Indoor positioning method based on uwb distance fingerprint and sequence matching

Abstract

The application discloses an indoor positioning method based on UWB distance fingerprint and sequence matching, which comprises the following steps: collecting distance data between each target point and a UWB base station in an indoor space by a UWB base station, and acquiring signal strength of each target point; constructing a UWB distance fingerprint library according to the distance data and the signal strength; collecting real-time UWB data by a portable tag; performing feature matching on the real-time UWB data and fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result; and continuously performing single-point sequencing on the UWB single-point positioning result of each target point to obtain an indoor real-time positioning result. The method can realize real-time positioning in a complex scene, improves positioning accuracy and stability, increases the success rate of fingerprint matching while ensuring matching efficiency, does not need to additionally deploy other equipment for burning, debugging and deployment, has low deployment cost, and improves the indoor positioning speed and efficiency based on the UWB distance fingerprint and sequence matching.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of indoor positioning technology, and in particular to an indoor positioning method based on UWB distance fingerprint and sequence matching. BACKGROUND

[0002] With the vigorous development of Internet of Things devices and technologies, a new era of Internet of Everything has gradually come. People have higher and higher demands for services in indoor scenarios, and the resolution of the indoor location of users also helps to provide targeted intelligent location services. For example, a desk lamp may need to be turned on when sitting at a desk, order placement, goods picking and delivery may be needed when entering a warehouse, and timely warning may be needed when entering a dangerous operation area. Due to the higher complexity and more diverse layout of indoor environments, problems such as signal shielding and propagation loss exist, so that the research in the field of indoor positioning at home and abroad tends to be specific to positioning scenarios, lacking in general applicability. Although some positioning technologies such as WIFI and Bluetooth have the characteristics of low cost and high adaptability, their precision is difficult to meet the needs of indoor positioning. Therefore, how to improve the scene adaptability of the positioning method while ensuring the precision and reducing the positioning cost is the main problem faced by the current indoor positioning field.

[0003] At present, there are many methods that can be used in the field of indoor positioning, which can be generally divided into four aspects of optical, radio frequency, various sensors and multi-source fusion positioning. The application of optical positioning in the field of indoor positioning can be divided into visible light and non-visible light. The visible light is, for example, imaging positioning or using modulated white light emitting diode (LED) signal to solve the corresponding position information. The non-visible light is, for example, infrared positioning technology. The optical positioning method often needs to configure expensive equipment, is difficult to solve the problem of light signal shielding, and involves user privacy. The indoor positioning technology based on radio frequency is the most widely used positioning technology, including Bluetooth, wireless fidelity (WIFI), millimeter wave and ultra wide band (UWB), etc. These technologies mainly use geometric measurement method and position fingerprint method to realize indoor positioning. The performance of the geometric measurement method depends on the accuracy of the received signal propagation model, but it is easily affected by multipath effect and non-line-of-sight propagation. In the field of traditional pedestrian dead reckoning (PDR), research and exploration are often carried out in the three directions of gait detection, step length estimation and heading estimation. The errors generated in the three steps are accumulated, and the traditional PDR is often used under harsh conditions due to the limitation of sensor accuracy. The multi-element fusion positioning technology makes up for the limitations of single positioning method in the indoor positioning system to some extent, and can theoretically make full use of the advantages of each positioning source. However, the introduction of additional equipment will bring additional cost, and the selection and design of the fusion method also greatly affect the positioning accuracy. SUMMARY

[0004] The main purpose of the present application is to provide an indoor positioning method based on UWB distance fingerprint and sequence matching, which aims to solve the technical problems in the prior art that the indoor positioning has high test cost, the test accuracy is easily affected by multipath effect, non-line-of-sight propagation and different fusion design, cannot guarantee the test accuracy, has poor real-time performance and poor positioning stability.

[0005] In a first aspect, the present application provides an indoor positioning method based on UWB distance fingerprint and sequence matching, which comprises the following steps:

[0006] The distance data between each target point in the indoor and the UWB base station is collected by the ultra wide band (UWB) base station, and the signal strength of each target point is obtained. The UWB distance fingerprint library is constructed according to the distance data and the signal strength.

[0007] Collecting real-time UWB data by using a portable tag, performing feature matching on the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, and obtaining a UWB single-point positioning result;

[0008] Serializing the UWB single-point positioning results of each target point in sequence to obtain an indoor real-time positioning result.

[0009] Optionally, the distance data between each target point and the UWB base station in the indoor area is collected by using the UWB base station, and the signal strength of each target point is obtained, and the UWB distance fingerprint library is constructed according to the distance data and the signal strength, comprising:

[0010] Collecting distance data between each target point and the UWB base station of a preset grid point in the indoor area to be positioned by using the UWB base station;

[0011] Obtaining the signal strength of each target point, constructing a horizontal axis according to the distance data, constructing a vertical axis according to the signal strength, drawing a feature point graph according to the horizontal axis and the vertical axis, and constructing the UWB distance fingerprint library according to the feature point graph of each target point.

[0012] Optionally, the real-time UWB data is collected by using a portable tag, the real-time UWB data is matched with the fingerprint library information in the UWB distance fingerprint library, and a UWB single-point positioning result is obtained, comprising:

[0013] Collecting real-time UWB data by using a portable tag, performing feature matching on the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, and obtaining a UWB single-point positioning result;

[0014] Obtaining an indoor plan, establishing a mapping relationship between the fingerprint data and the absolute position of the indoor plan, and storing the mapping relationship to the UWB distance fingerprint library;

[0015] Collecting real-time UWB data by using a portable tag, performing feature matching on the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, and obtaining a UWB single-point positioning result;

[0016] Optionally, the UWB single-point positioning results of each target point are serialized in sequence to obtain an indoor real-time positioning result, comprising:

[0017] Obtaining a fingerprint matching time sequence corresponding to each UWB single-point positioning result of each target point;

[0018] Collecting a corresponding to-be-matched sequence according to the fingerprint matching time sequence, analyzing the change trend of the to-be-matched sequence, and obtaining a candidate sequence;

[0019] traverse all the candidate sequences, calculate the dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence, map the end point of the candidate sequence with the minimum DTW value to the corresponding map coordinate, and take the map coordinates of each target point as the indoor real-time positioning result.

