WO2023116196A1 - 用于室内定位的aoa和tof联合估计方法、装置及存储介质 - Google Patents

用于室内定位的aoa和tof联合估计方法、装置及存储介质 Download PDF

Info

Publication number
WO2023116196A1
WO2023116196A1 PCT/CN2022/128242 CN2022128242W WO2023116196A1 WO 2023116196 A1 WO2023116196 A1 WO 2023116196A1 CN 2022128242 W CN2022128242 W CN 2022128242W WO 2023116196 A1 WO2023116196 A1 WO 2023116196A1
Authority
WO
WIPO (PCT)
Prior art keywords
layer
aoa
tof
joint estimation
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2022/128242
Other languages
English (en)
French (fr)
Inventor
徐友云
宋万达
威力
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Publication of WO2023116196A1 publication Critical patent/WO2023116196A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]

Definitions

  • the invention relates to an AOA and TOF joint estimation method, device and storage medium for indoor positioning, and belongs to the technical field of wireless signal processing.
  • Wireless signals are widely used in various fields of daily life. In the fields of health perception, fire positioning and rescue, and augmented reality-based navigation, it is very important to accurately estimate the direction of arrival (AOA) and time of arrival (TOF) of each path of the wireless signal. However, during the multipath propagation of wireless signals, objects near indoor APs and mobile clients will reflect wireless signals, resulting in low estimation accuracy of direction of arrival (AOA) and time of arrival (TOF).
  • AOA direction of arrival
  • TOF time of arrival
  • the purpose of the present invention is to overcome the deficiencies in the prior art, and provide an AOA and TOF joint estimation method, device and storage medium for indoor positioning.
  • the present invention provides an AOA and TOF joint estimation method for indoor positioning, the method comprising:
  • the joint estimation model is obtained by training a deep convolutional neural network, and the deep convolutional neural network uses convolution kernels of different sizes in parallel.
  • the acquired CSI data is represented as a complex data matrix image
  • the processed data is represented as a real number matrix image.
  • the processed data is represented as a three-channel real number matrix image.
  • the acquisition of the three-channel real matrix image includes:
  • Matrix composition is the acquired three-channel real matrix image.
  • the deep convolutional neural network includes an input layer, a 7*7 convolutional layer, a maximum pooling layer, a 1*1 convolutional layer, a 3*3 convolutional layer, a pooling layer, 2 Inception structures, Maximum pooling layer, 3 Inception structures, maximum pooling layer, 2 Inception structures, average pooling layer, fully connected layer, output layer.
  • the Inception structure includes four layers: the first layer is an input layer, the second layer is a 1*1 convolutional layer, a 1*1 convolutional layer, a 3*3 maximum pooling layer, and a 1*1 convolutional layer , the third layer is 3*3 convolutional layer, 5*5 convolutional layer and 1*1 convolutional layer, and the fourth layer is the output layer.
  • the training of the joint estimation model includes:
  • the training set is trained through a deep convolutional neural network to obtain a joint estimation model.
  • the present invention provides a device, including a processor and a storage medium;
  • the storage medium is used to store instructions
  • the processor is configured to operate according to the instructions to perform the steps of the method of the first aspect.
  • the present invention provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.
  • the beneficial effects of the present invention are: the present invention obtains a joint estimation model through deep convolutional neural network training based on parallel construction of convolution kernels of different sizes, and achieves a higher accuracy than that estimated by traditional methods. Accuracy, higher resolution and better noise immunity.
  • Fig. 1 is the working flowchart of the AOA and TOF joint estimation method for indoor positioning according to the embodiment of the present invention
  • FIG. 2 is a schematic diagram of an antenna array at a receiving end according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a single-channel construction method of CSI data in a data set according to an embodiment of the present invention
  • FIG. 4 is a schematic diagram of a multi-channel construction method for CSI data in a data set according to an embodiment of the present invention
  • FIG. 5 is a schematic diagram of a multi-scale convolution kernel and CSI data convolution method according to an embodiment of the present invention
  • Fig. 6 is a neural network structure diagram of parallel design of convolution kernels of different sizes according to an embodiment of the present invention
  • Fig. 7 is the root mean square error (RMSE) contrast chart of joint estimated value and multiple method estimated results of the embodiment of the present invention.
  • RMSE root mean square error
  • Fig. 8 is a comparison diagram of the error distribution between the joint estimated value and the estimated results of various methods according to the embodiment of the present invention.
  • the present invention provides an AOA and TOF joint estimation method, device and storage medium for indoor positioning.
  • the present invention will be further described below in conjunction with the accompanying drawings and embodiments, wherein:
  • an embodiment of the present invention provides an AOA and TOF joint estimation method for indoor positioning, including:
