Wireless terminal positioning method and system

Abstract

The invention discloses a wireless terminal positioning method and system. The method comprises the steps of data acquisition, feature extraction and error correction, environment perception recognition model establishment, positioning coordinate registration, multi-factor fusion and position positioning presentation. The invention belongs to the technical field of positioning, and particularly relates to a wireless terminal positioning method and system. According to the scheme, through color feature analysis, neighborhood averaging method smoothing and feature extraction based on a color space model, pulse spectrum features are adopted as measurement of a tracking algorithm, and an environment perception recognition model is established; adaptive virtual positioning is generated by changing parameters such as positions, radiuses and curvatures of nodes, and different factors in the environment are perceived and identified by constructing position codes and designing a similarity measurement function, so that interference in a complex environment can be dealt with, the stability, robustness, adaptability and real-time performance of a positioning result are improved, and the positioning accuracy is improved. The method is suitable for positioning requirements of various different scenes.

Description

Technical Field

[0001] The present invention relates to the field of positioning technology, and in particular to a wireless terminal positioning method and system. Background Art

[0002] Current wireless terminal positioning technologies mainly include methods based on the global positioning system (GPS), WiFi positioning, Bluetooth positioning, and UWB positioning. Among them, GPS positioning has high accuracy, but it is easy to fail in environments with poor signal coverage such as indoors or in urban canyons; Wi-Fi and Bluetooth positioning are limited by signal coverage and regional density, and the positioning accuracy is not high; UWB positioning has high accuracy, but it is expensive and is easily affected by multipath effects in complex environments, resulting in reduced positioning accuracy. Therefore, in the current wireless terminal positioning technology, the application of a single sensor often cannot meet the demand for precise positioning, and there are problems such as low positioning accuracy, poor robustness, limited applicability, and inability to cope with positioning in complex environments. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a wireless terminal positioning method and system. In view of the problem of low positioning accuracy, the present solution adopts a feature extraction and error correction method, and uses a visual feature extraction algorithm to extract and correct visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on a color space model. The pulse spectrum feature is used as a measurement of the tracking algorithm to improve the positioning accuracy. In view of the problem of poor robustness, the present solution adopts the establishment of an environmental perception and recognition model and positioning coordinate alignment, and generates an adaptive virtual positioning by changing the parameters of the node position, radius, curvature, and rotation angle. Then, the position code is constructed and the similarity measurement function is designed to quantify the transmission frequency to realize the perception and recognition of different factors in the environment, and the data is subjected to coordinate transformation, data spatiotemporal correlation and synchronization, and data fusion. It can better cope with interference in complex environments, improve the stability, robustness, adaptability and real-time performance of the positioning results, and make the present solution suitable for positioning needs in various scenarios, and has a wider applicability.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides a wireless terminal positioning method, the method comprising the following steps:

[0005] Step S1: data collection;

[0006] Step S2: Feature extraction and error correction, extracting visual features from environmental data, using visual feature extraction algorithm to perform feature extraction and error correction on visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on color space model to obtain preliminary positioning information; by using pulse spectrum features as the measurement of the tracking algorithm, extract the precise distance information between the terminal and the base station;

[0007] Visual features are usually the most intuitive and accurate reflection of environmental information. Planning is done based on the acquired environmental image information, and the surrounding local environmental information is continuously sensed during the journey to make preliminary positioning decisions. Using pulse spectrum features as a measurement for tracking algorithms can obtain precise distance information, which can improve the accuracy and reliability of data.

[0008] Step S3: Establishment of environmental perception and recognition model. Based on the visual feature data and precise distance information extracted and corrected by features, adaptive virtual positioning is generated by changing the position, radius, curvature and rotation angle parameters of the node to meet different environmental positioning requirements and generate the position coordinates of the node. Then, the position code is constructed and the similarity measurement function is designed to quantify the emission frequency to realize the perception and recognition of different factors in the environment.

[0009] Step S4: Positioning coordinate registration, coordinate conversion, data spatiotemporal association and synchronization, and data fusion of the feature extraction and error correction data and the environment perception recognition model data to obtain accurate positioning coordinates;

[0010] Step S5: Multi-factor fusion and position positioning presentation, combining the positioning coordinates output by the positioning coordinate registration module, and performing multi-factor fusion to finally realize real-time positioning of the wireless terminal;

[0011] The multi-factor fusion and location positioning presentation stage transmits the terminal's final location information to the user's device, providing users with accurate and real-time location positioning services.

[0012] Furthermore, in step S1, the data collection specifically involves acquiring environmental data through a data collection device; the data collection device includes a camera, a UWB radar and a global navigation satellite system, and the environmental data includes image data, UWB radar data, map data and positioning data.

[0013] Furthermore, in step S2, the visual feature extraction algorithm performs recognition based on the acquired image information, and continuously senses the surrounding local environment information to make preliminary visual feature positioning, which specifically includes the following steps:

[0014] Step S21: color feature analysis, using a CCD visual sensor to collect the original image, graying the color image collected by the CCD to obtain grayed image information. The specific algorithm formula is as follows:

[0015] ;

[0016] Among them, R, G, and B represent the data of the three color channels of red, green, and blue respectively;

[0017] The purpose of grayscale is to make the values ​​of the three color components R, G, and B equal. Using the average value algorithm of the three components R, G, and B, the grayscale image information that is only grayed out still contains various noises and distortions. Therefore, the grayscale image information must be smoothed and filtered before analyzing the image.

