CN117434497B - Indoor positioning method, device and equipment of satellite communication terminal and storage medium - Google Patents
Indoor positioning method, device and equipment of satellite communication terminal and storage medium Download PDFInfo
- Publication number
- CN117434497B CN117434497B CN202311756258.XA CN202311756258A CN117434497B CN 117434497 B CN117434497 B CN 117434497B CN 202311756258 A CN202311756258 A CN 202311756258A CN 117434497 B CN117434497 B CN 117434497B
- Authority
- CN
- China
- Prior art keywords
- positioning
- signal
- target
- frequency band
- historical
- 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.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004458 analytical method Methods 0.000 claims abstract description 79
- 239000011159 matrix material Substances 0.000 claims abstract description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 38
- 230000004927 fusion Effects 0.000 claims abstract description 28
- 238000005457 optimization Methods 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 95
- 230000015654 memory Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 13
- 238000011176 pooling Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 9
- 230000002068 genetic effect Effects 0.000 claims description 8
- 238000013524 data verification Methods 0.000 claims description 6
- 238000010183 spectrum analysis Methods 0.000 claims description 5
- 230000006978 adaptation Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 21
- 230000007613 environmental effect Effects 0.000 description 15
- 230000004807 localization Effects 0.000 description 7
- 238000010606 normalization Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0294—Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1851—Systems using a satellite or space-based relay
- H04B7/18515—Transmission equipment in satellites or space-based relays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/04—Large scale networks; Deep hierarchical networks
- H04W84/06—Airborne or Satellite Networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Automation & Control Theory (AREA)
- Astronomy & Astrophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention relates to the technical field of indoor positioning, and discloses an indoor positioning method, device and equipment of a satellite communication terminal and a storage medium, which are used for improving the indoor positioning accuracy of the satellite communication terminal. The method comprises the following steps: the method comprises the steps that multi-frequency signal acquisition is conducted on target equipment through a satellite communication terminal, a plurality of historical frequency band signals are obtained, signal characteristic analysis is conducted, and signal propagation path characteristics are obtained; carrying out signal modulation fusion to obtain a fused frequency band signal; inputting the fused frequency band signals into an initial indoor positioning model for equipment indoor positioning analysis to obtain a historical positioning data set; performing real-time image acquisition and equipment environment feature extraction to obtain an equipment environment feature set; constructing a target noise variance matrix and carrying out positioning deviation calculation to obtain positioning deviation data; and performing model parameter optimization to obtain a target indoor positioning model, and performing real-time positioning on target equipment through the target indoor positioning model to obtain real-time positioning data.
Description
Technical Field
The present invention relates to the field of indoor positioning technologies, and in particular, to an indoor positioning method, apparatus, device and storage medium for a satellite communication terminal.
Background
With rapid development of technology, satellite communication terminals are becoming more and more widely used in the field of wireless communication. In indoor environments, conventional GPS positioning systems often fail to provide accurate positioning information indoors due to building structure limitations and signal propagation complexity. Thus, research and innovation for indoor positioning technology becomes critical.
Traditional indoor positioning methods, such as Wi-Fi positioning or bluetooth positioning, are often limited by signal coverage, which results in low accuracy of the existing solutions.
Disclosure of Invention
The invention provides an indoor positioning method, device and equipment of a satellite communication terminal and a storage medium, which are used for improving the indoor positioning accuracy of the satellite communication terminal.
The first aspect of the present invention provides an indoor positioning method of a satellite communication terminal, where the indoor positioning method of the satellite communication terminal includes:
acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals, and respectively carrying out signal characteristic analysis on the plurality of historical frequency band signals to obtain signal propagation path characteristics of each historical frequency band signal;
According to the signal propagation path characteristics, carrying out signal modulation fusion on the plurality of historical frequency band signals to obtain fusion frequency band signals;
inputting the fused frequency band signals into a preset initial indoor positioning model to perform equipment indoor positioning analysis to obtain a historical positioning data set;
acquiring real-time images of the target equipment to obtain a plurality of equipment real-time operation images, and extracting equipment environment characteristics of the plurality of equipment real-time operation images to obtain an equipment environment characteristic set;
constructing a target noise variance matrix according to the equipment environment characteristic set and the historical positioning data set, and performing positioning deviation calculation on the historical positioning data set through the target noise variance matrix to obtain positioning deviation data;
and carrying out model parameter optimization on the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and carrying out real-time positioning on the target equipment through the target indoor positioning model to obtain real-time positioning data.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the acquiring, by using a preset satellite communication terminal, a multi-frequency signal of a target device to obtain a plurality of historical frequency band signals, and performing signal feature analysis on the plurality of historical frequency band signals to obtain signal propagation path features of each historical frequency band signal respectively, includes:
Acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals;
respectively carrying out time domain analysis on the plurality of historical frequency band signals to obtain a time domain feature set of each historical frequency band signal;
respectively carrying out spectrum analysis on the plurality of historical frequency band signals to obtain a frequency domain feature set of each historical frequency band signal;
respectively carrying out amplitude analysis on the plurality of historical frequency band signals to obtain a signal intensity characteristic set of each historical frequency band signal;
respectively carrying out phase analysis on the plurality of historical frequency band signals to obtain a phase characteristic set of each historical frequency band signal;
and extracting propagation path characteristics of the time domain characteristic set, the frequency domain characteristic set, the signal intensity characteristic set and the phase characteristic set to obtain signal propagation path characteristics of each historical frequency band signal, wherein the signal propagation path characteristics comprise propagation time, path loss and multipath effect of the signal.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, according to the signal propagation path feature, the performing signal modulation fusion on the plurality of historical frequency band signals to obtain a fused frequency band signal includes:
According to the signal propagation path characteristics, signal standardization parameter operation is carried out on the plurality of historical frequency band signals respectively, so that signal standardization parameters of each historical frequency band signal are obtained;
performing signal standardization processing on the plurality of historical frequency band signals according to the signal standardization parameters to obtain a plurality of standard frequency band signals;
inputting the plurality of standard frequency band signals into a preset signal modulation model, wherein the signal modulation model comprises the following steps: a plurality of weak classifiers, each weak classifier including a convolutional pooling layer, a full connection layer, a long short time memory layer, and an output layer;
respectively carrying out signal coding on the plurality of standard frequency band signals through a convolution pooling layer and a full connection layer in the plurality of weak classifiers to obtain signal coding data of each standard frequency band signal;
respectively carrying out signal modulation on the signal coded data through a long-short time memory layer and an output layer in the weak classifiers to obtain a target modulation signal of each weak classifier;
and acquiring classifier weight data of the weak classifiers, and carrying out signal fusion on target modulation signals of each weak classifier according to the classifier weight data to obtain fused frequency band signals.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, inputting the fused frequency band signal into a preset initial indoor positioning model to perform indoor positioning analysis of a device to obtain a historical positioning data set includes:
inputting the fused frequency band signals into a preset initial indoor positioning model, wherein the initial indoor positioning model comprises the following steps: the system comprises a positioning prediction layer and a positioning check layer, wherein the positioning prediction layer comprises a plurality of radial basis functions, and the positioning check layer comprises a path loss analysis function;
respectively carrying out positioning prediction on the fused frequency band signals according to the plurality of radial basis functions to obtain positioning prediction data of each radial basis function;
acquiring function weight data of the plurality of radial basis functions, and carrying out weighted summation on positioning prediction data of each radial basis function according to the function weight data to obtain a predicted positioning data set;
and carrying out positioning data verification on the predicted positioning data set through the path loss analysis function to obtain a historical positioning data set.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the acquiring the real-time image of the target device to obtain a plurality of real-time running images of the device, and extracting environmental features of the device from the plurality of real-time running images of the device to obtain an environmental feature set of the device includes:
Acquiring real-time images of the target equipment to obtain a plurality of initial real-time running images;
respectively carrying out image enhancement processing on the plurality of initial real-time running images to obtain a plurality of target real-time running images;
performing equipment center identification on the plurality of target real-time operation images to obtain a plurality of equipment center key points, and constructing an initial position cloud picture according to the plurality of equipment center key points;
carrying out adjacent point identification on each equipment center key point in the initial position cloud picture based on a K-time neighbor algorithm to obtain K nearest adjacent points corresponding to each equipment center key point;
respectively calculating the position offset between the K nearest neighbors and the corresponding equipment center key points, and carrying out drift correction on the initial position cloud picture according to the position offset to obtain a target position cloud picture;
mapping the target position cloud image to a corresponding target real-time operation image to obtain a plurality of equipment real-time operation images;
