Indoor positioning system based on multi-source equipment data acquisition

Abstract

The invention relates to the technical field of indoor positioning, and discloses an indoor positioning system based on multi-source equipment data acquisition, which is high in precision and good in stability, and comprises a data sampling module, a feature extraction module and a data fusion processing module, and is characterized in that the data sampling module is used for carrying out grid point division and sampling on three-dimensional space data; the feature extraction module performs algorithm calculation and target position processing on the extracted data of the target object; and the data fusion processing module is used for extracting the current position and the motion track of the target object and correspondingly generating a target interval so as to position the target object.

Description

Technical Field

[0001] The present invention relates to the field of indoor positioning technology, and more particularly to an indoor positioning system based on multi-source device data collection. Background Art

[0002] With the development of technologies such as the Internet of Things and big data, indoor positioning technology has become a research hotspot. Existing indoor positioning technologies primarily include those based on infrared, Bluetooth, WiFi, and ultra-wideband (UWB). However, positioning systems based on a single technology often suffer from issues such as low accuracy, poor stability, and significant susceptibility to environmental interference. For example, WiFi-based positioning technology, while low-cost and offering wide coverage, suffers from limited accuracy. Bluetooth positioning also has certain limitations in accuracy and coverage.

[0003] Therefore, how to achieve high-precision positioning using data from multiple devices to solve the problems of low accuracy and poor stability of positioning systems in the existing technology. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that the above-mentioned single-technology positioning systems in the prior art often have the defects of low accuracy, poor stability, and large environmental interference. An indoor positioning system based on multi-source device data collection with high accuracy and good stability is provided.

[0005] The technical solution adopted by the present invention to solve the technical problem is to construct an indoor positioning system based on multi-source device data collection, which has:

[0006] A data sampling module, which is used to perform grid point division and sampling on three-dimensional spatial data;

[0007] A feature extraction module, which is signal-connected to the data sampling module and performs algorithm calculation and target position processing on the extracted data of the target object;

[0008] The data fusion processing module is connected to the feature extraction module by signal, and is used to extract the current position and motion trajectory of the target object and generate a target interval accordingly to locate the target object.

[0009] In some implementations, in the three-dimensional space, a circle with the target object as a radius is used as a trajectory line to obtain the current circular trajectory of the target object.

[0010] In some embodiments, when the target objects are at the same radius, at a certain moment, the received phase difference is 0; when the target objects are at positions with inconsistent radii, at a certain moment, the received phase has a difference.

[0011] In some embodiments, the data sampling module includes at least Wi-Fi, Bluetooth, Zigbee or a camera.

[0012] The feature extraction module may collect data via the Wi-Fi, the Bluetooth, the Zigbee or the camera to match the position interval of the target object.

[0013] In some embodiments, the feature extraction module is used to capture images in real time and pair them with image key points of the target interval where the target object is located.

[0014] In some implementations, after the matching interval is determined, the angle of arrival of the signal of the target object is measured by multiple antenna groups to calculate the position of the target object.

[0015] In some embodiments, the two groups of antennas can measure at least two or more arrival angles, and the two arrival angles can determine the first position of the current target object. The target object is received on the current circle trajectory, and the current position coordinates of the target object can be confirmed based on the orthogonal antenna arrays.

[0016] In some embodiments, the data fusion processing module may use the coordinates of the sampling point corresponding to the image with the highest similarity among the first N images with the closest distance difference values as the current coordinates of the target object.