  • the OFDM signal is used as the transmission signal, the transmission channel is set to Gaussian channel, the channel bandwidth is 40MHz, the center frequency is 5.32GHz, the interval between adjacent subcarriers is set to 312.5KHz, and 30 subcarriers are selected, as shown in Figure 2, the receiving end adopts A linear array of three antennas generates a data set by setting different channel parameters.
  • the data set samples include input data and labels, and the received CSI is used as input data, and AOA and TOF are used as labels.
  • the CSI data in the data set is a matrix of complex numbers.
  • the current deep convolutional neural network does not have a proper processing method for complex input.
  • the present invention uses the complex CSI data received from the antenna array
  • the data matrix H 90 ⁇ 1 is divided into HR, H I, where HR is the real part matrix of H, and H I is the imaginary part matrix of H, and then convert it to the formula (1) to obtain the amplitude that can effectively retain the CSI and phase information;
  • Re(csi) represents the real value of csi part
  • Im(csi) means to take the imaginary part of csi.
  • the convolutional neural network extracts the features of the input image through the convolution kernel.
  • the window moves the data from the front end is used to fill in the end, so that the matrix obtained by moving the window i times, and finally these 90 matrices with a size of 180 ⁇ 2 are merged into a new matrix:
  • the present invention proposes a method for constructing a multi-channel input matrix, changing the moving step size to 4 and 6 respectively, and then performing the same filling operation on the window to obtain two
  • the obtained three matrices are composed of three-dimensional matrix H 180 ⁇ 180 ⁇ 3 used as the input of the neural network according to the graph.
  • a training set is constructed.
  • the deep convolutional neural network is designed based on the parallel connection of convolution kernels of different sizes.
  • the convolution kernels of different scales can be convoluted with the received signals of subcarriers of different frequencies according to the method shown in Figure 5, and then the data related to each subcarrier can be extracted.
  • the deep convolutional neural network includes an input layer, a 7*7 convolutional layer, a maximum pooling layer, a 1*1 convolutional layer, a 3*3 convolutional layer, a pooling layer, and 2 Inception structure, maximum pooling layer, 3 Inception structures, maximum pooling layer, 2 Inception structures, average pooling layer, fully connected layer, output layer;
  • the Inception structure includes four layers: the first layer is the input layer, The second layer is 1*1 convolutional layer, 1*1 convolutional layer, 3*3 maximum pooling layer and 1*1 convolutional layer, the third layer is 3*3 convolutional layer, 5*5 convolutional layer And 1*1 convolutional layer, the fourth layer is the output layer.
  • the training set is trained through a deep convolutional neural network to obtain a joint estimation model.
  • the estimated CSI data is preprocessed to obtain a three-channel real matrix image, and the three-channel indicator matrix is used as the input of the joint estimation model, and the AOA and TOF corresponding to the estimated CSI data are output.
  • FIG 7 it is a comparison diagram of the root mean square error (RMSE) of the estimated results of the method of the present invention and other algorithms.
  • RMSE root mean square error
  • the other two methods SpoFi and Join- 2D
  • the estimated RMSE of AOA and TOF decreases with the increase of SNR; since the training samples include data under multiple signal-to-noise ratios, the trained network has good generalization ability, so in different signal-to-noise ratios
  • the method proposed in this paper performs better than the other two methods at any signal-to-noise ratio.
  • the estimation errors of the AOA of the present invention are all distributed within 10°, while the estimation errors of the other two methods are within 10°
  • the amount of data only accounts for 80% and 70% of the total data, and nearly 20% of the data has an estimation error of more than 30°, that is, it cannot be accurately identified.
  • Another advantage of the method proposed in the present invention is that even if the angle of arrival and time of arrival of two paths are similar, they can be identified accurately, while the identification of the other two paths in this case is not ideal.
  • the estimation algorithms in SpoFi and Join-2D are both improved algorithms based on the MUSIC algorithm, in which the MUSIC algorithm utilizes the orthogonality of the signal subspace and the noise subspace to construct a spatial spectral function, and searches through spectral peaks To estimate AOA, if the spectral peaks are similar, it is difficult to distinguish them, so the traditional algorithm has certain resolution limitations.
  • the neural network-based method proposed in the present invention estimates AOA and TOF by extracting relevant features of the signal.
  • True value SpoFi Join-2D method path 1 of the present invention (123°, 96ns) (125°, 107ns) (124°, 99ns) (123.6°, 85ns) path 2: (132°, 102ns) null null (133.7° ,94ns)
  • This embodiment provides a device, including a processor and a storage medium
  • the storage medium is used to store instructions
  • the processor is configured to operate according to the instructions to execute the steps of the method described in Embodiment 1.
  • This embodiment provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions
  • the device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)

