Quantity monitoring method, device and equipment and readable storage medium

Abstract

The invention provides a quantity monitoring method, device and equipment and a readable storage medium. The method comprises the following steps: acquiring channel state information of a space to be measured; performing data processing on the channel state information to obtain first amplitude data of the channel state information; taking the first amplitude data as the input of a target calculation model, and obtaining a monitoring result used for indicating the number of target objects in the to-be-detected space; according to the scheme, the channel state information of the to-be-detected space is obtained, and the features of the target objects can be extracted, so that the number of the target objects passing through the to-be-detected space is determined; by processing the channel state information, the interference of multipath components can be filtered while the characteristics of the channel state information are reserved, so that the calculation pressure of performing calculation according to a target calculation model is reduced. The problems that in the prior art, under the scene that the crossing object density is large and the target objects in the image are seriously overlapped, the image segmentation difficulty is high, and the estimation precision of the number of the target objects is poor are solved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a quantity monitoring method, device, equipment and readable storage medium. Background Art

[0002] Monitoring the number of target objects is widely used in estimation scenarios. For example, crowd estimation is an application of crowd estimation in special scenarios. The current estimation method is mainly based on computer vision. By constructing a neural network to detect or track human bodies in images captured by the camera, the foreground of the crowd in the image is segmented, and various underlying physical signs such as crowd area and perimeter are extracted from the segmented foreground. Finally, the extracted features are regressed to the number of people in the image to detect the flow of people. However, in the face of increasingly complex scenes, the complexity of the neural network also increases, which increases the computational burden of the computer. In addition, in scenes with high density of crossing objects and serious overlap of target objects in the image, image segmentation is difficult and the accuracy of estimating the number of target objects is poor. Summary of the invention

[0003] The purpose of the present invention is to provide a quantity monitoring method, device, equipment and readable storage medium to solve the problem in the prior art that in a scene with a high density of crossing objects and serious overlap of target objects in the image, image segmentation is difficult and the estimation accuracy of the number of target objects is poor.

[0004] To achieve the above object, an embodiment of the present invention provides a quantity monitoring method, comprising:

[0005] Obtaining channel state information of the space to be measured;

[0006] Performing data processing on the channel state information to obtain first amplitude data of the channel state information;

[0007] Using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured;

[0008] The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

[0009] Further, the performing data processing on the channel state information to obtain first amplitude data of the channel state information includes:

[0010] The channel state information is processed using a MUSIC algorithm and a parallel factor model to obtain target channel state information;

[0011] The amplitude of the target channel state information is extracted to obtain first amplitude data of the channel state information.

[0012] Further, the using of the MUSIC algorithm and the parallel factor model to process the channel state information includes:

[0013] Using the frequency domain forward and backward smoothing MUSIC algorithm and the parallel factor model to perform multipath separation on the channel state information;

[0014] The interfering multipath components of the channel state information are filtered out to obtain the target channel state information.

[0015] Furthermore, the using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured includes:

[0016] Performing principal component analysis on the first amplitude data of the channel state information to obtain first target principal component data;

[0017] The first target principal component data is used as an input of the target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured.

[0018] Furthermore, the target calculation model is determined by the following method:

[0019] Obtaining a first number of crossings of the target object within a plurality of preset time periods captured by a camera set in the space to be tested;

[0020] Acquire second amplitude data of the channel state information in each of the preset time periods;

[0021] Performing principal component analysis on the second amplitude data to obtain second target principal component data;

[0022] Determine a mapping relationship between the first crossing quantity and second target principal component data corresponding to a preset time period;

[0023] Using the mapping relationship as training data to train the first computing model, to obtain the target computing model;

[0024] Among them, the first computing model is a model that uses a long short-term memory recurrent neural network combined with a one-dimensional fully convolutional neural network.