and extracting the device environment characteristics from the plurality of device real-time running images to obtain a device environment characteristic set.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the constructing a target noise variance matrix according to the device environmental feature set and the historical positioning data set, and performing positioning deviation calculation on the historical positioning data set through the target noise variance matrix, to obtain positioning deviation data includes:
Performing normal cloud distribution mapping on the historical positioning data set through a preset normal cloud model to obtain initial normal cloud distribution, wherein the initial normal cloud distribution comprises a plurality of historical positioning data points;
calculating the weight of each historical positioning data point based on the equipment environment characteristic set, and generating a target weight matrix according to the weight of each historical positioning data point;
carrying out noise variance calculation on the initial normal cloud distribution to obtain a target noise variance matrix;
and carrying out weight weighted average on the historical positioning data set according to the target weight matrix, and carrying out positioning deviation calculation according to the target noise variance matrix to obtain positioning deviation data.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, performing model parameter optimization on the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and performing real-time positioning on the target device by using the target indoor positioning model to obtain real-time positioning data, where the method includes:
acquiring a first function parameter set of a plurality of radial basis functions in the initial indoor positioning model and a second function parameter set of a path loss analysis function;
Initializing model parameters of the first function parameter set and the second function parameter set through a preset genetic algorithm according to the positioning deviation data, and generating an initial model parameter group, wherein the initial model parameter group comprises a plurality of candidate model parameter combinations;
performing fitness calculation on the plurality of candidate model parameter combinations to obtain fitness data of each candidate model parameter combination;
carrying out model parameter optimization solving on the plurality of candidate model parameter combinations according to the adaptation data to obtain a target model parameter combination;
updating model parameters of the initial indoor positioning model through the target model parameter combination to obtain a target indoor positioning model;
and acquiring a real-time multi-frequency signal through the satellite communication terminal, and inputting the real-time multi-frequency signal into the target indoor positioning model for real-time positioning to obtain real-time positioning data.
A second aspect of the present invention provides an indoor positioning device of a satellite communication terminal, the indoor positioning device of the satellite communication terminal including:
the acquisition module is used for acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals, and respectively carrying out signal characteristic analysis on the plurality of historical frequency band signals to obtain signal propagation path characteristics of each historical frequency band signal;
The fusion module is used for carrying out signal modulation fusion on the plurality of historical frequency band signals according to the signal propagation path characteristics to obtain fusion frequency band signals;
the analysis module is used for inputting the fused frequency band signals into a preset initial indoor positioning model to perform equipment indoor positioning analysis to obtain a historical positioning data set;
the extraction module is used for acquiring the real-time images of the target equipment to obtain a plurality of equipment real-time operation images, and extracting equipment environment characteristics of the equipment real-time operation images to obtain an equipment environment characteristic set;
the calculation module is used for constructing a target noise variance matrix according to the equipment environment characteristic set and the historical positioning data set, and carrying out positioning deviation calculation on the historical positioning data set through the target noise variance matrix to obtain positioning deviation data;
and the positioning module is used for optimizing the model parameters of the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and positioning the target equipment in real time through the target indoor positioning model to obtain real-time positioning data.
A third aspect of the present invention provides an indoor positioning apparatus of a satellite communication terminal, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the indoor positioning device of the satellite communication terminal to perform the indoor positioning method of the satellite communication terminal described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the indoor positioning method of a satellite communication terminal as described above.
In the technical scheme provided by the invention, the satellite communication terminal is used for acquiring the multi-frequency signals of the target equipment to obtain a plurality of historical frequency band signals, and the signal characteristic analysis is carried out to obtain the signal propagation path characteristics; carrying out signal modulation fusion to obtain a fused frequency band signal; inputting the fused frequency band signals into an initial indoor positioning model for equipment indoor positioning analysis to obtain a historical positioning data set; performing real-time image acquisition and equipment environment feature extraction to obtain an equipment environment feature set; constructing a target noise variance matrix and carrying out positioning deviation calculation to obtain positioning deviation data; the method and the device have the advantages that the model parameters are optimized, the target indoor positioning model is obtained, the target equipment is positioned in real time through the target indoor positioning model, and real-time positioning data are obtained. The feature analysis of the multi-band signal helps to understand the signal propagation path, providing a more accurate indoor positioning data base. By carrying out signal modulation fusion on a plurality of historical frequency band signals, the information of different frequency bands is integrated, so that the signal noise is reduced, the signal quality is improved, and the accuracy of a positioning model is enhanced. The real-time image acquisition of the target equipment is utilized, and the actual environment of the target equipment can be more comprehensively known by combining the equipment environment characteristic extraction. The multi-mode data is provided for indoor positioning, and the adaptability to the environment complexity is improved. And constructing a target noise variance matrix through the combination of the equipment environment characteristics and the historical positioning data. This helps to quantify and model various disturbances and noise in the indoor environment, improving the robustness of the positioning system to complex environments. And carrying out parameter optimization on the initial indoor positioning model by using the positioning deviation data, thereby further improving the positioning accuracy. This enables the system to continuously adapt to different environmental conditions and changes in the state of the device. Finally, the real-time positioning of the target equipment is realized through the target indoor positioning model, and the indoor positioning accuracy of the satellite communication terminal is further improved.
Drawings
Fig. 1 is a schematic diagram of an embodiment of an indoor positioning method of a satellite communication terminal according to an embodiment of the present invention;
FIG. 2 is a flow chart of signal modulation fusion in an embodiment of the invention;
FIG. 3 is a flow chart of an indoor positioning analysis of a device in an embodiment of the invention;
FIG. 4 is a flow chart of device environmental feature extraction in an embodiment of the invention;
FIG. 5 is a schematic view of an embodiment of an indoor positioning device of a satellite communication terminal according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of an indoor positioning device of a satellite communication terminal according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides an indoor positioning method, device and equipment of a satellite communication terminal and a storage medium, which are used for improving the indoor positioning accuracy of the satellite communication terminal. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and an embodiment of an indoor positioning method of a satellite communication terminal in the embodiment of the present invention includes:
s101, acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals, and respectively carrying out signal characteristic analysis on the plurality of historical frequency band signals to obtain signal propagation path characteristics of each historical frequency band signal;
it is to be understood that the execution subject of the present invention may be an indoor positioning device of a satellite communication terminal, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the target device is subjected to multi-frequency signal acquisition through a preset satellite communication terminal, and a plurality of historical frequency band signals are obtained, wherein the signals reflect signal propagation conditions on different frequency bands. Time domain analysis is performed on these multiple historical frequency band signals. Time domain analysis allows the server to observe the time characteristics of the signal, including the rate of change and periodicity of the signal. And obtaining a time domain feature set of each historical frequency band signal by the server through time domain analysis. For example, for a signal in a particular frequency band, the time domain analysis may tell the server what the period of the signal is, and whether the signal has significant time domain fluctuations. And simultaneously, carrying out spectrum analysis to obtain a frequency domain feature set of each historical frequency band signal. Spectral analysis reveals the characteristics of the signal in the frequency domain, including the main frequency components and the spectral shape. This information is important for determining the frequency characteristics of the signals and can be used to identify the frequency characteristic differences between the different signals. Also, an amplitude analysis is performed to obtain a set of signal strength characteristics for each of the historical frequency band signals. Amplitude analysis tells the server about amplitude or intensity variations of the signal, which is critical to estimating the propagation path loss and multipath effects of the signal. For example, if the amplitude of the signal drops sharply, this indicates that the signal has undergone path loss. In addition, a phase analysis is performed to obtain a set of phase characteristics for each historical frequency band signal. Phase analysis provides information about the phase change of the signal, which is very useful in solving multipath effects and phase difference problems. Combining the time domain feature set, the frequency domain feature set, the signal intensity feature set and the phase feature set together, extracting propagation path features, integrating information of different feature sets together, and generating signal propagation path features of each historical frequency band signal. These propagation path characteristics include information such as the propagation time of the signal, path loss, and multipath effects. For example, assume that the target device is located at a certain location within a building. By analyzing the plurality of historical frequency band signals, the server identifies the specific location of the device, including the coordinates of the device indoors and the distance from the satellite communication terminal. This helps to provide accurate indoor navigation, location services, and location related information.
