Indoor positioning method and system based on vision, geomagnetism and inertial navigation

Abstract

The invention provides an indoor positioning method and system based on vision, geomagnetism and inertial navigation, and the method comprises the steps: obtaining inertial navigation data, and determining a local region where a target object is located in an indoor space according to the inertial navigation data; wherein the inertial navigation data is obtained by a positioning device carried by a target object; obtaining a visual image of the local area, and determining the position of the target object in a pre-constructed spatial model according to the visual image to obtain a first position; determining a target range according to the first position, and simulating an environment magnetic field around the target object under the condition that the magnetic disturbance object exists in the target range; real-time magnetic field data is obtained, the real-time magnetic field data is obtained through measurement of magnetic field measurement equipment carried by the target object, the real-time magnetic field data is matched with the environment magnetic field, the specific position of the target object in the local area is determined, and a second position is obtained. According to the invention, multiple positioning technologies are fused, and the indoor positioning accuracy can be further improved.

Description

Technical Field

[0001] The present invention relates to the field of indoor positioning technology, and in particular to an indoor positioning method, system, equipment and medium based on vision, geomagnetism and inertial navigation. Background Art

[0002] Traditional indoor positioning technologies, such as those that rely solely on a certain type of sensor data (such as WiFi signal strength or Bluetooth signal strength) for positioning, often have poor accuracy. This is because the indoor environment is complex and changeable, with challenges such as wall shielding, numerous obstacles, and complex interference sources, which make the signal transmission process susceptible to interference, thus affecting positioning accuracy.

[0003] In order to solve the problem of positioning accuracy, a method of performing real-time video detection on all indoor spaces to achieve positioning has been proposed. Although this method can theoretically provide more intuitive location information, in actual applications, a large number of cameras deployed need to collect video of the indoor environment at all times, which brings huge energy consumption.

[0004] It can be seen that indoor positioning achieved through a single positioning technology cannot meet the accuracy and reliability of indoor positioning. Therefore, it is necessary to explore how to integrate multiple positioning technologies to give full play to their respective advantages and further improve positioning performance to meet the growing demand for indoor positioning. Summary of the invention

[0005] The embodiment of the present invention provides an indoor positioning method, system, device and medium based on vision, geomagnetism and inertial navigation to solve the problems existing in the related technologies. The technical solution is as follows:

[0006] In a first aspect, an embodiment of the present invention provides an indoor positioning method based on vision, geomagnetic and inertial navigation, comprising:

[0007] Acquire inertial navigation data, and determine the local area where the target object is located in the indoor space according to the inertial navigation data; wherein the inertial navigation data is obtained by a positioning device carried by the target object;

[0008] Acquire a visual image of a local area, determine a position of a target object in a pre-constructed spatial model according to the visual image, and obtain a first position;

[0009] Determine the target range according to the first position, and simulate the environmental magnetic field around the target object when there is a magnetic disturbance object in the target range;

[0010] Acquire real-time magnetic field data, which is measured by a magnetic field measurement device carried by the target object, match the real-time magnetic field data with the ambient magnetic field, determine the specific position of the target object in the local area, and obtain a second position.

[0011] In one embodiment, it further includes:

[0012] A corresponding space model is constructed according to the layout of the indoor space, the space model is divided into a number of sub-areas, and object information of all objects in the indoor space is marked in the space model;

[0013] Determine the relative position of the target object relative to the initial state based on the inertial navigation data;

[0014] The relative position is converted into the spatial position of the target object in the spatial model, and the sub-region where the target object is located in the spatial model is determined and marked as a local region.

[0015] In one embodiment, determining the position of the target object in the pre-constructed space model according to the visual image to obtain the first position includes:

[0016] Based on the matching algorithm, the area matching the preset object is found in the visual image as the target object;

[0017] Identify multiple landmark objects in the visual image, and determine the positional relationship between each landmark object in the visual image and the target object;

[0018] The positional relationship between each landmark object and the target object is converted into the spatial model to determine the first position of the target object in the spatial model.