[0018] Step S22: The grayscale image information is smoothed using the neighborhood average method. First, the grayscale image information is convolved with a one-dimensional Gaussian function, and then the convolution result is convolved with a one-dimensional Gaussian function in the same vertical direction. The specific algorithm formula is as follows:

[0019] ;

[0020] in, Indicates that the coordinates are The pixel value at i and j are the horizontal and vertical coordinates of the pixel respectively. represents the smoothing parameter;

[0021] ;

[0022] in, Indicates that the coordinates are The filtered pixel value at ; is the weight coefficient, expressed in The relationship between the pixel at and the surrounding pixels; m and n are relative to The position offset of Indicates that in the original image, at coordinates The pixel value of and Respectively represent the coordinates of the pixels in the original image; K represents the distance of the window to the left or right from the center pixel in the horizontal direction; L represents the distance of the window up or down from the center pixel in the vertical direction;

[0023] Different from simple image smoothing, in the neighborhood average smoothing of the image in this scheme, pixels at different positions are given different weights when the image neighborhood is averaged, which has a better removal effect on noise that obeys the normal distribution; after smoothing and filtering, it is still impossible to determine the type, including light intensity, shadows, obstacles or background, so the original image needs to be classified according to the difference in color;

[0024] Step S23: Segment the image using color features; this solution uses a binarization method that has a simple algorithm, is easy to understand and implement, has a fast calculation speed, consumes little memory, and has low requirements on computing devices. Specifically, it is a feature extraction based on a color space model, and the content is as follows:

[0025] ,

[0026] ,

[0027] ;

[0028] in, Indicates the brightness of the color, ranging from 0 to 1; brightness refers to the intensity of light stimulation produced by colored light to the human eye, and brightness is related to the energy and color of the light; is a proportional value ranging from 0 to 1, representing the ratio between the selected color and the maximum purity of that color; Represents color information, expressed from 0° to 360°, with red, green, and blue separated by 120°; hue is mainly determined by the wavelength of each component of visible light, which is the basic characteristic of colored light; and It is basically unaffected by light and can be used for image processing with good results;

[0029] In the formula, The specific algorithm formula is as follows:

[0030] ;

[0031] in, It is a spatial transformation equation, where R, G, and B represent the data of the three color channels of red, green, and blue respectively.

[0032] For some specific colors, it is difficult to extract their features using RGB. Since they are easily affected by light intensity and the surrounding environment, the extraction effect is not particularly good, which brings problems to the acquisition of later visual feature information. Therefore, the color space model of this scheme is used for feature extraction, which can effectively solve the problem of poor extraction effect.

[0033] Furthermore, in step S2, by using the pulse spectrum feature as the measurement of the tracking algorithm, the specific algorithm formula of the tracking algorithm is:

[0034] ,

[0035] ;

[0036] in, Indicates the horizontal position of the target; Indicates the target's horizontal speed; Indicates the standard deviation of the error of the target's horizontal position; Indicates the angle of the target in the horizontal direction; Indicates the vertical position of the target; Indicates the target's vertical speed; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's vertical angle;

[0037] In two-dimensional space, the UWB radar system is orthogonally set up for two-dimensional tracking, where: and The specific algorithm formula is as follows:

[0038] ,

[0039] ;

[0040] in, Indicates the angle of the target in the horizontal direction; Indicates the distance from the target to the sensor; Indicates the standard deviation of the error of the target's horizontal position; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's horizontal speed; Indicates the target's vertical angle; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's vertical speed.

[0041] Furthermore, in step S3, the environment perception recognition model is established, which specifically includes the following contents:

[0042] Step S31, obtaining landmarks, the specific algorithm formula is as follows:

[0043] ;

[0044] in, Indicates at time The above number is The position coordinates of the node, Indicates at time The above number is The radius where the node is located; Indicates at time The above number is The curvature of the nodes; Indicates at time The above number is The rotation angle of the node; Indicates at time The above number is The tangent direction of the node;

[0045] By changing the parameters of the node's position, radius, curvature, and rotation angle, adaptive virtual positioning can be generated to meet different environmental positioning requirements and generate the node's position coordinates;

[0046] Step S32, constructing a location code, the specific algorithm formula is as follows:

[0047] ;

[0048] in, Indicates at time The location code of the previous node; Indicates at time From the starting point to the node The path length; Indicates at time The length of the path from the starting point to node 2; Indicates at time The length of the path from the starting point to node N; Indicates at time The path length from the starting point to node N multiplied by the time;

[0049] By calculating the location code and path length of the node at different times, the location and path length of the positioning node on the path can be determined;

[0050] Step S33, designing a similarity measurement function to quantify the emission frequency;

[0051] ;

