Radiation source positioning method and apparatus, computer device, and storage medium

Abstract

The application relates to a radiation source positioning method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring signal information of a target radiation source in a target area and position information of each sensor; the signal information of the target radiation source comprises a signal frequency of the target radiation source and a signal strength of the target radiation source; for each sensor, according to a signal propagation loss network of the sensor, geographical data information detected by the sensor, the position information of the sensor and the signal information of the target radiation source, the position range data of the target radiation source detected by the sensor is determined; the position range data of the target radiation source detected by all the sensors is input into a radiation source positioning model to obtain a position probability distribution matrix of the target radiation source in the target area, and the position information of the target radiation source is determined according to the position probability distribution matrix. The method can improve the positioning accuracy of the target radiation source.

Description

Technical Field

[0001] This application relates to the field of passive positioning technology, and in particular to a radiation source positioning method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the continuous improvement of urbanization and informatization, urban spaces have become the most concentrated areas of human social activities, and the urban electromagnetic environment is becoming increasingly complex. Therefore, electromagnetic monitoring and protection of urban spaces are becoming increasingly important. The presence of illegal electromagnetic radiation targets may occupy spectrum resources without permission or maliciously interfere with other communication systems, leading to data loss and other communication failures in important communication networks. Locating illegal radiation sources is crucial for maintaining the safety of the urban electromagnetic environment.

[0003] Traditional techniques rely on geometric positioning principles, using time of arrival (TOA), time difference of arrival (TDOA), and angle of arrival (AOA), along with trilateration based on received signal strength, to determine the location of a radiation source. However, this method requires a line-of-sight path for the transmitted signal between the transmitter and receiver. In complex urban electromagnetic environments, signals typically reach the receiver via multiple reflections and diffraction, creating non-line-of-sight paths. In such environments, where a line-of-sight path doesn't exist, this method fails, leading to significant discrepancies between the located radiation source and its actual location. Summary of the Invention

[0004] Therefore, it is necessary to provide a radiation source location method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for locating a radiation source. The method includes:

[0006] Acquire signal information of the target radiation source in the target area, as well as the position information of each sensor; the signal information of the target radiation source includes the signal frequency and the signal intensity of the target radiation source;

[0007] For each sensor, the location range data of the target radiation source detected by the sensor is determined based on the sensor's signal propagation loss network, the geographic data information detected by the sensor, the sensor's location information, and the signal information of the target radiation source.

[0008] The location range data of the target radiation source detected by all sensors are input into the radiation source localization model to obtain the location probability distribution matrix of the target radiation source in the target area, and the location information of the target radiation source is determined according to the location probability distribution matrix.

[0009] Optionally, the method further includes:

[0010] The system acquires signal information of each sample radiation source, location information of each sample radiation source, and geographic data information detected by each sensor; the geographic data information is used to represent the location information of each obstacle detected by the sensor in the target area.

[0011] For each sensor, a signal propagation loss network is determined based on the geographic data detected by the sensor, the sensor's location information, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the location information of each sample radiation source, and a signal propagation loss algorithm.

[0012] Optionally, determining the location range data of the target radiation source detected by the sensor based on the signal propagation loss network of the sensor, the geographical data information detected by the sensor, the location information of the sensor, and the signal information of the target radiation source includes:

[0013] The signal information of the target radiation source and the geographical data information detected by the sensor are input into the signal propagation loss network of the sensor to obtain the signal transmission loss of the target radiation source.

[0014] Based on the signal transmission loss of the target radiation source and the location information of the sensor, the location range data of the target radiation source is determined from the geographical data information detected by the sensor.

[0015] Optionally, the radiation source localization model includes a downsampling layer, an upsampling layer, and a convolutional layer; the step of inputting the location range data of the target radiation source detected by all sensors into the radiation source localization model to determine the location probability distribution matrix of the target radiation source in the target area includes:

[0016] The location range data of the target radiation source are input into the downsampling layer to extract the location feature information of the target radiation source.

[0017] By using an upsampling layer, the location feature information of the target radiation source is fused to obtain a probability distribution map of the target radiation source.

[0018] By using a convolutional layer, the probability distribution map of the target radiation source is convolved to obtain the position probability distribution matrix of the target radiation source in the target region.

[0019] Optionally, determining the signal propagation loss network of the sensor based on the geographic data information detected by the sensor, the location information of the sensor, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the location information of each sample radiation source, and a signal propagation loss algorithm includes:

[0020] For each sample radiation source, the signal propagation loss of the sample radiation source is determined based on the signal information of the sample radiation source, the signal transmission intensity of the sample radiation source detected by the sensor, and the signal propagation loss algorithm.

[0021] Based on the signal propagation loss of the sample radiation source, the location information of the sensor, and the location information of the sample radiation source, the signal attenuation of each obstacle detected by the sensor is determined from the geographical data information detected by the sensor.

[0022] Based on the signal attenuation of all obstacles detected by the sensor and the signal propagation loss algorithm, the signal propagation loss network of the sensor is determined.

