Method and device for determining mapping relation between sensor and object pose

Abstract

The invention relates to the technical field of magnetic field sensing, in particular to a method and a device for determining a mapping relation between a sensor and an object pose. The method comprises the following steps: acquiring three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is asymmetric magnetic field distribution; determining a magnetic field sensing array formed by magnetic field sensors based on a preset sensor distance and a sensor arrangement direction; performing magnetic field data acquisition on the three-dimensional magnetic field distribution based on a magnetic field sensing array to obtain target magnetic field images corresponding to the at least two rectangular permanent magnets; and according to the target magnetic field image, carrying out object pose analysis on the magnetic field sensing array to obtain a mapping relation between the magnetic field sensing array and the object pose. According to the invention, object pose analysis is carried out on the magnetic field sensing array, the mapping relation between the magnetic field sensing array and the object pose is obtained, and the complete space pose of the object is accurately sensed with high efficiency, low time delay and low power consumption.

Description

Technical Field

[0001] The present application relates to the field of magnetic field sensing technology, and in particular to a method and device for determining a mapping relationship between a sensor and an object's posture. Background Art

[0002] With the rapid development of industry and technology, space magnetic field sensing technology has played an important role in multi-target pose estimation, object positioning and attitude measurement. Compared with vision, lidar and inertial navigation sensors, magnetic field-based space sensing methods have gradually become an important technical means in close-range complex environments due to their advantages of low cost, high resolution and strong environmental robustness.

[0003] However, the current spatial magnetic field sensing technology performs posture estimation based on the rotationally symmetric magnetic field distribution of a cylindrical permanent magnet, which limits the degree of freedom of posture estimation and makes it impossible to accurately perceive the mapping relationship between the sensor and the object's posture. Summary of the invention

[0004] Based on this, it is necessary to provide a method and device for determining the mapping relationship between a sensor and an object's posture, which can accurately perceive the mapping relationship between the sensor and the object's posture, in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for determining a mapping relationship between a sensor and an object's posture. The method comprises:

[0006] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0007] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0008] Performing magnetic field data acquisition on the three-dimensional magnetic field distribution based on the magnetic field sensing array to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets;

[0009] According to the target magnetic field image, the magnetic field sensor array is subjected to object posture analysis to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0010] In one embodiment, the collecting magnetic field data of the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain the target magnetic field image corresponding to the at least two rectangular permanent magnets includes:

[0011] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain an initial magnetic field image corresponding to each magnetic field sensor;

[0012] Magnetic field vectors are superimposed on each of the initial magnetic field images to obtain target magnetic field images corresponding to the at least two rectangular permanent magnets.

[0013] In one embodiment, the step of performing magnetic field vector superposition on each of the initial magnetic field images to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets includes:

[0014] Performing invalid data trimming and key data enhancement on each of the initial magnetic field images to obtain a candidate magnetic field image corresponding to each of the initial magnetic field images;

[0015] Magnetic field vectors are superimposed on each of the candidate magnetic field images to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets.

[0016] In one embodiment, the pose analysis neural network based on the target magnetic field image performs an object pose analysis for the magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array and the object pose, including:

[0017] The target magnetic field image is input into the posture analysis neural network, so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array, and obtains the mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

[0018] In one embodiment, the method further comprises:

[0019] The target magnetic field image is input into the posture analysis neural network so that the second multi-processing network in the posture analysis neural network learns the key features in the target magnetic field image and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

[0020] In a second aspect, the present application also provides a device for determining a mapping relationship between a sensor and an object's posture. The device comprises:

[0021] An acquisition module, used to acquire a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0022] A determination module, used to determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0023] An acquisition module, used for acquiring magnetic field data of the three-dimensional magnetic field distribution based on the magnetic field sensing array, and obtaining a target magnetic field image corresponding to the at least two rectangular permanent magnets;

[0024] The analysis module is used to perform object posture analysis on the magnetic field sensor array according to the target magnetic field image to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0025] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0026] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0027] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0028] Performing magnetic field data acquisition on the three-dimensional magnetic field distribution based on the magnetic field sensing array to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets;