Abstract

本发明公开了用于室内定位的AOA和TOF联合估计方法、装置及存储介质，所述方法包括对获取的CSI数据进行预处理，获得处理后的数据；将处理后的数据输入预先训练好的联合估计模型，得到处理后的数据所对应的AOA和TOF；所述联合估计模型通过深度卷积神经网络训练得到，所述深度卷积神经网络采用不同大小卷积核并联。本发明通过基于不同大小卷积核并联构建的深度卷积神经网络,训练得到联合估计模型，提高了估计结果的精确度、分辨率和抗噪声能力。

Description

用于室内定位的AOA和TOF联合估计方法、装置及存储介质 技术领域
本发明涉及用于室内定位的AOA和TOF联合估计方法、装置及存储介质，属于无线信号处理技术领域。
背景技术
无线信号广泛应用于日常生活各领域，在健康感知，消防定位救援和基于增强现实的导航等领域，精确地估计无线信号每条路径的到达方向(AOA)和到达时间(TOF)至关重要，但是，在无线信号多径传播过程中，室内AP与移动客户端附近的物体会对无线信号造成反射，导致到达方向(AOA)和到达时间(TOF)的估计精度不高。
目前，大多研究是通过构建数学模型并结合信号处理相关算法来得到从接收信号到AOA的一种对应关系，但是，在模型建立和求解过程中会做出大量近似，而近似操作会损失部分信息，对AOA的准确估计有一定的阻碍。
发明内容
本发明的目的在于克服现有技术中的不足，提供了用于室内定位的AOA和TOF联合估计方法、装置及存储介质。
第一方面，本发明提供了用于室内定位的AOA和TOF联合估计方法，所述方法包括：
对获取的CSI数据进行预处理，获得处理后的数据；
将处理后的数据输入预先训练好的联合估计模型，得到处理后的数据所对应的AOA和TOF；
所述联合估计模型通过深度卷积神经网络训练得到，所述深度卷积神 经网络采用不同大小卷积核并联。
进一步的，所述获取的CSI数据表示为复数数据矩阵图像，所述处理后的数据表示为实数矩阵图像。
进一步的，所述处理后的数据表示为三通道实数矩阵图像。
进一步的，所述三通道实数矩阵图像的获取包括：
将获取的CSI数据的复数数据矩阵及其共轭矩阵，按实部和虚部分成四个子矩阵并进行重组，获得重组矩阵；
通过滑动步长为2、4和6的滑动窗口，分别对所述重组矩阵进行移位截取，分别得到若干个子矩阵，再将分别得到的若干个子矩阵拼接，获得三个矩阵，所述三个矩阵组成即获取的三通道实数矩阵图像。
进一步的，所述深度卷积神经网络包括输入层、7*7卷积层、最大池化层、1*1的卷积层、3*3卷积层、池化层、2个Inception结构、最大池化层、3个Inception结构、最大池化层、2个Inception结构、平均池化层、全连接层、输出层。
进一步的，所述Inception结构包括四层：第一层为输入层，第二层为1*1卷积层、1*1卷积层、3*3最大池化层和1*1卷积层，第三层为3*3卷积层、5*5卷积层和1*1卷积层，第四层为输出层。
进一步的，所述联合估计模型的训练包括：
获取历史CSI数据以及CSI数据对应的AOA和TOF，构建数据集；
对所述数据集进行预处理，构建训练集；
将训练集通过深度卷积神经网络进行训练，得到联合估计模型。
第二方面，本发明提供了一种装置，包括处理器及存储介质；
所述存储介质用于存储指令；
所述处理器用于根据所述指令进行操作以执行第一方面所述方法的步骤。
第三方面，本发明提供了一种存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现第一方面所述方法的步骤。
与现有技术相比，本发明的有益效果为：本发明通过基于不同大小卷积核并联构建的深度卷积神经网络训练得到联合估计模型，实现了比传统方法所估计的结果更高的精确度、更高的分辨率以及更好的抗噪声能力。