[0023] Optionally, the method further includes:

[0024] Acquire the location information of each sample radiation source in the sample area, the signal information of each sample radiation source, and the location information of each sample sensor;

[0025] For each sample radiation source, the location range data of each sample radiation source are determined based on the signal information of the sample radiation source, the location information of each sample sensor, the location information of each sensor, and the signal propagation loss network of each sample sensor.

[0026] The location range data of each sample radiation source are input into the initial radiation source localization model to determine the location probability distribution matrix of the sample radiation source in the sample area; and the sample location information of the sample radiation source is determined based on the location probability distribution matrix.

[0027] The initial radiation source localization model is trained using the sample location information of the sample radiation source, the location information of the sample radiation source, and the weighted loss function to obtain the radiation source localization model.

[0028] Secondly, this application also provides a radiation source locating device. The device includes:

[0029] The first acquisition module is used to acquire signal information of the target radiation source in the target area and position information of each sensor; the signal information of the target radiation source includes the signal frequency and signal strength of the target radiation source.

[0030] The first determining module is used to determine the location range data of the target radiation source detected by the sensor for each sensor, based on the signal propagation loss network of the sensor, the geographical data information detected by the sensor, the location information of the sensor, and the signal information of the target radiation source.

[0031] The first positioning module is used to input the location range data of the target radiation source detected by all sensors into the radiation source positioning model to obtain the location probability distribution matrix of the target radiation source in the target area, and determine the location information of the target radiation source based on the location probability distribution matrix.

[0032] Optionally, the device further includes:

[0033] The second acquisition module is used to acquire signal information of each sample radiation source, location information of each sample radiation source, and geographic data information detected by each sensor; the geographic data information is used to represent the location information of each obstacle detected by the sensor in the target area;

[0034] The training module is used to determine the signal propagation loss network of each sensor based on the geographical data information detected by the sensor, the location information of the sensor, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the location information of each sample radiation source, and the signal propagation loss algorithm.

[0035] Optionally, the first determining module is specifically used for:

[0036] The signal information of the target radiation source and the geographical data information detected by the sensor are input into the signal propagation loss network of the sensor to obtain the signal transmission loss of the target radiation source.

[0037] Based on the signal transmission loss of the target radiation source and the location information of the sensor, the location range data of the target radiation source is determined from the geographical data information detected by the sensor.

[0038] Optionally, the radiation source localization model includes a downsampling layer, an upsampling layer, and a convolutional layer; the first localization module is specifically used for:

[0039] The location range data of the target radiation source are input into the downsampling layer to extract the location feature information of the target radiation source.

[0040] By using an upsampling layer, the location feature information of the target radiation source is fused to obtain a probability distribution map of the target radiation source.

[0041] By using a convolutional layer, the probability distribution map of the target radiation source is convolved to obtain the position probability distribution matrix of the target radiation source in the target region.

[0042] Optionally, the first training module is specifically used for:

[0043] For each sample radiation source, the signal propagation loss of the sample radiation source is determined based on the signal information of the sample radiation source, the signal transmission intensity of the sample radiation source detected by the sensor, and the signal propagation loss algorithm.

[0044] Based on the signal propagation loss of the sample radiation source, the location information of the sensor, and the location information of the sample radiation source, the signal attenuation of each obstacle detected by the sensor is determined from the geographical data information detected by the sensor.

[0045] Based on the signal attenuation of all obstacles detected by the sensor and the signal propagation loss algorithm, the signal propagation loss network of the sensor is determined.

[0046] Optionally, the device further includes:

[0047] The second acquisition module is used to acquire the location information of each sample radiation source in the sample area, the signal information of each sample radiation source, and the location information of each sample sensor.

[0048] The second determining module is used to determine the location range data of each sample radiation source for each sample radiation source based on the signal information of the sample radiation source, the location information of each sample sensor, the location information of each sensor, and the signal propagation loss network of each sample sensor.

[0049] The second positioning module is used to input the location range data of the sample radiation source into the initial radiation source positioning model, determine the location probability distribution matrix of the sample radiation source in the sample area, and determine the sample location information of the sample radiation source based on the location probability distribution matrix.

[0050] The second training module is used to train the initial radiation source localization model using the sample location information of the sample radiation source, the location information of the sample radiation source, and a weighted loss function, so as to obtain the radiation source localization model.

[0051] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0052] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0053] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0054] The aforementioned radiation source localization method, apparatus, computer equipment, and storage medium acquire signal information of a target radiation source in a target area, as well as location information of each sensor. The signal information of the target radiation source includes its signal frequency and signal strength. For each sensor, based on its signal propagation loss network, the geographic data detected by the sensor, its location information, and the signal information of the target radiation source, the location range data of the target radiation source detected by the sensor is determined. The location range data of the target radiation source detected by all sensors are input into a radiation source localization model to obtain a probability distribution matrix of the target radiation source's location in the target area. Based on this probability distribution matrix, the location information of the target radiation source is determined. By considering the influencing factors of geographic data information between the target radiation source and each sensor, and by calculating the signal information of the target radiation source using the signal propagation loss network of each sensor, the location range data of the target radiation source is obtained. Finally, by using the location range of the target radiation source and the radiation source localization model, the target radiation source is located, thus improving the accuracy of locating the target radiation source. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating a radiation source localization method in one embodiment;

[0056] Figure 2 This is a flowchart illustrating the steps for determining the location range data of a target radiation source in one embodiment.