[0029] According to the target magnetic field image, the magnetic field sensor array is subjected to object posture analysis to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0031] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0032] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0033] Performing magnetic field data acquisition on the three-dimensional magnetic field distribution based on the magnetic field sensing array to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets;

[0034] According to the target magnetic field image, the magnetic field sensor array is subjected to object posture analysis to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0035] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0036] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0037] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0038] Performing magnetic field data acquisition on the three-dimensional magnetic field distribution based on the magnetic field sensing array to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets;

[0039] According to the target magnetic field image, the magnetic field sensor array is subjected to object posture analysis to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0040] The method and device for determining the mapping relationship between the above-mentioned sensor and the object posture, by obtaining the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets, and determining the magnetic field sensing array composed of magnetic field sensors, and then, based on the magnetic field sensing array, magnetic field data collection is performed on the three-dimensional magnetic field distribution to obtain the target magnetic field image corresponding to at least two rectangular permanent magnets, so as to realize the object posture analysis of the magnetic field sensing array according to the target magnetic field image, and obtain the mapping relationship between the magnetic field sensing array and the object posture. According to the above content, it can be known that in the process of determining the mapping relationship between the magnetic field sensing array and the object posture, the present application obtains at least two rectangular permanent magnets distributed by an asymmetric magnetic field, overcomes the defect of insufficient degrees of freedom of traditional cylindrical permanent magnets, and realizes accurate magnetic field measurement for multiple targets and multiple postures; and, by forming the operation of obtaining the target magnetic field image by the magnetic field sensing array, data redundancy is effectively reduced, the complexity of data processing operations is reduced, and data compatibility is improved. Finally, by analyzing the object posture of the magnetic field sensing array, the mapping relationship between the magnetic field sensing array and the object posture is obtained, and the complete spatial posture of the object is accurately perceived with high efficiency, low latency and low power consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 An application environment diagram of a method for determining a mapping relationship between a sensor and an object posture provided in an embodiment of the present application;

[0042] Figure 2 A schematic flow chart of a method for determining a mapping relationship between a sensor and an object posture provided in a first embodiment of the present application;

[0043] Figure 3 A schematic flow chart of a method for determining a mapping relationship between a second sensor and an object posture provided in an embodiment of the present application;

[0044] Figure 4 A schematic flow chart of a method for determining a mapping relationship between a third sensor and an object posture provided in an embodiment of the present application;

[0045] Figure 5A structural block diagram of a device for determining a mapping relationship between a sensor and an object posture provided in an embodiment of the present application;

[0046] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The method for determining the mapping relationship between the sensor and the object posture provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. By obtaining the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets, and determining the magnetic field sensing array composed of magnetic field sensors, and then, based on the magnetic field sensing array, the three-dimensional magnetic field distribution is subjected to magnetic field data acquisition, and the target magnetic field image corresponding to at least two rectangular permanent magnets is obtained, so as to realize the object posture analysis of the magnetic field sensing array according to the target magnetic field image, and obtain the mapping relationship between the magnetic field sensing array and the object posture. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0049] In one embodiment, Figure 2 As shown, a method for determining the mapping relationship between a sensor and an object posture is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0050] S201, obtaining three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets.

[0051] Among them, the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution.

[0052] It should be noted that in order to prevent the degree of freedom of pose estimation from being limited when performing pose estimation on the rotationally symmetric magnetic field distribution of a cylindrical permanent magnet, a rectangular permanent magnet is used as a magnetic field source. Then, an asymmetric magnetic field distribution is constructed by at least two rectangular permanent magnets, and the magnetic field in the chassis of at least two rectangular permanent magnets is analyzed to obtain a three-dimensional magnetic field distribution corresponding to the at least two rectangular permanent magnets.

[0053] The rectangular permanent magnet may be a rectangular permanent magnet with a magnetization direction along the Z axis and a size of 2a×2b×2c mm^3.

[0054] Furthermore, the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets can be obtained according to the rectangular permanent magnet molecular current model.