[0020] Optionally, the fingerprint matching time sequence corresponding to each UWB single-point positioning result of each target point is obtained, including:

[0021] Taking any point in the UWB single-point positioning result of each target point as a starting point, a cluster center coordinate of the starting point is recorded;

[0022] According to the cluster center coordinate, other points within a preset range of the starting point are taken as successor nodes;

[0023] According to a preset time interval, the starting point and the successor nodes, a plurality of fingerprint matching time sequences with a length of the preset time interval are generated.

[0024] Optionally, the to-be-matched sequence corresponding to the fingerprint matching time sequence is collected, a variation trend analysis is performed on the to-be-matched sequence, and a candidate sequence is obtained, including:

[0025] According to the fingerprint matching time sequence, a UWB distance sub-sequence within a preset collection time is collected, the UWB distance sub-sequence is taken as a to-be-matched sequence, and a current trend vector of the to-be-matched sequence is calculated and obtained;

[0026] A reference sequence of a to-be-determined positioning path is obtained from the UWB distance fingerprint library, and a reference trend vector of the reference sequence is calculated and obtained;

[0027] The similarity distance between the current trend vector and the reference trend vector is obtained, and a sequence with a similarity distance smaller than a preset similarity distance threshold value is selected from the to-be-matched sequence as a candidate sequence.

[0028] Optionally, the to-be-matched sequence and the candidate sequence are traversed, the dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence is calculated, the end point of the candidate sequence with the minimum DTW value is mapped to the corresponding map coordinate, and the map coordinates of each target point are taken as the indoor real-time positioning result, including:

[0029] All the candidate sequences are traversed, and the dynamic time warping (DTW) values of the to-be-matched sequence and the candidate sequence in distance and signal strength are calculated;

[0030] The minimum DTW value is found from the DTW values, and the candidate sequence corresponding to the minimum DTW value is taken as a target matching sequence;

[0031] Obtaining end point coordinates of the target matching sequence, and mapping the end point coordinates of each target point to corresponding map coordinates as the indoor real-time positioning result.

[0032] In a second aspect, the present application provides an indoor positioning device based on UWB distance fingerprint and sequence matching, which comprises:

[0033] A fingerprint library construction module is configured to collect distance data between each target point and a UWB base station in an indoor environment by a UWB base station, and obtain signal strength of each target point, and construct a UWB distance fingerprint library according to the distance data and the signal strength.

[0034] A feature matching module is configured to collect real-time UWB data by a portable tag, and perform feature matching between the real-time UWB data and fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result.

[0035] A sequence positioning module is configured to sequentially position each UWB single-point positioning result of each target point to obtain an indoor real-time positioning result.

[0036] In a third aspect, the present application provides an indoor positioning device based on UWB distance fingerprint and sequence matching, which comprises a memory, a processor, and an indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory and executable on the processor, wherein the indoor positioning program based on UWB distance fingerprint and sequence matching is configured to implement the steps of the indoor positioning method based on UWB distance fingerprint and sequence matching as described above.

[0037] In a fourth aspect, the present application provides a storage medium having an indoor positioning program based on UWB distance fingerprint and sequence matching stored thereon, wherein the indoor positioning program based on UWB distance fingerprint and sequence matching, when executed by a processor, implements the steps of the indoor positioning method based on UWB distance fingerprint and sequence matching as described above.

[0038] The indoor positioning method based on UWB distance fingerprint and sequence matching provided in the application can realize indoor real-time positioning in a complex scene, has high environmental adaptability, improves positioning precision and positioning stability, increases the success rate of fingerprint matching while ensuring matching efficiency, does not need to additionally deploy other equipment for burning, debugging and testing, has low deployment cost, and improves the indoor positioning speed and efficiency based on UWB distance fingerprint and sequence matching. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 The device structure schematic diagram of the hardware running environment involved in the embodiment scheme of the application;

[0040] Figure 2 The flowchart of the first embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the application;

[0041] Figure 3 The flowchart of the second embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the application;

[0042] Figure 4 The flowchart of the third embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the application;

[0043] Figure 5 The flowchart of the fourth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the application;

[0044] Figure 6 The flowchart of the fifth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the application;

[0045] Figure 7 The flowchart of the sixth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the application;

[0046] Figure 8 The function module diagram of the first embodiment of the indoor positioning device based on UWB distance fingerprint and sequence matching of the application.

[0047] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are merely exemplary and do not limit the application.

[0049] The solution of the embodiment of the application is mainly: the UWB base station collects distance data between each target point in the room and the UWB base station, and acquires the signal strength of each target point, constructs a UWB distance fingerprint library according to the distance data and the signal strength; the portable tag collects real-time UWB data, performs feature matching on the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, and obtains a UWB single-point positioning result; the UWB single-point positioning results of each target point are sequentially serialized, and indoor real-time positioning results are obtained, which can realize indoor real-time positioning in a complex scene, has high environmental adaptability, improves positioning accuracy and positioning stability, increases the success rate of fingerprint matching while ensuring matching efficiency, does not need to additionally deploy other equipment for burning, debugging and testing, has low deployment cost, improves the indoor positioning speed and efficiency based on UWB distance fingerprint and sequence matching, and solves the technical problems in the prior art that indoor positioning has high test cost, test accuracy is easily affected by multipath effect, non-line-of-sight propagation and different fusion designs, cannot guarantee test accuracy, has poor real-time performance and poor positioning stability.

[0050] Reference Figure 1 , Figure 1 The device structure diagram of a hardware running environment involved in the embodiment of the application is shown.

[0051] As shown in Figure 1 , the device can include a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 can include a display screen (Display) and an input unit such as a keyboard (Keyboard). The optional user interface 1003 can also include a standard wired interface and a wireless interface. The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 1005 can be a high-speed RAM memory or a stable memory (Non-Volatile Memory), such as a magnetic disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0052] Those skilled in the art can understand that Figure 1 the device structure shown in the foregoing embodiments does not constitute a limitation on the device, and can include more or fewer components than the diagram, or combine certain components, or different component arrangements.

[0053] As Figure 1 shown, the memory 1005 as a storage medium can include an operating device, a network communication module, a user interface module, and an indoor positioning program based on UWB distance fingerprint and sequence matching.

[0054] The device of the application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and performs the following operations:

[0055] Collect the distance data between each target point in the indoor area and the UWB base station through the ultra-wideband UWB base station, and obtain the signal strength of each target point, and construct a UWB distance fingerprint library according to the distance data and the signal strength;

[0056] Collect real-time UWB data using a portable tag, and perform feature matching on the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result;

[0057] Serializing each UWB single-point positioning result of each target point to obtain an indoor real-time positioning result.