S102, carrying out signal modulation fusion on a plurality of historical frequency band signals according to signal propagation path characteristics to obtain fused frequency band signals;
specifically, signal normalization parameter calculation is performed on a plurality of historical frequency band signals according to signal propagation path characteristics. A set of signal normalization parameters is calculated for each historical frequency band signal, which may reflect characteristics of the signal, such as propagation distance, propagation time, etc. And carrying out signal standardization processing on the plurality of historical frequency band signals according to the calculated signal standardization parameters, and standardizing the characteristics of the signals of different historical frequency bands so as to facilitate subsequent processing. And inputting a plurality of standard frequency band signals into a preset signal modulation model. The signal modulation model comprises a plurality of weak classifiers, wherein each weak classifier comprises a convolution pooling layer, a full connection layer, a long and short time memory layer, an output layer and other components. And through the convolution pooling layer and the full connection layer, each weak classifier respectively codes a plurality of standard frequency band signals. This encoding process facilitates extraction of important features of the signal for subsequent processing. Each weak classifier then signal modulates the signal encoded data through the long and short memory layers and the output layer. Each weak classifier generates a target modulated signal for the standard band signal that reflects the signal specific characteristics and positioning information. Classifier weight data for a plurality of weak classifiers is obtained. These weight data are used to guide the signal fusion process for each weak classifier. And carrying out signal fusion on the target modulation signal of each weak classifier according to the classifier weight data. The signals generated by the different weak classifiers are combined to generate a fused frequency band signal containing information from a plurality of historical frequency band signals, and the fused frequency band signal is processed by signal coding and modulation to form a more comprehensive positioning signal.
S103, inputting the fused frequency band signals into a preset initial indoor positioning model to perform equipment indoor positioning analysis to obtain a historical positioning data set;
it should be noted that, the fused frequency band signal is input into a preset initial indoor positioning model. This initial indoor positioning model consists of two main parts, namely a positioning prediction layer and a positioning verification layer. In the positioning prediction layer there are a plurality of radial basis functions, while in the positioning verification layer a path loss analysis function is included. And respectively carrying out positioning prediction on the fused frequency band signals according to the plurality of radial basis functions. Each radial basis function processes the fused band signal to produce a particular one of the positioning prediction data. Each radial basis function performs a localization prediction on the input signal based on its unique characteristics and parameters. These prediction data may provide approximate location information of the device. Function weight data of a plurality of radial basis functions are acquired. These weight data are used to guide how the predictions of the different radial basis functions are combined to generate a more accurate position estimate. The weight data reflects the extent to which each radial basis function contributes to the positioning, and therefore they are important factors in adjusting and optimizing the positioning predictions. The positioning prediction data for each radial basis function is weighted summed using the function weight data. This process generates a set of so-called predicted position data, which contains information from different radial basis functions, taking their contributions into account. And carrying out positioning data verification on the predicted positioning data set through a path loss analysis function to obtain a historical positioning data set. The path loss analysis function can detect and verify the accuracy of the positioning data by comparing the data in the predicted positioning data set with the actual observed data. It helps to correct any potential errors or deviations to ensure that the resulting historical positional data set is more reliable and accurate.
S104, acquiring real-time images of target equipment to obtain a plurality of equipment real-time operation images, and extracting equipment environment characteristics of the plurality of equipment real-time operation images to obtain an equipment environment characteristic set;
specifically, real-time image acquisition is performed on the target device to obtain a plurality of initial real-time running images. These images capture the actual operating state of the device and its surroundings. Image enhancement processing is performed to improve the quality and the analyzability of an image. Image enhancement may include denoising, increasing contrast, color correction, etc., to make the image more suitable for subsequent analysis and feature extraction. And carrying out equipment center identification on the multiple target real-time running images. The aim is to detect the device centre position in the image, typically using computer vision techniques and image processing algorithms. The location of the center of the device is the key information for positioning. And after the equipment center identification is completed, an initial position cloud picture is constructed by extracting a plurality of equipment center key points. This cloud is a data structure containing the central location of each device for subsequent processing. And then, using K times of neighbor algorithm to identify the neighboring points of each equipment center key point in the initial position cloud picture. For each device center key point, K nearest neighbors around it are found, which are related to the device center. And respectively calculating the position offset between the K nearest neighbors and the corresponding equipment center key points. These offsets represent the difference in the position of the center of the device relative to its neighbors. This step helps to understand the relative position and movement of the device center. And carrying out drift correction on the initial position cloud image based on the position offset. The drift correction is helpful for correcting errors introduced in the image acquisition or processing process, and the positioning accuracy is improved. And then, mapping the target position cloud image back to the corresponding target real-time operation image. This mapping process allows to correlate the positioning information with the image of the actual device, thereby providing location information of the device. And extracting the device environment characteristics from the real-time running images of the plurality of devices. This process involves analyzing environmental features in the image, such as objects, structures, or other identifiable features surrounding the device. These environmental features help to better understand the environment in which the device is located.
S105, constructing a target noise variance matrix according to the equipment environment feature set and the historical positioning data set, and performing positioning deviation calculation on the historical positioning data set through the target noise variance matrix to obtain positioning deviation data;
specifically, a normal cloud distribution mapping is performed on the historical positioning data set through a preset normal cloud model. The purpose is to map the historical positioning data into a normal distribution space so as to better understand the distribution situation of the positioning data. The initial normal cloud distribution includes a plurality of historically located data points, each representing a historical location observation of a device. Weights for each of the historically located data points are calculated based on the set of device environmental features. These weights may be determined based on the characteristics of the device environment and the correlation of the historical data points to reflect the contribution of each data point to the position fix. For example, if a certain historically located data point is located in a similar area as the current environment of the target device, it is weighted higher because it is more representative. Then, a target weight matrix is generated based on the calculated weights. This matrix reflects the relative importance of the historically located data points and will be used in subsequent calculations. And carrying out noise variance calculation on the initial normal cloud distribution. This step helps to estimate the noise level in the historical positional data to determine the reliability of the historical data. Noise variance calculation may take into account the weight of each data point to more accurately reflect the variability of the noise. And carrying out weight weighted average on the historical positioning data set according to the target weight matrix. The weight of the data point will determine its impact on the final position. The higher the weight of the data point, the more significantly its observations will affect the positioning result. And performing positioning deviation calculation by using the target noise variance matrix. This process helps measure the reliability of the historical localization data set and correct the localization result by taking into account the noise variance. The positioning bias data provides a more accurate and reliable device position estimate.
S106, performing model parameter optimization on the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and performing real-time positioning on target equipment through the target indoor positioning model to obtain real-time positioning data.