[0057] Figure 3 This is a flowchart illustrating the steps for determining the location probability distribution matrix of a target radiation source in one embodiment.

[0058] Figure 4 This is a flowchart illustrating the training method for a radiation source localization model in one embodiment;

[0059] Figure 5 This is a flowchart illustrating an example of radiation source localization in one embodiment;

[0060] Figure 6 This is a structural block diagram of a radiation source locating device in one embodiment;

[0061] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] The radiation source localization method provided in this application can be applied to a terminal, a server, or a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can include, but is not limited to, various personal computers, laptops, tablets, etc. This terminal is used to acquire signal information of the target radiation source in the target area, as well as the location information of each sensor. Based on the influencing factors of geographical data information between the target radiation source and each sensor, and the signal propagation loss network of each sensor, the target radiation source is located, thereby improving the accuracy of locating the target radiation source.

[0064] In one embodiment, such as Figure 1 As shown, a method for locating radiation sources is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0065] Step S101: Obtain the signal information of the target radiation source in the target area and the position information of each sensor.

[0066] The signal information of the target radiation source includes its signal frequency and signal strength. The signal frequency is used to distinguish whether the received radiation source signal is from the target radiation source, and the signal strength is used to determine the signal propagation range of the target radiation source.

[0067] In this embodiment, the terminal acquires the pre-set location information of each sensor within the target area, and obtains the signal information of the target radiation source based on the signal frequency and signal intensity of the target radiation source detected by each sensor in different directions. The sensors can detect the signal intensity of target radiation sources in different directions. For example, taking the location of sensor A as the center, with due north as 0 degrees and the angle increasing clockwise, the signal intensity of the target radiation source detected at a 39-degree angle of sensor A is 15 dBm; the signal intensity at a 45-degree angle of sensor A is 30 dBm; and the signal intensity at a 50-degree angle of sensor A is 20 dBm. The sum of the detection ranges of all sensors may not completely cover the entire target area.

[0068] Step S102: For each sensor, determine the location range data of the target radiation source detected by the sensor based on the sensor's signal propagation loss network, the geographic data information detected by the sensor, the sensor's location information, and the signal information of the target radiation source.

[0069] In this embodiment, for each sensor, the terminal calculates the signal strength of the target radiation source detected by the sensor based on the geographic data and the sensor's location information, using a pre-trained signal propagation loss network pre-programmed within the sensor. This calculation yields the signal strength radiated by the target radiation source in the absence of obstructions. Based on the geographic data detected by the sensor and the signal strength radiated by the target radiation source in the absence of obstructions, the terminal determines the location range data of the target radiation source. This location range data consists of image data showing the possible location range of the target radiation source within the target area. The specific process for determining the location range data will be explained in detail later.

[0070] The geographic data detected by the sensor may include, but is not limited to, geographic image data. This geographic image data refers to geographic images within the sensor's detection range in the target area. These images include images corresponding to factors affecting the propagation of the radiation source. These factors influence the signal strength and transmission path of the radiation source, thus altering its transmission characteristics. These influencing factors may include, but are not limited to, various obstacles, such as buildings, trees, grasslands, and rivers.

[0071] Step S103: Input the location range data of the target radiation source detected by all sensors into the radiation source localization model to determine the location probability distribution matrix of the target radiation source in the target area; and determine the location information of the target radiation source based on the location probability distribution matrix.

[0072] In this embodiment, the terminal inputs the location range data of the target radiation source detected by all sensors into the radiation source localization model. Using the radiation source localization model, the terminal first fuses the feature information from each location range data of the target radiation source to obtain comprehensive location range data of the target radiation source in the target area. Then, it calculates the probability distribution of this comprehensive location range data to obtain the location probability distribution matrix of the target radiation source in the target area. The location probability distribution matrix includes the probability value corresponding to each location information. The terminal selects the highest probability value from the target radiation source's location probability distribution matrix and uses the location information corresponding to this probability value as the location information of the target radiation source.

[0073] Specifically, the formula for selecting the location information corresponding to the highest probability value is:

[0074]

[0075] In the above formula, x i Let y be the x-coordinate of the location information with the highest probability in the probability distribution matrix. i The vertical coordinate represents the position information with the highest probability in the probability distribution matrix.

[0076] Based on the above scheme, the signal information of the target radiation source is calculated through the signal propagation loss network of each sensor to obtain the location range data of the target radiation source. Then, the target radiation source is located by using the location range of the target radiation source and the radiation source positioning model to obtain the location information of the target radiation source, thereby improving the accuracy of locating the target radiation source.