[0058] The device of the application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and performs the following operations:

[0059] Collect the distance data between each target point in the indoor area and the UWB base station through the ultra-wideband UWB base station;

[0060] Obtain the signal strength of each target point, construct a horizontal axis according to the distance data, construct a vertical axis according to the signal strength, draw a feature point graph according to the horizontal axis and the vertical axis, and construct a UWB distance fingerprint library according to the feature point graph of each target point.

[0061] The device of the application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and performs the following operations:

[0062] Collect real-time UWB data using a portable tag, and perform feature matching on the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result;

[0063] Obtain the signal strength of each target point, construct a horizontal axis according to the distance data, construct a vertical axis according to the signal strength, draw a feature point graph according to the horizontal axis and the vertical axis, and construct a UWB distance fingerprint library according to the feature point graph of each target point.

[0064] Collect real-time UWB data using a portable tag, and perform feature matching on the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result;

[0065] The device of the application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0066] Obtain the fingerprint matching time sequence corresponding to each UWB single point positioning result of each target point;

[0067] According to the fingerprint matching time sequence, the corresponding to-be-matched sequence is collected, the to-be-matched sequence is analyzed for variation trend, and a candidate sequence is obtained;

[0068] All candidate sequences are traversed, the dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence is calculated, the endpoint of the candidate sequence with the minimum DTW value is mapped as the corresponding map coordinate, and the map coordinate of each target point is taken as the indoor real-time positioning result.

[0069] The device of the application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0070] Taking any point in each UWB single point positioning result of each target point as a starting point, the cluster center coordinate of the starting point is recorded;

[0071] According to the cluster center coordinate, other points within a preset range of the starting point are taken as successor nodes;

[0072] According to a preset time interval, the starting point and the successor nodes, a plurality of fingerprint matching time sequences with a length of the preset time interval are generated.

[0073] The device of the application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0074] According to the fingerprint matching time sequence, a UWB distance sub-sequence within a preset collection time is collected, the UWB distance sub-sequence is taken as a to-be-matched sequence, and a current trend vector of the to-be-matched sequence is calculated and obtained;

[0075] A reference sequence of a to-be-determined positioning path is obtained from the UWB distance fingerprint library, and a reference trend vector of the reference sequence is calculated and obtained;

[0076] The similarity distance between the current trend vector and the reference trend vector is obtained, and a sequence with a similarity distance smaller than a preset similarity distance threshold value is selected from the to-be-matched sequence as a candidate sequence.

[0077] The device of the present application calls the indoor positioning program based on UWB distance fingerprint and sequence matching stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0078] All candidate sequences are traversed, and dynamic time warping (DTW) values of the to-be-matched sequence and the candidate sequence in distance and signal strength are calculated respectively.

[0079] The minimum DTW value is found from each DTW value, and the candidate sequence corresponding to the minimum DTW value is taken as the target matching sequence.

[0080] The end point coordinates of the target matching sequence are obtained, and the end point coordinates of each target point are mapped to the corresponding map coordinates as the indoor real-time positioning result.

[0081] The above scheme is used in the present embodiment. The distance data between each target point and the UWB base station in the indoor environment is collected by the ultra-wideband (UWB) base station, and the signal strength of each target point is obtained. A UWB distance fingerprint library is constructed according to the distance data and the signal strength. Real-time UWB data is collected by a portable tag, and feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result. The UWB single-point positioning results of each target point are continuously sequenced to obtain an indoor real-time positioning result. The indoor real-time positioning can be realized in a complex scene, which has high environmental adaptability, improves the positioning accuracy and stability, increases the success rate of fingerprint matching while ensuring the matching efficiency, does not require additional deployment of other equipment for burning, debugging, and has low deployment cost, and improves the indoor positioning speed and efficiency based on UWB distance fingerprint and sequence matching.

[0082] Based on the above hardware structure, the present application proposes an indoor positioning method based on UWB distance fingerprint and sequence matching.

[0083] Referring to Figure 2 , Figure 2 The flowchart of the first embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the present application is shown.

[0084] In the first embodiment, the indoor positioning method based on UWB distance fingerprint and sequence matching includes the following steps:

[0085] In step S10, the distance data between each target point and the UWB base station in the indoor environment is collected by the ultra-wideband (UWB) base station, and the signal strength of each target point is obtained. A UWB distance fingerprint library is constructed according to the distance data and the signal strength.

[0086] It should be noted that the distance data between each target test point in the indoor space to be positioned and the UWB base station can be collected by the ultra-wideband UWB base station, and the signal strength of each target point can be obtained, and the UWB distance fingerprint library can be constructed according to the distance data and the signal strength.

[0087] In step S20, real-time UWB data is collected by the portable tag, and feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result.

[0088] It can be understood that the real-time UWB data is collected by the portable tag, and the feature matching method is combined with the fingerprint library information to obtain the UWB single-point positioning result, that is, the feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain the UWB single-point positioning result generated after the feature matching is successful.

[0089] In step S30, the UWB single-point positioning results of each target point are sequentially processed to obtain an indoor real-time positioning result.

[0090] It should be understood that the indoor real-time positioning result can be obtained after the UWB single-point positioning results of each target point are sequentially processed.

[0091] According to the above scheme, the distance data between each target point in the indoor space and the UWB base station is collected by the ultra-wideband UWB base station, and the signal strength of each target point is obtained, and the UWB distance fingerprint library is constructed according to the distance data and the signal strength; the real-time UWB data is collected by the portable tag, and feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result; the UWB single-point positioning results of each target point are sequentially processed to obtain an indoor real-time positioning result, which can realize indoor real-time positioning in a complex scene, has high environmental adaptability, improves positioning accuracy and stability, increases the success rate of fingerprint matching while ensuring matching efficiency, does not need to deploy other devices for burning, debugging and deployment, has low deployment cost, and improves the indoor positioning speed and efficiency based on the UWB distance fingerprint and sequence matching.

[0092] Further, Figure 3 The flowchart of the second embodiment of the indoor positioning method based on the UWB distance fingerprint and sequence matching of the present application is shown in Figure 3 According to the first embodiment, the second embodiment of the indoor positioning method based on the UWB distance fingerprint and sequence matching of the present application is proposed, and in this embodiment, the step S10 specifically includes the following steps:

[0093] Step S11, collecting distance data between each target point of the preset grid point in the indoor positioning area and the UWB base station by the ultra-wideband UWB base station.