[0052] in, Indicates at time The above number is The transmission frequency of the node; Indicates the number The number of nodes related to Representation and numbering The weights associated with the nodes; Representation and distance The relevant weights range from 0 to 1; Indicates at time The above number is The distance of the node; Indicates the number and The distance between nodes; represents the variance of the distance; Representation and angle The relevant weights range from 0 to 1; Indicates at time The above number is The angle of the node; Indicates the number The angle of the node; represents the variance of the angle;

[0053] In the formula, The specific algorithm formula is as follows:

[0054] ;

[0055] in, Representation and numbering The weights associated with the nodes; Represents the similarity metric of the current node, which is used to measure the similarity between nodes; Indicates at time The number of nodes on the

[0056] The environmental perception recognition model calculates the transmission frequency of each node based on the similarity measurement function between nodes. The transmission frequency can be used to represent the importance or weight of the node in positioning. It can be used to determine the location of the node and evaluate and compare the characteristics of the node to provide a more comprehensive environmental perception for the model. Combining the importance and characteristics of the node, the perception and recognition of different factors in the environment can be achieved. The transmission frequency plays an important role in positioning and environmental perception recognition, and can be used for precise positioning, improving the accuracy of positioning and the reliability of environmental recognition.

[0057] Furthermore, in step S4, the positioning coordinate registration integrates and calibrates the data of feature extraction and error correction and the data of the environment perception recognition model to obtain accurate positioning coordinates, and the specific contents are as follows:

[0058] Coordinate conversion: the received positioning data comes from different sensors or different coordinate systems, and coordinate conversion is required to convert all data into the same coordinate system for subsequent data processing and analysis;

[0059] Data spatiotemporal correlation and synchronization: data collected and processed at different times or by different sensors are temporally correlated and synchronized, and the spatiotemporal relationship between data is determined by using timestamp or feature matching methods, spatiotemporal calibration is performed, and real-time positioning is performed;

[0060] Data fusion: fusing data that has been temporally correlated and synchronized, taking advantage of the strengths of each data source, including accuracy and coverage, to improve the overall performance of wireless terminal positioning;

[0061] Quality assessment and feedback: perform quality assessment on the registered data, check the accuracy and stability of the positioning results, and feed the assessment results back to the system to optimize the algorithm and parameter settings;

[0062] Positioning coordinate alignment can significantly improve the performance and reliability of the positioning system, is applicable to various complex environments and application scenarios, and provides more reliable positioning services for wireless terminals.

[0063] Further, in step S5, the multi-factor fusion and position positioning presentation, combined with the positioning coordinates output by positioning coordinate registration, specifically include the following steps:

[0064] Position information coding: the final position information after data fusion is encoded so as to effectively compress data and optimize transmission during transmission. The coding adopts a standard coding algorithm or a specific position information coding algorithm.

[0065] Select a communication method, and select an appropriate communication method to transmit location information; the communication methods include wireless network, Bluetooth, infrared, or point-to-point communication or broadcast communication according to the specific scenario;

[0066] Establishing a communication connection: according to the selected communication mode, a communication connection is established between the wireless terminal and the user equipment; including the steps of pairing the devices and establishing the network connection to ensure effective data transmission;

[0067] Data transmission and reception: the encoded location information is transmitted from the wireless terminal to the user equipment through the selected communication method; after the user equipment receives the location information, it decodes and processes it to obtain the final location information;

[0068] Location information display: Display the received final location information on the user's device. The final location information includes marking the location on a map and displaying a detailed text description of the location information so that the user can intuitively understand and use this information;

[0069] Error handling and feedback: If an error or data loss occurs during the transmission process, the corresponding error handling and retransmission mechanism will be implemented to ensure the integrity and accuracy of the location information; at the same time, the transmission status and results will be fed back to the user device so that the user can understand the transmission status in a timely manner.

[0070] Through the above steps, the multi-factor fusion and location positioning presentation steps can effectively transmit the final location information of the wireless terminal to the user equipment, providing the user with accurate and real-time location positioning services.

[0071] A wireless terminal positioning system provided by the present invention includes a data acquisition module, a feature extraction and error correction module, an environment perception recognition model establishment module, a positioning coordinate registration module, and a multi-factor fusion and position positioning presentation module;

[0072] The data acquisition module acquires environmental data through a data acquisition device and sends the environmental data to a feature extraction and error correction module;

[0073] The feature extraction and error correction module is used to extract visual features from environmental data, and use the visual feature extraction algorithm to perform feature extraction and error correction on the visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on the color space model to obtain preliminary positioning information; by using the pulse spectrum feature as the measurement of the tracking algorithm, the precise distance information between the terminal and the base station is extracted;

[0074] The environment perception recognition model building module generates adaptive virtual positioning based on feature extraction and error correction visual feature data and precise distance information by changing the parameters of the node's position, radius, curvature, and rotation angle to meet different environmental positioning requirements and generate the node's position coordinates; then, by constructing a position code and designing a similarity measurement function to quantify the emission frequency, the perception and recognition of different factors in the environment are realized;

[0075] The positioning coordinate registration module performs coordinate conversion, data spatiotemporal association and synchronization, and data fusion on the data of feature extraction and error correction and the data of the environment perception recognition model to obtain accurate positioning coordinates;

[0076] The multi-factor fusion and position positioning presentation module is used to combine the positioning coordinates output by the positioning coordinate registration module to perform multi-factor fusion, and finally realize the real-time positioning of the wireless terminal.