[0077] Optionally, after acquiring the signal information of the target radiation source in the target area and the location information of each sensor, the method further includes: acquiring the signal information of each sample radiation source, the location information of each sample radiation source, and the geographic data information detected by each sensor; the geographic data information is used to represent the location information of each obstacle detected by the sensor in the target area; for each sensor, based on the geographic data information detected by the sensor, the location information of the sensor, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the location information of each sample radiation source, and the signal propagation loss algorithm, the sensor's signal propagation loss network is determined.

[0078] In this embodiment, during the training process of the signal propagation loss network, the terminal uses a simulated geographical environment of the target area as the training environment and pre-sets multiple virtual radiation sources with different signal frequencies, signal strengths, and location information as sample radiation sources. The terminal trains the signal propagation loss network by simulating the radiation process of the radiation sources in the simulated geographical environment.

[0079] Specifically, with the location information of each sensor unchanged, in a simulated geographical environment, for each sensor, the terminal inputs its location information, the signal strength of each sample radiation source detected by the sensor, and the signal strength of each sample radiation source into a signal propagation loss algorithm to obtain signal strength attenuation data of the surrounding obstacles on the outward radiation of the sample radiation source. Based on the signal strength attenuation data of the surrounding obstacles and the signal propagation loss algorithm, a signal propagation loss network for the sensor is obtained. The signal propagation loss network includes the signal propagation loss algorithm. The signal information of the sample radiation source includes the signal frequency and the signal strength of the sample radiation source (i.e., the signal strength when the sample radiation source radiates outward).

[0080] Specifically, the sensor can detect the signal intensity of the sample radiation source in each direction. Since the signal transmission path of the sample radiation source is different in each direction, and the loss of signal propagation due to obstacles on each path is also different, the terminal needs to calculate the signal transmission loss of each transmission path of the sample radiation source, so as to provide data support for subsequently determining the signal transmission range of the sample signal source.

[0081] For each sample radiation source, the terminal determines the signal strength loss along each signal transmission path based on the signal information of that sample radiation source and the signal transmission intensity detected by the sensor. For each signal transmission path, based on the number of obstacles, the length, width, and height of the obstacles, the signal transmission loss of the sample radiation source along that path (i.e., the geographical data detected by the sensor), and a signal propagation loss algorithm, the terminal determines the signal strength attenuation of each obstacle within the sensor's detection range, centered on the sensor's location, to the radiation source of that signal frequency. Similarly, the terminal processes the signal information of each sample radiation source through the above steps to obtain the signal strength attenuation of each obstacle within the sensor's detection range, centered on the sensor's location, to multiple signal frequency radiation sources.

[0082] Based on the obstacles detected centered on the sensor's location information, the terminal analyzes the signal attenuation of radiation sources at multiple signal frequencies and uses a signal propagation loss algorithm to obtain the signal propagation loss network corresponding to that sensor. Similarly, the terminal processes each sensor using the same steps to obtain the signal propagation loss network for each sensor.

[0083] In one embodiment, S = {s1, s2, ..., s} P Let M = {m1, m2, ..., m} represent the set of locations of a single radiation source in G. QLet} represent the set of all receiving locations in G. Then, the length of the propagation path between the radiation source and the receiving point can be expressed as a function d(s). i ,m j ∈M(s i The unit is meters (m). This propagation path may change direction due to obstacles. When the propagation path direction changes, a function is used to... This indicates that the k-th interaction with the obstacle leads to a new propagation direction. The interaction loss during signal propagation. The formula for the signal propagation loss algorithm is as follows:

[0084]

[0085] Where f is the electromagnetic wave frequency in MHz; the coefficient p is determined by the line-of-sight and non-line-of-sight conditions of the propagation path; and the waveguide coefficient w reflects the reflection and refraction of the radiation source signal by obstacles during propagation along the main path. Since received signal strength (RSS) has the lowest sensor requirements and is easily measured, RSS is used as the measured physical quantity in this study. Therefore, in m... j The RSS at a given location can be obtained using the following formula:

[0086] P r (s i ,m j ) = P t (s i )-L(s i ,m j )

[0087] Among them, P r (s i ) indicates that it is located at s i The emission power of the radiation source at that location. Using H... full ={P r (s i ,m j )} represents the RSS collection within the target area.

[0088] Based on the above scheme, the terminal improves the accuracy of each sensor in detecting target signal sources in the geographical environment of the target area by training the signal propagation loss network of each sensor.

[0089] Optional, such as Figure 2 As shown, based on the sensor's signal propagation loss network, the geographic data detected by the sensor, the sensor's location information, and the signal information of the target radiation source, the location range data of the target radiation source detected by the sensor is determined, including:

[0090] Step S201: Input the signal information of the target radiation source and the geographical data information detected by the sensor into the signal propagation loss network of the sensor to obtain the signal transmission loss of the target radiation source.