[0025] Further, the acquiring the channel state information of the space to be measured includes:

[0026] Acquire a first signal of the space to be measured; the first signal is a waveform signal serving as a communication signal and a perception signal;

[0027] To achieve the above object, an embodiment of the present invention provides a quantity monitoring device, which is characterized by comprising:

[0028] An acquisition module, used to acquire channel state information of the space to be measured;

[0029] A processing module, configured to perform data processing on the channel state information to obtain first amplitude data of the channel state information;

[0030] A calculation module, used for taking the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured;

[0031] The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

[0032] To achieve the above object, an embodiment of the present invention provides a quantity monitoring device, including a processor and a transceiver, wherein:

[0033] The transceiver is used to obtain channel state information of the space to be measured;

[0034] The processor is used to perform data processing on the channel state information to obtain first amplitude data of the channel state information;

[0035] Using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured;

[0036] The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

[0037] To achieve the above-mentioned purpose, an embodiment of the present invention provides a terminal device, including a transceiver, a processor, a memory, and a program or instruction stored in the memory and executable on the processor; when the processor executes the program or instruction, the method for monitoring the quantity as described above is implemented.

[0038] To achieve the above objective, an embodiment of the present invention provides a readable storage medium having a program or instruction stored thereon, wherein the program or instruction, when executed by a processor, implements the steps in the quantity monitoring method as described above.

[0039] The beneficial effects of the above technical solution of the present invention are as follows:

[0040] The number monitoring method of the embodiment of the present invention can extract the characteristics of the target object by acquiring the channel state information of the space to be detected, thereby determining the number of target objects passing through the space to be detected; by processing the channel state information, it can retain the characteristics of the channel state information while filtering out the interference of multipath components, thereby reducing the calculation pressure of calculating according to the target calculation model. The solution of the present invention does not need to extract features from the image captured by the camera, which solves the problem in the prior art that in scenes with high density of passing objects and serious overlap of target objects in the image, image segmentation is difficult and the estimation accuracy of the number of target objects is poor. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of a flow chart of a method for monitoring quantity according to an embodiment of the present invention;

[0042] Figure 2 A logical diagram of a method for monitoring quantity according to an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of a number monitoring device according to an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of the structure of a quantity monitoring device according to an embodiment of the present invention;

[0045] Figure 5 It is a schematic diagram of the structure of a terminal device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0047] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present invention. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0048] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0049] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0050] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0051] like Figure 1 As shown, a quantity monitoring method according to an embodiment of the present invention includes the following steps:

[0052] Step 101, obtaining channel state information of a space to be measured;

[0053] Step 102, performing data processing on the channel state information to obtain first amplitude data of the channel state information;

[0054] Step 103, using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured;

[0055] The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

[0056] In the embodiment of the present invention, the space to be tested is an indoor corridor environment;

[0057] Transmitters and receivers are evenly arranged on both sides of the corridor in the space to be tested;

[0058] The receiving device uses an array form with a spacing of about one wavelength, which is common in commercial (wireless) access points and routers; it can ensure the original communication capacity, performance and architecture, and realize the integration of communication and perception;

[0059] The transmission waveform of the transceiver link of the transmitting device and the receiving device is a first signal that serves as both a communication signal and a perception signal.

[0060] In the embodiment of the present invention, the distance between the transmitting device and the receiving device is 2.5m;

[0061] The antennas in the receiving device are arranged at a spacing of 5.4 cm;

[0062] The carrier frequency of the first signal is 5.4 GHz, the signal bandwidth is 80 MHz, and the signal transmission rate is 100 Hz.

[0063] In the embodiment of the present invention, the transmitting device continuously sends the first signal to the receiving device at a signal transmission rate of 100 Hz.

[0064] Optionally, the target object may be a person, a vehicle, a device or an animal.

[0065] In an embodiment of the present invention, the target object is a person in a crowd.

[0066] Optionally, the acquired channel state information (Channel State Information, CSI) of the measured space is a channel state information matrix.