[0077] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0078] (1) To address the problem of low positioning accuracy, this solution adopts a feature extraction and error correction method. It uses a visual feature extraction algorithm to perform feature extraction and error correction on visual features through color feature analysis, neighborhood average smoothing, and feature extraction based on a color space model. It uses pulse spectrum features as a measurement for the tracking algorithm to improve positioning accuracy.

[0079] (2) To address the problem of poor robustness, this solution adopts the establishment of an environmental perception and recognition model and positioning coordinate registration. By changing the parameters of the node's position, radius, curvature, and rotation angle, an adaptive virtual positioning is generated. Then, by constructing a position code and designing a similarity measurement function to quantify the transmission frequency, the different factors in the environment can be perceived and identified. The data is then subjected to coordinate transformation, data spatiotemporal correlation and synchronization, and data fusion. This allows the solution to better cope with interference in complex environments and improve the stability, robustness, adaptability, and real-time performance of the positioning results, making it suitable for positioning needs in various scenarios and having a wider range of applicability.

[0080] (3) For some specific colors, it is difficult to extract their features using RGB. Since they are easily affected by light intensity and the surrounding environment, the extraction effect is not particularly good, which brings problems to the acquisition of later visual feature information. Therefore, the color space model of this scheme is used for feature extraction, which can effectively solve the problem of poor extraction effect.

[0081] (4) The environmental perception and recognition model calculates the transmission frequency of each node based on the similarity measurement function between nodes. The transmission frequency is used to represent the importance or weight of the node in positioning, to determine the location of the node, and to evaluate and compare the characteristics of the node, providing the model with a more comprehensive environmental perception. Combining the importance and characteristics of the node, it is possible to perceive and recognize different factors in the environment. The transmission frequency plays an important role in positioning and environmental perception and recognition, and can be used for precise positioning, improving the accuracy of positioning and the reliability of environmental recognition.

[0082] (5) Positioning coordinate alignment can significantly improve the performance and reliability of the positioning system, and is suitable for various complex environments and application scenarios, providing more reliable positioning services for wireless terminals.

[0083] (6) The multi-factor fusion and location positioning presentation module can effectively transmit the final location information of the wireless terminal to the user device, providing users with accurate and real-time location positioning services. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 A schematic diagram of a flow chart of a wireless terminal positioning method provided by the present invention;

[0085] Figure 2 A schematic diagram of a wireless terminal positioning system provided by the present invention;

[0086] Figure 3 It is a schematic diagram of the process of step S3.

[0087] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0088] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0089] In the description of the present invention, it is necessary to understand that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred system or element must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0090] Example 1, see Figure 1 The present invention provides a wireless terminal positioning method, which comprises the following steps:

[0091] Step S1: data collection;

[0092] Step S2: Feature extraction and error correction, extracting visual features from environmental data, using visual feature extraction algorithm to perform feature extraction and error correction on visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on color space model to obtain preliminary positioning information; by using pulse spectrum features as the measurement of the tracking algorithm, extract the precise distance information between the terminal and the base station;

[0093] Visual features are usually the most intuitive and accurate reflection of environmental information. Planning is done based on the acquired environmental image information, and the surrounding local environmental information is continuously sensed during the journey to make preliminary positioning decisions. Using pulse spectrum features as a measurement for tracking algorithms can obtain precise distance information, which can improve the accuracy and reliability of data.

[0094] Step S3: Establishment of environmental perception and recognition model. Based on the visual feature data and precise distance information extracted and corrected by features, adaptive virtual positioning is generated by changing the position, radius, curvature and rotation angle parameters of the node to meet different environmental positioning requirements and generate the position coordinates of the node. Then, the position code is constructed and the similarity measurement function is designed to quantify the emission frequency to realize the perception and recognition of different factors in the environment.

[0095] Step S4: Positioning coordinate registration, coordinate conversion, data spatiotemporal association and synchronization, and data fusion of the feature extraction and error correction data and the environment perception recognition model data to obtain accurate positioning coordinates;

[0096] Step S5: Multi-factor fusion and position positioning presentation, combining the positioning coordinates output by the positioning coordinate registration module, and performing multi-factor fusion to finally realize real-time positioning of the wireless terminal;

[0097] The multi-factor fusion and location positioning presentation stage transmits the terminal's final location information to the user's device, providing users with accurate and real-time location positioning services.

[0098] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, data collection specifically involves acquiring environmental data through a data collection device; the data collection device includes a camera, a UWB radar, and a global navigation satellite system, and the environmental data includes image data, UWB radar data, map data, and positioning data.