Specifically, a first function parameter set of a plurality of radial basis functions and a second function parameter set of a path loss analysis function in an initial indoor positioning model are obtained. These parameters are part of the initial model for performing positioning predictions and checks. And initializing model parameters of the first function parameter set and the second function parameter set according to the positioning deviation data and by using a preset genetic algorithm. Under the direction of a genetic algorithm, an initial model parameter population is generated, which includes a plurality of candidate model parameter combinations. These combinations represent model parameter settings. And carrying out fitness calculation on the plurality of candidate model parameter combinations. Fitness calculations are used to evaluate the performance of each candidate model parameter combination, typically by comparison with positioning bias data. This step helps determine which model parameter combinations more accurately match the historical positional data. And then, carrying out model parameter optimization solving on a plurality of candidate model parameter combinations according to the fitness data. The goal of this process is to find the optimal combination of model parameters to minimize positioning bias and improve positioning accuracy. And then, updating model parameters of the initial indoor positioning model through the target model parameter combination to obtain the target indoor positioning model. This object model will have better performance and accuracy because it is optimized by adapting to historical positioning data and positioning bias data. And acquiring real-time multi-frequency signals through a satellite communication terminal, and inputting the real-time multi-frequency signals into the target indoor positioning model to perform real-time positioning to obtain real-time positioning data. The method comprises the step of combining an actual real-time signal with a model on the basis of an optimized target indoor positioning model so as to obtain real-time equipment position information. Through the steps, the server can position the position of the equipment in a real-time environment with high precision, and provide accurate positioning data for various applications, including navigation, tracking and positioning related services.
In the embodiment of the invention, the satellite communication terminal is used for acquiring the multi-frequency signals of the target equipment to obtain a plurality of historical frequency band signals, and the signal characteristic analysis is carried out to obtain the signal propagation path characteristics; carrying out signal modulation fusion to obtain a fused frequency band signal; inputting the fused frequency band signals into an initial indoor positioning model for equipment indoor positioning analysis to obtain a historical positioning data set; performing real-time image acquisition and equipment environment feature extraction to obtain an equipment environment feature set; constructing a target noise variance matrix and carrying out positioning deviation calculation to obtain positioning deviation data; the method and the device have the advantages that the model parameters are optimized, the target indoor positioning model is obtained, the target equipment is positioned in real time through the target indoor positioning model, and real-time positioning data are obtained. The feature analysis of the multi-band signal helps to understand the signal propagation path, providing a more accurate indoor positioning data base. By carrying out signal modulation fusion on a plurality of historical frequency band signals, the information of different frequency bands is integrated, so that the signal noise is reduced, the signal quality is improved, and the accuracy of a positioning model is enhanced. The real-time image acquisition of the target equipment is utilized, and the actual environment of the target equipment can be more comprehensively known by combining the equipment environment characteristic extraction. The multi-mode data is provided for indoor positioning, and the adaptability to the environment complexity is improved. And constructing a target noise variance matrix through the combination of the equipment environment characteristics and the historical positioning data. This helps to quantify and model various disturbances and noise in the indoor environment, improving the robustness of the positioning system to complex environments. And carrying out parameter optimization on the initial indoor positioning model by using the positioning deviation data, thereby further improving the positioning accuracy. This enables the system to continuously adapt to different environmental conditions and changes in the state of the device. Finally, the real-time positioning of the target equipment is realized through the target indoor positioning model, and the indoor positioning accuracy of the satellite communication terminal is further improved.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals;
(2) Respectively carrying out time domain analysis on a plurality of historical frequency band signals to obtain a time domain feature set of each historical frequency band signal;
(3) Respectively carrying out spectrum analysis on a plurality of historical frequency band signals to obtain a frequency domain feature set of each historical frequency band signal;
(4) Respectively carrying out amplitude analysis on a plurality of historical frequency band signals to obtain a signal intensity characteristic set of each historical frequency band signal;
(5) Respectively carrying out phase analysis on a plurality of historical frequency band signals to obtain a phase characteristic set of each historical frequency band signal;
(6) And carrying out propagation path feature extraction on the time domain feature set, the frequency domain feature set, the signal intensity feature set and the phase feature set to obtain signal propagation path features of each historical frequency band signal, wherein the signal propagation path features comprise propagation time, path loss and multipath effect of the signal.
Specifically, the target device is subjected to multi-frequency signal acquisition through a preset satellite communication terminal. The satellite communication terminal captures a plurality of frequency band signals from the target device, which signals are subject to various effects and variations in propagation. And performing time domain analysis on the plurality of historical frequency band signals. Time domain analysis involves the temporal characteristics of a signal, such as the waveform, periodicity, and frequency of the signal. This allows the server to know the time domain characteristics of the signal, including the period of the signal, the pulse width and the start and end times of the signal. And carrying out frequency domain analysis on the plurality of historical frequency band signals. Frequency domain analysis involves frequency characteristics of the signal, such as frequency spectrum and frequency components. Through frequency domain analysis, the server determines frequency domain characteristics of the signal, including primary frequency components, spectral width, and frequency domain amplitude. Then, amplitude analysis is performed on the plurality of historical frequency band signals. Amplitude analysis focuses on the amplitude or intensity of the signal to determine the change and attenuation of the signal. This helps to understand the decay rate of the signal and the signal strength on the propagation path. Then, a phase analysis is performed on the plurality of historical band signals. Phase analysis focuses on phase characteristics of the signal, such as phase offset and phase difference. Through phase analysis, the server knows the phase characteristics of the signal, which is important in terms of multipath effects and signal synchronization. And carrying out propagation path feature extraction on the time domain feature set, the frequency domain feature set, the signal strength feature set and the phase feature set. And integrating various analysis results to obtain the signal propagation path characteristics of each historical frequency band signal. These characteristics include the propagation time of the signal, path loss, and multipath effects. The propagation time tells the server the time it takes for the signal to be transmitted to be received, the path loss tells the server the extent to which the signal is lost in propagation, and multipath effects reveal the signal reflection and refraction.
In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:
s201, respectively carrying out signal standardization parameter operation on a plurality of historical frequency band signals according to signal propagation path characteristics to obtain signal standardization parameters of each historical frequency band signal;
s202, performing signal standardization processing on a plurality of historical frequency band signals according to signal standardization parameters to obtain a plurality of standard frequency band signals;
s203, inputting a plurality of standard frequency band signals into a preset signal modulation model, wherein the signal modulation model comprises: a plurality of weak classifiers, each weak classifier including a convolutional pooling layer, a full connection layer, a long short time memory layer, and an output layer;
s204, respectively carrying out signal coding on a plurality of standard frequency band signals through a convolution pooling layer and a full connection layer in a plurality of weak classifiers to obtain signal coding data of each standard frequency band signal;
s205, respectively carrying out signal modulation on signal coding data through a long-short time memory layer and an output layer in a plurality of weak classifiers to obtain a target modulation signal of each weak classifier;
s206, acquiring classifier weight data of a plurality of weak classifiers, and carrying out signal fusion on the target modulation signal of each weak classifier according to the classifier weight data to obtain a fused frequency band signal.
Specifically, signal normalization parameter calculation is performed on a plurality of historical frequency band signals according to signal propagation path characteristics. The propagation path characteristics are used to calculate normalized parameters for each of the historical frequency band signals. These parameters may include propagation time, path loss, multipath effects, etc. of the signal. And performing signal normalization processing on the plurality of historical frequency band signals by using the calculated signal normalization parameters. Normalization may involve normalizing the amplitude or spectrum of the signals to ensure that they have similar dimensions and amplitudes. This helps to extract the features of the signal and reduces the range of variation of the data. And inputting a plurality of standard frequency band signals into a preset signal modulation model. The signal modulation model typically includes a plurality of weak classifiers, each of which includes a convolutional pooling layer, a fully-connected layer, a long short-term memory layer, and an output layer. These components work in concert to further process and extract features from the input signal. And carrying out signal coding on the signals of the plurality of standard frequency bands through a convolution pooling layer and a full connection layer in the plurality of weak classifiers. This process converts the signal into feature vectors, capturing specific features of the signal, such as spectral features and temporal features. And carrying out signal modulation on the signal coding data through a long-short-time memory layer and an output layer in the weak classifiers. This is a key step in mapping the signal encoded data to the target modulated signal. The long-time and short-time memory layer is beneficial to processing time sequence information, and the output layer generates a modulation form of signals so as to adapt to the requirements of a positioning model. And acquiring classifier weight data of a plurality of weak classifiers, and carrying out signal fusion on target modulation signals of each weak classifier according to the weight data. This step combines the outputs of the multiple weak classifiers together to obtain a fused band signal. The fused frequency band signal is a signal with higher accuracy and stability, and can be used for further indoor positioning analysis.
