the present invention will be further described below with reference to the accompanying drawings.

[0039] The present invention proposes a 3D indoor radio map estimation method based on 2D deep learning, which estimates the 3D indoor radio map according to the building layout, furniture layout and transmitter position, and considers the impact of the height of indoor transmitters, receivers and obstacles on the radio map. Existing indoor radio map estimation based on deep learning mainly focuses on 2D radio maps, ignoring the impact of the height of transmitters, receivers and obstacles, while height must be considered in indoor scenes. Although 3D indoor radio map estimation can be achieved by changing the 2D operation of the existing 2D radio map estimation method to 3D, the computational overhead of the 3D deep learning algorithm is large. In order to reduce the computational overhead, the present invention proposes a 2D deep learning algorithm, a radio residual network (i.e., R 2Net) to estimate the 3D radio map. Since the input and output of the 2D deep learning algorithm are both 2D images, the present invention proposes to use pixel values ​​to represent the height of buildings, furniture, and transmitters, and use different output channels to generate 3D radio maps at different heights. The present invention converts 3D radio map estimation into a 2D deep learning task, reducing computational overhead and memory requirements. The 2D deep learning method R proposed in this invention is a 2D deep learning method that can be used to estimate the radio map of a building or a transmitter. 2 Net has strong generalization ability and enhances feature extraction based on indoor path loss characteristics, thereby improving estimation accuracy and efficiency.

[0040] A 3D indoor radio map estimation method based on 2D deep learning includes the following steps:

[0041] Step 1: Construct the inputs and outputs of several 3D radio map estimates obtained in advance through simulation into 2D images containing height information, using pixel values ​​to represent the heights of buildings, furniture, and transmitters. 3D radio maps at different heights are generated using different output channels. The 2D images include a building layout, furniture layout, and transmitter location map.

[0042] Step 2: Build a 2D deep learning estimation model based on the characteristics of the 3D radio map, and divide the 2D images obtained in step 1 into a training set, a cross-validation set, and a test set.

[0043] Step 3: Set the training parameters and loss function of the 2D deep learning method estimation model;

[0044] Step 4: Use the training set to train the 2D deep learning method estimation model, use the cross-validation set for verification, and update the parameters of the 2D deep learning method estimation model in real time until the training is completed. Use the test set to evaluate the estimation accuracy of the model;

[0045] Step 5: Input the environmental parameters into the optimal 2D deep learning method estimation model obtained in step 4 to estimate the 3D indoor radio map.

[0046] Specific embodiments, such as Figures 1 to 6 As shown,

[0047] This embodiment uses pixel values ​​to represent the heights of buildings, furniture, and transmitters, uses different output channels to generate 3D radio maps at different heights, and constructs the input and output of the 3D radio map estimation into 2D images. Figure 1 , converting 3D radio map estimation into a 2D deep learning task to reduce computational overhead and memory requirements. Among them, the green and white circles emphasize the transmitter locations.

[0048] See attached Figure 2 -Attached Figure 5 , the R2 Based on the encoder and decoder structure of 2D U-Net and according to the characteristics of indoor path loss, this paper proposes to use random dropout layers to enhance the feature extraction of penetration loss and cascade residual modules to enhance the feature extraction of diffraction loss. At the same time, the nearest neighbor interpolation algorithm is used to reduce the information loss caused by random dropout layers and downsampling to improve the estimation accuracy.

[0049] The present embodiment proposes a 3D indoor radio map estimation method based on 2D deep learning, which includes the following steps:

[0050] Step 1: Construct the inputs and outputs of several 3D radio map estimates obtained in advance through simulation into 2D images containing height information. Pixel values ​​are used to represent the heights of buildings, furniture, and transmitters. 3D radio maps at different heights are generated using different output channels. The output dimension is reduced from 3D to 2D. The 2D images include a building layout, furniture layout, and transmitter location map.

[0051] In this embodiment, the specific method of using pixel values ​​to represent the heights of buildings, furniture, and transmitters is as follows:

[0052] Use pixel value 0 to represent no object, and pixel value 1 to represent the highest object h max , height h env The value of the pixel where the object is located is calculated according to the following formula:

[0053] v env =(h env +ε) / (h max +ε), where ε is a constant set to distinguish objects located on the ground, and is usually a small value. In this embodiment, ε is 0.1.

[0054] Step 2: Construct a 2D deep learning estimation model (i.e., R 2 Net neural network model), the 2D images obtained in step 1 are divided into a training set, a cross-validation set, and a test set;

[0055] The R 2 Net neural network model is specifically:

[0056] Overall network architecture: see attached Figure 2 ,This network uses 2D U-Net as the basic network architecture, and adds a cascaded residual module to the U-Net encoder to enhance the diffraction loss feature extraction. The structure of the cascaded residual module is shown in the attached Figure 3 ;

[0057] The proposed path loss feature enhancement module: R 2Net adopts the proposed path loss feature enhancement module containing cascaded residual modules and random dropout layers between the encoder and decoder of U-Net to enhance the extraction of penetration loss and diffraction loss features. The structure of the proposed path loss feature enhancement module is shown in the attached Figure 4 , where the circled area shows that the proposed path loss feature enhancement module effectively extracts the path loss features at locations far away from the transmitter;

[0058] Nearest neighbor upsampling module: R 2 Net uses the nearest neighbor upsampling module to reduce the information loss caused by random dropout layer and downsampling. The structure of the nearest neighbor upsampling module is shown in the attached Figure 5 .