[0055] In one embodiment of the present application, when it is necessary to obtain the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets, the following contents may be included: according to the molecular current model of the rectangular permanent magnet, a Cartesian coordinate system centered on the rectangular permanent magnet is constructed; further, according to the Biot-Savart law, the magnetic induction intensity Bx, By, Bz of the rectangular permanent magnet at any point in space is calculated; wherein the magnetic field component formula for at least two rectangular permanent magnets is as follows:

[0056] Bx=fx(x,y,z,a,b,c);

[0057] By=fy(x,y,z,a,b,c);

[0058] Bz=fz(x,y,z,a,b,c);

[0059] Furthermore, according to the above magnetic field component formula, the magnetic field distribution of at least two rectangular permanent magnets is analyzed to obtain the three-dimensional magnetic field distribution corresponding to the at least two rectangular permanent magnets.

[0060] S202: Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction.

[0061] It should be noted that when it is necessary to determine the magnetic field sensing array composed of magnetic field sensors, the number of magnetic field sensors can be determined in advance, and the magnetic field acquisition range and data accuracy can be ensured based on the preset sensor spacing and sensor arrangement direction; furthermore, the magnetic field sensing array composed of magnetic field sensors is determined;

[0062] The magnetic field sensor may be a single-axis tunneling magnetoresistance (T MR) sensor.

[0063] In one embodiment of the present application, an 8×8 magnetic field sensing array of single-axis tunneling magnetoresistive sensors can be constructed; wherein each single-axis tunneling magnetoresistive sensor is arranged in the same direction and plane at a uniform spacing d, and the array elements are numbered U(i, j), i, j=0, ..., 7 array signal outputs.

[0064] S203, collecting magnetic field data on the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0065] In one embodiment of the present application, when it is necessary to obtain a target magnetic field image corresponding to at least two rectangular permanent magnets, each magnetic field sensor in the magnetic field sensor array can be obtained separately, and the collection results of the magnetic field data collection for the three-dimensional magnetic field distribution can be performed. Then, based on the collection results of each magnetic field sensor, the target magnetic field image corresponding to at least two rectangular permanent magnets can be combined to obtain.

[0066] Among them, in the process of combining the acquisition results of each magnetic field sensor, invalid data can be trimmed and key data can be enhanced for the acquisition results to ensure that the final target magnetic field image can be effectively used for object posture analysis, thereby ensuring the accuracy of subsequent object posture analysis.

[0067] S204, performing object posture analysis on the magnetic field sensor array according to the target magnetic field image, and obtaining a mapping relationship between the magnetic field sensor array and the object posture.

[0068] In one embodiment of the present application, when it is necessary to perform object posture analysis on the magnetic field sensor array based on the target magnetic field image to obtain a mapping relationship between the magnetic field sensor array and the object posture, the posture analysis neural network can be pre-trained, and then, based on the posture analysis neural network, the target magnetic field image is subjected to object posture analysis for the magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0069] The method for determining the mapping relationship between the above-mentioned sensor and the object posture is to obtain the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets, and determine the magnetic field sensing array composed of magnetic field sensors, and then, based on the magnetic field sensing array, the magnetic field data is collected for the three-dimensional magnetic field distribution to obtain the target magnetic field image corresponding to at least two rectangular permanent magnets, so as to realize the object posture analysis of the magnetic field sensing array according to the target magnetic field image, and obtain the mapping relationship between the magnetic field sensing array and the object posture. According to the above content, it can be known that in the process of determining the mapping relationship between the magnetic field sensing array and the object posture, the present application obtains at least two rectangular permanent magnets distributed by an asymmetric magnetic field, overcomes the defect of insufficient degrees of freedom of traditional cylindrical permanent magnets, and realizes accurate magnetic field measurement for multiple targets and multiple postures; and, by forming the operation of obtaining the target magnetic field image by the magnetic field sensing array, data redundancy is effectively reduced, the complexity of data processing operations is reduced, and the compatibility of data is improved. Finally, by analyzing the object posture of the magnetic field sensing array, the mapping relationship between the magnetic field sensing array and the object posture is obtained, and the complete spatial posture of the object is accurately perceived with high efficiency, low latency and low power consumption.