In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:
s301, inputting a fused frequency band signal into a preset initial indoor positioning model, wherein the initial indoor positioning model comprises: the positioning prediction layer comprises a plurality of radial basis functions, and the positioning check layer comprises a path loss analysis function;
s302, respectively carrying out positioning prediction on the fused frequency band signals according to a plurality of radial basis functions to obtain positioning prediction data of each radial basis function;
s303, acquiring function weight data of a plurality of radial basis functions, and carrying out weighted summation on positioning prediction data of each radial basis function according to the function weight data to obtain a predicted positioning data set;
s304, performing positioning data verification on the predicted positioning data set through a path loss analysis function to obtain a historical positioning data set.
Specifically, the server inputs the fused frequency band signals to a preset initial indoor positioning model. This model is generally divided into two key parts: and a positioning prediction layer and a positioning check layer. The positioning prediction layer includes a plurality of radial basis functions and the positioning verification layer includes a path loss analysis function. And the server performs positioning prediction on the fused frequency band signals through a plurality of radial basis functions. Each radial basis function is responsible for processing a particular aspect of the signal and generating corresponding positioning prediction data. Such data typically covers the direction, distance and position information of the signals. Such as determining the distance between the device and the reference point, the orientation of the device, etc. These functions work together to provide multi-dimensional positioning data for determining the location of the device. The server obtains function weight data for a plurality of radial basis functions. These weight data reflect the relative importance of each radial basis function in the positioning prediction. Typically, these weights are determined by training and optimizing models to make the positioning predictions more accurate. The server performs a weighted summation of the positioning prediction data for each radial basis function based on the function weight data. The more important radial basis functions have a greater impact on the final predicted positioning data, while the less important functions have a smaller impact. Those functions that are considered more reliable will have a greater impact on the results when forming the final predicted position data set. And carrying out positioning data verification on the predicted positioning data set through a path loss analysis function. The path loss analysis function helps to verify the positioning data to ensure its accuracy. This may involve comparing the predicted location with the actual path loss of the building environment to detect and correct for deviations.
In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:
s401, acquiring real-time images of target equipment to obtain a plurality of initial real-time operation images;
s402, respectively carrying out image enhancement processing on a plurality of initial real-time operation images to obtain a plurality of target real-time operation images;
s403, carrying out equipment center identification on a plurality of target real-time operation images to obtain a plurality of equipment center key points, and constructing an initial position cloud picture according to the plurality of equipment center key points;
s404, identifying adjacent points of each equipment center key point in the initial position cloud picture based on a K-time neighbor algorithm to obtain K nearest adjacent points corresponding to each equipment center key point;
s405, respectively calculating the position offset between K nearest neighbors and corresponding equipment center key points, and carrying out drift correction on the initial position cloud picture according to the position offset to obtain a target position cloud picture;
s406, mapping the target position cloud image to a corresponding target real-time operation image to obtain a plurality of device real-time operation images;
s407, extracting the device environment characteristics of the real-time running images of the plurality of devices to obtain a device environment characteristic set.
Specifically, the server performs real-time image acquisition on the target device to obtain a plurality of initial real-time running images. These images capture the different positions and angles of the device in its current environment. The server performs image enhancement processing on each of the initial live images. The aim is to improve the quality of the image, reduce noise and enhance useful features in order to better identify the device and its surroundings. The server performs equipment center recognition, and recognizes the center position of the equipment by analyzing each target real-time operation image. This typically involves computing the center or keypoint of the device's image to determine its location in the image. Based on the K-time neighbor algorithm, the server identifies the neighboring points of the central key point of each device in the initial position cloud picture. Each keypoint is found its nearest neighbors in the same or adjacent images to establish a relationship between keypoints. Then, the server calculates the position offset between each key point and its K nearest neighbors. These offsets represent small movements and positional changes of the device in the different images. And according to the calculated position offset, the server carries out drift correction on the initial position cloud picture. The key points in the initial position cloud image are adjusted to more accurate positions according to the offset of the key points, so that the target position cloud image is obtained. The target location cloud map reflects the exact location of the device at different points in time, which is the basic data required for real-time positioning. The server then maps the target location cloud image into a corresponding target real-time running image, which allows the server to correlate the location information of the device with the actual image, enabling real-time device tracking. And the server extracts the device environment characteristics of the real-time running images of the plurality of devices. This may include analyzing information in the image, such as background, surrounding objects, lighting conditions, etc., to further understand the environment in which the device is located. Consider, for example, a cargo tracking system within a warehouse. By capturing real-time images, the server monitors the location of the goods in real time, ensuring that they are properly stored and handled. Through the equipment center identification and the proximity point identification, the server accurately tracks the location of the goods even if they move within the warehouse. Drift correction ensures tracking accuracy, while device environmental feature extraction can detect any environmental changes affecting cargo tracking, such as light conditions or movement of obstructions.
In a specific embodiment, the process of executing step S105 may specifically include the following steps:
(1) Carrying out normal cloud distribution mapping on the historical positioning data set through a preset normal cloud model to obtain initial normal cloud distribution, wherein the initial normal cloud distribution comprises a plurality of historical positioning data points;
(2) Calculating the weight of each historical positioning data point based on the equipment environment characteristic set, and generating a target weight matrix according to the weight of each historical positioning data point;
(3) Carrying out noise variance calculation on the initial normal cloud distribution to obtain a target noise variance matrix;
(4) And carrying out weight weighted average on the historical positioning data set according to the target weight matrix, and carrying out positioning deviation calculation according to the target noise variance matrix to obtain positioning deviation data.
Specifically, the server uses a preset normal cloud model to perform normal cloud distribution mapping on the historical positioning data set. The server converts the historically located data points into normally distributed data for a better understanding of their distribution and characteristics. This initial normal cloud distribution contains a plurality of historical location data points, each representing location information of the device at a different time and location. The server calculates a weight for each historical localization data point based on the set of device environmental features. These environmental characteristics include the structure of the building, wall materials, signal propagation characteristics, etc. The calculation of weights takes these features into account to determine which data points are more trusted in a particular environment. Then, the server generates a target weight matrix according to the calculated weights. The target weight matrix reflects the relative importance of each historical localization data point in localization. Higher weighted data points contribute more to the positioning result because they are more representative in certain circumstances. And the server calculates noise variance of the initial normal cloud distribution. The aim is to estimate errors and noise introduced during the positioning process. Noise variance typically accounts for uncertainty in signal propagation, measurement errors in device position, and the like. The server then performs a weight weighted average on the historical localization data set, taking into account the weight of each data point. In the positioning calculation, the data points with higher weights will have more impact in the results, while those with lower weights will contribute less. The server uses the target noise variance matrix to perform positioning deviation calculation. This process helps the server to know the accuracy and precision of the positioning results in a particular environment. Based on the noise variance, the server estimates the error range and uncertainty in the position fix.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Acquiring a first function parameter set of a plurality of radial basis functions in an initial indoor positioning model and a second function parameter set of a path loss analysis function;
(2) According to the positioning deviation data, initializing model parameters of the first function parameter set and the second function parameter set through a preset genetic algorithm, and generating an initial model parameter group, wherein the initial model parameter group comprises a plurality of candidate model parameter combinations;
(3) Carrying out fitness calculation on the plurality of candidate model parameter combinations to obtain fitness data of each candidate model parameter combination;
(4) Carrying out model parameter optimization solving on a plurality of candidate model parameter combinations according to the fitness data to obtain a target model parameter combination;
(5) Updating model parameters of the initial indoor positioning model through the target model parameter combination to obtain a target indoor positioning model;
(6) And acquiring real-time multi-frequency signals through the satellite communication terminal, and inputting the real-time multi-frequency signals into the target indoor positioning model for real-time positioning to obtain real-time positioning data.