[0059] The R 2 The specific construction method of the Net neural network model is as follows:

[0060] Step 2.1, based on the U-Net encoder and decoder structure model, according to the characteristics of penetration loss, that is, in the same building with the same furniture layout, once the transmitter position changes, the penetration loss will cause a large change in the 3D indoor radio map, requiring the model to have strong generalization ability. The proposed method R 2 Net enhances generalization by using random dropout layers in feature maps with lower resolution. Due to the sudden signal power attenuation and propagation direction change caused by diffraction loss, that is, indoor obstacles (such as furniture) have a nonlinear effect on path loss, the model needs to extract nonlinear features at the same time. The proposed method R 2 Net enhances nonlinear feature extraction through cascaded residual modules.

[0061] Step 2.2: Using the nearest neighbor interpolation algorithm, the decoder restores the features extracted by the encoder to the size of the original image, thereby achieving pixel-level radio map estimation; enhancing feature extraction through random dropout layers and downsampling layers will lead to information loss. To reduce the impact of information loss, the interpolation method commonly used by U-Net, namely deconvolution, cannot be used. Therefore, the proposed method R 2 Net uses the nearest neighbor interpolation algorithm.

[0062] Step 2.3: To improve the estimation accuracy, a skip connection is used to pass the features proposed by the encoder to the decoder.

[0063] Step 3: Set the training parameters and loss function of the 2D deep learning method estimation model; the training parameters include setting the network initial learning rate, learning rate decay method, and number of network iterations; the initial learning rate used here is 0.0001, the learning rate decay method is 0.00001 after 30 iterations, the number of network iterations is 50, and the loss function is the mean square error;

[0064] The loss function is specifically expressed as follows:

[0065]

[0066] in, is the i-th estimated radio map, V(i) is the true value; N train is the number of training samples.

[0067] Step 4: Use the training set to train the 2D deep learning method estimation model and use the cross-validation set for validation to avoid overfitting. That is, select the model parameters with the smallest mean square error of the cross-validation set in 50 iterations, and update the parameters of the 2D deep learning method estimation model in real time until the training is completed. Use the test set to evaluate the estimation accuracy of the model.

[0068] Step 5: Input the environmental parameters into the optimal 2D deep learning method estimation model obtained in step 4 to estimate the 3D indoor radio map.

[0069] This example uses simulation software to generate the 3D indoor radio map dataset 3DiRM3200, which contains 3200 3D radio maps, 200 building layouts, 200 furniture layouts, and 3200 randomly generated transmitter location maps. The 3D indoor radio map estimation experiment uses the generated 3DiRM3200 dataset. The 3200 samples are randomly divided into a training set of 2560 samples, a cross-validation set of 320 samples, and a test set of 320 samples.

[0070] The mentioned R 2 Net and the comparison methods RadioUNet, FadeNet, RadioTrans, and PPNet were all trained on an Nvidia GeForce RTX 3090 graphics card. RadioUNet, FadeNet, RadioTrans, and PPNet are deep learning methods for 2D radio map estimation. Using the proposed method, they can be used to estimate 3D radio maps. Each model was trained 50 times. To avoid overfitting, the model parameters with the lowest Mean Sequential Error (MSE) on the cross-validation set were selected. Since the simulation software used to generate the 3DiRM3200 dataset runs on a CPU, all methods were tested on an Intel Core i5-11400F to compare the inference speed of the simulation software and deep learning methods.

[0071] Experimental verification shows that the 3D indoor radio map estimated by this inventive method is more accurate than the existing radio map estimation method based on deep learning.

[0072] The radio map of the randomly selected samples in the test set at a height of 0.5m is shown in the attached Figure 6 The radio map estimated by the proposed R2Net is closest to the true value, especially for locations in the radio map that are far away from the transmitter. This shows that the proposed R2Net enhances indoor path loss feature extraction, thereby improving estimation accuracy.

[0073] On the test set, the normalized mean square errors of the comparison methods RadioUNet, FadeNet, RadioTrans and PPNet are 0.0292, 0.0583, 0.0714 and 0.1433 respectively. 2 Net can achieve a normalized mean square error of 0.0268, which is 8.22% smaller than RadioUNet and 81.30% smaller than PPNet. 2 Net can significantly improve the estimation accuracy of 3D indoor radio maps.