[0019] In one embodiment, simulating the ambient magnetic field around the target object includes:

[0020] In the case where there are magnetically disturbing objects within the target range, the type of each magnetically disturbing object within the target range is determined according to the object information of the spatial model, and the interfering magnetic field generated by each magnetically disturbing object is determined according to the type of each magnetically disturbing object; wherein the target range is a spatial range in the spatial model that is centered at the first position and extends outward by a specified distance;

[0021] On the basis of the earth's magnetic field, the interfering magnetic fields generated by all magnetic disturbing objects within the target range are superimposed to obtain the ambient magnetic field.

[0022] In one embodiment, it further includes:

[0023] Based on all object information of the space model, it is judged whether there is a magnetically disturbing object within the target range. When there is no magnetically disturbing object within the target range, the ambient magnetic field is directly the earth's magnetic field.

[0024] In one embodiment, it further includes:

[0025] The future movement direction of the target object is predicted based on inertial navigation data and visual images, the sub-area to which the target object will go in the spatial model is determined based on the future movement direction, and the camera of the sub-area to which the target object will go is activated in advance to capture the visual image when the target object moves to the sub-area.

[0026] In one embodiment, it further includes:

[0027] The positioning device is calibrated for inertial navigation according to the second position, and the real-time position of the target object is measured using the calibrated positioning device to obtain new inertial navigation data.

[0028] In a second aspect, an embodiment of the present invention provides an indoor positioning system based on vision, geomagnetism and inertial navigation, which executes the indoor positioning method based on vision, geomagnetism and inertial navigation as described above.

[0029] In a third aspect, an embodiment of the present invention provides an electronic device, the device comprising: a memory and a processor. The memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory, the processor executes the method in any one of the above-mentioned embodiments.

[0030] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.

[0031] The advantages or beneficial effects of the above technical solution include at least:

[0032] The present invention determines the local area of ​​the indoor space where the target object is located through inertial navigation data, controls the camera in the local area to capture images, and analyzes the visual image of a single local area to obtain the first position of the target object in the indoor space, replacing the traditional method of real-time shooting of all cameras in the entire indoor space. The method of analyzing the local area visual image of the present invention can reduce energy consumption to a certain extent and improve positioning performance;

[0033] The present invention combines the interfering magnetic field of the magnetic disturbing object to simulate the environmental magnetic field around the target object, and determines the second position of the target object in the indoor space through the geomagnetic technology, which can further improve the accuracy of the geomagnetic positioning technology when there is an interference source in the indoor space;

[0034] The present invention integrates multiple positioning technologies such as inertial navigation technology, geomagnetic positioning technology and visual analysis, which can further improve the accuracy of indoor positioning.

[0035] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present invention and should not be regarded as limiting the scope of the present invention.

[0037] Figure 1 It is a flow chart of the indoor positioning method based on vision, geomagnetism and inertial navigation of the present invention;

[0038] Figure 2 The structure block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0040] Embodiment 1

[0041] The embodiment of the present invention provides an indoor positioning method based on vision, geomagnetism and inertial navigation. The method integrates multiple positioning technologies, gives full play to their respective advantages, and can further improve positioning performance.

[0042] like Figure 1 As shown, the indoor positioning method based on vision, geomagnetic and inertial navigation includes the following steps:

[0043] Step S1: Acquire inertial navigation data, and determine the local area where the target object is located in the indoor space according to the inertial navigation data.

[0044] Among them, inertial navigation data is obtained by the positioning device carried by the target object. The positioning device carried by the target object must have an inertial measurement unit (IMU). The inertial measurement unit contains a variety of sensors for measuring the motion state of the carrier.

[0045] It should be noted that the inertial measurement unit mainly includes an accelerometer and a gyroscope. The accelerometer is used to measure the acceleration of the carrier. Through integration operations, the data of the accelerometer can be converted into velocity and position information; while the gyroscope is used to measure the angular velocity of the carrier. By integrating the angular velocity, the change of posture over time can be obtained.