[0091] In this embodiment, for each sensor, the terminal inputs the signal information of the target radiation source and the geographical data information detected by the sensor into the signal propagation loss algorithm in the signal propagation loss network of the sensor to obtain the signal transmission loss of each propagation path from the target radiation source to the sensor.

[0092] Step S202: Based on the signal transmission loss of the target radiation source and the location information of the sensor, determine the location range data of the target radiation source from the geographical data information detected by the sensor.

[0093] In this embodiment, the terminal, considering the signal propagation loss along each signal propagation path from the target radiation source to the sensor, determines the signal transmission strength of the target radiation source (i.e., the signal strength when the signal is transmitted to the sensor) along the transmission path in the absence of obstacles, based on the signal transmission loss of that path, the sensor's location information, and the number and range of obstacles detected by the sensor in the geographical data. Since, in the absence of obstacles, the straight-line signal propagation path has the shortest distance and the least signal transmission loss among all signal propagation paths, the sensor can detect the maximum signal strength of the radiation source. In the absence of obstacles, the terminal selects the transmission path with the highest signal transmission strength of the target radiation source and, using that path as the center, determines the location range data of the target radiation source within a preset angle range. The location range data of the target radiation source detected by a single sensor is represented as a fan-shaped region bounded by the target area.

[0094] Based on the above scheme, the terminal determines the location range data of the target radiation source detected by the sensor by using the signal propagation loss network of each sensor, the signal information of the target radiation source, the geographical data detected by the sensor, and the location information of the sensor. This provides data for subsequent calculation of the specific location information of the target radiation source.

[0095] Optionally, the radiation source localization model includes downsampling layers, upsampling layers, and convolutional layers; correspondingly, such as Figure 3 As shown, the location range data of the target radiation source detected by all sensors are input into the radiation source localization model to determine the probability distribution matrix of the target radiation source's location in the target area, including:

[0096] Step S301: Input the location range data of the target radiation source into the downsampling layer and extract the location feature information of the target radiation source.

[0097] In this embodiment, the terminal inputs the location range data of the target radiation source detected by each sensor into the downsampling layer of the radiation source localization model. Through multiple sampling and extraction operations of the downsampling layer, the feature information of each location range data of the target radiation source is extracted, and the feature information of each location range data is used as the location feature information of the target radiation source. The number of downsampling layers can be, but is not limited to, 5, that is, 5 downsampling and extraction operations are performed on each location range data of the target radiation source. The location range data is represented as a sparse sensing matrix.

[0098] Specifically, the downsampling layer includes an extraction module, a convolution module, an activation module, and a pooling module. For each downsampling process, the location range data of the target radiation source is input into the downsampling layer. The extraction module of the downsampling layer extracts the feature information from the location range data. This feature information is then input into two 3×3 convolution modules in the downsampling layer for convolution. The convolutional feature information is then input into the activation module in the downsampling layer for activation processing. Finally, it is input into the pooling module for pooling processing to obtain the feature information at each location. The max pooling module can be, but is not limited to, a max pooling layer; the activation module can be, but is not limited to, a ReLU activation layer; and the extraction module can be, but is not limited to, the residual module of the ResNet extractor.

[0099] Step S302: The location feature information of the target radiation source is fused through the upsampling layer to obtain the probability distribution map of the target radiation source.

[0100] In this embodiment, the terminal first processes the high-dimensional location feature information obtained from the downsampling layer, then performs dimensionality reduction using bilinear interpolation, ensuring that the dimension of the reduced high-dimensional location feature information is the same as the dimension of the low-dimensional location feature information in each location feature information. The terminal then multiplies the reduced high-dimensional location feature information with the low-dimensional location feature information in each location feature information to complete the multi-dimensional feature information fusion operation, obtaining the probability distribution map of the target radiation source. The number of upsampling layers can be, but is not limited to, four, meaning that four upsampling operations are performed on the location range data of the target radiation source.

[0101] Specifically, before upsampling, the terminal first uses 3×3 and 1×1 convolutional layers to unify the number of channels of high-dimensional feature information and low-dimensional feature information in each location feature information, and then performs upsampling processing on each location feature information.

[0102] Step S303: The probability distribution map of the target radiation source is convolved by a convolutional layer to obtain the position probability distribution matrix of the target radiation source in the target region.

[0103] In this embodiment, the terminal performs convolution processing on the probability distribution map of the target radiation source through a convolutional layer, and extracts and labels the probability of each location information in the probability distribution map to obtain the location probability distribution matrix of the target radiation source in the target area.

[0104] In this embodiment, the terminal performs feature extraction on the location range data of the target radiation source obtained by each sensor, and performs convolution processing on the extracted location feature information to obtain the location probability distribution matrix of the target radiation source in the target area, thereby improving the accuracy of subsequently determining the specific location information of the target radiation source.