[0067] Optionally, after interpreting the first signal, the receiving device unpacks the first signal according to a preamble code in a physical layer frame structure of a preset protocol to obtain the channel state information.

[0068] The quantity monitoring method of the embodiment of the present invention has certain advantages in scenes with a large density of target objects due to the penetrability of electromagnetic waves. It is less affected by the density of target objects and has a higher accuracy in quantity estimation.

[0069] The number monitoring method of the embodiment of the present invention can extract the characteristics of the target object by acquiring the channel state information of the space to be detected, thereby determining the number of target objects passing through the space to be detected; by processing the channel state information, it can retain the characteristics of the channel state information while filtering out the interference of multipath components, thereby reducing the calculation pressure of calculating according to the target calculation model. The solution of the present invention does not need to extract features from the image captured by the camera, which solves the problem in the prior art that in scenes with high density of passing objects and serious overlap of target objects in the image, image segmentation is difficult and the estimation accuracy of the number of target objects is poor.

[0070] Optionally, performing data processing on the channel state information to obtain first amplitude data of the channel state information includes:

[0071] The channel state information is processed using a MUSIC algorithm and a parallel factor model to obtain target channel state information;

[0072] The amplitude of the target channel state information is extracted to obtain first amplitude data of the channel state information.

[0073] The method for monitoring the number in the embodiment of the present invention can filter out the interference of multipath components by processing the channel state information, thereby reducing the amount of calculated data and reducing the calculation pressure.

[0074] Optionally, the adopting a MUSIC algorithm and a parallel factor model to process the channel state information includes:

[0075] Using the frequency domain forward and backward smoothing MUSIC algorithm and the parallel factor model to separate multipaths of the channel state information;

[0076] The interfering multipath components of the channel state information are filtered out to obtain the target channel state information.

[0077] Specifically, filtering out the interfering multipath component of the channel state information includes:

[0078] Unnecessary components in the multipath components of the channel state information are filtered out to obtain the target channel state information including only the required multipath components.

[0079] Optionally, the channel state information is processed using a MUSIC algorithm and a parallel factor model to obtain target channel state information, including:

[0080] Determine signal frequency domain carrier information according to the channel state information;

[0081] According to the channel state information matrix and the signal frequency domain carrier information, a frequency domain forward and backward smoothing MUSIC algorithm is used to estimate the delay parameter to obtain the signal delay information of the channel state information;

[0082] Constructing a parallel factorization model through the time delay information;

[0083] Decomposing and iterating the initial channel state information matrix by using the parallel factor decomposition model, filtering out multipath interference, and obtaining a target channel state information matrix;

[0084] According to the target channel state information, amplitude data of the channel state information is extracted.

[0085] The method for monitoring the number in the embodiment of the present invention can filter out the interference of multipath components by decomposing the channel state information, thereby reducing the amount of calculated data and reducing the calculation pressure.

[0086] Optionally, the using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured includes:

[0087] Performing principal component analysis on the first amplitude data of the channel state information to obtain first target principal component data;

[0088] The first target principal component data is used as an input of the target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured.

[0089] Optionally, the first target principal component data is a principal component amplitude sequence of a first level among principal component amplitude data of multiple levels of the channel state information.

[0090] The quantity monitoring method of the embodiment of the present invention performs principal component analysis on the first amplitude data of the channel state information through principal component analysis (PCA), thereby retaining the characteristics of the original information to the greatest extent possible and realizing denoising processing of the channel state information, while improving the data processing speed and accelerating the iteration speed and computational burden of the neural network.

[0091] It should be noted that since the entry and exit activities of the target object crossing the transceiver link vertically in any direction will cause continuous fluctuations in the antenna response amplitude, the crossing activity can be regarded as a time series problem by learning the features of the continuously changing amplitude to perform the classification task.

[0092] LSTM-FCN is a time series prediction model that combines long short-term memory (LSTM) and one-dimensional full convolutional neural network (FCN) to process time-dependent sequence data. Among them, LSTM is a powerful recurrent neural network that can capture long-term dependencies and changes in the situation in the input sequence. LSTM can remember, forget and use previous information. For the antenna response amplitude sequence that has been processed, an LSTM network with 128 hidden units is used for learning. A dropout layer with a dropout rate of 50% is added after the LSTM network to prevent overfitting; FCN is a neural network with a fixed receptive field that can independently process variable-length time series signals. It extracts spatial dependencies in time series data through a one-dimensional convolution sliding window. The specific structure uses a one-dimensional CNN with a convolution size of (3, 32) as a feature extraction module, followed by a batch normalization layer (BN) and a rectified linear unit (ReLU) layer, and then compresses all feature values ​​into a fixed-length vector through a global pooling operation. LSTM-FCN combines these two models together to extract and process the spatial dependencies in the time series, and finally obtains a global feature vector of fixed length for time series prediction.

[0093] Optionally, the target computing model is determined by the following method:

[0094] Obtaining a first number of crossings of the target object within a plurality of preset time periods captured by a camera set in the space to be tested;

[0095] Acquire second amplitude data of the channel state information in each of the preset time periods;

[0096] Performing principal component analysis on the second amplitude data to obtain second target principal component data;

[0097] Determine a mapping relationship between the first crossing quantity and second target principal component data corresponding to a preset time period;

[0098] Using the mapping relationship as training data to train the first computing model, to obtain the target computing model;

[0099] Among them, the first computing model is a model that uses a long short-term memory recurrent neural network combined with a one-dimensional fully convolutional neural network.

[0100] In one embodiment of the present invention, determining the mapping relationship between the first crossing quantity and the second target principal component data corresponding to the preset time period includes:

[0101] Using each of the first crossing numbers as a label;

[0102] Determine a mapping relationship between the label and the second target principal component data;

[0103] The second target principal component data is a principal component amplitude sequence of the first level among the principal component amplitude data of multiple levels of the second amplitude data.

[0104] In the embodiment of the present invention, training data is obtained to train the LSTM-FCN;

[0105] The training data can be obtained in the following ways:

[0106] The YOLOv5 detection algorithm is used to call the camera on the receiving device to process the time period when the crossing activity occurs and the number of crossing target objects, so as to obtain the corresponding relationship between the multiple time periods and the number of crossing target objects.

[0107] In an embodiment of the present invention, multiple groups of training data are used, and the training data include situations where 1, 2, 3 and 4 target objects pass through at the same time, and a cross entropy function is used as a loss function L for evaluating the difference between the predicted result and the actual result.

[0108] Optionally, the network's loss is calculated based on the predicted probabilities as follows:

[0109]

[0110] Among them, Ln is the loss of the nth sample, c is the category index, yic is the indicator symbol, when the true category of sample n is c, yic = 1, otherwise yic = 0, snc is the probability that sample n is predicted to be category c, and verification is performed after the model is trained.

[0111] Optionally, the acquiring channel state information of the space to be measured includes:

[0112] Acquire a first signal of the space to be measured; the first signal is a waveform signal serving as a communication signal and a perception signal;

[0113] The first signal is unpacked to obtain the channel state information.

[0114] like Figure 2 As shown, the method for monitoring quantity in an embodiment of the present invention includes:

[0115] Acquire the CSI received by the receiving devices arranged at both sides of the corridor;

[0116] Processing the CSI using a MUSIC algorithm and a parallel factor model to obtain first amplitude data of the CSI;

[0117] Analyze the first amplitude data of the CSI by a principal component analysis method to obtain a target principal component;

[0118] The target principal component is used as the input of the target calculation model to obtain the number of target objects in the space to be measured.