[0099] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, the visual feature extraction algorithm performs recognition based on the acquired image information, and continuously senses the surrounding local environment information to make preliminary visual feature positioning, which specifically includes the following steps:

[0100] Step S21: color feature analysis, using a CCD visual sensor to collect the original image, graying the color image collected by the CCD to obtain grayed image information. The specific algorithm formula is as follows:

[0101] ;

[0102] Among them, R, G, and B represent the data of the three color channels of red, green, and blue respectively;

[0103] The purpose of grayscale is to make the values ​​of the three color components R, G, and B equal. Using the average value algorithm of the three components R, G, and B, the grayscale image information that is only grayed out still contains various noises and distortions. Therefore, the grayscale image information must be smoothed and filtered before analyzing the image.

[0104] Step S22: The grayscale image information is smoothed using the neighborhood average method. First, the grayscale image information is convolved with a one-dimensional Gaussian function, and then the convolution result is convolved with a one-dimensional Gaussian function in the same vertical direction. The specific algorithm formula is as follows:

[0105] ;

[0106] in, Indicates that the coordinates are The pixel value at i and j are the horizontal and vertical coordinates of the pixel respectively. represents the smoothing parameter;

[0107] ;

[0108] in, Indicates that the coordinates are The filtered pixel value at ; is the weight coefficient, expressed in The relationship between the pixel at and the surrounding pixels; m and n are relative to The position offset of Indicates that in the original image, at coordinates The pixel value of and Respectively represent the coordinates of the pixels in the original image; K represents the distance of the window to the left or right from the center pixel in the horizontal direction; L represents the distance of the window up or down from the center pixel in the vertical direction;

[0109] As an embodiment of the present scheme, this embodiment is different from simple image smoothing. In the neighborhood averaging method for image smoothing, pixels at different positions are assigned different weights when the image neighborhood is averaged, which has a better removal effect on noise that obeys a normal distribution.

[0110] After smoothing and filtering, it is still impossible to determine the type, including lighting intensity, shadows, obstacles or background, so the original image needs to be classified based on the difference in color;

[0111] Step S23: This embodiment uses a binarization method that has a simple algorithm, is easy to understand and implement, has a fast calculation speed, consumes little memory, and has low requirements on computing devices, and uses color features to segment the image; specifically, it is feature extraction based on a color space model, and the specific contents are as follows:

[0112] ,

[0113] ,

[0114] ;

[0115] in, Indicates the brightness of the color, ranging from 0 to 1; brightness refers to the intensity of light stimulation produced by colored light to the human eye, and brightness is related to the energy and color of the light; is a proportional value ranging from 0 to 1, representing the ratio between the selected color and the maximum purity of that color; Represents color information, expressed from 0° to 360°, with red, green, and blue separated by 120°; hue is mainly determined by the wavelength of each component of visible light, which is the basic characteristic of colored light; and It is basically unaffected by light and can be used for image processing with good results;

[0116] In the above formula The specific algorithm formula is as follows:

[0117] ;

[0118] in, It is a spatial transformation equation, where R, G, and B represent the data of the three color channels of red, green, and blue respectively.

[0119] For some specific colors, it is difficult to extract their features using RGB. Since they are easily affected by light intensity and the surrounding environment, the extraction effect is not particularly good, which brings problems to the acquisition of later visual feature information. Therefore, the color space model of this scheme is used for feature extraction, which can effectively solve the problem of poor extraction effect.

[0120] Example 4, see Figure 1 This embodiment is based on the above embodiment. In step S2, by using the pulse spectrum feature as the measurement of the tracking algorithm, the specific algorithm formula of the tracking algorithm is:

[0121] ,

[0122] ;

[0123] in, Indicates the horizontal position of the target; Indicates the target's horizontal speed; Indicates the standard deviation of the error of the target's horizontal position; Indicates the angle of the target in the horizontal direction; Indicates the vertical position of the target; Indicates the target's vertical speed; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's vertical angle;

[0124] In two-dimensional space, the UWB radar system is orthogonally set up for two-dimensional tracking, where: and The specific algorithm formula is as follows:

[0125] ,

[0126] ;

[0127] in, Indicates the angle of the target in the horizontal direction; Indicates the distance from the target to the sensor; Indicates the standard deviation of the error of the target's horizontal position; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's horizontal speed; Indicates the target's vertical angle; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's vertical speed.

[0128] Example 5, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, an environment perception recognition model is established, which specifically includes the following contents:

[0129] Step S31, obtaining landmarks, the specific algorithm formula is as follows:

[0130] ;

[0131] in, Indicates at time The above number is The position coordinates of the node, Indicates at time The above number is The radius where the node is located; Indicates at time The above number is The curvature of the nodes; Indicates at time The above number is The rotation angle of the node; Indicates at time The above number is The tangent direction of the node;

[0132] By changing the parameters of the node's position, radius, curvature, and rotation angle, adaptive virtual positioning can be generated to meet different environmental positioning requirements and generate the node's position coordinates;

[0133] Step S32, constructing a location code, the specific algorithm formula is as follows:

[0134] ;

[0135] in, Indicates at time The location code of the previous node; Indicates at time From the starting point to the node The path length; Indicates at time The length of the path from the starting point to node 2; Indicates at time The length of the path from the starting point to node N; Indicates at time The path length from the starting point to node N multiplied by the time;