附图说明
图1是本发明实施例用于室内定位的AOA和TOF联合估计方法工作流程图；
图2是本发明实施例接收端的天线阵列示意图；
图3是本发明实施例数据集中CSI数据的单通道构造方法示意图；
图4是本发明实施例数据集中CSI数据的多通道构造方法示意图；
图5是本发明实施例多尺度卷积核与CSI数据相卷积方法示意图；
图6是本发明实施例不同大小卷积核并联设计的神经网络结构图；
图7是本发明实施例联合估计值与多种方法估计结果的均方根误差(RMSE)对比图；
图8是本发明实施例联合估计值与多种方法估计结果的误差分布对比图。
具体实施方式
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其 中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本发明，而不能理解为对本发明的限制。
在本发明的描述中，若干的含义是一个以上，多个的含义是两个以上，大于、小于、超过等理解为不包括本数，以上、以下、以内等理解为包括本数。如果有描述到第一、第二只是用于区分技术特征为目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量或者隐含指明所指示的技术特征的先后关系。
本发明的描述中，除非另有明确的限定，设置、安装、连接等词语应做广义理解，所属技术领域技术人员可以结合技术方案的具体内容合理确定上述词语在本发明中的具体含义。
本发明的描述中，参考术语“一个实施例”、“一些实施例”、“示意性实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
本发明提供了用于室内定位的AOA和TOF联合估计方法、装置及存储介质，下面结合附图和实施例对本发明做进一步的说明，其中：
实施例1：
如图1所示，本发明实施例提供了用于室内定位的AOA和TOF联合估计方法，包括：
使用OFDM信号作为传输信号，传输信道设置为高斯信道，信道带宽为40MHz，中心频率为5.32GHz，相邻子载波间隔设置为312.5KHz，选用30个子载波，如图2所示，接收端采用具有三根天线的线性阵列，通过设置不同的信道参数生成数据集，数据集样本包括输入数据和标签，将接收到的CSI作为输入数据，AOA和TOF作为标签。
数据集中的CSI数据为复数矩阵，然而目前深度卷积神经网络对输入为复数的情况并没有较为妥当的处理方式，为了获得可以作为输入的CSI图像，本发明将从天线阵列接收到的CSI复数数据矩阵H 90×1分为H R，H I，其中H R为H的实部矩阵，H I为H的虚部矩阵，然后对其进行公式(1)的转换得到可以有效保留CSI的幅度和相位等信息；
其中csi m，k，m＝1，2，3，k＝1，2，...，30表示第m个天线上的第k个子载波，为复数数据，Re(csi)表示取csi的实部，Im(csi)表示取csi的虚部。
卷积神经网络通过卷积核来提取输入图像的特征，考虑到TOF和AOA的估计值与多个子载波相关，如图3所示，本发明提出构建单通道输入矩阵的方法，令h i，j表示矩阵第i(i＝1,2,…,180)行第j(j＝1,2)列的值，设置移动步长为2使得在训练网络时卷积核能够覆盖多个子载波，当窗口移动时使用前端数据向尾端进行填充，令表示窗口移动i次得到的矩阵，最终将此90个规模均为180×2的矩阵合并为一个新矩阵：
为了更多的提取各子载波信号组合的特征，如图4所示，本发明提出 构建多通道输入矩阵的方法，分别改变移动步长为4和6，接着对窗口进行相同的填充操作得到两个二维矩阵将得到的三个矩阵按图组成用作神经网络输入的三维矩阵H 180×180×3。