[0070] In one embodiment, if Figure 3 As shown, when it is necessary to collect magnetic field data for the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain a target magnetic field image corresponding to at least two rectangular permanent magnets, the following contents may be included:

[0071] S301 , collecting magnetic field data of a three-dimensional magnetic field distribution based on a magnetic field sensor array, and obtaining an initial magnetic field image corresponding to each magnetic field sensor.

[0072] In one embodiment of the present application, a collection signal of each magnetic field sensor in the magnetic field sensor array for collecting magnetic field data on the three-dimensional magnetic field distribution is received, and an image is generated for the collection signal corresponding to each magnetic field sensor to obtain an initial magnetic field image corresponding to each magnetic field sensor.

[0073] S302, performing magnetic field vector superposition on each initial magnetic field image to obtain a target magnetic field image corresponding to at least two rectangular permanent magnets.

[0074] It should be noted that when it is necessary to perform magnetic field vector superposition on each initial magnetic field image, the following contents may be included: invalid data trimming and key data enhancement on each initial magnetic field image to obtain candidate magnetic field images corresponding to each initial magnetic field image; and magnetic field vector superposition on each candidate magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0075] Furthermore, in order to ensure the accuracy of the final target magnetic field image, in the process of vector superposition of each candidate magnetic field image, it is necessary to ensure the independence of the vector superposition and the authenticity of the target magnetic field image.

[0076] The method for determining the mapping relationship between the above-mentioned sensor and the object posture obtains the initial magnetic field image corresponding to each magnetic field sensor, and performs invalid data trimming and key data enhancement on each initial magnetic field image, so as to realize magnetic field vector superposition of each processed candidate magnetic field image, and obtain target magnetic field images corresponding to at least two rectangular permanent magnets, which effectively reduces data redundancy, reduces the operational complexity of processing data, and improves data compatibility.

[0077] In one embodiment, when it is necessary to perform object posture analysis on the magnetic field sensor array according to the target magnetic field image to obtain a mapping relationship between the magnetic field sensor array and the object posture, the following contents may be included:

[0078] Based on the posture analysis neural network, the target magnetic field image is subjected to object posture analysis for the magnetic field sensor array, and the mapping relationship between the magnetic field sensor array and the object posture is obtained.

[0079] Among them, the posture analysis neural network can be an MPNet convolutional neural network constructed with the ResNet network architecture as the backbone network; and the posture analysis neural network includes a first multi-processing network and a second multi-processing network, the first multi-processing network is the SMPNet network, and the SMPNet network can output the mapping relationship between the magnetic field sensor array and the object posture; the second multi-processing network is the CMPNet network, and the CMPNet network can reduce the difference between the simulation array data and the actual test data, and realize the high-precision estimation of the object posture by the spatial magnetic field sensor.

[0080] Among them, the trained posture analysis neural network can be deployed to the ZYNQ SoC hardware platform to achieve real-time reasoning.

[0081] Furthermore, the first multi-processing network is trained using the simulation data set to establish a preliminary mapping relationship between the magnetic field sensor array and the position and posture. The second multi-processing network is trained using the actual test data to correct the deviation between the simulation data and the actual data.

[0082] Specifically, the target magnetic field image is input into the posture analysis neural network, so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array, and obtains the mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

[0083] And, the target magnetic field image is input into the posture analysis neural network, so that the second multi-processing network in the posture analysis neural network learns the key features in the target magnetic field image, and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

[0084] The training parameters of the pose analysis neural network can be: using a 3×3 convolution kernel, adding a BN layer after the convolution layer for normalization, and using ReLU as the activation function. The Adam optimizer is used, the learning rate is set to 0.1, the batch size is 256, and the number of iterations is 50.

[0085] Therefore, in one embodiment of the present application, the first multi-processing network includes multiple convolutional layers, two pooling layers and one fully connected layer; each convolutional layer uses a convolution kernel of size 3×3, and extracts magnetic field image features through the following steps: adding a BN layer for normalization after the convolution operation; using the ReLU activation function to achieve nonlinear transformation; adding Dropout regularization between hidden layers with a drop probability of 0.1; and outputting the feature map generated by the fully connected layer.