[0136] By calculating the location code and path length of the node at different times, the location and path length of the positioning node on the path can be determined;

[0137] Step S33, designing a similarity measurement function to quantify the emission frequency;

[0138] ;

[0139] in, Indicates at time The above number is The transmission frequency of the node; Indicates the number The number of nodes related to Representation and numbering The weights associated with the nodes; Representation and distance The relevant weights range from 0 to 1; Indicates at time The above number is The distance of the node; Indicates the number and The distance between nodes; represents the variance of the distance; Representation and angle The relevant weights range from 0 to 1; Indicates at time The above number is The angle of the node; Indicates the number The angle of the node; represents the variance of the angle;

[0140] In the formula, The specific algorithm formula is as follows:

[0141] ;

[0142] in, Representation and numbering The weights associated with the nodes; Represents the similarity metric of the current node, which is used to measure the similarity between nodes; Indicates at time The number of nodes on the

[0143] The environmental perception and recognition model calculates the transmission frequency of each node based on the similarity measurement function between nodes. The transmission frequency can be used to represent the importance or weight of the node in positioning. It can be used to determine the location of the node and evaluate and compare the characteristics of the node to provide a more comprehensive environmental perception for the model. Combining the importance and characteristics of the node, it can achieve the perception and recognition of different factors in the environment. The transmission frequency plays an important role in positioning and environmental perception and recognition. It can be used for precise positioning, improving the accuracy of positioning and the reliability of environmental recognition.

[0144] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S4, the positioning coordinate registration integrates and calibrates the data of feature extraction and error correction and the data of the environment perception recognition model to obtain accurate positioning coordinates. The specific contents are as follows:

[0145] Coordinate conversion: the received positioning data comes from different sensors or different coordinate systems, and coordinate conversion is required to convert all data into the same coordinate system for subsequent data processing and analysis;

[0146] Data spatiotemporal correlation and synchronization: data collected and processed at different times or by different sensors are temporally correlated and synchronized, and the spatiotemporal relationship between data is determined by using timestamp or feature matching methods, spatiotemporal calibration is performed, and real-time positioning is performed;

[0147] Data fusion: fusing data that has been temporally correlated and synchronized, taking advantage of the strengths of each data source, including accuracy and coverage, to improve the overall performance of wireless terminal positioning;

[0148] Quality assessment and feedback: perform quality assessment on the registered data, check the accuracy and stability of the positioning results, and feed the assessment results back to the system to optimize the algorithm and parameter settings;

[0149] Positioning coordinate alignment can significantly improve the performance and reliability of the positioning system, is applicable to various complex environments and application scenarios, and provides more reliable positioning services for wireless terminals.

[0150] Embodiment 7, see Figure 1 This embodiment is based on the above embodiment. In step S5, the multi-factor fusion and position positioning presentation are combined with the positioning coordinates output by the positioning coordinate registration, and specifically includes the following steps:

[0151] Position information coding: the final position information after data fusion is encoded so as to effectively compress data and optimize transmission during transmission. The coding adopts a standard coding algorithm or a specific position information coding algorithm.

[0152] Select a communication method, and select an appropriate communication method to transmit location information; the communication methods include wireless network, Bluetooth, infrared, or point-to-point communication or broadcast communication according to the specific scenario;

[0153] Establishing a communication connection: according to the selected communication mode, a communication connection is established between the wireless terminal and the user equipment; including the steps of pairing the devices and establishing the network connection to ensure effective data transmission;

[0154] Data transmission and reception: the encoded location information is transmitted from the wireless terminal to the user equipment through the selected communication method; after the user equipment receives the location information, it decodes and processes it to obtain the final location information;

[0155] Location information display: Display the received final location information on the user's device. The final location information includes marking the location on a map and displaying a detailed text description of the location information so that the user can intuitively understand and use this information;

[0156] Error handling and feedback: If an error or data loss occurs during the transmission process, the corresponding error handling and retransmission mechanism will be implemented to ensure the integrity and accuracy of the location information; at the same time, the transmission status and results will be fed back to the user device so that the user can understand the transmission status in a timely manner.

[0157] Through the above steps, the multi-factor fusion and location positioning presentation steps can effectively transmit the final location information of the wireless terminal to the user equipment, providing the user with accurate and real-time location positioning services.

[0158] Embodiment 8, see Figure 2 , this embodiment is based on the above embodiment, and a wireless terminal positioning system provided by the present invention includes a data acquisition module, a feature extraction and error correction module, an environment perception recognition model establishment module, a positioning coordinate registration module, and a multi-factor fusion and position positioning presentation module;

[0159] The data acquisition module obtains environmental data through the data acquisition device and sends the environmental data to the feature extraction and error correction module;

[0160] The feature extraction and error correction module is used to extract visual features from environmental data. It uses the visual feature extraction algorithm to extract and correct visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on the color space model to obtain preliminary positioning information. It uses pulse spectrum features as the measurement of the tracking algorithm to extract the precise distance information between the terminal and the base station.