[0094] It should be noted that the UWB distance data of the grid point in the required positioning area can be collected by the ultra-wideband UWB base station, that is, the distance data between each target point of the preset grid point in the indoor positioning area and the UWB base station.

[0095] In a specific implementation, UWB system deployment needs to be performed in the positioning area before data collection. The application scenario of the embodiment can generally be UWB positioning in a complex environment under the interference of multi-metal equipment. Based on this, the following conditions should be followed when selecting the position of the UWB base station: the installation position of the base station should be at a certain distance from the surrounding metal devices, about 1 m or more; the base stations should be deployed dispersedly to ensure that there are three or more base stations deployed within a range of 15 m with each coordinate point as the center. If this condition cannot be guaranteed, the deployment of base stations in places with dense metal equipment should be prioritized, and the base stations can be deployed sparsely in open environments; the height of the deployed base stations should be as consistent as possible to reduce the positioning error caused by the height difference; similarly, the base stations should be deployed on a straight line as much as possible to improve the positioning accuracy of the base stations; the base stations should be deployed as much as possible to avoid being blocked by objects; after the deployment points are determined and tested correctly, the base stations should be installed at positions near the deployment points that meet the installation conditions and allow installation; the base station ID should be confirmed to match the deployment point before the base station is installed, and it should be detected whether the base station can be started normally.

[0096] Step S12, obtaining the signal strength of each target point, constructing a horizontal axis according to the distance data, constructing a vertical axis according to the signal strength, drawing a feature point graph according to the horizontal axis and the vertical axis, and constructing a UWB distance fingerprint library according to the feature point graph of each target point.

[0097] It can be understood that after obtaining the signal strength of each target point, a horizontal axis can be constructed according to the distance data, a vertical axis can be constructed according to the signal strength, a feature point graph can be drawn according to the horizontal axis and the vertical axis, and a UWB distance fingerprint library can be constructed according to the feature point graph of each target point.

[0098] In a specific implementation, the grid of the positioning area is divided, and the absolute position is defined as (x, y), where x, y = 0, 1, 2, …; 200 frames of data are collected at a sampling frequency of 10 Hz on (x n , y m ), and the data format is as follows:

[0099] [S i ,D j ,T j ]

[0100] Wherein S represents a base station, i is a base station number, D is a distance measurement value from the base station to a target position, T is a UWB measurement signal strength, j represents a data frame serial number, j=0,1,2, …, 199.

[0101] A point graph is drawn with D as the horizontal axis and T as the vertical axis, that is, a feature point graph of the base station S i At (x n ,y m ).

[0102] The above process is repeated, and a feature point graph at all (x n ,y m ) of all base stations S i can be obtained.

[0103] The embodiment can quickly construct a UWB fingerprint library, realize indoor real-time positioning in a complex scene, has high environmental adaptability, and improves positioning accuracy and positioning stability.

[0104] Further, Figure 4 The flowchart of the third embodiment of the indoor positioning method based on UWB distance fingerprints and sequence matching of the present application is shown in FIG. 6. Figure 4 The third embodiment of the indoor positioning method based on UWB distance fingerprints and sequence matching of the present application is proposed based on the first embodiment.

[0105] Step S21: Collecting real-time UWB data using a portable tag, clustering and optimizing dimension reduction of the real-time UWB data, and obtaining fingerprint data after dimension reduction.

[0106] It should be noted that the real-time UWB data can be collected using a portable tag, and the collected real-time UWB data can be clustered and optimized for dimension reduction to obtain fingerprint data after dimension reduction.

[0107] In a specific implementation, due to the influence of multipath effect and non-line-of-sight reach, there can be more than one cluster center for a feature point graph, that is, the UWB ranging signal collected by the tag can come from multiple paths, thereby obtaining different distance values D. In order to utilize as much multipath information as possible, when performing K-Means clustering, we will also retain multiple cluster centers. The optimized feature graph can be represented as follows:

[0108] {Si (x n ,y m ),[(D1,T1)(D2,T2)…]}

[0109] wherein, [(D1, T1) (D2, T2) …] is the coordinate of the cluster center.

[0110] Step S22, obtaining an indoor plan, establishing a mapping relationship between the fingerprint data and the absolute position of the indoor plan, and storing the mapping relationship to the UWB distance fingerprint library.

[0111] It can be understood that after obtaining the indoor plan, the fingerprint library and the absolute position of the indoor plan can be mapped, that is, the mapping relationship between the fingerprint data and the absolute position of the indoor plan is established, and the mapping relationship is stored to the UWB distance fingerprint library.

[0112] Step S23, performing feature matching between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library, and obtaining a UWB single-point positioning result.

[0113] It should be understood that after performing feature matching between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library, a UWB single-point positioning result after successful feature matching can be obtained.

[0114] The above scheme is used to obtain the fingerprint data after dimensionality reduction by using the portable tag to collect real-time UWB data, performing clustering optimization and dimensionality reduction on the real-time UWB data, obtaining an indoor plan, establishing a mapping relationship between the fingerprint data and the absolute position of the indoor plan, storing the mapping relationship to the UWB distance fingerprint library, performing feature matching between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library, and obtaining a UWB single-point positioning result. The UWB single-point positioning result can be quickly obtained, indoor real-time positioning can be realized in a complex scene, the environmental adaptability is high, the positioning accuracy and stability are improved, the matching efficiency is ensured, and the success rate of fingerprint matching is increased.

[0115] Further, Figure 5 The flowchart of the fourth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the present application is shown in FIG. 4. Figure 5 The fourth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the present application is proposed based on the first embodiment. In this embodiment, the step S30 specifically includes the following steps:

[0116] Step S31, obtaining a fingerprint matching time sequence corresponding to each UWB single-point positioning result of each target point.

[0117] It should be noted that the corresponding UWB distance fingerprint matching time sequence can be obtained from each UWB single point positioning result of each target point.

[0118] Step S32, according to the fingerprint matching time sequence, a corresponding to-be-matched sequence is collected, and a change trend analysis is performed on the to-be-matched sequence to obtain a candidate sequence.

[0119] It can be understood that the corresponding to-be-matched sequence can be collected through the fingerprint matching time sequence, and then the change trend analysis is performed on the to-be-matched sequence to obtain a candidate sequence.