[0086] The method for determining the mapping relationship between the above-mentioned sensor and the object posture obtains the mapping relationship between the magnetic field sensor array and the object posture by performing object posture analysis on the magnetic field sensor array, so as to achieve accurate perception of the complete spatial posture of the object with high efficiency, low latency and low power consumption.

[0087] In one embodiment, if Figure 4 As shown, when it is necessary to obtain the mapping relationship between the magnetic field sensor array and the object posture, the following contents may be included:

[0088] S401, obtaining three-dimensional magnetic field distributions corresponding to at least two rectangular permanent magnets.

[0089] S402: Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction.

[0090] S403, collecting magnetic field data on the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain an initial magnetic field image corresponding to each magnetic field sensor.

[0091] S404 , performing invalid data trimming and key data enhancement on each initial magnetic field image to obtain a candidate magnetic field image corresponding to each initial magnetic field image.

[0092] S405 , performing magnetic field vector superposition on each candidate magnetic field image to obtain a target magnetic field image corresponding to at least two rectangular permanent magnets.

[0093] S406, based on the posture analysis neural network, perform object posture analysis on the target magnetic field image with respect to the magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0094] In one embodiment of the present application, the control logic and operation steps of the spatial magnetic field sensor are as follows: After the system is started, the ADC sampling parameters are configured and the static bias is measured, and the compensation value is written into the hardware module. The magnetic field data is collected and the neural network reasoning is triggered. After completing one pose estimation, the next cycle is entered until the preset number of times is reached. All estimation results are saved and output.

[0095] The method for determining the mapping relationship between the above-mentioned sensor and the object posture is to obtain the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets, and determine the magnetic field sensing array composed of magnetic field sensors, and then, based on the magnetic field sensing array, the magnetic field data is collected for the three-dimensional magnetic field distribution to obtain the target magnetic field image corresponding to at least two rectangular permanent magnets, so as to realize the object posture analysis of the magnetic field sensing array according to the target magnetic field image, and obtain the mapping relationship between the magnetic field sensing array and the object posture. According to the above content, it can be known that in the process of determining the mapping relationship between the magnetic field sensing array and the object posture, the present application obtains at least two rectangular permanent magnets distributed by an asymmetric magnetic field, overcomes the defect of insufficient degrees of freedom of traditional cylindrical permanent magnets, and realizes accurate magnetic field measurement for multiple targets and multiple postures; and, by forming the operation of obtaining the target magnetic field image by the magnetic field sensing array, data redundancy is effectively reduced, the complexity of data processing operations is reduced, and the compatibility of data is improved. Finally, by analyzing the object posture of the magnetic field sensing array, the mapping relationship between the magnetic field sensing array and the object posture is obtained, and the complete spatial posture of the object is accurately perceived with high efficiency, low latency and low power consumption.

[0096] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0097] Based on the same inventive concept, the embodiment of the present application also provides a device for determining the mapping relationship between a sensor and an object posture for implementing the method for determining the mapping relationship between the sensor and the object posture involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiment of the device for determining the mapping relationship between one or more sensors and the object posture provided below can be referred to the limitations of the method for determining the mapping relationship between the sensor and the object posture above, and will not be repeated here.

[0098] In one embodiment, Figure 5 As shown, a device for determining a mapping relationship between a sensor and an object posture is provided, comprising: an acquisition module 10, a determination module 20, a collection module 30 and an analysis module 40, wherein:

[0099] The acquisition module 10 is used to acquire the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution.

[0100] The determination module 20 is used to determine the magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction.

[0101] The acquisition module 30 is used to acquire magnetic field data of the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0102] The analysis module 40 is used to perform object posture analysis on the magnetic field sensor array according to the target magnetic field image, and obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0103] In one embodiment, magnetic field data is collected for the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain an initial magnetic field image corresponding to each magnetic field sensor;

[0104] Magnetic field vectors are superimposed on each initial magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0105] In one embodiment, invalid data trimming and key data enhancement are performed on each initial magnetic field image to obtain a candidate magnetic field image corresponding to each initial magnetic field image;

[0106] Magnetic field vectors are superimposed on each candidate magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0107] In one embodiment, based on a posture analysis neural network, an object posture analysis is performed on a target magnetic field image with respect to a magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array and the object posture.