[0105] Optionally, based on the geographic data information detected by the sensor, the sensor's location information, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the location information of each sample radiation source, and the signal propagation loss algorithm, the signal propagation loss network of the sensor is determined. This includes: for the signal information of each sample radiation source, determining the signal propagation loss of the sample radiation source based on the signal information of the sample radiation source, the signal transmission intensity of the sample radiation source detected by the sensor, and the signal propagation loss algorithm; determining the signal attenuation of each obstacle detected by the sensor in the geographic data information detected by the sensor based on the signal propagation loss of the sample radiation source, the sensor's location information, and the location information of the sample radiation source; and determining the signal propagation loss network of the sensor based on the signal attenuation of all obstacles detected by the sensor and the signal propagation loss algorithm.

[0106] In this embodiment, for each sample radiation source, the terminal inputs the signal information of the sample radiation source and the signal transmission strength detected by the sensor into an initial signal propagation loss network to obtain the signal propagation loss of each signal propagation path of the sample radiation source. Based on the signal propagation loss of each signal propagation path, the sensor's location information, and the sample radiation source's location information, the terminal determines, from the geographic data detected by the sensor, the number of obstacles between the target radiation source and the sensor in each signal propagation path, and the signal transmission strength of the target radiation source in the absence of obstacles in each signal propagation path. Based on the number of obstacles between the target radiation source and the sensor in each signal propagation path, and the signal transmission strength of the target radiation source in the absence of obstacles, the terminal determines the signal attenuation of each obstacle detected by the sensor.

[0107] Similarly, the terminal processes each sample radiation source through the above steps to obtain the signal attenuation of all obstacles detected by the sensor. Based on the signal attenuation of all obstacles detected by the sensor and the signal propagation loss algorithm, the terminal determines the signal propagation loss network of the sensor.

[0108] Based on the above scheme, the terminal improves the efficiency and accuracy of subsequent calculation of the target radiation source's location information by obtaining in advance the signal attenuation of all obstacles detected by the sensors in the target area.

[0109] Optional, such as Figure 4 As shown, the method also includes:

[0110] Step S401: Obtain the location information of each sample radiation source in the sample area, the signal information of each sample radiation source, and the location information of each sample sensor.

[0111] In this embodiment, the terminal presets the location information of each sample sensor and presets multiple sample radiation sources with different signal frequencies, signal intensities, and location information within the sample area. The terminal uses the signal intensity and signal frequency of the sample radiation sources as the signal information of the sample radiation sources. The specific process is shown in step S101.

[0112] Step S402: For each sample radiation source, determine the location range data of each sample radiation source based on the signal information of the sample radiation source, the location information of each sample sensor, the location information of each sensor, and the signal propagation loss network of each sample sensor.

[0113] In this embodiment, for each sample radiation source and each sensor, the terminal inputs the signal information of the sample radiation source and the location information of the sample sensor into the signal propagation loss network of each sample sensor to obtain the signal loss of the sample radiation source. Based on the signal transmission loss of the target radiation source and the location information of the sensor, the terminal determines the location range data of the target radiation source from the geographical data detected by the sensor. Similarly, the terminal performs the above operation for each sensor to obtain the location range data of each sample radiation source. For detailed processing, see step S102.

[0114] Step S403: Input the location range data of each sample radiation source into the initial radiation source positioning model to determine the location probability distribution matrix of the sample radiation source in the sample area; and determine the sample location information of the sample radiation source based on the location probability distribution matrix.

[0115] In this embodiment, for each sample radiation source, the terminal inputs the location range data of that sample radiation source into the initial radiation source localization model to determine the location probability distribution matrix of that sample radiation source in the sample area. The terminal selects the location information with the highest probability from the location probability distribution matrix of the sample radiation source and uses this location information as the sample location information of that sample radiation source. Similarly, the terminal performs the above operation for each sample radiation source to obtain the sample location information of each sample radiation source. For detailed processing steps, please refer to step S103.

[0116] Step S404: Train the initial radiation source localization model using the sample location information of the sample radiation source, the location information of the sample radiation source, and the weighted loss function to obtain the radiation source localization model.

[0117] In this embodiment, the terminal trains the initial radiation source localization model using a weighted loss function, sample location information of the sample radiation source, and location information of the sample radiation source to obtain the radiation source localization model.

[0118] Specifically, the key to training the initial radiation source localization model lies in minimizing the loss function between the output and the label. For example, assuming the weight distribution decreases outwards from the label location using a two-dimensional normal probability density function, the weight matrix W can be expressed as:

[0119]

[0120] Where (x) i ,y i ) is the radiation source s i The coordinates of W are also the center of the weighting, and W has the same size as the input-output matrix. Setting the radius of the weighting range to R = 3σ, the probability of the radiation source appearing within the weighting range is 99.7%. In other words, by weighting the loss function, we expand the neural network's focus on location features from a single pixel to a region of radius R, with stronger focus closer to the actual location of the radiation source. The formula for the weighted loss function is:

[0121]

[0122] Based on the above scheme, the initial radiation source localization model is trained by a weighted loss function to obtain the radiation source localization model, thereby improving the accuracy of the radiation source localization model.

[0123] This application also provides an example of radiation source location, such as... Figure 5 As shown, the specific processing procedure includes the following steps:

[0124] Step S501: Obtain the signal information of the target radiation source in the target area and the position information of each sensor.