根据处理获得的三通道实数矩阵图像以及三通道实数矩阵图像对应的AOA和TOF，构建训练集。
基于不同大小卷积核并联设计深度卷积神经网络，不同尺度的卷积核可以按照图5所表示的方法与不同频率子载波的接收信号做卷积运算，继而提取与各个子载波相关的数据特征，如图6所示，深度卷积神经网络包括输入层、7*7卷积层、最大池化层、1*1的卷积层、3*3卷积层、池化层、2个Inception结构、最大池化层、3个Inception结构、最大池化层、2个Inception结构、平均池化层、全连接层、输出层；所述Inception结构包括四层：第一层为输入层，第二层为1*1卷积层、1*1卷积层、3*3最大池化层和1*1卷积层，第三层为3*3卷积层、5*5卷积层和1*1卷积层，第四层为输出层。
将训练集通过深度卷积神经网络进行训练，得到联合估计模型。
对待估计的CSI数据进行预处理，获得三通道实数矩阵图像，将三通道示数矩阵作为联合估计模型的输入，输出待估计的CSI数据对应的AOA和TOF。
如图7所示，为本发明方法与其他算法的估计结果的均方根误差(RMSE)的比较图，可以看出，与本发明所提方法相比，另外两种方法(SpoFi和Join-2D)的AOA和TOF的估计RMSE均随着SNR的的增加而减小；由于训练样本包括多个信噪比下的数据，训练得到的网络有很好的泛化能力，所以 在不同信噪比下有更为稳定的估计结果；从结果可以看出本文所提出的方法在任一信噪比下均比另两种方法表现更好。
如图8所示，以左图中的AOA估计误差分布为例，从误差分布来看，本发明的AOA的估计误差都分布在10°以内，而另外两种方法的估计误差在10°以内的数据量仅占总数据的80％和70％，有将近20％的数据估计误差超过了30°，即不能准确识别。
本发明所提方法的另一个优势在于，即使两条路径的到达角度和到达时间相近也能准确地识别出来，而另外两种在这种情况下的识别情况并不理想。这是因为SpoFi和Join-2D中的估计算法都是基于MUSIC算法做出的改进算法，其中MUSIC算法利用了信号的信号子空间和噪声子空间的正交性构造空间谱函数，通过谱峰搜索来估计AOA，如果谱峰相近的话，很难将其区分，所以传统算法具有一定的分辨率局限性，本发明所提的基于神经网络的方法通过提取信号的相关特征来估计AOA和TOF，各个路径之间的估计值互不影响，故不存在分辨率不足的问题，在表1情况下，SpoFi和Join-2D由于分辨率较低只能识别出一条路径，而本发明所提方法可以在一定误差范围内将两条路径都准确地识别出来。
表1相近AOA路径下的估计结果(null表示识别失败)
真实值SpoFi Join-2D本发明方法路径1：(123°,96ns)(125°,107ns)(124°,99ns)(123.6°,85ns)路径2：(132°,102ns)null null(133.7°,94ns)
实施例2：
本实施例提供了一种装置，包括处理器及存储介质；
所述存储介质用于存储指令；
所述处理器用于根据所述指令进行操作以执行实施例1所述方法的步骤。
实施例3：
本实施例提供了一种存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现实施例1所述方法的步骤。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个 流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明技术原理的前提下，还可以做出若干改进和变形，这些改进和变形也应视为本发明的保护范围。