[0046] In this embodiment, the positioning device carried by the target object is a mobile phone terminal, and the inertial navigation data is measured by the mobile phone terminal with a built-in inertial measurement unit. The built-in inertial measurement unit of the mobile phone terminal is used to infer the movement trajectory, speed, posture and other information of the mobile phone, thereby roughly calculating the preliminary position of the target object in the indoor space.

[0047] In this embodiment, the indoor space is pre-divided into multiple areas, and the space division rules can be pre-defined. The indoor space can be divided in the same way as the indoor area, or can be divided according to the functions of each area of ​​the indoor space. It should be explained that the space division rules of the indoor space are not limited here.

[0048] A corresponding space model is constructed according to the division results of the indoor space and the actual layout of the indoor space, and the space model is divided into several sub-areas according to the same space division rules. The space model is used to restore the actual indoor space in proportion.

[0049] At the same time, all objects existing in the indoor space are added to the space model, and the object information of all objects in the indoor space is marked in the space model to facilitate subsequent object positioning.

[0050] This embodiment determines the relative position of the target object relative to the initial state based on the inertial navigation data, wherein the initial state refers to the attitude, velocity and position information of the target object when the navigation starts. After determining the initial state, the inertial navigation unit can measure the motion parameters such as the acceleration and angular velocity of the target object, and use these parameters to perform calculations such as integration and coordinate transformation, to infer the real-time position and attitude of the target object in the navigation coordinate system.

[0051] The real-time position and posture of the target object in the navigation coordinate system are converted into the spatial model according to the preset conversion relationship, so as to determine the spatial position of the target object in the spatial model, and mark the sub-area where the target object is located in the spatial model as a local area.

[0052] Since positioning equipment will have a certain degree of error after long-term use, this embodiment determines the local area where the target object is located in the indoor space through inertial navigation data, which can reduce the problems caused by errors, and then further locates the specific position of the target object through subsequent visual positioning technology and geomagnetic positioning technology to improve positioning accuracy.

[0053] Step S2: Acquire a visual image of a local area, determine the position of the target object in the pre-constructed space model according to the visual image, and obtain a first position.

[0054] It should be noted that, in this embodiment, each sub-area of ​​the indoor space is provided with at least one camera, and each camera has a certain shooting angle to ensure that the camera can capture most of the objects in the sub-area where it is located.

[0055] After determining the local area where the target object is located, this embodiment sends a shooting instruction to the camera deployed in the local area, so that the camera in the local area performs the shooting task to obtain a visual image of the local area. The visual image can be a single image obtained by a single shot or multiple frames of images taken continuously.

[0056] This embodiment determines the target object in the visual image through a matching algorithm, that is, the visual image is analyzed, the outer contours of all objects in the visual image are extracted, the outer contours of all objects in the visual image are traversed, and the outer contours of each object in the visual image are matched with the outer contour of a preset object. When the matching degree is higher than a set threshold, it can be determined that the preset object exists in the visual image, and the object in the visual image that matches the outer contour of the preset object is marked as the target object.

[0057] Similarly, the presence of a landmark object in the visual image is determined by also calculating the degree of matching. When a landmark object exists in the visual image, the position of the landmark object and the position of the target object are associated to determine the positional relationship between the landmark object and the target object, such as determining the distance and direction between the landmark object and the target object.

[0058] Each landmark object in the visual image is mapped back to the spatial model, the position of the landmark object in the spatial model is determined, and then the position of the target object in the spatial model is determined according to the positional relationship between each landmark object and the target object, so as to realize the conversion of the target object into the spatial model. In this embodiment, the position of the target object in the spatial model is referred to as the first position.

[0059] It should be noted that iconic objects refer to objects in the indoor environment that have significant visual features and can define or highlight the characteristics of the space, such as furniture, decorations, architectural structural elements, etc. Iconic objects can be set in advance, and when setting, the image of the iconic object is recorded to determine the outer contour of the iconic object, so as to determine whether there is an iconic object in the visual image through matching calculation.

[0060] Step S3: determining a target range according to the first position, and simulating an ambient magnetic field around the target object when there is a magnetic disturbance object within the target range.

[0061] After determining the first position of the target object in the space model, expand outward by a specified distance with the first position as the center in the space model to determine the target range outside the target object; retrieve the object information of all objects in the local area where the target object is located in the space model, the object information includes the object type, object parameters, etc., and determine whether there is an object that will interfere with the magnetic field within the target range based on the object information. If so, mark the object as a magnetic disturbing object.

[0062] In this embodiment, the magnetic disturbance object may be an electronic device that generates a certain electromagnetic field during operation, a ferromagnetic object containing ferromagnetic materials, a power grid interference that generates a magnetic field due to current changes, etc.

[0063] Assuming that there are no magnetic disturbance objects within the target range around the target object, the environmental magnetic field is directly the earth's magnetic field; assuming that there are magnetic disturbance objects within the target range, the magnetic field generated by each magnetic disturbance object within the target range needs to be considered to simulate the environmental magnetic field at that location. Specifically:

[0064] The type of each magnetically disturbing object and the working parameters of the magnetically disturbing object within the target range are determined according to the object information pre-stored in the space model. The interfering magnetic field generated by each magnetically disturbing object can be determined in combination with the working state of the magnetically disturbing object. The interfering magnetic fields generated by all magnetically disturbing objects within the target range are superimposed on the earth's magnetic field to obtain the environmental magnetic field within the target range.

[0065] For example, when it is determined that the magnetic disturbance object in the target range is a microwave oven, the interference magnetic field generated by the microwave oven in the working state can be determined according to the working parameters of the microwave oven, and the interference magnetic field generated by the microwave oven is superimposed with the earth's magnetic field to determine the magnetic field conditions in the target range where the target object is located, and obtain the environmental magnetic field. The environmental magnetic field presents the magnetic field distribution of the environment surrounding the target object, so that the specific position of the target object in the room can be further accurately located according to the magnetic field conditions in the future.

[0066] Step S4: Acquire real-time magnetic field data, which is measured by a magnetic field measurement device carried by the target object, match the real-time magnetic field data with the ambient magnetic field, determine the specific position of the target object in the local area, and obtain a second position.

[0067] It should be noted that the magnetic field measurement equipment can measure the difference in magnetic field signal strength at different locations and match the real-time magnetic field data with the ambient magnetic field within the target range. When the real-time magnetic field data matches the magnetic field distribution at a certain location within the target range, the exact location of the target object indoors can be determined.

[0068] In some embodiments, indoor positioning can also be achieved according to the weighted average method, specifically: after obtaining the first position of the target object in the room through visual image analysis and the second position of the target object in the room through geomagnetic positioning technology, different weights are assigned to them according to the reliability or accuracy of the two position data, and then the weighted average is calculated as the final position of the target object in the indoor space. It should be noted that the allocation of weights can be based on a variety of factors, such as the stability of geomagnetic positioning technology, the accuracy of image analysis, the influence of environmental noise, etc. The specific value of the weight can be determined according to experiments and is not specifically limited here.

[0069] In addition, since this embodiment starts the camera in a local area of ​​the indoor space to shoot the target object, the cameras in other areas of the room are in standby mode to reduce energy consumption. In order to accurately locate the target object, the future moving direction of the target object is predicted, and the corresponding camera is controlled to start in advance according to the future moving direction to ensure that there is a camera shooting the target object at all times. Specifically:

[0070] The future moving direction of the target object can be predicted based on the inertial navigation data and the visual image. Specifically, the inertial navigation data and the visual image data are fused. The fusion method can be implemented through algorithms such as Kalman filtering and particle filtering to combine the advantages of the two data and improve the accuracy of the prediction. Based on the fused data, the current speed, acceleration, posture of the object and the direction information extracted from the visual image are considered, and the prediction model (such as time series analysis, machine learning model, etc.) is used to predict the future moving direction of the target object. The prediction model can be obtained through a large amount of data training, and its training process is not described in detail here.

[0071] The sub-area to which the target object will go in the spatial model is determined according to the future moving direction, and the sub-area to which the target object will go is called the prediction area. Controlling the camera in the prediction area to turn on is equivalent to activating the camera in standby state in advance, so that as soon as the target object enters the prediction area, the camera can immediately capture the target object and its surrounding environment to obtain the corresponding visual image, thereby analyzing the visual image of the prediction area to achieve accurate positioning of the real-time position of the target object.

[0072] Since the positioning device used to measure inertial navigation data will have errors after long-term use, in order to improve the positioning accuracy, the positioning device is calibrated for inertial navigation according to the accurate position of the target object in the indoor space (i.e., the second position), which is equivalent to comparing the second position with the positioning position calculated according to the inertial navigation data to determine whether the error between the two exceeds a preset error value. If the error value is exceeded, the positioning device is calibrated according to the second position, so that the measurement of the positioning device can be more accurate. The calibrated positioning device is used to measure the real-time position of the target object, and new inertial navigation data is obtained to determine the indoor area where the target object is located, so as to facilitate the subsequent accurate positioning of the target object.

[0073] This embodiment preliminarily determines the local indoor area where the target object is located through inertial navigation data. The measurement errors accumulated by the long-term use of inertial navigation technology can be ignored for a large local area. The visual image of the local area is analyzed to further analyze the position of the target object in the room through the visual image, which can avoid a large amount of energy consumption caused by a large number of cameras shooting at the same time. While analyzing the visual image, the environmental magnetic field around the target object is simulated, and the real-time magnetic field data is compared with the environmental magnetic field to further determine the precise position of the target object in the room, and make up for the error caused by image analysis and positioning. This embodiment integrates multiple positioning technologies to gradually limit the position of the target object in the indoor space, thereby improving the accuracy of indoor positioning of the target object.

[0074] Embodiment 2

[0075] The present embodiment provides an indoor positioning system based on vision, geomagnetism and inertial navigation, and the indoor positioning system includes an inertial navigation module, a vision module, a magnetic field measurement module and a positioning analysis module, wherein the inertial navigation module is used to obtain inertial navigation data; the vision module is used to obtain visual images; the magnetic field measurement module is used to obtain real-time magnetic field data; and the positioning analysis module executes the indoor positioning method based on vision, geomagnetism and inertial navigation as described in Example 1, which is used to determine the local area where the target object is located in the indoor space according to the inertial navigation data, determine the position of the target object in a pre-constructed spatial model according to the visual image, and obtain a first position. When it is determined based on the spatial model that there is a magnetically disturbing object within the target range outside the target object, the environmental magnetic field around the target object is simulated; and the real-time magnetic field data is matched with the environmental magnetic field to determine the specific position of the target object in the local area to obtain a second position.

[0076] The functions of each module in the system in the embodiment of the present invention can refer to the corresponding description in the above method, which will not be repeated here.

[0077] Embodiment 3

[0078] Figure 2FIG. 2 shows a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 2 As shown, the electronic device provided in this embodiment includes: a memory 100 and a processor 200, and the memory 100 stores a computer program that can be run on the processor 200. When the processor 200 executes the computer program, the indoor positioning method based on vision, geomagnetism and inertial navigation in the above embodiment is implemented. The number of the memory 100 and the processor 200 can be one or more.

[0079] The electronic device also includes:

[0080] The communication interface 300 is used to communicate with external devices and perform data exchange transmission.

[0081] If the memory 100, the processor 200 and the communication interface 300 are implemented independently, the memory 100, the processor 200 and the communication interface 300 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0082] Optionally, in a specific implementation, if the memory 100, the processor 200 and the communication interface 300 are integrated on a chip, the memory 100, the processor 200 and the communication interface 300 can communicate with each other through an internal interface.