[0125] The signal information of the target radiation source includes the signal frequency and signal strength of the target radiation source.

[0126] Step S502: For each sensor, input the signal information of the target radiation source and the geographical data detected by the sensor into the sensor's signal propagation loss network to obtain the signal transmission loss of the target radiation source.

[0127] Step S503: Based on the signal transmission loss of the target radiation source and the location information of the sensor, determine the location range data of the target radiation source from the geographical data information detected by the sensor.

[0128] Step S504: Input the location range data of the target radiation source into the downsampling layer and extract the location feature information of the target radiation source.

[0129] Step S505: The location feature information of the target radiation source is fused through the upsampling layer to obtain the probability distribution map of the target radiation source.

[0130] Step S506: The probability distribution map of the target radiation source is convolved through a convolutional layer to obtain the position probability distribution matrix of the target radiation source in the target region.

[0131] Step S507: Determine the location information of the target radiation source based on the location probability distribution matrix.

[0132] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0133] Based on the same inventive concept, this application also provides a radiation source locating device for implementing the radiation source locating method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more radiation source locating device embodiments provided below can be found in the limitations of the radiation source locating method described above, and will not be repeated here.

[0134] In one embodiment, such as Figure 6 As shown, a radiation source locating device is provided, comprising: a first acquisition module 610, a first determination module 620, and a first positioning module 630, wherein:

[0135] The first acquisition module 610 is used to acquire the signal information of the target radiation source in the target area and the position information of each sensor; the signal information of the target radiation source includes the signal frequency and the signal strength of the target radiation source.

[0136] The first determining module 620 is used to determine the location range data of the target radiation source detected by the sensor for each sensor, based on the sensor's signal propagation loss network, the geographic data information detected by the sensor, the sensor's location information, and the signal information of the target radiation source.

[0137] The first positioning module 630 is used to input the location range data of the target radiation source detected by all sensors into the radiation source positioning model to obtain the location probability distribution matrix of the target radiation source in the target area, and determine the location information of the target radiation source based on the location probability distribution matrix.

[0138] Optionally, the device may also include:

[0139] The second acquisition module is used to acquire signal information of each sample radiation source, location information of each sample radiation source, and geographic data information detected by each sensor; the geographic data information is used to represent the location information of each obstacle detected by the sensor in the target area;

[0140] The first training module is used to determine the signal propagation loss network of each sensor based on the geographic data information detected by the sensor, the sensor's location information, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the location information of each sample radiation source, and the signal propagation loss algorithm.

[0141] Optionally, the first determining module 620 is specifically used for:

[0142] The signal information of the target radiation source and the geographical data detected by the sensor are input into the signal propagation loss network of the sensor to obtain the signal transmission loss of the target radiation source.

[0143] Based on the signal transmission loss of the target radiation source and the location information of the sensor, the location range data of the target radiation source is determined from the geographical data information detected by the sensor.

[0144] Optionally, the radiation source localization model includes a downsampling layer, an upsampling layer, and a convolutional layer; the first localization module 630 is specifically used for:

[0145] Input the location range data of the target radiation source into the downsampling layer to extract the location feature information of the target radiation source;

[0146] By using an upsampling layer, the location feature information of the target radiation source is fused to obtain a probability distribution map of the target radiation source.

[0147] By using convolutional layers, the probability distribution map of the target radiation source is convolved to obtain the position probability distribution matrix of the target radiation source in the target region.

[0148] Optional, the first training module is specifically used for:

[0149] For each sample radiation source, the signal propagation loss of the sample radiation source is determined based on the signal information of the sample radiation source, the signal transmission intensity of the sample radiation source detected by the sensor, and the signal propagation loss algorithm.

[0150] Based on the signal propagation loss of the sample radiation source, the location information of the sensor, and the location information of the sample radiation source, the signal attenuation of each obstacle detected by the sensor is determined in the geographic data information detected by the sensor.

[0151] Based on the signal attenuation of all obstacles detected by the sensor and the signal propagation loss algorithm, the signal propagation loss network of the sensor is determined.

[0152] Optionally, the device may also include:

[0153] The second acquisition module is used to acquire the location information of each sample radiation source in the sample area, the signal information of each sample radiation source, and the location information of each sample sensor.

[0154] The second determining module is used to determine the location range data of each sample radiation source for each sample radiation source based on the signal information of the sample radiation source, the location information of each sample sensor, the location information of each sensor, and the signal propagation loss network of each sample sensor.

[0155] The second positioning module is used to input the location range data of each sample radiation source into the initial radiation source positioning model to determine the location probability distribution matrix of the sample radiation source in the sample area; and to determine the sample location information of the sample radiation source based on the location probability distribution matrix.

[0156] The second training module is used to train the initial radiation source localization model using the sample location information of the sample radiation source, the location information of the sample radiation source, and the weighted loss function, so as to obtain the radiation source localization model.