Claims (9)

  1. 用于室内定位的AOA和TOF联合估计方法，其特征在于，所述方法包括：
    对获取的CSI数据进行预处理，获得处理后的数据；
    将处理后的数据输入预先训练好的联合估计模型，得到处理后的数据所对应的AOA和TOF；
    所述联合估计模型通过深度卷积神经网络训练得到，所述深度卷积神经网络采用不同大小卷积核并联。
  2. 根据权利要求1所述的用于室内定位的AOA和TOF联合估计方法，其特征在于，所述获取的CSI数据表示为复数数据矩阵图像，所述处理后的数据表示为实数矩阵图像。
  3. 根据权利要求2所述的用于室内定位的AOA和TOF联合估计方法，其特征在于，所述处理后的数据表示为三通道实数矩阵图像。
  4. 根据权利要求3所述的用于室内定位的AOA和TOF联合估计方法，其特征在于，所述三通道实数矩阵图像的获取包括：
    将获取的CSI数据的复数数据矩阵及其共轭矩阵，按实部和虚部分成四个子矩阵并进行重组，获得重组矩阵；
    通过滑动步长为2、4和6的滑动窗口，分别对所述重组矩阵进行移位截取，分别得到若干个子矩阵，再将分别得到的若干个子矩阵拼接，获得三个矩阵，所述三个矩阵组成即获取的三通道实数矩阵图像。
  5. 根据权利要求1所述的用于室内定位的AOA和TOF联合估计方法，其特征在于，所述深度卷积神经网络包括输入层、7*7卷积层、最大池化层、1*1的卷积层、3*3卷积层、池化层、2个Inception结构、最大池化 层、3个Inception结构、最大池化层、2个Inception结构、平均池化层、全连接层、输出层。
  6. 根据权利要求5所述的用于室内定位的AOA和TOF联合估计方法，其特征在于，所述Inception结构包括四层：第一层为输入层，第二层为1*1卷积层、1*1卷积层、3*3最大池化层和1*1卷积层，第三层为3*3卷积层、5*5卷积层和1*1卷积层，第四层为输出层。
  7. 根据权利要求1所述的用于室内定位的AOA和TOF联合估计方法，其特征在于，所述联合估计模型的训练包括：
    获取历史CSI数据以及CSI数据对应的AOA和TOF，构建数据集；
    对所述数据集进行预处理，构建训练集；
    将训练集通过深度卷积神经网络进行训练，得到联合估计模型。
  8. 一种装置，其特征在于，包括处理器及存储介质；
    所述存储介质用于存储指令；
    所述处理器用于根据所述指令进行操作以执行根据权利要求1至7任一项所述方法的步骤。
  9. 一种存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至7任一项所述方法的步骤。
PCT/CN2022/128242 2021-12-24 2022-10-28 用于室内定位的aoa和tof联合估计方法、装置及存储介质 Ceased WO2023116196A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111601839.7A CN114386321B (zh) 2021-12-24 2021-12-24 用于室内定位的aoa和tof联合估计方法、装置及存储介质
CN202111601839.7 2021-12-24

Publications (1)

Publication Number Publication Date
WO2023116196A1 true WO2023116196A1 (zh) 2023-06-29

Family

ID=81198452

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/128242 Ceased WO2023116196A1 (zh) 2021-12-24 2022-10-28 用于室内定位的aoa和tof联合估计方法、装置及存储介质

Country Status (2)