[0017] The indoor positioning system based on multi-source device data acquisition described in the present invention includes a data sampling module, a feature extraction module, and a data fusion processing module. The data sampling module is used to grid-point and sample three-dimensional spatial data; the feature extraction module performs algorithm calculation and target position processing on the extracted data of the target object; and the data fusion processing module is used to extract the current position and motion trajectory of the target object and generate a corresponding target interval to locate the target object. Compared with the existing technology, the indoor positioning system uploads the collected indoor environment data to the data fusion processing server module in real time, and then the data fusion processing module pre-processes the collected multi-source data, extracts effective features, and uses an algorithm that integrates multiple calculation methods such as signal strength-based algorithms, time difference algorithms, and multilateral positioning methods to perform target positioning, thereby achieving high-precision indoor positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0019] Figure 1 This is a schematic diagram of the architecture of an embodiment of an indoor positioning system based on multi-source device data collection provided by the present invention;

[0020] Figure 2This is a schematic diagram of the multi-antenna measurement of the arrival angle of the target object provided by the present invention;

[0021] Figure 3 This is a schematic diagram of the device position for determining a target object by triangulation provided by the present invention;

[0022] Figure 4 is a schematic diagram of the phase difference between the target object and the antenna provided by the present invention;

[0023] Figure 5 is a schematic diagram of the position coordinates of the target object provided by the present invention;

[0024] Figure 6 Schematic diagram of the antenna array provided by the present invention. DETAILED DESCRIPTION

[0025] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0026] like Figure 1 As shown, in the first embodiment of the indoor positioning system based on multi-source device data collection of the present invention, the indoor positioning system based on multi-source device data collection 100 includes at least a data sampling module 110, a feature extraction module and a data fusion processing module 120.

[0027] The data sampling module 110 effectively acquires and collects various characteristic parameters (such as sound, face, posture, acceleration, distance, temperature, etc.) in the three-dimensional space through at least sensors or controller components, so as to provide data processing and analysis for subsequent processing modules or other digital processing modules;

[0028] The feature extraction module can extract meaningful features from video frames for subsequent motion analysis and action recognition. The feature extraction module usually includes two sub-modules: key point detection and feature representation;

[0029] Keypoint detection: Detect key points of interest (such as human joints, hand key points, facial key points, etc.) from video frames;

[0030] Feature representation: Represent the detected key points in a format suitable for subsequent processing (such as coordinates, feature vectors, etc.);

[0031] The data fusion processing module 120 is used to pre-process the collected multi-source data, extract effective features, and perform target positioning using an algorithm that integrates multiple calculation methods such as a signal strength-based algorithm, a time difference algorithm, and a multilateration method;

[0032] Specifically, the indoor positioning system needs to model the actual scene (such as three-dimensional space), deploy receivers in the indoor area, and mark the corresponding location on the modeled map. The mobile phone or beacon module acts as the transmitter of the target object, sending a wireless signal. The receiver deployed in a fixed position can determine that the beacon has entered the area after receiving the wireless signal.

[0033] After determining the area, the target object's precise location can be calculated by measuring the signal arrival angle of the target object through multiple sets of antennas and using the triangulation positioning method.

[0034] Specifically, the data sampling module 110 is used to perform grid point division and sampling on the three-dimensional space data, and send the acquired data information to the feature extraction module (not shown);

[0035] Furthermore, a signal interaction channel is established between the input end of the feature extraction module and the output end of the data sampling module to realize data signal interaction, and algorithm calculation and target position processing can be performed on the data of the target object extracted by the data sampling module 110;

[0036] The input end of the data fusion processing module 120 establishes a signal interaction channel with the output end of the feature extraction module to realize data signal interaction. The data fusion processing module 120 is used to extract the current position and motion trajectory of the target object, and generate a target interval accordingly to locate the target object.

[0037] Using this technical solution, the collected indoor environment data is uploaded to the data fusion processing server module in real time. The data fusion processing module then pre-processes the collected multi-source data, extracts effective features, and uses an algorithm that integrates multiple calculation methods such as signal strength-based algorithms, time difference algorithms, and multilateral positioning methods to locate the target, thereby achieving high-precision indoor positioning.

[0038] In some embodiments, as Figure 2 As shown, in the constructed three-dimensional space, the data sampling module 110 uses the circle with the target object as the radius as the trajectory line to obtain the circular trajectory of the current target object.