[0108] In one embodiment, the target magnetic field image is input into a posture analysis neural network so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

[0109] In one embodiment, the target magnetic field image is input into a posture analysis neural network so that the second multi-processing network in the posture analysis neural network learns key features in the target magnetic field image and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

[0110] The device for determining the mapping relationship between the above-mentioned sensor and the object posture, by obtaining the three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets, and determining the magnetic field sensing array composed of magnetic field sensors, and then, based on the magnetic field sensing array, magnetic field data collection is performed on the three-dimensional magnetic field distribution to obtain the target magnetic field image corresponding to at least two rectangular permanent magnets, so as to realize the object posture analysis of the magnetic field sensing array according to the target magnetic field image, and obtain the mapping relationship between the magnetic field sensing array and the object posture. According to the above content, it can be known that in the process of determining the mapping relationship between the magnetic field sensing array and the object posture, the present application obtains at least two rectangular permanent magnets distributed by an asymmetric magnetic field, overcomes the defect of insufficient degrees of freedom of traditional cylindrical permanent magnets, and realizes accurate magnetic field measurement for multiple targets and multiple postures; and, by forming the operation of obtaining the target magnetic field image by the magnetic field sensing array, data redundancy is effectively reduced, the complexity of data processing operations is reduced, and data compatibility is improved. Finally, by analyzing the object posture of the magnetic field sensing array, the mapping relationship between the magnetic field sensing array and the object posture is obtained, and the complete spatial posture of the object is accurately perceived with high efficiency, low latency and low power consumption.

[0111] Each module in the above-mentioned device for determining the mapping relationship between the sensor and the object posture can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0112] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining a mapping relationship between a sensor and an object posture is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0113] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0115] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0116] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0117] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain target magnetic field images corresponding to at least two rectangular permanent magnets;

[0118] According to the target magnetic field image, the object posture analysis is performed on the magnetic field sensor array to obtain the mapping relationship between the magnetic field sensor array and the object posture.

[0119] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0120] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain an initial magnetic field image corresponding to each magnetic field sensor;

[0121] Magnetic field vectors are superimposed on each initial magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0122] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0123] Invalid data trimming and key data enhancement are performed on each initial magnetic field image to obtain a candidate magnetic field image corresponding to each initial magnetic field image;

[0124] Magnetic field vectors are superimposed on each candidate magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0125] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0126] Based on the posture analysis neural network, the target magnetic field image is subjected to object posture analysis for the magnetic field sensor array, and the mapping relationship between the magnetic field sensor array and the object posture is obtained.

[0127] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0128] The target magnetic field image is input into the posture analysis neural network, so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array, and obtains the mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

[0129] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0130] The target magnetic field image is input into the posture analysis neural network so that the second multi-processing network in the posture analysis neural network learns the key features in the target magnetic field image and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

[0131] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0132] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0133] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0134] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain target magnetic field images corresponding to at least two rectangular permanent magnets;

[0135] According to the target magnetic field image, the object posture analysis is performed on the magnetic field sensor array to obtain the mapping relationship between the magnetic field sensor array and the object posture.

[0136] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0137] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain an initial magnetic field image corresponding to each magnetic field sensor;

[0138] Magnetic field vectors are superimposed on each initial magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0139] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0140] Invalid data trimming and key data enhancement are performed on each initial magnetic field image to obtain a candidate magnetic field image corresponding to each initial magnetic field image;

[0141] Magnetic field vectors are superimposed on each candidate magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0142] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0143] Based on the posture analysis neural network, the target magnetic field image is subjected to object posture analysis for the magnetic field sensor array, and the mapping relationship between the magnetic field sensor array and the object posture is obtained.