Country Link
CN (1) CN114386321B (zh)
WO (1) WO2023116196A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117034077A (zh) * 2023-07-21 2023-11-10 南京邮电大学 基于迁移学习和gasf的csi定位方法、装置及设备
CN117315886A (zh) * 2023-09-07 2023-12-29 安徽建筑大学 一种基于uwb雷达的人员即将跌倒检测方法及装置
CN117452332A (zh) * 2023-12-26 2024-01-26 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) 一种位置确定方法及装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114386321B (zh) * 2021-12-24 2025-09-02 南京邮电大学 用于室内定位的aoa和tof联合估计方法、装置及存储介质
CN114581958B (zh) * 2022-05-06 2022-08-16 南京邮电大学 一种基于csi信号到达角估计的静态人体姿势估计方法
CN115267655A (zh) * 2022-08-02 2022-11-01 上海师范大学 一种基于多任务学习卷积神经网络的时延-到达角联合估计方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110351658A (zh) * 2019-06-03 2019-10-18 西北大学 一种基于卷积神经网络的室内定位方法
CN111212379A (zh) * 2020-01-06 2020-05-29 天津工业大学 一种基于卷积神经网络的新型csi室内定位方法
CN111698695A (zh) * 2019-04-28 2020-09-22 南京恩瑞特实业有限公司 一种基于神经网络的lte指纹式定位方法
CN114386321A (zh) * 2021-12-24 2022-04-22 南京邮电大学 用于室内定位的aoa和tof联合估计方法、装置及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4008094A1 (en) * 2019-05-03 2022-06-08 Lenovo (Singapore) Pte. Ltd. Method and apparatus for determining validity information for a protocol data unit session
CN113613170A (zh) * 2021-08-16 2021-11-05 苏州云享阁智能科技有限公司 一种基于低成本天线扩展的高精度室内定位系统及方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111698695A (zh) * 2019-04-28 2020-09-22 南京恩瑞特实业有限公司 一种基于神经网络的lte指纹式定位方法
CN110351658A (zh) * 2019-06-03 2019-10-18 西北大学 一种基于卷积神经网络的室内定位方法
CN111212379A (zh) * 2020-01-06 2020-05-29 天津工业大学 一种基于卷积神经网络的新型csi室内定位方法
CN114386321A (zh) * 2021-12-24 2022-04-22 南京邮电大学 用于室内定位的aoa和tof联合估计方法、装置及存储介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117034077A (zh) * 2023-07-21 2023-11-10 南京邮电大学 基于迁移学习和gasf的csi定位方法、装置及设备
CN117315886A (zh) * 2023-09-07 2023-12-29 安徽建筑大学 一种基于uwb雷达的人员即将跌倒检测方法及装置
CN117315886B (zh) * 2023-09-07 2024-04-12 安徽建筑大学 一种基于uwb雷达的人员即将跌倒检测方法及装置
CN117452332A (zh) * 2023-12-26 2024-01-26 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) 一种位置确定方法及装置
CN117452332B (zh) * 2023-12-26 2024-03-12 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) 一种位置确定方法及装置

Also Published As

Publication number Publication date
CN114386321A (zh) 2022-04-22
CN114386321B (zh) 2025-09-02

Similar Documents

Publication Publication Date Title
CN114386321B (zh) 用于室内定位的aoa和tof联合估计方法、装置及存储介质
US12276746B2 (en) Sound source identification method and system based on array measurement and sparse prior information
CN112153736B (zh) 一种基于信道状态信息的人员动作识别和位置估计方法
CN108802722B (zh) 一种基于虚拟谱的弱目标检测前跟踪方法
CN106842165B (zh) 一种基于不同距离角度分辨率雷达集中式异步融合方法
CN103297924B (zh) 基于信道估计的新型定位指纹设计方法及室内定位系统
CN107202976B (zh) 低复杂度的分布式麦克风阵列声源定位系统
CN109738861A (zh) 一种基于Wi-Fi信道状态信息的三维联合估计方法
CN109683126A (zh) 波达角测量方法、信号处理设备及存储介质
CN111479231A (zh) 一种用于毫米波大规模mimo系统的室内指纹定位方法
CN110045322B (zh) 一种基于高分辨测向语图智能识别的短波自动测向方法
CN103237344A (zh) 一种基于接收信号强度指示的室内无线传感器网络定位方法
CN108182474A (zh) 基于未校正阵列和神经网络的多目标直接定位方法
CN113259837B (zh) 基于角度估计和指纹定位算法的室内定位方法
CN108710758A (zh) 基于嵌套阵和协方差矩阵重构的自适应波束形成算法
CN109709510A (zh) 一种相干信源二维波达方向的估计方法及系统
CN105301557A (zh) 波达方位估计架构方法
CN111505565B (zh) 一种估计直接路径到达角的方法
Zhang et al. Indoor fingerprint localization algorithm based on WKNN and LightGBM-GA
CN109932679A (zh) 一种传感器列系统最大似然角度分辨率估计方法
CN117528770A (zh) 用多样化数据的特征提取增强的室内指纹定位方法及系统
CN114972460B (zh) 一种结合图特征上下文匹配的点云配准方法
CN115278516A (zh) 一种基于深度残差网络的鲁棒无线图像指纹室内定位算法
CN100566345C (zh) 基于超宽带的无线传感器网络节点定位方法
CN105425204A (zh) 波达方位估计架构方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22909514

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22909514

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27.01.2025)

122 Ep: pct application non-entry in european phase

Ref document number: 22909514

Country of ref document: EP

Kind code of ref document: A1