[0161] The environment perception and recognition model building module is based on the visual feature data and precise distance information of feature extraction and error correction. By changing the parameters of the node's position, radius, curvature, and rotation angle, it generates adaptive virtual positioning to meet different environmental positioning requirements and generate the node's position coordinates. Then, by constructing the position code and designing the similarity measurement function to quantify the emission frequency, it realizes the perception and recognition of different factors in the environment.

[0162] The positioning coordinate registration module performs coordinate conversion, data temporal and spatial correlation and synchronization, and data fusion on the data of feature extraction and error correction and the data of the environment perception recognition model to obtain accurate positioning coordinates;

[0163] The multi-factor fusion and position positioning presentation module is used to combine the positioning coordinates output by the positioning coordinate registration module, perform multi-factor fusion, and finally realize the real-time positioning of the wireless terminal.

[0164] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0165] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0166] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A wireless terminal positioning method, characterized in that: The method comprises the following steps: Step S1: data collection; Step S2: Feature extraction and error correction, extracting visual features from environmental data, using visual feature extraction algorithm to perform feature extraction and error correction on visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on color space model to obtain preliminary positioning information; by using pulse spectrum features as the measurement of the tracking algorithm, extract the precise distance information between the terminal and the base station; Step S3: Establishment of environmental perception and recognition model. Based on the visual feature data and precise distance information extracted and corrected by features, adaptive virtual positioning is generated by changing the parameters of the node position, radius, curvature, and rotation angle to meet different environmental positioning requirements and generate the node position coordinates. Then, the position code is constructed and the similarity measurement function is designed to quantify the emission frequency to realize the perception and recognition of different factors in the environment. Step S4: Positioning coordinate registration, coordinate conversion, data spatiotemporal association and synchronization, and data fusion of the feature extraction and error correction data and the environment perception recognition model data to obtain accurate positioning coordinates; Step S5: Multi-factor fusion and position positioning presentation, combining the positioning coordinates output by the positioning coordinate registration module, and performing multi-factor fusion to finally achieve real-time positioning of the wireless terminal.

2. A wireless terminal positioning method according to claim 1, characterized in that: In step S2, the visual feature extraction algorithm performs recognition based on the acquired image information, and continuously senses the surrounding local environment information to make preliminary visual feature positioning, which specifically includes the following steps: Step S21: color feature analysis, using a CCD visual sensor to collect the original image, graying the color image collected by the CCD to obtain grayed image information. The specific algorithm formula is as follows: ； Among them, R, G, and B represent the data of the three color channels of red, green, and blue respectively; Step S22: The grayscale image information is smoothed using the neighborhood average method. First, the grayscale image information is convolved with a one-dimensional Gaussian function, and then the convolution result is convolved with a one-dimensional Gaussian function in the same vertical direction. The specific algorithm formula is as follows: ； in, Indicates that the coordinates are The pixel value at i and j are the horizontal and vertical coordinates of the pixel respectively. represents the smoothing parameter; ； in, Indicates that the coordinates are The filtered pixel value at ; is the weight coefficient, expressed in The relationship between the pixel at and the surrounding pixels; m and n are relative to The position offset of Indicates that in the original image, at coordinates The pixel value of and Respectively represent the coordinates of the pixels in the original image; K represents the distance of the window to the left or right from the center pixel in the horizontal direction; L represents the distance of the window up or down from the center pixel in the vertical direction; Step S23: Feature extraction based on the color space model, the specific contents are as follows: ， ， ； in, Indicates the brightness of the color, ranging from 0 to 1; is a ratio value ranging from 0 to 1, representing the ratio between the selected color and the maximum purity of that color; Represents color information, from 0° to 360°, with red, green, and blue separated by 120°; and Not affected by light; In the formula, The specific algorithm formula is as follows: ； in, It is a spatial transformation equation, where R, G, and B represent the data of the three color channels of red, green, and blue respectively.

3. A wireless terminal positioning method according to claim 1, characterized in that: In step S2, by using the pulse spectrum feature as the measurement of the tracking algorithm, the specific algorithm formula of the tracking algorithm is: ， ； in, Indicates the horizontal position of the target; Indicates the target's horizontal speed; Indicates the standard deviation of the error of the target's horizontal position; Indicates the angle of the target in the horizontal direction; Indicates the vertical position of the target; Indicates the target's vertical speed; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's vertical angle; In two-dimensional space, the UWB radar system is orthogonally set up for two-dimensional tracking, where: and The specific algorithm formula is as follows: ， ； in, Indicates the angle of the target in the horizontal direction; Indicates the distance from the target to the sensor; Indicates the standard deviation of the error of the target's horizontal position; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's horizontal speed; Indicates the target's vertical angle; Indicates the standard deviation of the error of the target's vertical upward position; Indicates the target's vertical speed.