Specifically, the server obtains a first set of function parameters for a plurality of radial basis functions and a second set of function parameters for a path loss analysis function in an initial indoor positioning model. These parameters are typically determined from experimental data and a priori knowledge during modeling. And initializing model parameters of the first function parameter set and the second function parameter set by using a preset genetic algorithm. Genetic algorithms are optimization algorithms that can help a server search a parameter space to find the best model parameter combination. Through genetic algorithms, the server generates an initial model parameter population that includes a plurality of candidate model parameter combinations. The server then performs fitness calculations on the plurality of candidate model parameter combinations. Fitness calculations evaluate the performance of each parameter combination by applying these parameters to historical positioning data and comparing with actual observations. The fitness data reflects the behavior of each model parameter combination in indoor positioning. According to the fitness data, the server uses an optimization algorithm to perform model parameter optimization solving on a plurality of candidate model parameter combinations. This procedure aims to find the parameter combinations that are most suitable for indoor positioning tasks to minimize positioning errors and improve accuracy. Once the server obtains the target model parameter combination, the server applies it to the initial indoor positioning model, thereby obtaining the target indoor positioning model. This new model will better adapt to specific indoor environments and equipment, providing more accurate positioning predictions. And acquiring real-time multi-frequency signals through the satellite communication terminal, and inputting the real-time signals into the target indoor positioning model for real-time positioning. This process can help the server track the location of the target device in real-time indoors, while using the just updated model parameters to ensure higher positioning accuracy.
The indoor positioning method of the satellite communication terminal in the embodiment of the present invention is described above, and the indoor positioning device of the satellite communication terminal in the embodiment of the present invention is described below, referring to fig. 5, an embodiment of the indoor positioning device of the satellite communication terminal in the embodiment of the present invention includes:
the acquisition module 501 is configured to acquire multiple frequency signals of a target device through a preset satellite communication terminal, obtain multiple historical frequency band signals, and perform signal feature analysis on the multiple historical frequency band signals respectively to obtain signal propagation path features of each historical frequency band signal;
the fusion module 502 is configured to perform signal modulation fusion on the plurality of historical frequency band signals according to the signal propagation path characteristics, so as to obtain a fused frequency band signal;
the analysis module 503 is configured to input the fused frequency band signal into a preset initial indoor positioning model to perform indoor positioning analysis of the device, so as to obtain a historical positioning data set;
the extracting module 504 is configured to perform real-time image acquisition on the target device to obtain a plurality of device real-time running images, and perform device environment feature extraction on the plurality of device real-time running images to obtain a device environment feature set;
The calculation module 505 is configured to construct a target noise variance matrix according to the device environmental feature set and the historical positioning data set, and perform positioning deviation calculation on the historical positioning data set through the target noise variance matrix to obtain positioning deviation data;
and the positioning module 506 is configured to perform model parameter optimization on the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and perform real-time positioning on the target device through the target indoor positioning model to obtain real-time positioning data.
Through the cooperative cooperation of the components, the satellite communication terminal acquires the multi-frequency signals of the target equipment to obtain a plurality of historical frequency band signals, and performs signal characteristic analysis to obtain signal propagation path characteristics; carrying out signal modulation fusion to obtain a fused frequency band signal; inputting the fused frequency band signals into an initial indoor positioning model for equipment indoor positioning analysis to obtain a historical positioning data set; performing real-time image acquisition and equipment environment feature extraction to obtain an equipment environment feature set; constructing a target noise variance matrix and carrying out positioning deviation calculation to obtain positioning deviation data; the method and the device have the advantages that the model parameters are optimized, the target indoor positioning model is obtained, the target equipment is positioned in real time through the target indoor positioning model, and real-time positioning data are obtained. The feature analysis of the multi-band signal helps to understand the signal propagation path, providing a more accurate indoor positioning data base. By carrying out signal modulation fusion on a plurality of historical frequency band signals, the information of different frequency bands is integrated, so that the signal noise is reduced, the signal quality is improved, and the accuracy of a positioning model is enhanced. The real-time image acquisition of the target equipment is utilized, and the actual environment of the target equipment can be more comprehensively known by combining the equipment environment characteristic extraction. The multi-mode data is provided for indoor positioning, and the adaptability to the environment complexity is improved. And constructing a target noise variance matrix through the combination of the equipment environment characteristics and the historical positioning data. This helps to quantify and model various disturbances and noise in the indoor environment, improving the robustness of the positioning system to complex environments. And carrying out parameter optimization on the initial indoor positioning model by using the positioning deviation data, thereby further improving the positioning accuracy. This enables the system to continuously adapt to different environmental conditions and changes in the state of the device. Finally, the real-time positioning of the target equipment is realized through the target indoor positioning model, and the indoor positioning accuracy of the satellite communication terminal is further improved.
Fig. 5 above describes the indoor positioning device of the satellite communication terminal in the embodiment of the present invention in detail from the point of view of the modularized functional entity, and the indoor positioning device of the satellite communication terminal in the embodiment of the present invention is described in detail from the point of view of hardware processing.
Fig. 6 is a schematic structural diagram of an indoor positioning device of a satellite communication terminal according to an embodiment of the present invention, where the indoor positioning device 600 of the satellite communication terminal may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the indoor positioning device 600 of the satellite communication terminal. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the indoor positioning device 600 of the satellite communication terminal.
The indoor positioning device 600 of the satellite communication terminal may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the indoor positioning device structure of the satellite communication terminal shown in fig. 6 does not constitute a limitation of the indoor positioning device of the satellite communication terminal, and may include more or less components than those illustrated, or may combine certain components, or may be arranged in different components.
The invention also provides an indoor positioning device of the satellite communication terminal, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the indoor positioning method of the satellite communication terminal in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the indoor positioning method of the satellite communication terminal.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. An indoor positioning method of a satellite communication terminal is characterized in that the indoor positioning method of the satellite communication terminal comprises the following steps:
acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals, and respectively carrying out signal characteristic analysis on the plurality of historical frequency band signals to obtain signal propagation path characteristics of each historical frequency band signal;
according to the signal propagation path characteristics, carrying out signal modulation fusion on the plurality of historical frequency band signals to obtain fusion frequency band signals; the method specifically comprises the following steps: according to the signal propagation path characteristics, signal standardization parameter operation is carried out on the plurality of historical frequency band signals respectively, so that signal standardization parameters of each historical frequency band signal are obtained; performing signal standardization processing on the plurality of historical frequency band signals according to the signal standardization parameters to obtain a plurality of standard frequency band signals; inputting the plurality of standard frequency band signals into a preset signal modulation model, wherein the signal modulation model comprises the following steps: a plurality of weak classifiers, each weak classifier including a convolutional pooling layer, a full connection layer, a long short time memory layer, and an output layer; respectively carrying out signal coding on the plurality of standard frequency band signals through a convolution pooling layer and a full connection layer in the plurality of weak classifiers to obtain signal coding data of each standard frequency band signal; respectively carrying out signal modulation on the signal coded data through a long-short time memory layer and an output layer in the weak classifiers to obtain a target modulation signal of each weak classifier; acquiring classifier weight data of the weak classifiers, and performing signal fusion on target modulation signals of each weak classifier according to the classifier weight data to obtain fused frequency band signals;
Inputting the fused frequency band signals into a preset initial indoor positioning model to perform equipment indoor positioning analysis to obtain a historical positioning data set; the method specifically comprises the following steps: inputting the fused frequency band signals into a preset initial indoor positioning model, wherein the initial indoor positioning model comprises the following steps: the system comprises a positioning prediction layer and a positioning check layer, wherein the positioning prediction layer comprises a plurality of radial basis functions, and the positioning check layer comprises a path loss analysis function; respectively carrying out positioning prediction on the fused frequency band signals according to the plurality of radial basis functions to obtain positioning prediction data of each radial basis function; acquiring function weight data of the plurality of radial basis functions, and carrying out weighted summation on positioning prediction data of each radial basis function according to the function weight data to obtain a predicted positioning data set; performing positioning data verification on the predicted positioning data set through the path loss analysis function to obtain a historical positioning data set;
acquiring real-time images of the target equipment to obtain a plurality of equipment real-time operation images, and extracting equipment environment characteristics of the plurality of equipment real-time operation images to obtain an equipment environment characteristic set; the method specifically comprises the following steps: acquiring real-time images of the target equipment to obtain a plurality of initial real-time running images; respectively carrying out image enhancement processing on the plurality of initial real-time running images to obtain a plurality of target real-time running images; performing equipment center identification on the plurality of target real-time operation images to obtain a plurality of equipment center key points, and constructing an initial position cloud picture according to the plurality of equipment center key points; carrying out adjacent point identification on each equipment center key point in the initial position cloud picture based on a K-time neighbor algorithm to obtain K nearest adjacent points corresponding to each equipment center key point; respectively calculating the position offset between the K nearest neighbors and the corresponding equipment center key points, and carrying out drift correction on the initial position cloud picture according to the position offset to obtain a target position cloud picture; mapping the target position cloud image to a corresponding target real-time operation image to obtain a plurality of equipment real-time operation images; extracting the device environment characteristics of the plurality of device real-time operation images to obtain a device environment characteristic set;
Constructing a target noise variance matrix according to the equipment environment characteristic set and the historical positioning data set, and performing positioning deviation calculation on the historical positioning data set through the target noise variance matrix to obtain positioning deviation data; the method specifically comprises the following steps: performing normal cloud distribution mapping on the historical positioning data set through a preset normal cloud model to obtain initial normal cloud distribution, wherein the initial normal cloud distribution comprises a plurality of historical positioning data points; calculating the weight of each historical positioning data point based on the equipment environment characteristic set, and generating a target weight matrix according to the weight of each historical positioning data point; carrying out noise variance calculation on the initial normal cloud distribution to obtain a target noise variance matrix; carrying out weight weighted average on the historical positioning data set according to the target weight matrix, and carrying out positioning deviation calculation according to the target noise variance matrix to obtain positioning deviation data;
and carrying out model parameter optimization on the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and carrying out real-time positioning on the target equipment through the target indoor positioning model to obtain real-time positioning data.