[0120] Step S33, all candidate sequences are traversed, a dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence is calculated, an endpoint of a candidate sequence with a minimum DTW value is mapped as a corresponding map coordinate, and the map coordinates of each target point are taken as indoor real-time positioning results.

[0121] It should be understood that all candidate sequences are traversed, a dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence is calculated, an endpoint of a candidate sequence with a minimum DTW value is mapped as a corresponding map coordinate, and the map coordinates of each target point are taken as indoor real-time positioning results.

[0122] Further, the step S33 specifically includes the following steps:

[0123] All candidate sequences are traversed, and dynamic time warping (DTW) values of the to-be-matched sequence and the candidate sequence in distance and signal strength are calculated, respectively.

[0124] A minimum DTW value is found from each DTW value, and a candidate sequence corresponding to the minimum DTW value is taken as a target matching sequence.

[0125] An endpoint coordinate of the target matching sequence is obtained, and the endpoint coordinates of each target point are mapped as corresponding map coordinates as indoor real-time positioning results.

[0126] It can be understood that all candidate matching sequences in step 3 are traversed, and a dynamic time warping (DTW) distance between a to-be-matched UWB distance subsequence X and a candidate matching sequence Y in two dimensions of D and T is calculated:

[0127]

[0128] A candidate matching sequence with the highest similarity to the to-be-matched UWB distance subsequence, that is, with the minimum dynamic time warping distance, is found, and an endpoint coordinate of the sequence is mapped as a corresponding positioning result to complete positioning.

[0129] D dtw(X, Y) is the DTW value between the UWB distance sub-sequence X to be matched and the candidate matching sequence Y in the D, T two dimensions respectively, d(x1, y1) is the similarity distance of the trend vector x1 and y1, Rest(X) is the sequence of X except x1, Rest(Y) is the sequence of Y except y1, and d(x, y) = ||x-y|| is the calculation of the similarity distance of x and y.

[0130] The embodiment obtains the fingerprint matching time sequence corresponding to each UWB single-point positioning result of each target point, collects the corresponding to-be-matched sequence according to the fingerprint matching time sequence, analyzes the change trend of the to-be-matched sequence, obtains a candidate sequence, traverses all the candidate sequences, calculates the dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence, maps the endpoint of the candidate sequence with the minimum DTW value to the corresponding map coordinate, and takes the map coordinates of each target point as the indoor real-time positioning result, thereby realizing indoor real-time positioning in a complex scene, having high environmental adaptability, improving positioning accuracy and stability, increasing the success rate of fingerprint matching while ensuring matching efficiency, not needing to additionally deploy other equipment for burning, debugging, and deployment, having low deployment cost, and improving the speed and efficiency of indoor positioning based on UWB distance fingerprint and sequence matching.

[0131] Further, Figure 6 The flowchart of the fifth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the present application is shown in FIG. 5. Figure 6 The fifth embodiment of the indoor positioning method based on UWB distance fingerprint and sequence matching of the present application is proposed based on the fourth embodiment, and in the embodiment, the step S31 specifically includes the following steps.

[0132] In the step S311, any point in each UWB single-point positioning result of each target point is taken as a starting point, and the cluster center coordinates of the starting point are recorded.

[0133] It should be noted that in the sequence generation stage, any point in each UWB single-point positioning result of each target point can be taken as a starting point, and the cluster center coordinates of the starting point are recorded.

[0134] In the step S312, other points within a preset range of the starting point are taken as successor nodes according to the cluster center coordinates.

[0135] It can be understood that according to the cluster center coordinates, other points within a preset range of the starting point can be taken as successor nodes.

[0136] In a specific implementation, taking the 9 points in the starting nine-square grid as an example, any point in the positioning area can be taken as a starting point, and the 9 points in the starting nine-square grid can be taken as successor nodes (including the starting point).

[0137] Step S313, generating a fingerprint matching time sequence with several segments of a preset time interval according to the preset time interval, the starting point and the subsequent node.

[0138] It should be understood that a fingerprint matching time sequence with several segments of a preset time interval can be generated by the preset time interval, the starting point and the subsequent node.

[0139] In a specific implementation, taking the 9 points in the nine-square grid as the starting point and the preset time interval as 2s as an example, a UWB distance fingerprint matching time sequence with several segments of 2s can be generated, and any point (x n ,y m ) in the positioning area is taken as the starting point to record the cluster center coordinates at the point. If there are multiple cluster centers, all of them are recorded, (x n ,y m ), (x n-1 ,y m ), (x n+1 ,y m ), (x n ,y m-1 ), (x n ,y m+1 ), (x n-1 ,y m-1 ), (x n-1 ,y m+1 ), (x n+1 ,y m-1 ), (x n+1 ,y m+1 ) nine points are taken as the subsequent nodes; the UWB distance fingerprint matching time sequence of 2s under the sampling rate of 10Hz is about 20 frames, that is, 20 layers of loops are needed to generate the corresponding matching sequence.

[0140] Due to the complexity of the indoor environment, there are obstacles that cannot be crossed and other factors, and the actual number of subsequent nodes is much smaller than 9. In order to facilitate pruning, the number of possible subsequent nodes of each starting point needs to be constrained, so as to reduce the traversal time.

[0141] The finally generated UWB distance fingerprint sequence can be expressed as:

[0142]

[0143] Wherein, D is distance data, T is signal strength, D, T subscript represents the number of cluster centers, that is, the number of the cluster center, and superscript represents the position coordinates of D, T.

[0144] The embodiment records the cluster center coordinates of the starting point by taking any point in the UWB single-point positioning result of each target point as the starting point, takes other points within a preset range of the starting point as the successor node according to the cluster center coordinates, and generates several fingerprint matching time sequences with a preset time interval according to the starting point and the successor node, so that the memory fingerprint matching time sequence can be accurately obtained, indoor real-time positioning can be realized in a complex scene, environmental adaptability is high, and positioning accuracy and positioning stability are improved.

[0145] Further, Figure 7 A flowchart of a sixth embodiment of the indoor positioning method based on UWB distance fingerprints and sequence matching of the application is shown in Figure 7 The sixth embodiment of the indoor positioning method based on UWB distance fingerprints and sequence matching of the application is proposed based on the fourth embodiment, and in the embodiment, the step S32 specifically includes the following steps.