[0144] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0145] The target magnetic field image is input into the posture analysis neural network, so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array, and obtains the mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

[0146] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0147] The target magnetic field image is input into the posture analysis neural network so that the second multi-processing network in the posture analysis neural network learns the key features in the target magnetic field image and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

[0148] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0149] Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution;

[0150] Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction;

[0151] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain target magnetic field images corresponding to at least two rectangular permanent magnets;

[0152] According to the target magnetic field image, the object posture analysis is performed on the magnetic field sensor array to obtain the mapping relationship between the magnetic field sensor array and the object posture.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0154] Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain an initial magnetic field image corresponding to each magnetic field sensor;

[0155] Magnetic field vectors are superimposed on each initial magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0157] Invalid data trimming and key data enhancement are performed on each initial magnetic field image to obtain a candidate magnetic field image corresponding to each initial magnetic field image;

[0158] Magnetic field vectors are superimposed on each candidate magnetic field image to obtain target magnetic field images corresponding to at least two rectangular permanent magnets.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0160] Based on the posture analysis neural network, the target magnetic field image is subjected to object posture analysis for the magnetic field sensor array, and the mapping relationship between the magnetic field sensor array and the object posture is obtained.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0162] The target magnetic field image is input into the posture analysis neural network, so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array, and obtains the mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0164] The target magnetic field image is input into the posture analysis neural network so that the second multi-processing network in the posture analysis neural network learns the key features in the target magnetic field image and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0166] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0167] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0168] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a mapping relationship between a sensor and an object posture, characterized in that: The method comprises: Obtaining a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution; Determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction; Performing magnetic field data acquisition on the three-dimensional magnetic field distribution based on the magnetic field sensing array to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets; According to the target magnetic field image, the magnetic field sensor array is subjected to object posture analysis to obtain a mapping relationship between the magnetic field sensor array and the object posture.

2. The method according to claim 1, characterized in that The method of collecting magnetic field data on the three-dimensional magnetic field distribution based on the magnetic field sensor array to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets includes: Based on the magnetic field sensor array, magnetic field data is collected for the three-dimensional magnetic field distribution to obtain an initial magnetic field image corresponding to each magnetic field sensor; Magnetic field vectors are superimposed on each of the initial magnetic field images to obtain target magnetic field images corresponding to the at least two rectangular permanent magnets.

3. The method according to claim 2, characterized in that The step of performing magnetic field vector superposition on each of the initial magnetic field images to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets includes: Performing invalid data trimming and key data enhancement on each of the initial magnetic field images to obtain a candidate magnetic field image corresponding to each of the initial magnetic field images; Magnetic field vectors are superimposed on each of the candidate magnetic field images to obtain a target magnetic field image corresponding to the at least two rectangular permanent magnets.

4. The method according to claim 1, characterized in that: The step of performing object posture analysis on the magnetic field sensor array according to the target magnetic field image to obtain a mapping relationship between the magnetic field sensor array and the object posture includes: Based on the posture analysis neural network, the target magnetic field image is subjected to object posture analysis for the magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array and the object posture.

5. The method according to claim 4, characterized in that The pose analysis neural network based on the target magnetic field image performs an object pose analysis for the magnetic field sensor array to obtain a mapping relationship between the magnetic field sensor array and the object pose, including: The target magnetic field image is input into the posture analysis neural network, so that the first multi-processing network in the posture analysis neural network performs object posture analysis on the magnetic field sensor array, and obtains the mapping relationship between the magnetic field sensor array output by the first multi-processing network and the object posture.

6. The method according to claim 4, characterized in that The method further comprises: The target magnetic field image is input into the posture analysis neural network so that the second multi-processing network in the posture analysis neural network learns the key features in the target magnetic field image and improves the accuracy of the mapping relationship output by the first multi-processing network through the key features.

7. A device for determining a mapping relationship between a sensor and an object posture, characterized in that: The device comprises: An acquisition module, used to acquire a three-dimensional magnetic field distribution corresponding to at least two rectangular permanent magnets; wherein the three-dimensional magnetic field distribution is an asymmetric magnetic field distribution; A determination module, used to determine a magnetic field sensing array composed of magnetic field sensors based on a preset sensor spacing and sensor arrangement direction; An acquisition module, used for acquiring magnetic field data of the three-dimensional magnetic field distribution based on the magnetic field sensing array, and obtaining a target magnetic field image corresponding to the at least two rectangular permanent magnets; The analysis module is used to perform object posture analysis on the magnetic field sensor array according to the target magnetic field image to obtain a mapping relationship between the magnetic field sensor array and the object posture.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images