[0039] Specifically, after determining the area range, the signal arrival angle of the target object can be measured through multiple antennas, and the triangulation positioning method can be used to calculate the precise location of the current target object.

[0040] In some embodiments, as Figure 1 As shown, in order to improve the performance of the positioning system, the data sampling module 110 may include at least Wi-Fi, Bluetooth, Zigbee or a camera,

[0041] Among them, the feature extraction module can collect data through Wi-Fi, Bluetooth, Zigbee or camera to match the location interval of the target object.

[0042] Among them, Wi-Fi positioning can achieve meter-level positioning (1 to 10 meters). Wi-Fi positioning can use the wireless signal strength of the mobile device and three wireless network access points, and use the differential algorithm to more accurately triangulate the positioning of people or vehicles.

[0043] ZigBee indoor positioning can form a network between several blind nodes to be located and a reference node with a known location and a gateway. Each tiny blind node coordinates and communicates with each other to achieve full positioning.

[0044] In some embodiments, as Figure 3 As shown, to obtain the phase value of the target object, when the target object is at the same radius, at a certain moment, the received phase difference is 0; when the target object is at a position with inconsistent radius, at a certain moment, the received phase has a difference.

[0045] For example, triangulation can be used to determine the device location of a target object using two sets of arrival angles. It uses various signal parameters to determine the distance or angle between the target and the AP, and then calculates the location using geometric methods. These methods include time of arrival, relative time of arrival, angle of arrival, signal strength-based ranging, and hybrid algorithms.

[0046] like Figure 3 As shown, two sets of antennas can measure an arrival angle, and two arrival angles can determine the position of device A;

[0047] like Figure 4 As shown in the figure, the measurement principle of the angle of arrival (AoA) is as follows:

[0048] Operating frequency: Bluetooth signals operate in the ISM (Industrial Scientific and Medical) 2.40GHz to 2.41GHz band with a bandwidth of 2Mhz. Bluetooth can be divided into three broadcast channels: 37, 38, and 39. In the Bluetooth 5.x specification, the extended broadcast channel of the Bluetooth LE part can be any channel 0-39, which means that Bluetooth beacons can operate on any Bluetooth channel (the inconsistent operating frequency of Bluetooth during operation will affect the change of Bluetooth wavelength λ);

[0049] Phase: Wireless signals propagate continuously in the air. The RX receiver usually receives and demodulates the signal within the frequency band of 0-2π for the entire wireless signal transmission time.

[0050] Arrival Angle Calculation: Assume that a fixed-frequency Bluetooth target signal is propagating in an open area (ignoring obstacles and interference from other 2.4G signals in the air). If two receivers are located at the same TX end and the same radius, at a certain time t, the phase difference received by the RX receiver should be 0. If the two receivers are located at different radii, there will be a phase difference at a certain time t.

[0051] During the transmission process, due to the different antenna positions, the phase of the signal sampled at a certain time t is different;

[0052] When the two antenna positions d and the target object's signal frequency (i.e., wavelength) are known, the phase difference θ between the target object's signal and antennas A1 and A2 can be calculated. By calculating two sets of θ at different positions, the position of the target object's signal can be calculated.

[0053] In some embodiments, the feature extraction module is used to capture images in real time and pair them with image key points at the target interval where the target object is located.

[0054] In some embodiments, as Figure 6 As shown, after the matching interval is determined, the signal arrival angle of the target object is measured by multiple groups of antennas to calculate the position of the target object.

[0055] In some embodiments, two groups of antennas can measure at least two or more arrival angles, and the two arrival angles can determine the first position of the current target object. The received target object is on the current circle trajectory, and the current position coordinates of the target object can be confirmed based on the orthogonal antenna arrays.