2. The indoor positioning method of a satellite communication terminal according to claim 1, wherein the acquiring the multi-frequency signal of the target device by the preset satellite communication terminal to obtain a plurality of historical frequency band signals, and performing signal feature analysis on the plurality of historical frequency band signals to obtain signal propagation path features of each historical frequency band signal respectively, includes:
acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals;
respectively carrying out time domain analysis on the plurality of historical frequency band signals to obtain a time domain feature set of each historical frequency band signal;
respectively carrying out spectrum analysis on the plurality of historical frequency band signals to obtain a frequency domain feature set of each historical frequency band signal;
respectively carrying out amplitude analysis on the plurality of historical frequency band signals to obtain a signal intensity characteristic set of each historical frequency band signal;
respectively carrying out phase analysis on the plurality of historical frequency band signals to obtain a phase characteristic set of each historical frequency band signal;
and extracting propagation path characteristics of the time domain characteristic set, the frequency domain characteristic set, the signal intensity characteristic set and the phase characteristic set to obtain signal propagation path characteristics of each historical frequency band signal, wherein the signal propagation path characteristics comprise propagation time, path loss and multipath effect of the signal.
3. The indoor positioning method of the satellite communication terminal according to claim 1, wherein the performing model parameter optimization on the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and performing real-time positioning on the target device through the target indoor positioning model to obtain real-time positioning data includes:
acquiring a first function parameter set of a plurality of radial basis functions in the initial indoor positioning model and a second function parameter set of a path loss analysis function;
initializing model parameters of the first function parameter set and the second function parameter set through a preset genetic algorithm according to the positioning deviation data, and generating an initial model parameter group, wherein the initial model parameter group comprises a plurality of candidate model parameter combinations;
performing fitness calculation on the plurality of candidate model parameter combinations to obtain fitness data of each candidate model parameter combination;
carrying out model parameter optimization solving on the plurality of candidate model parameter combinations according to the adaptation data to obtain a target model parameter combination;
updating model parameters of the initial indoor positioning model through the target model parameter combination to obtain a target indoor positioning model;
And acquiring a real-time multi-frequency signal through the satellite communication terminal, and inputting the real-time multi-frequency signal into the target indoor positioning model for real-time positioning to obtain real-time positioning data.
4. An indoor positioning device of a satellite communication terminal, characterized in that the indoor positioning device of the satellite communication terminal comprises:
the acquisition module is used for acquiring multi-frequency signals of target equipment through a preset satellite communication terminal to obtain a plurality of historical frequency band signals, and respectively carrying out signal characteristic analysis on the plurality of historical frequency band signals to obtain signal propagation path characteristics of each historical frequency band signal;
the fusion module is used for carrying out signal modulation fusion on the plurality of historical frequency band signals according to the signal propagation path characteristics to obtain fusion frequency band signals; the method specifically comprises the following steps: according to the signal propagation path characteristics, signal standardization parameter operation is carried out on the plurality of historical frequency band signals respectively, so that signal standardization parameters of each historical frequency band signal are obtained; performing signal standardization processing on the plurality of historical frequency band signals according to the signal standardization parameters to obtain a plurality of standard frequency band signals; inputting the plurality of standard frequency band signals into a preset signal modulation model, wherein the signal modulation model comprises the following steps: a plurality of weak classifiers, each weak classifier including a convolutional pooling layer, a full connection layer, a long short time memory layer, and an output layer; respectively carrying out signal coding on the plurality of standard frequency band signals through a convolution pooling layer and a full connection layer in the plurality of weak classifiers to obtain signal coding data of each standard frequency band signal; respectively carrying out signal modulation on the signal coded data through a long-short time memory layer and an output layer in the weak classifiers to obtain a target modulation signal of each weak classifier; acquiring classifier weight data of the weak classifiers, and performing signal fusion on target modulation signals of each weak classifier according to the classifier weight data to obtain fused frequency band signals;
The analysis module is used for inputting the fused frequency band signals into a preset initial indoor positioning model to perform equipment indoor positioning analysis to obtain a historical positioning data set; the method specifically comprises the following steps: inputting the fused frequency band signals into a preset initial indoor positioning model, wherein the initial indoor positioning model comprises the following steps: the system comprises a positioning prediction layer and a positioning check layer, wherein the positioning prediction layer comprises a plurality of radial basis functions, and the positioning check layer comprises a path loss analysis function; respectively carrying out positioning prediction on the fused frequency band signals according to the plurality of radial basis functions to obtain positioning prediction data of each radial basis function; acquiring function weight data of the plurality of radial basis functions, and carrying out weighted summation on positioning prediction data of each radial basis function according to the function weight data to obtain a predicted positioning data set; performing positioning data verification on the predicted positioning data set through the path loss analysis function to obtain a historical positioning data set;
the extraction module is used for acquiring the real-time images of the target equipment to obtain a plurality of equipment real-time operation images, and extracting equipment environment characteristics of the equipment real-time operation images to obtain an equipment environment characteristic set; the method specifically comprises the following steps: acquiring real-time images of the target equipment to obtain a plurality of initial real-time running images; respectively carrying out image enhancement processing on the plurality of initial real-time running images to obtain a plurality of target real-time running images; performing equipment center identification on the plurality of target real-time operation images to obtain a plurality of equipment center key points, and constructing an initial position cloud picture according to the plurality of equipment center key points; carrying out adjacent point identification on each equipment center key point in the initial position cloud picture based on a K-time neighbor algorithm to obtain K nearest adjacent points corresponding to each equipment center key point; respectively calculating the position offset between the K nearest neighbors and the corresponding equipment center key points, and carrying out drift correction on the initial position cloud picture according to the position offset to obtain a target position cloud picture; mapping the target position cloud image to a corresponding target real-time operation image to obtain a plurality of equipment real-time operation images; extracting the device environment characteristics of the plurality of device real-time operation images to obtain a device environment characteristic set;
The calculation module is used for constructing a target noise variance matrix according to the equipment environment characteristic set and the historical positioning data set, and carrying out positioning deviation calculation on the historical positioning data set through the target noise variance matrix to obtain positioning deviation data; the method specifically comprises the following steps: performing normal cloud distribution mapping on the historical positioning data set through a preset normal cloud model to obtain initial normal cloud distribution, wherein the initial normal cloud distribution comprises a plurality of historical positioning data points; calculating the weight of each historical positioning data point based on the equipment environment characteristic set, and generating a target weight matrix according to the weight of each historical positioning data point; carrying out noise variance calculation on the initial normal cloud distribution to obtain a target noise variance matrix; carrying out weight weighted average on the historical positioning data set according to the target weight matrix, and carrying out positioning deviation calculation according to the target noise variance matrix to obtain positioning deviation data;
and the positioning module is used for optimizing the model parameters of the initial indoor positioning model according to the positioning deviation data to obtain a target indoor positioning model, and positioning the target equipment in real time through the target indoor positioning model to obtain real-time positioning data.