[0083] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present invention when executed by a processor.

[0084] An embodiment of the present invention further provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present invention.

[0085] An embodiment of the present invention also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided by the embodiment of the invention.

[0086] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0087] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0088] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0090] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0091] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An indoor positioning method based on vision, geomagnetism and inertial navigation, characterized in that: include: Acquire inertial navigation data, and determine a local area where a target object is located in an indoor space according to the inertial navigation data; wherein the inertial navigation data is obtained by a positioning device carried by the target object; Acquire a visual image of the local area, and determine a position of the target object in a pre-constructed spatial model according to the visual image to obtain a first position; Determine a target range according to the first position, and simulate the environmental magnetic field around the target object when there is a magnetic disturbance object within the target range; Acquire real-time magnetic field data, where the real-time magnetic field data is measured by a magnetic field measurement device carried by the target object, match the real-time magnetic field data with the ambient magnetic field, determine the specific position of the target object in the local area, and obtain a second position.

2. The indoor positioning method based on vision, geomagnetic and inertial navigation according to claim 1 is characterized in that: Also includes: Constructing a corresponding space model according to the layout of the indoor space, wherein the space model is divided into a plurality of sub-areas, and object information of all objects in the indoor space is marked in the space model; Determining a relative position of the target object relative to an initial state according to the inertial navigation data; The relative position is converted into the spatial position of the target object in the spatial model, and a sub-region where the target object is located in the spatial model is determined and marked as the local region.

3. The indoor positioning method based on vision, geomagnetic and inertial navigation according to claim 2 is characterized in that: Determining the position of the target object in the pre-constructed space model according to the visual image to obtain a first position includes: Based on a matching algorithm, searching in the visual image for an area that matches a preset object as the target object; Identify multiple landmark objects in the visual image, and determine the positional relationship between each landmark object in the visual image and the target object; The positional relationship between each of the landmark objects and the target object is converted into the spatial model to determine the first position of the target object in the spatial model.

4. The indoor positioning method based on vision, geomagnetic and inertial navigation according to claim 2 is characterized in that: The simulating the environmental magnetic field around the target object comprises: In the case where the magnetically disturbing object exists within the target range, determining the type of each magnetically disturbing object within the target range according to the object information of the spatial model, and determining the interfering magnetic field generated by each magnetically disturbing object according to the type of each magnetically disturbing object; wherein the target range is a spatial range in the spatial model that is centered at the first position and extends outward by a specified distance; The interfering magnetic fields generated by all the magnetically disturbing objects within the target range are superimposed on the earth's magnetic field to obtain the environmental magnetic field.

5. The indoor positioning method based on vision, geomagnetic and inertial navigation according to claim 4 is characterized in that: Also includes: Based on all the object information of the space model, it is determined whether the magnetic disturbing object exists within the target range. When the magnetic disturbing object does not exist within the target range, the environmental magnetic field is directly the earth's magnetic field.

6. The indoor positioning method based on vision, geomagnetic and inertial navigation according to claim 1, characterized in that: Also includes: The future moving direction of the target object is predicted based on the inertial navigation data and the visual image, the sub-area to which the target object will go in the spatial model is determined based on the future moving direction, and the camera of the sub-area to which the target object will go is activated in advance to capture the visual image of the target object when it moves to the sub-area.

7. The indoor positioning method based on vision, geomagnetic and inertial navigation according to claim 1, characterized in that: Also includes: The positioning device is calibrated for inertial navigation according to the second position, and the real-time position of the target object is measured using the calibrated positioning device to obtain new inertial navigation data.

8. An indoor positioning system based on vision, geomagnetism and inertial navigation, characterized in that: Execute the indoor positioning method based on vision, geomagnetism and inertial navigation as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the indoor positioning method based on vision, geomagnetism and inertial navigation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the indoor positioning method based on vision, geomagnetism and inertial navigation as claimed in any one of claims 1 to 7 is implemented.

Images