[0119] like Figure 3 As shown, a number of monitoring devices 300 in an embodiment of the present invention include:

[0120] An acquisition module 301 is used to acquire channel state information of a space to be measured;

[0121] A processing module 302 is used to perform data processing on the channel state information to obtain first amplitude data of the channel state information;

[0122] The calculation module 303 uses the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured;

[0123] The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

[0124] The number monitoring device of the embodiment of the present invention can extract the characteristics of the target object by acquiring the channel state information of the space to be detected, thereby determining the number of target objects passing through the space to be detected; by processing the channel state information, it can retain the characteristics of the channel state information while filtering out the interference of multipath components, thereby reducing the calculation pressure of calculating according to the target calculation model. The solution of the present invention does not need to extract features from the image captured by the camera, which solves the problem in the prior art that in scenes with high density of passing objects and serious overlap of target objects in the image, the image segmentation is difficult and the estimation accuracy of the number of target objects is poor.

[0125] like Figure 4 As shown, a quantity monitoring device 400 according to an embodiment of the present invention includes a processor 410 and a transceiver 420, wherein:

[0126] The transceiver is used to obtain channel state information of the space to be measured;

[0127] The processor is used to perform data processing on the channel state information to obtain first amplitude data of the channel state information;

[0128] Using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured;

[0129] The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

[0130] The number monitoring device of the embodiment of the present invention can extract the characteristics of the target object by acquiring the channel state information of the space to be detected, thereby determining the number of target objects passing through the space to be detected; by processing the channel state information, it can retain the characteristics of the channel state information while filtering out the interference of multipath components, thereby reducing the calculation pressure of calculating according to the target calculation model. The solution of the present invention does not need to extract features from the image captured by the camera, which solves the problem in the prior art that in scenes with high density of passing objects and serious overlap of target objects in the image, image segmentation is difficult and the estimation accuracy of the number of target objects is poor.

[0131] A terminal device according to another embodiment of the present invention, such as Figure 5 As shown, it includes a transceiver 510, a processor 500, a memory 520, and a program or instruction stored in the memory 520 and executable on the processor 500; when the processor 500 executes the program or instruction, the above-mentioned monitoring method applied to quantity is implemented.

[0132] The transceiver 510 is used to receive and send data under the control of the processor 500 .

[0133] Among them, Figure 5 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 500 and various circuits of memory represented by memory 520 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 510 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface 530 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0134] The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 can store data used by the processor 500 when performing operations.

[0135] A readable storage medium of an embodiment of the present invention stores a program or instruction thereon. When the program or instruction is executed by a processor, the steps in the quantity monitoring method as described above are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0136] The processor is a processor in the number of monitoring devices described in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0137] It should be further explained that the terminals described in this specification include but are not limited to smart phones, tablet computers, etc., and many of the functional components described are called modules in order to more particularly emphasize the independence of their implementation methods.

[0138] In the embodiment of the present invention, module can be implemented with software so that it can be executed by various types of processors. For example, an executable code module of an identification can include one or more physical or logical blocks of computer instructions, for example, it can be constructed as an object, process or function. Nevertheless, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different positions, and when these instructions are logically combined together, it constitutes a module and realizes the specified purpose of the module.

[0139] In fact, executable code module can be a single instruction or many instructions, and can even be distributed on a plurality of different code segments, distributed among different programs, and distributed across a plurality of memory devices. Similarly, operating data can be identified in the module, and can be implemented and organized in the data structure of any appropriate type according to any appropriate form. The operating data can be collected as a single data set, or can be distributed in different locations (including on different storage devices), and can only be present on a system or network as an electronic signal at least in part.

[0140] When a module can be implemented by software, considering the level of existing hardware technology, a person skilled in the art can build a corresponding hardware circuit to implement the corresponding function of the module that can be implemented by software without considering the cost. The hardware circuit includes a conventional very large scale integration (VLSI) circuit or gate array and existing semiconductors such as logic chips, transistors, or other discrete components. The module can also be implemented by a programmable hardware device, such as a field programmable gate array, a programmable array logic, a programmable logic device, etc.