[0074] On an Intel Core i5-11400F, the simulation software estimates 0.04 3D indoor radio maps per second. The comparison methods RadioUNet, FadeNet, RadioTrans, and PPNet estimate 2, 1, 2, and 1 3D indoor radio maps per second, respectively. 2 Net can estimate 3 3D indoor radio maps per second. 2 Net's estimation speed is faster than other comparison algorithms, and R 2 Net is two orders of magnitude faster than the main path model of the physical simulation method. In addition, the comparison methods RadioUNet, FadeNet, RadioTrans and PPNet contain 13M, 65M, 55M and 15M parameters respectively. 2 The number of parameters of RNet is 8M, which is much smaller than the comparison algorithm, 38.46% smaller than RadioUNet and 87.69% smaller than FadeNet. 2 Net occupies less memory than the comparison algorithms. The comparison methods RadioUNet, FadeNet, RadioTrans and PPNet require 25.8G, 51.7G, 18.7G and 34.7G respectively. 2 The number of multiplication-addition-accumulation operations required by Net is 6.5G, which is less than the comparison algorithm, that is, the computational efficiency is higher.

[0075] The computer-readable storage medium is characterized in that: the computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, all or part of the steps of the method are called.

[0076] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0077] A 3D indoor radio map estimation system based on 2D deep learning includes a processor module, a 3D radio map simulation module, and a memory module. The processor module calls the method to estimate the 3D indoor radio map. The 3D radio map simulation module is used to simulate and obtain the data set required for model training and perform preprocessing. The memory module is used to classify and store the preprocessed data.

[0078] It should be understood that this solution is not limited to the specific implementation methods described above. Devices and structures not described in detail should be understood to be implemented in a common manner in the art. Any person skilled in the art can, without departing from the scope of this solution, use the methods and technical content disclosed above to make many possible changes and modifications to this solution, or modify it into equivalent embodiments with equivalent changes, without affecting the essence of this solution. Therefore, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of this solution without departing from the content of this solution are still within the scope of protection of this solution.

Claims

1. A 3D indoor radio map estimation method based on 2D deep learning, characterized by: The steps include: Step 1: Construct the inputs and outputs of several 3D radio map estimates obtained in advance through simulation into 2D images containing height information. Pixel values ​​are used to represent the heights of buildings, furniture, and transmitters. 3D radio maps at different heights are generated using different output channels. The 2D images include a building layout, furniture layout, and transmitter location map. The specific method for representing the heights of buildings, furniture, and transmitters using pixel values ​​is as follows: Use pixel value 0 to represent no object, and pixel value 1 to represent the highest object h max , height h env The value of the pixel where the object is located is calculated according to the following formula: v env =(h env +ε) / (h max +ε), where ε is a constant set to distinguish objects located on the ground; Step 2: Construct a 2D deep learning method estimation model based on the features of the 3D radio map. The 2D images obtained in step 1 are divided into a training set, a cross-validation set, and a test set. The specific architecture of the 2D deep learning method estimation model includes an encoder and a decoder, wherein the encoder includes several cascaded residual modules; the decoder includes several nearest neighbor upsampling modules; and a path loss feature enhancement module is connected between the encoder and the decoder. The specific process of constructing the 2D deep learning method estimation model is as follows: Step 2.1: Based on the U-Net encoder and decoder structure model, random dropout layers and cascaded residual modules are used to enhance feature extraction according to the characteristics of path loss. Step 2.2: Using the nearest neighbor interpolation algorithm, the decoder restores the features extracted by the encoder to the size of the original image, thereby achieving pixel-level radio map estimation; Step 2.3: Use skip connection to pass the features proposed by the encoder to the decoder; Step 3: Set the training parameters and loss function of the 2D deep learning method estimation model; Step 4: Use the training set to train the 2D deep learning method estimation model, use the cross-validation set for verification, and update the parameters of the 2D deep learning method estimation model in real time until the training is completed. Use the test set to evaluate the estimation accuracy of the model; Step 5: Input the environmental parameters into the optimal 2D deep learning method estimation model obtained in step 4 to estimate the 3D indoor radio map.

2. The 3D indoor radio map estimation method based on 2D deep learning according to claim 1, characterized in that: In step 2.1, for feature maps with relatively low resolution, a random dropout layer is used to enhance generalization; nonlinear feature extraction is enhanced through cascaded residual modules.

3. The 2D deep learning-based 3D indoor radio map estimation method according to claim 1, wherein: The training parameters in step 3 include the network initial learning rate, the learning rate decay method, and the number of network iterations.

4. The 3D indoor radio map estimation method based on 2D deep learning according to claim 3, characterized in that: The loss function selects the mean square error, which is specifically expressed as follows: in, is the i-th estimated radio map, V(i) is the true value; N train is the number of training samples.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, call all or part of the steps of the method according to any one of claims 1 to 4.

6. 3D indoor radio map estimation system based on 2D deep learning, characterized by: The system comprises a processor module, a 3D radio map simulation module, and a memory module; wherein the processor module calls the method described in any one of claims 1 to 4 to estimate a 3D indoor radio map; the 3D radio map simulation module is used to simulate and obtain the data set required for model training and perform preprocessing; and the memory module is used to classify and store the preprocessed data.

Images