[0157] Each module in the aforementioned radiation source locating device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0158] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a radiation source localization method. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0159] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0160] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0161] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0162] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0163] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0164] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0165] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0166] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of positioning a radiation source, characterized by, The method comprises: acquiring signal information of a target radiation source in a target area, and position information of each sensor; the signal information of the target radiation source comprises a signal frequency of the target radiation source, and a signal intensity of the target radiation source; for each sensor, determining position range data of the target radiation source detected by the sensor according to a signal propagation loss network of the sensor, geographical data information detected by the sensor, position information of the sensor, and signal information of the target radiation source; inputting each position range data of the target radiation source into a down-sampling layer to extract each position feature information of the target radiation source; performing fusion processing on each position feature information of the target radiation source through an up-sampling layer to obtain a probability distribution map of the target radiation source; performing convolution processing on the probability distribution map of the target radiation source through a convolution layer to obtain a position probability distribution matrix of the target radiation source in the target area; determining position information of the target radiation source according to the position probability distribution matrix.

2. The method of claim 1, wherein, The method further comprises: acquiring signal information of each sample radiation source, position information of each sample radiation source, and geographical data information detected by each sensor; the geographical data information is used to represent position information of each obstacle detected by the sensor in the target area; for each sensor, determining a signal propagation loss network of the sensor according to geographical data information detected by the sensor, position information of the sensor, signal transmission intensity of each sample radiation source detected by the sensor, signal information of each sample radiation source, position information of each sample radiation source, and a signal propagation loss algorithm.

3. The method of claim 1, wherein, The determination of the position range data of the target radiation source detected by the sensor according to the signal propagation loss network of the sensor, the geographical data information detected by the sensor, the position information of the sensor, and the signal information of the target radiation source comprises: inputting the signal information of the target radiation source and the geographical data information detected by the sensor into the signal propagation loss network of the sensor to obtain signal transmission loss of the target radiation source; determining position range data of the target radiation source in the geographical data information detected by the sensor according to the signal transmission loss of the target radiation source and the position information of the sensor.

4. The method of claim 2, wherein, The determination of the signal propagation loss network of the sensor according to the geographical data information detected by the sensor, the position information of the sensor, the signal transmission intensity of each sample radiation source detected by the sensor, the signal information of each sample radiation source, the position information of each sample radiation source, and the signal propagation loss algorithm comprises: for signal information of each sample radiation source, determining signal propagation loss of the sample radiation source according to the signal information of the sample radiation source, the signal transmission intensity of the sample radiation source detected by the sensor, and the signal propagation loss algorithm; determine, according to the signal propagation loss of the sample radiation source, the position information of the sensor, and the position information of the sample radiation source, signal weakening conditions of each of the obstacles detected by the sensor in geographical data information detected by the sensor; determine, according to the signal weakening conditions of all the obstacles detected by the sensor and a signal propagation loss algorithm, a signal propagation loss network of the sensor.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: obtaining position information of each sample radiation source in a sample region, signal information of each sample radiation source, and position information of each sample sensor; for each sample radiation source, determining, according to the signal information of the sample radiation source, the position information of each sample sensor, the position information of each sensor, and a signal propagation loss network of each sample sensor, position range data of the sample radiation source; inputting the position range data of the sample radiation source into an initial radiation source positioning model to determine a position probability distribution matrix of the sample radiation source in the sample region, and determining sample position information of the sample radiation source according to the position probability distribution matrix; training the initial radiation source positioning model by using the sample position information of the sample radiation source, the position information of the sample radiation source, and a weighted loss function to obtain the radiation source positioning model.

6. A radiation source positioning device, characterized by, The device comprises: a first obtaining module configured to obtain signal information of a target radiation source in a target region and position information of each sensor; the signal information of the target radiation source comprises a signal frequency of the target radiation source and a signal strength of the target radiation source; a first determining module configured to, for each sensor, determine position range data of the target radiation source detected by the sensor according to a signal propagation loss network of the sensor, geographical data information detected by the sensor, the position information of the sensor, and the signal information of the target radiation source; a first positioning module configured to input the position range data of the target radiation source into a down-sampling layer to extract position feature information of the target radiation source, perform fusion processing on the position feature information of the target radiation source through an up-sampling layer to obtain a probability distribution map of the target radiation source, perform convolution processing on the probability distribution map of the target radiation source through a convolution layer to obtain a position probability distribution matrix of the target radiation source in the target region, and determine position information of the target radiation source according to the position probability distribution matrix.

7. The apparatus of claim 6, wherein, The first obtaining module is specifically configured to: obtain signal information of each sample radiation source, position information of each sample radiation source, and geographical data information detected by each sensor; the geographical data information is used to represent position information of each obstacle detected by the sensor in the target region; For each sensor, according to the geographical data information detected by the sensor, the position information of the sensor, the signal transmission intensity of each of the sample radiation sources detected by the sensor, the signal information of each of the sample radiation sources, the position information of each of the sample radiation sources, and a signal propagation loss algorithm, a signal propagation loss network of the sensor is determined.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images