[0056] like Figure 5 As shown in the figure, the AoA measurement error, taking a 2D plane as an example, will have two angles a. In the real 3D coordinates, there will be a circular trajectory with a as the radius. The AoA receiver only knows that the target object's signal is on the circular trajectory, but cannot determine their location. At this time, an orthogonal antenna array is needed to confirm the position coordinates of the target object point.

[0057] AoA design challenges: signal reflection interference

[0058] In open space without interference from other signals, the RX receiver may receive reflected signals from itself or other aoabecaon signals in real-world scenarios. This signal also carries the CTE extended data packet, but it is a noise signal that needs to be eliminated.

[0059] There are various ways to arrange antenna arrays. One is for positioning, and the other is to minimize the number of deployed receivers. The Bluetooth Alliance has made corresponding specifications for the AoA protocol at the logical link layer (LL) in the 5.1 protocol.

[0060] The AoA / AoD specification is specified in the PDU data packet. CTE is the extended data of the AoA / AoD data packet, which lasts for 16-160us. The 250kHz signal is modulated on the carrier without whitening and CRC validation. This signal is used by the receiver RX to sample the signal I / Q value at time t and calculate the phase difference.

[0061] In some embodiments, the data fusion processing module 120 may use the coordinates of the sampling point corresponding to the image with the highest similarity among the first N images with the closest distance difference values as the coordinates of the current target object.

[0062] In some implementations, to ensure reliability of signal transmission, one core may control multiple antennas. During signal transmission in the air medium, time compensation needs to be considered during switching.

[0063] Among them, an RF core controls multiple RF antennas. In addition to the time it takes for the signal to transmit in the air medium, the RF switch switching time must be taken into account and compensated. In addition, there will inevitably be errors in the measurement, and the error range is usually 3%-5%, which needs to be reduced by algorithms.

[0064] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are protected by the present invention.

Claims

1. An indoor positioning system based on multi-source device data collection, characterized in that: have: A data sampling module, which is used to perform grid point division and sampling on three-dimensional spatial data; A feature extraction module, which is signal-connected to the data sampling module and performs algorithm calculation and target position processing on the extracted data of the target object; The data fusion processing module is connected to the feature extraction module by signal, and is used to extract the current position and motion trajectory of the target object and generate a target interval accordingly to locate the target object.

2. The indoor positioning system based on multi-source device data acquisition according to claim 1, characterized in that: In the three-dimensional space, a circle with the target object as a radius is used as a trajectory line to obtain the current circular trajectory of the target object.

3. The indoor positioning system based on multi-source device data acquisition according to claim 2, characterized in that: When the target objects are at the same radius, at a certain moment, the received phase difference is 0. When the target objects are at positions with inconsistent radii, at a certain moment, the received phase has a difference.

4. The indoor positioning system based on multi-source device data acquisition according to claim 3, characterized in that: The data sampling module includes at least Wi-Fi, Bluetooth, Zigbee or a camera, The feature extraction module may collect data via the Wi-Fi, the Bluetooth, the Zigbee or the camera to match the position interval of the target object.

5. The indoor positioning system based on multi-source device data acquisition according to claim 4, characterized in that: The feature extraction module is used to capture images in real time and pair them with image key points of the target interval where the target object is located.

6. The indoor positioning system based on multi-source device data collection according to claim 5, characterized in that: After the matching interval is determined, the signal arrival angle of the target object is measured by multiple antenna groups to calculate the position of the target object.

7. The indoor positioning system based on multi-source device data collection according to claim 6, characterized in that: The two groups of antennas can measure at least two or more arrival angles, and the two arrival angles can determine the first position of the current target object. The target object is received on the current circle trajectory, and the current position coordinates of the target object can be confirmed based on the orthogonal antenna arrays.

8. The indoor positioning system based on multi-source device data acquisition according to claim 7, characterized in that: The data fusion processing module may use the coordinates of the sampling points corresponding to the images with the highest similarity among the first N images with the closest distance difference values as the current coordinates of the target object.

Images