4. A wireless terminal positioning method according to claim 1, characterized in that: In step S3, the environment perception recognition model is established, which specifically includes the following contents: Step S31, obtaining landmarks, the specific algorithm formula is as follows: ； in, Indicates at time The above number is The position coordinates of the node, Indicates at time The above number is The radius where the node is located; Indicates at time The above number is The curvature of the nodes; Indicates at time The above number is The rotation angle of the node; Indicates at time The above number is The tangent direction of the node; By changing the parameters of the node's position, radius, curvature, and rotation angle, adaptive virtual positioning can be generated to meet different environmental positioning requirements and generate node position coordinates; Step S32, constructing a location code, the specific algorithm formula is as follows: ； in, Indicates at time The location code of the previous node; Indicates at time From the starting point to the node The path length; Indicates at time The length of the path from the starting point to node 2; Indicates at time The length of the path from the starting point to node N; Indicates at time The path length from the starting point to node N multiplied by the time; By calculating the location code and path length of the node at different times, the location and path length of the positioning node on the path can be determined; Step S33, designing a similarity measurement function to quantify the emission frequency; ； in, Indicates at time The above number is The transmission frequency of the node; Indicates the number The number of nodes related to Representation and numbering The weights associated with the nodes; Representation and distance The relevant weights range from 0 to 1; Indicates at time The above number is The distance of the node; Indicates the number and The distance between nodes; represents the variance of the distance; Representation and angle The relevant weights range from 0 to 1; Indicates at time The above number is The angle of the node; Indicates the number The angle of the node; represents the variance of the angle; In the formula, The specific algorithm formula is as follows: ； in, Representation and numbering The weights associated with the nodes; Represents the similarity metric of the current node, which is used to measure the similarity between nodes; Indicates at time The number of nodes on the The environment perception and recognition model calculates the transmission frequency of each node according to the similarity measurement function between nodes, so as to realize the perception and recognition of different factors in the environment.

5. A wireless terminal positioning method according to claim 1, characterized in that: In step S4, the positioning coordinate registration integrates and calibrates the data of feature extraction and error correction and the data of the environment perception recognition model to obtain accurate positioning coordinates. The specific contents are as follows: Coordinate conversion: the received positioning data comes from different sensors or different coordinate systems, and coordinate conversion is required to convert all data into the same coordinate system for subsequent data processing and analysis; Data spatiotemporal correlation and synchronization: data collected and processed at different times or by different sensors are temporally correlated and synchronized, and the spatiotemporal relationship between data is determined by using timestamp or feature matching methods, spatiotemporal calibration is performed, and real-time positioning is performed; Data fusion: fusing data that has been temporally correlated and synchronized, taking advantage of the strengths of each data source, including accuracy and coverage, to improve the overall performance of wireless terminal positioning; Quality assessment and feedback: perform quality assessment on the registered data, check the accuracy and stability of the positioning results, and feed the assessment results back to the system to optimize the algorithm and parameter settings.

6. A wireless terminal positioning method according to claim 1, characterized in that: In step S1, the data collection specifically involves acquiring environmental data through a data collection device; the data collection device includes a camera, a UWB radar, and a global navigation satellite system, and the environmental data includes image data, UWB radar data, map data, and positioning data.

7. A wireless terminal positioning method according to claim 1, characterized in that: In step S5, the multi-factor fusion and position positioning presentation are combined with the positioning coordinates to output the positioning coordinates, specifically including the following steps: Position information encoding, encoding the final position information after data fusion; Select the communication method according to the specific scenario and transmit the location information; Establishing a communication connection: establishing a communication connection between the wireless terminal and the user equipment according to the selected communication mode; Data transmission and reception, transmitting the encoded location information from the wireless terminal to the user equipment via the selected communication method; After receiving the location information, the user equipment decodes and processes it to obtain the final location information; Position information display, displaying the received final position information on the user's device; Error handling and feedback: If an error or data loss occurs during the transmission process, the corresponding error handling and retransmission mechanism will be implemented to ensure the integrity and accuracy of the location information; at the same time, the transmission status and results will be fed back to the user device so that the user can understand the transmission status in a timely manner.

8. A wireless terminal positioning system, used to implement a wireless terminal positioning method according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, feature extraction and error correction module, environment perception and recognition model building module, positioning coordinate registration module, multi-factor fusion and position positioning presentation module; The data acquisition module acquires environmental data through a data acquisition device and sends the environmental data to a feature extraction and error correction module; The feature extraction and error correction module is used to extract visual features from environmental data, and use the visual feature extraction algorithm to perform feature extraction and error correction on the visual features through color feature analysis, neighborhood average method smoothing, and feature extraction based on the color space model to obtain preliminary positioning information; by using the pulse spectrum feature as the measurement of the tracking algorithm, the precise distance information between the terminal and the base station is extracted; The environment perception recognition model building module generates adaptive virtual positioning based on feature extraction and error correction visual feature data and precise distance information by changing the parameters of the node's position, radius, curvature, and rotation angle to meet different environmental positioning requirements and generate the node's position coordinates; then, by constructing a position code and designing a similarity measurement function to quantify the emission frequency, the perception and recognition of different factors in the environment are realized; The positioning coordinate registration module performs coordinate conversion, data spatiotemporal association and synchronization, and data fusion on the data of feature extraction and error correction and the data of the environment perception recognition model to obtain accurate positioning coordinates; The multi-factor fusion and position positioning presentation module is used to combine the positioning coordinates output by the positioning coordinate registration module to perform multi-factor fusion, and finally realize the real-time positioning of the wireless terminal.

Images