[0141] The above exemplary embodiments are described with reference to the accompanying drawings, and many different forms and embodiments are feasible without departing from the spirit and teachings of the present invention. Therefore, the present invention should not be constructed as a limitation of the exemplary embodiments proposed herein. More specifically, these exemplary embodiments are provided so that the present invention will be perfect and complete, and the scope of the present invention will be conveyed to those who are familiar with the technology. In these figures, the component sizes and relative sizes may be exaggerated for clarity. The terms used here are only based on the purpose of describing specific exemplary embodiments and are not intended to be limiting. As used herein, unless the text clearly indicates otherwise, the singular forms "one", "an" and "the" are intended to include these multiple forms. It will be further understood that the terms "including" and / or "comprising" when used in this specification indicate the presence of the features, integers, steps, operations, components and / or components, but do not exclude the presence or increase of one or more other features, integers, steps, operations, components, components and / or their groups. Unless otherwise indicated, when stated, a range of values ​​includes the upper and lower limits of that range and any subranges therebetween.

[0142] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A quantity monitoring method, characterized in that: include: Obtaining channel state information of the space to be measured; Performing data processing on the channel state information to obtain first amplitude data of the channel state information; Using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured; The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

2. The method for monitoring quantity according to claim 1, characterized in that: The performing data processing on the channel state information to obtain first amplitude data of the channel state information includes: The channel state information is processed using a MUSIC algorithm and a parallel factor model to obtain target channel state information; The amplitude of the target channel state information is extracted to obtain first amplitude data of the channel state information.

3. The method for monitoring quantity according to claim 2, characterized in that: The adopting of the MUSIC algorithm and the parallel factor model to process the channel state information includes: Using the frequency domain forward and backward smoothing MUSIC algorithm and the parallel factor model to perform multipath separation on the channel state information; The interfering multipath components of the channel state information are filtered out to obtain the target channel state information.

4. The method for monitoring quantity according to claim 1, characterized in that: The step of using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured includes: Performing principal component analysis on the first amplitude data of the channel state information to obtain first target principal component data; The first target principal component data is used as an input of the target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured.

5. The method for monitoring quantity according to claim 1, characterized in that: The target calculation model is determined by the following method: Obtaining a first number of crossings of the target object within a plurality of preset time periods captured by a camera set in the space to be tested; Acquire second amplitude data of the channel state information in each of the preset time periods; Performing principal component analysis on the second amplitude data to obtain second target principal component data; Determine a mapping relationship between the first crossing quantity and second target principal component data corresponding to a preset time period; Using the mapping relationship as training data to train the first computing model, to obtain the target computing model; Among them, the first computing model is a model that uses a long short-term memory recurrent neural network combined with a one-dimensional fully convolutional neural network.

6. The method for monitoring quantity according to claim 1, characterized in that: The acquiring the channel state information of the space to be measured includes: Acquire a first signal of the space to be measured; the first signal is a waveform signal serving as a communication signal and a perception signal; The first signal is unpacked to obtain the channel state information.

7. A quantity monitoring device, characterized in that: include: An acquisition module, used to acquire channel state information of the space to be measured; A processing module, configured to perform data processing on the channel state information to obtain first amplitude data of the channel state information; A calculation module, used for taking the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured; The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

8. A quantity monitoring device, characterized in that: include: transceivers and processors; The transceiver is used to obtain channel state information of the space to be measured; The processor is used to perform data processing on the channel state information to obtain first amplitude data of the channel state information; Using the first amplitude data as an input of a target calculation model to obtain a monitoring result indicating the number of target objects in the space to be measured; The target calculation model is used to characterize the corresponding relationship between the first amplitude data of the channel state information and the number of the target objects.

9. A terminal device, comprising: A transceiver, a processor, a memory, and a program or instruction stored in the memory and executable on the processor; characterized in that when the processor executes the program or instruction, the method for monitoring the quantity as described in any one of claims 1 to 6 is implemented.

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

Images