[0146] In step S321, a UWB distance sub-sequence within a preset collection time is collected according to the fingerprint matching time sequence, the UWB distance sub-sequence is taken as a to-be-matched sequence, and a current trend vector of the to-be-matched sequence is calculated and obtained.

[0147] It should be noted that the UWB distance sub-sequence within the preset collection time can be collected according to the fingerprint matching time sequence, and then the UWB distance sub-sequence is taken as the to-be-matched sequence, and the current trend vector of the to-be-matched sequence is calculated and obtained.

[0148] In a specific implementation, a to-be-matched UWB distance sub-sequence with a length of about 2s can be collected in the positioning stage, the change trend (increasing or decreasing trend, maximum or minimum value, etc.) of the sub-sequence is judged, and a candidate sequence is screened in the UWB distance fingerprint library according to the trend.

[0149] In step S322, a reference sequence of a to-be-determined positioning path is obtained from the UWB distance fingerprint library, and a reference trend vector of the reference sequence is calculated and obtained.

[0150] It can be understood that the reference sequence of the to-be-determined positioning path can be obtained from the UWB distance fingerprint library, and the reference trend vector of the reference sequence is calculated and obtained accordingly.

[0151] In a specific implementation, a to-be-matched UWB distance sub-sequence with a length of 2s

[0152]

[0153] The trend vector a of the to-be-matched UWB distance sub-sequence is calculated as follows:

[0154] a = [(x1, y1, AD1, AT1), (x2, y2, AD2, AT2),..., (xN, yN, ADN, ATN)] 19 19 19 19

[0155] wherein

[0156] wherein, D is distance data, T is signal strength, D, T subscript indicates the number of clustering centers, that is, the number of the clustering center, superscript indicates the position coordinate where D, T is located, AD i is the horizontal axis vector, that is, the distance data vector, AT i is the vertical axis vector, that is, the signal strength vector.

[0157] Step S323, obtaining the similarity distance between the current trend vector and the reference trend vector, and screening the sequence with the similarity distance less than the preset similarity distance threshold from the to-be-matched sequence as the candidate sequence.

[0158] It should be understood that the similarity distance between the current trend vector and the reference trend vector is obtained, and the sequence with the similarity distance less than the preset similarity distance threshold is screened from the to-be-matched sequence as the candidate sequence.

[0159] In a specific implementation, the reference sequence of the corresponding to-be-positioned path is taken out from the UWB distance fingerprint sequence library, and the trend vector A of the reference sequence is also calculated. Based on the trend vectors of the to-be-matched UWB distance subsequence and the reference sequence, the similarity distance d(a, A) between the corresponding reference sequence trend vector and the to-be-matched sequence trend vector in the window is calculated by using the sliding window technology, and the candidate matching sequence with the similarity distance within the preset similarity distance threshold ω is screened.

[0160] The embodiment obtains the UWB distance subsequence in the preset collection time according to the fingerprint matching time sequence, takes the UWB distance subsequence as the to-be-matched sequence, and calculates the current trend vector of the to-be-matched sequence; the reference sequence of the to-be-positioned path is obtained from the UWB distance fingerprint library, and the reference trend vector of the reference sequence is calculated; the similarity distance between the current trend vector and the reference trend vector is obtained, and the sequence with the similarity distance less than the preset similarity distance threshold is screened from the to-be-matched sequence as the candidate sequence, so that the candidate matching sequence can be accurately found, indoor real-time positioning in a complex scene is realized, high environmental adaptability is achieved, and the positioning accuracy and the positioning stability are improved.

[0161] Correspondingly, the application further provides an indoor positioning device based on UWB distance fingerprints and sequence matching.​​​​

[0162] Referring to Figure 8 , Figure 8 Figure 1 is a functional module diagram of a first embodiment of an indoor positioning device based on UWB distance fingerprint and sequence matching of the present application.

[0163] In the first embodiment of the indoor positioning device based on UWB distance fingerprint and sequence matching of the present application, the indoor positioning device based on UWB distance fingerprint and sequence matching comprises:

[0164] A fingerprint library construction module 10 is configured to collect distance data between each target point in an indoor area and a UWB base station by a UWB base station, and obtain signal strengths of each target point, and construct a UWB distance fingerprint library according to the distance data and the signal strengths.

[0165] A feature matching module 20 is configured to collect real-time UWB data by a portable tag, and perform feature matching between the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, and obtain a UWB single-point positioning result.

[0166] A sequenced positioning module 30 is configured to sequentially sequence each UWB single-point positioning result of each target point, and obtain an indoor real-time positioning result.

[0167] The fingerprint library construction module 10 is further configured to collect distance data between each target point of a preset grid point in an indoor area to be positioned and a UWB base station by a UWB base station, obtain signal strengths of each target point, construct a horizontal axis according to the distance data, construct a vertical axis according to the signal strengths, draw a feature point graph according to the horizontal axis and the vertical axis, and construct a UWB distance fingerprint library according to a feature point graph of each target point.

[0168] The feature matching module 20 is further configured to collect real-time UWB data by a portable tag, perform clustering optimization and dimension reduction on the real-time UWB data, obtain fingerprint data after dimension reduction, obtain an indoor plan, establish a mapping relationship between the fingerprint data and an absolute position of the indoor plan, store the mapping relationship to the UWB distance fingerprint library, perform feature matching between the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, and obtain a UWB single-point positioning result.

[0169] The serialization positioning module 30 is further configured to acquire a fingerprint matching time sequence corresponding to each UWB single-point positioning result of each target point; collect a to-be-matched sequence corresponding to the fingerprint matching time sequence, analyze a variation trend of the to-be-matched sequence, and obtain a candidate sequence; traverse all the candidate sequences, calculate a dynamic time warping (DTW) value between the to-be-matched sequence and each candidate sequence, map an end point of a candidate sequence with the minimum DTW value to a corresponding map coordinate, and take the map coordinate of each target point as an indoor real-time positioning result.

[0170] The serialization positioning module 30 is further configured to take any point in each UWB single-point positioning result of each target point as a starting point, record a clustering center coordinate of the starting point, take other points within a preset range of the starting point as a successor node according to the clustering center coordinate, and generate a plurality of fingerprint matching time sequences with a preset time interval according to the starting point and the successor node.

[0171] The serialization positioning module 30 is further configured to collect a UWB distance sub-sequence within a preset collection time according to the fingerprint matching time sequence, take the UWB distance sub-sequence as a to-be-matched sequence, calculate a current trend vector of the to-be-matched sequence, acquire a reference sequence of a to-be-determined positioning path from the UWB distance fingerprint library, calculate a reference trend vector of the reference sequence, acquire a similarity distance between the current trend vector and the reference trend vector, and filter a sequence with a similarity distance less than a preset similarity distance threshold from the to-be-matched sequence as a candidate sequence.

[0172] The serialization positioning module 30 is further configured to traverse all the candidate sequences, calculate dynamic time warping (DTW) values of the to-be-matched sequence and each candidate sequence in terms of distance and signal strength respectively, find a minimum DTW value from the DTW values, take a candidate sequence corresponding to the minimum DTW value as a target matching sequence, acquire an end point coordinate of the target matching sequence, and map an end point coordinate of each target point to a corresponding map coordinate as an indoor real-time positioning result.

[0173] The steps implemented by each functional module of the indoor positioning device based on UWB distance fingerprints and sequence matching can refer to each embodiment of the indoor positioning method based on UWB distance fingerprints and sequence matching.

[0174] In addition, an embodiment of the present application further provides a storage medium having an indoor positioning program based on UWB distance fingerprints and sequence matching stored thereon, and the indoor positioning program based on UWB distance fingerprints and sequence matching, when executed by a processor, implements the following operations:

[0175] The distance data between each target point and the UWB base station in the indoor area is collected by the ultra-wideband (UWB) base station, and the signal strength of each target point is obtained, and a UWB distance fingerprint library is constructed according to the distance data and the signal strength.

[0176] Real-time UWB data is collected by a portable tag, and feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result.

[0177] The UWB single-point positioning results of each target point are sequentially processed to obtain an indoor real-time positioning result.

[0178] Further, when the indoor positioning program based on UWB distance fingerprint and sequence matching is executed by the processor, the following operations are also implemented:

[0179] The distance data between each target point and the UWB base station in the indoor area is collected by the ultra-wideband (UWB) base station, and the signal strength of each target point is obtained, and a UWB distance fingerprint library is constructed according to the distance data and the signal strength.

[0180] The signal strength of each target point is obtained, the horizontal axis is constructed according to the distance data, the vertical axis is constructed according to the signal strength, the feature point graph is drawn according to the horizontal axis and the vertical axis, and the UWB distance fingerprint library is constructed according to the feature point graph of each target point.

[0181] Further, when the indoor positioning program based on UWB distance fingerprint and sequence matching is executed by the processor, the following operations are also implemented:

[0182] Real-time UWB data is collected by a portable tag, and feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result.

[0183] An indoor plan is obtained, a mapping relationship between the fingerprint data and the absolute position of the indoor plan is established, and the mapping relationship is stored in the UWB distance fingerprint library.

[0184] Real-time UWB data is collected by a portable tag, and feature matching is performed between the real-time UWB data and the fingerprint library information in the UWB distance fingerprint library to obtain a UWB single-point positioning result.

[0185] Further, when the indoor positioning program based on UWB distance fingerprint and sequence matching is executed by the processor, the following operations are also implemented:

[0186] The fingerprint matching time sequence corresponding to each UWB single-point positioning result of each target point is obtained.

[0187] According to the fingerprint matching time sequence, a corresponding to-be-matched sequence is collected, and change trend analysis is performed on the to-be-matched sequence to obtain a candidate sequence.

[0188] Traverse all candidate sequences, calculate the dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence, map the end point of the candidate sequence with the minimum DTW value to the corresponding map coordinate, and take the map coordinate of each target point as the indoor real-time positioning result.

[0189] Further, the indoor positioning procedure based on UWB distance fingerprint and sequence matching further implements the following operations when executed by the processor:

[0190] Taking any point in the UWB single-point positioning result of each target point as a starting point, record the cluster center coordinate of the starting point;

[0191] According to the cluster center coordinate, take other points within a preset range of the starting point as a successor node;

[0192] According to a preset time interval, the starting point and the successor node, generate a plurality of fingerprint matching time sequences with a preset time interval.

[0193] Further, the indoor positioning procedure based on UWB distance fingerprint and sequence matching further implements the following operations when executed by the processor:

[0194] According to the fingerprint matching time sequence, collect a UWB distance sub-sequence within a preset collection time, take the UWB distance sub-sequence as a to-be-matched sequence, and calculate a current trend vector of the to-be-matched sequence;

[0195] Obtain a reference sequence of a to-be-determined positioning path from the UWB distance fingerprint library, and calculate a reference trend vector of the reference sequence;

[0196] Obtain a similarity distance between the current trend vector and the reference trend vector, and filter a sequence with a similarity distance less than a preset similarity distance threshold from the to-be-matched sequence as a candidate sequence.

[0197] Further, the indoor positioning procedure based on UWB distance fingerprint and sequence matching further implements the following operations when executed by the processor:

[0198] Traverse all candidate sequences, calculate the dynamic time warping (DTW) value between the to-be-matched sequence and the candidate sequence, map the end point of the candidate sequence with the minimum DTW value to the corresponding map coordinate, and take the map coordinate of each target point as the indoor real-time positioning result.

[0199] Find a minimum DTW value from each DTW value, and take a candidate sequence corresponding to the minimum DTW value as a target matching sequence;

[0200] Obtain the end point coordinate of the target matching sequence, and map the end point coordinate of each target point to the corresponding map coordinate as the indoor real-time positioning result.

[0201] The embodiment acquires distance data between each target point and the UWB base station in the room and signal strength of each target point through the UWB base station, constructs a UWB distance fingerprint library according to the distance data and the signal strength, collects real-time UWB data through a portable tag, performs feature matching on the real-time UWB data and fingerprint library information in the UWB distance fingerprint library, obtains a UWB single-point positioning result, serializes each UWB single-point positioning result of each target point, and obtains indoor real-time positioning results, so that indoor real-time positioning can be realized in a complex scene, environmental adaptability is improved, positioning accuracy and stability are improved, the matching efficiency is ensured, the success rate of fingerprint matching is improved, other devices do not need to be additionally deployed for burning, debugging and testing, deployment cost is low, and indoor positioning speed and efficiency based on UWB distance fingerprint and sequence matching are improved.

[0202] It should be noted that in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0203] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0204] The above is only the preferred embodiment of the application, and does not limit the patent scope of the application, and any equivalent structure or equivalent process transformation according to the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the application.

Claims

1. An indoor positioning method based on UWB distance fingerprinting and sequence matching, characterized in that, The indoor positioning method based on UWB distance fingerprinting and sequence matching includes: Distance data between indoor target points and UWB base stations are collected using ultra-wideband (UWB) base stations, and the signal strength of each target point is obtained. A UWB distance fingerprint database is constructed based on the distance data and the signal strength. Real-time UWB data is collected using a portable tag. The real-time UWB data is then matched with fingerprint information in the UWB distance fingerprint database to obtain UWB single-point positioning results. The UWB single-point positioning results of each target point are continuously serialized to obtain the indoor real-time positioning results.

2. The indoor positioning method based on UWB distance fingerprinting and sequence matching as described in claim 1, characterized in that, The process of collecting distance data between indoor target points and UWB base stations via ultra-wideband (UWB) base stations, obtaining the signal strength of each target point, and constructing a UWB distance fingerprint database based on the distance data and the signal strength includes: Distance data between each target point and the UWB base station in the indoor positioning area is collected using an ultra-wideband (UWB) base station. The signal strength of each target point is obtained, a horizontal axis is constructed based on the distance data, a vertical axis is constructed based on the signal strength, a feature point map is drawn based on the horizontal axis and the vertical axis, and a UWB distance fingerprint database is constructed based on the feature point map of each target point.

3. The indoor positioning method based on UWB distance fingerprinting and sequence matching as described in claim 1, characterized in that, The process of collecting real-time UWB data using a portable tag, performing feature matching between the real-time UWB data and fingerprint database information in the UWB distance fingerprint database to obtain UWB single-point localization results includes: Real-time UWB data is collected using portable tags, and the real-time UWB data is clustered, optimized, and dimensionality reduced to obtain dimensionality-reduced fingerprint data. Obtain an indoor floor plan, establish a mapping relationship between the fingerprint data and the absolute position of the indoor floor plan, and store the mapping relationship in the UWB distance fingerprint database; The real-time UWB data is matched with the fingerprint database information in the UWB distance fingerprint database to obtain the UWB single-point positioning result.

4. The indoor positioning method based on UWB distance fingerprinting and sequence matching as described in claim 1, characterized in that, The step of continuously serializing the UWB single-point positioning results of each target point to obtain indoor real-time positioning results includes: Obtain the fingerprint matching time series corresponding to each UWB single-point localization result of each target point; Based on the fingerprint matching time series, the corresponding sequence to be matched is collected, and the trend analysis of the sequence to be matched is performed to obtain candidate sequences; Traverse all candidate sequences, calculate the Dynamic Time Warping (DTW) value between the sequence to be matched and the candidate sequences, map the endpoint of the candidate sequence with the smallest DTW value to the corresponding map coordinates, and use the map coordinates of each target point as the indoor real-time positioning result.

5. The indoor positioning method based on UWB distance fingerprinting and sequence matching as described in claim 4, characterized in that, The step of obtaining the fingerprint matching time series corresponding to each UWB single-point localization result of each target point includes: Taking any point from each UWB single-point positioning result of each target point as the starting point, record the cluster center coordinates of the starting point; Based on the coordinates of the cluster center, other points within the preset range of the starting point are taken as successor nodes; Several fingerprint matching time sequences with a preset time interval are generated based on the preset time interval, the starting point, and the successor node.

6. The indoor positioning method based on UWB distance fingerprinting and sequence matching as described in claim 4, characterized in that, The step of collecting the corresponding sequence to be matched based on the fingerprint matching time series, performing trend analysis on the sequence to be matched, and obtaining candidate sequences includes: According to the fingerprint matching time series, UWB distance subsequences within a preset collection time are collected, the UWB distance subsequences are used as the sequences to be matched, and the current trend vector of the sequences to be matched is calculated. Obtain a reference sequence of the undetermined positioning path from the UWB distance fingerprint database, and calculate the reference trend vector of the reference sequence; Obtain the similarity distance between the current trend vector and the reference trend vector, and select sequences from the sequences to be matched whose similarity distance is less than a preset similarity distance threshold as candidate sequences.

7. The indoor positioning method based on UWB distance fingerprinting and sequence matching as described in claim 4, characterized in that, The process involves traversing all candidate sequences, calculating the Dynamic Time Warped (DTW) value between the sequence to be matched and the candidate sequences, mapping the endpoint of the candidate sequence with the smallest DTW value to its corresponding map coordinates, and using the map coordinates of each target point as the indoor real-time positioning result, including: Traverse all candidate sequences and calculate the dynamic time warp (DTW) values ​​of the sequence to be matched and the candidate sequences in terms of distance and signal strength, respectively. Find the minimum DTW value among all DTW values, and use the candidate sequence corresponding to the minimum DTW value as the target matching sequence; Obtain the endpoint coordinates of the target matching sequence, and map the endpoint coordinates of each target point to the corresponding map coordinates as the indoor real-time positioning result.

8. An indoor positioning device based on UWB distance fingerprinting and sequence matching, characterized in that, The indoor positioning device based on UWB distance fingerprinting and sequence matching includes: The fingerprint database construction module is used to collect distance data between indoor target points and UWB base stations through ultra-wideband (UWB) base stations, obtain the signal strength of each target point, and construct a UWB distance fingerprint database based on the distance data and the signal strength. The feature matching module is used to collect real-time UWB data using a portable tag, and perform feature matching between the real-time UWB data and the fingerprint database information in the UWB distance fingerprint database to obtain UWB single-point positioning results. The serialization positioning module is used to continuously serialize the UWB single-point positioning results of each target point to obtain real-time indoor positioning results.

9. An indoor positioning device based on UWB distance fingerprinting and sequence matching, characterized in that, The indoor positioning device based on UWB distance fingerprinting and sequence matching includes: a memory, a processor, and an indoor positioning program based on UWB distance fingerprinting and sequence matching stored in the memory and executable on the processor, wherein the indoor positioning program based on UWB distance fingerprinting and sequence matching is configured to implement the steps of the indoor positioning method based on UWB distance fingerprinting and sequence matching as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores an indoor positioning program based on UWB distance fingerprinting and sequence matching. When the indoor positioning program based on UWB distance fingerprinting and sequence matching is executed by a processor, it implements the steps of the indoor positioning method based on UWB distance fingerprinting and sequence matching as described in any one of claims 1 to 7.

Images