5. An indoor positioning apparatus of a satellite communication terminal, characterized in that the indoor positioning apparatus of a satellite communication terminal comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invoking the instructions in the memory to cause an indoor positioning device of the satellite communication terminal to perform the indoor positioning method of the satellite communication terminal of any of claims 1-3.
6. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the indoor positioning method of a satellite communication terminal according to any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311756258.XA CN117434497B (en) | 2023-12-20 | 2023-12-20 | Indoor positioning method, device and equipment of satellite communication terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311756258.XA CN117434497B (en) | 2023-12-20 | 2023-12-20 | Indoor positioning method, device and equipment of satellite communication terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117434497A CN117434497A (en) | 2024-01-23 |
| CN117434497B true CN117434497B (en) | 2024-03-19 |
Family
ID=89553852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311756258.XA Active CN117434497B (en) | 2023-12-20 | 2023-12-20 | Indoor positioning method, device and equipment of satellite communication terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117434497B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110749859A (en) * | 2019-10-22 | 2020-02-04 | 清华大学 | Single base station array positioning method and device based on multiple carrier frequencies |
| WO2021003757A1 (en) * | 2019-07-10 | 2021-01-14 | 博睿泰克科技（宁波）有限公司 | Indoor positioning method and system based on signal multipath propagation measurement |
| CN112737668A (en) * | 2020-12-30 | 2021-04-30 | 广东省电信规划设计院有限公司 | Satellite communication signal high-precision modulation classification method, device and system |
| CN114745684A (en) * | 2022-04-13 | 2022-07-12 | 天津工业大学 | CSI indoor positioning method based on multi-mode GAN |
| CN115524723A (en) * | 2021-06-24 | 2022-12-27 | 中国极地研究中心(中国极地研究所) | Satellite positioning error calculation method based on spatial ionosphere environment chromatographic parameters, storage medium and computing equipment |
| CN115758852A (en) * | 2021-09-02 | 2023-03-07 | 中移(苏州)软件技术有限公司 | Path loss modeling method, device, equipment and storage medium |
| CN116643293A (en) * | 2023-04-28 | 2023-08-25 | 广州吉欧电子科技有限公司 | GNSS positioning method and device, equipment and storage medium |
| CN116702093A (en) * | 2023-08-08 | 2023-09-05 | 海南智慧海事科技有限公司 | Marine target positioning method based on big data fusion |
| CN116824396A (en) * | 2023-08-29 | 2023-09-29 | 湖北省泛星信息技术有限公司 | Multi-satellite data fusion automatic interpretation method |
| CN116866828A (en) * | 2023-07-28 | 2023-10-10 | 中国联合网络通信集团有限公司 | Position information determining method, device, server and storage medium |
| CN117216481A (en) * | 2023-09-28 | 2023-12-12 | 浙江巴赫厨具有限公司 | Remote monitoring method and system for electric appliance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3933444A1 (en) * | 2020-06-30 | 2022-01-05 | Spaceopal GmbH | Method for determining a state parameter of a receiver and an apparatus for performing such a method |
-
2023
- 2023-12-20 CN CN202311756258.XA patent/CN117434497B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021003757A1 (en) * | 2019-07-10 | 2021-01-14 | 博睿泰克科技（宁波）有限公司 | Indoor positioning method and system based on signal multipath propagation measurement |
| CN110749859A (en) * | 2019-10-22 | 2020-02-04 | 清华大学 | Single base station array positioning method and device based on multiple carrier frequencies |
| CN112737668A (en) * | 2020-12-30 | 2021-04-30 | 广东省电信规划设计院有限公司 | Satellite communication signal high-precision modulation classification method, device and system |
| CN115524723A (en) * | 2021-06-24 | 2022-12-27 | 中国极地研究中心(中国极地研究所) | Satellite positioning error calculation method based on spatial ionosphere environment chromatographic parameters, storage medium and computing equipment |
| CN115758852A (en) * | 2021-09-02 | 2023-03-07 | 中移(苏州)软件技术有限公司 | Path loss modeling method, device, equipment and storage medium |
| CN114745684A (en) * | 2022-04-13 | 2022-07-12 | 天津工业大学 | CSI indoor positioning method based on multi-mode GAN |
| CN116643293A (en) * | 2023-04-28 | 2023-08-25 | 广州吉欧电子科技有限公司 | GNSS positioning method and device, equipment and storage medium |
| CN116866828A (en) * | 2023-07-28 | 2023-10-10 | 中国联合网络通信集团有限公司 | Position information determining method, device, server and storage medium |
| CN116702093A (en) * | 2023-08-08 | 2023-09-05 | 海南智慧海事科技有限公司 | Marine target positioning method based on big data fusion |
| CN116824396A (en) * | 2023-08-29 | 2023-09-29 | 湖北省泛星信息技术有限公司 | Multi-satellite data fusion automatic interpretation method |
| CN117216481A (en) * | 2023-09-28 | 2023-12-12 | 浙江巴赫厨具有限公司 | Remote monitoring method and system for electric appliance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117434497A (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016138800A1 (en) | Optimizing position estimates of a device for indoor localization | |
| KR101901039B1 (en) | Method and apparatus for cross device automatic calibration | |
| CN110913338B (en) | Positioning track correction method and device, computer equipment and storage medium | |
| US20180329022A1 (en) | Method, apparatus and system for locating an object using cluster-type magnetic field | |
| CN110501010A (en) | Determine position of the mobile device in geographic area | |
| DK2928243T3 (en) | PROCEDURE FOR INDOOR POSITIONING OF WIRELESS LOCAL DEVICES (WLAN) | |
| CN111060132B (en) | Calibration method and device for travelling crane positioning coordinates | |
| CN111856447A (en) | Radar positioning method and device and storage medium | |
| Huilla et al. | Indoor localization with Wi-Fi fine timing measurements through range filtering and fingerprinting methods | |
| Fang et al. | Compensating for orientation mismatch in robust Wi-Fi localization using histogram equalization | |
| Martinelli | Robot localization using the phase of passive UHF-RFID signals under uncertain tag coordinates | |
| CN114863129A (en) | Instrument numerical analysis method, device, equipment and storage medium | |
| CN117434497B (en) | Indoor positioning method, device and equipment of satellite communication terminal and storage medium | |
| CN108712725B (en) | SLAM method based on rodent model and WIFI fingerprint | |
| Madray et al. | Relative angle correction for distance estimation using K-nearest neighbors | |
| WO2020255796A1 (en) | Receiver terminal, positioning method, and program | |
| KR102150276B1 (en) | Finger print constructing method for radio map in communication network and apparatus therefor | |
| CN114543810B (en) | Unmanned aerial vehicle cluster passive positioning method and device under complex environment | |
| CA3094328C (en) | Magnetic parameter-based localization in mobile device navigation | |
| CN114252871A (en) | Radar measurement accuracy compensation method based on machine learning | |
| CN113483661A (en) | Point cloud data acquisition method, device, equipment and storage medium | |
| CN114102574B (en) | Positioning error evaluation system and method | |
| CN117668574B (en) | Data model optimization method, device and equipment for light shadow show and storage medium | |
| CN111291581B (en) | Signal source positioning data processing method, device, equipment and storage medium | |
| US20230075165A1 (en) | Method for creating a model for positioning, and a method for positioning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |