A multi-dimensional optical information detection method and system

Abstract

The present invention relates to the field of optical detection technology, and particularly to a multi-dimensional optical information detection method and system. It includes obtaining reference optical information of multiple target optical signals as a marker set and a photocurrent response matrix as a signal set, establishing a multi-layer perceptron model to output multi-dimensional optical information, and randomly sampling the above data sets into a training set, a test set, and a validation set according to the same random seed function; training the multi-layer perceptron model and outputting it as a model file; using the validation set to validate the trained model file, and if the obtained accuracy rate is greater than the first threshold range, it is considered qualified, otherwise, repeat the above steps using a new random seed function for iterative model training and validation until the accuracy rate is greater than the first threshold range. The present invention not only realizes high-precision detection of multi-dimensional optical information such as polarization and wavelength, but also significantly improves the measurement accuracy and data processing efficiency, effectively solving the limitation that the traditional detection system can only achieve two-dimensional parameter detection.

Description

Technical Field

[0001] The present invention relates to the technical field of optical detection, and in particular to a multi-dimensional optical information detection method and system. Background Art

[0002] Existing optical detection systems can usually only detect the parameter of wavelength, and it is difficult to obtain the polarization information of light at the same time. And existing multi-dimensional optical detection systems usually require complex optical elements and precise calibration processes, resulting in complex system structures and high costs. Summary of the Invention

[0003] The present invention aims to at least improve one of the technical problems existing in the prior art. To this end, the present invention provides a multi-dimensional optical information detection method and system.

[0004] The technical solution of the present invention is as follows:

[0005] A multi-dimensional optical information detection method, which includes:

[0006] S1, obtaining the reference optical information and the photocurrent response matrix of multiple target optical signals;

[0007] S2, using the reference optical information as a label set and the photocurrent response matrix as a signal set to establish a multi-layer perceptron model to output multi-dimensional optical information;

[0008] S3, according to the same random seed function, randomly sampling and dividing the corresponding data set composed of the label set and the signal set into a training set, a test set and a validation set according to a first range ratio;

[0009] S4, training the multi-layer perceptron model, and the loss function is as follows:

[0010] ,

[0011] where S is the reference polarization information, λ is the reference wavelength information, is the polarization information predicted by the model, is the wavelength information predicted by the model, is the L2 regularization equation, and β is the regularization factor; its function is to enhance network optimization and prevent the network from overfitting;

[0012] When the minimum value of the loss function obtained by training with the training set is less than the set threshold, output it as the model file;

[0013] S5, using the validation set to verify the trained model file, and if the obtained accuracy rate is greater than the first threshold range, it is qualified; otherwise, repeat S3 to S4 using a new random seed function for iterative model training and verification until the accuracy rate is greater than the first threshold range.

[0014] In a possible technical solution, further, in S1, each element in the photocurrent response matrix is jointly determined by the polarization information S and the wavelength information λ of the reference optical information. By applying different bias voltages and collecting the current signals of each electrode of the multi-electrode thermoelectric thin film detector, a photocurrent response matrix characterizing multi-dimensional optical information is formed. The reference optical information of the i-th incident light beam is ; the photocurrent response matrix is expressed as follows:

[0015] ,

[0016] where S is the polarization information of the reference optical information, λ is the wavelength information of the reference optical information; U 1 , U 2 , …, U M are different bias voltage values; I 1 , I 2 , I 3 , …, I N are the current signals collected by the detector, and M and N are the electrode numbers.

[0017] In a possible technical solution, further, in S2, in the multi-layer perceptron model, the input layer receives the vectorized data of the photocurrent response matrix; each hidden layer includes a connection matrix, an activation function, and a bias term. The neural activity of the L-th layer is obtained by weighting the output of the previous layer by the connection matrix, adding the bias, and then passing through the activation function; the output layer maps through a read matrix and an activation function to finally output multi-dimensional optical information. The multi-layer perceptron model consists of an input layer, an output layer, and multiple hidden layers. Each hidden layer includes a fully connected layer and an optimization model layer, where the input layer is:

[0018] ,

[0019] The neural activity in the L-th layer of the hidden layer is expressed as:

[0020] ,

[0021] where is the connection matrix from the (L - 1)-th layer to the L-th layer, is the activation function of the L-th layer, is the bias between adjacent hidden layers, is the neural activity in the (L - 1)-th layer;

[0022] The output layer is:

[0023]

[0024] where For reading the matrix, is the activation function of the output layer, is the bias of the output unit, used to correct the bias of the output layer.

[0025] In a possible technical solution, further, each hidden layer includes a fully connected layer and a batch normalization layer, and the ReLU activation function is used in the hidden layer.

[0026] In a possible technical solution, further, in S1, the reference optical information includes the polarization S and wavelength λ of light.

[0027] According to the multi-dimensional optical information detection method of the embodiments of the present invention, through the polarization light sensitivity and wavelength sensitivity generated by the lattice symmetry breaking at the interface between the thermoelectric thin film and the substrate, combined with the deep learning neural network, the high-precision detection of multi-dimensional optical information such as polarization and wavelength is realized. This system does not require complex optical elements and spectrometer structures, is applicable to the detection of multi-dimensional optical information from the visible light to the mid-infrared band, and has the characteristics of simple structure, low cost, and high measurement accuracy. At the same time, the deep learning algorithm is used for optical information decoding, significantly improving the measurement accuracy and data processing efficiency, and effectively solving the limitation that the traditional detection system can only achieve two-dimensional parameter detection.

[0028] A multi-dimensional optical information detection system for implementing the multi-dimensional optical information detection method as described above, wherein it includes:

[0029] A light source for emitting a light beam;

[0030] An optical component for modulating the polarization state of the light beam;

[0031] A multi-electrode thermoelectric thin film detector that receives light beams with different polarization states to obtain reference optical information and generates current signals of different electrodes according to the reference optical information;

[0032] A signal acquisition and control unit for performing bias modulation on the multi-electrode thermoelectric thin film detector and collecting current signals to form a photocurrent response matrix;

[0033] A building module for using the reference optical information as a label set and the photocurrent response matrix as a signal set to build a multi-layer perceptron model;

[0034] A sorting module for randomly sampling and dividing the corresponding data set into a training set, a test set, and a validation set according to the same random seed function and in a first range ratio;

[0035] A training module for training the multi-layer perceptron model. When the minimum value of the loss function obtained through training with the training set is less than a set threshold, it outputs as a model file;

[0036] A verification module is used to verify the trained model file. If the obtained accuracy rate is greater than the first threshold range, it is considered qualified; otherwise, the iterative model training and verification are repeated using a new random seed function until the accuracy rate is greater than the first threshold range.

[0037] An output unit outputs multi-dimensional optical information.

[0038] In a possible technical solution, further, the multi-electrode thermoelectric thin film detector is a single crystal thin film detector with a thermoelectric effect and a lattice symmetry breaking at the interface with the substrate material. It has N signal output electrodes (N > 3), a bias electrode, and a common ground electrode, and is modulated by M biases with a certain step size.

[0039] In a possible technical solution, further, the signal acquisition and control unit includes:

[0040] A bias modulation circuit is used to modulate the bias of the multi-electrode thermoelectric thin film detector.

[0041] A current signal acquisition module is used to acquire current signals.

[0042] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the multi-dimensional optical information detection method as described above.

[0043] A computer storage medium stores instructions. When the instructions are executed on a computer, the computer is made to execute the multi-dimensional optical information detection method as described above.

[0044] The additional aspects and advantages of the present invention will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present invention. Description of the Drawings

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 It is a flowchart of the multi-dimensional optical information detection method according to an embodiment of the present invention;

[0047] Figure 2 It is a schematic diagram of the multi-dimensional optical information detection system according to an embodiment of the present invention;

[0048] Figure 3It is a polarization response characteristic curve diagram of a thermoelectric thin film detector in the multi-dimensional optical information detection method according to an embodiment of the present invention;

[0049] Figure 4 It is a schematic diagram of a multi-layer perceptron in the multi-dimensional optical information detection method according to an embodiment of the present invention;

[0050] Figure 5 It is a schematic diagram of a training loss curve of a deep learning framework in the multi-dimensional optical information detection method according to an embodiment of the present invention. Detailed implementation manners

[0051] The embodiments of the present invention will be described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. 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.

[0052] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there may also be a central element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be a central element at the same time.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0054] The terms "first", "second", "third", etc. in the specification and claims of the present application and the accompanying drawings are used to distinguish different objects and are not used to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a series of steps or units are included, or optionally, steps or units not listed are also included, or optionally, other steps or units inherent in these processes, methods, products or devices are also included.

[0055] Only parts related to the present application are shown in the drawings, not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. When the operations are completed, the process can be terminated, but there may also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0056] As used in this specification, the terms "component", "module", "system", "unit", etc. are used to denote computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable, an execution thread, a program, and / or one or more computers distributed between two or more computers. In addition, these units can be executed from various computer-readable media storing various data structures. A unit can communicate, for example, through local and / or remote processes according to signals having one or more data packets (e.g., data from a second unit interacting with a local system, a distributed system, and / or a network. For example, the Internet interacting with other systems through signals).

[0057] Embodiment 1

[0058] As shown in the attached Figure 1 drawing, this embodiment provides a multi-dimensional optical information detection method, which includes:

[0059] S1. Obtain the reference optical information and the photocurrent response matrix of multiple target optical signals, where the reference optical information of the i-th incident light beam is ; the photocurrent response matrix is expressed as follows:

[0060] ,

[0061] where S is the polarization information of the reference optical information, λ is the wavelength information of the reference optical information; U 1 , U 2 , …, U M are different bias voltage values; I 1 , I 2 , I 3 , …, I N are the current signals collected by the detector, and M and N are the electrode numbers.

[0062] S2. Use the reference optical information as the tag set and the photocurrent response matrix as the signal set to establish a multi-layer perceptron model to output multi-dimensional optical information, where the multi-dimensional optical information for decoding the i-th incident light beam is:

[0063] ,

[0064] where is the multi-layer perceptron, is the photocurrent response matrix of the i-th incident light beam;

[0065] S3. According to the same random seed function, the corresponding dataset composed of a tag set and a signal set is randomly sampled and divided into a training set, a test set, and a validation set in a ratio of the first range.

[0066] S4. Train the multi-layer perceptron model, and the loss function is as follows:

[0067] ,

[0068] where S is the reference polarization information, λ is the reference wavelength information, is the polarization information predicted by the model, is the wavelength information predicted by the model, is the L2 regularization equation, and β is the regularization factor; its function is to enhance network optimization and prevent the network from overfitting;

[0069] When the minimum value of the loss function obtained by training with the training set is less than the set threshold, output it as the model file;

[0070] S5. Use the validation set to verify the trained model file. If the obtained accuracy rate is greater than the first threshold range, it is qualified; otherwise, repeat S3 to S4 using a new random seed function for iterative model training and verification until the accuracy rate is greater than the first threshold range.

[0071] It should be noted that in S2, each element in the photocurrent response matrix is jointly determined by the polarization information S and the wavelength information λ of the reference optical information. By applying different bias voltages and collecting the current signals of each electrode of the multi-electrode thermoelectric thin-film detector, a photocurrent response matrix representing multi-dimensional optical information is formed.

[0072] It should be noted that in S2, in the multi-layer perceptron model, the input layer receives the vectorized data of the photocurrent response matrix; each hidden layer includes a connection matrix, an activation function, and a bias term. Among them, the neural activity of the L-th layer is obtained by weighting the output of the previous layer by the connection matrix, adding the bias, and then passing through the activation function; the output layer maps through the read matrix and the activation function and finally outputs multi-dimensional optical information. In this embodiment, the multi-layer perceptron model includes an input layer, an output layer, and multiple hidden layers. Among them, the input layer is:

[0073] ,

[0074] The neural activity in the L-th layer of the hidden layer is expressed as:

[0075] ,

[0076] where is the connection matrix from the (L - 1)-th layer to the L-th layer, is the activation function of the L-th layer, is the bias for adjacent hidden layers, is the neural activity in the (L - 1)-th layer;

[0077] The output layer is:

[0078]

[0079] where is the read matrix, is the activation function of the output layer, is the bias of the output unit, used to correct the bias of the output layer.

[0080] It should be noted that in S2 of this embodiment, each hidden layer includes a fully connected layer and a batch normalization layer, and the ReLU activation function is used in the hidden layer.

[0081] It should be noted that in S1 of this embodiment, the reference optical information includes the polarization S and wavelength λ of light.

[0082] In this embodiment, a set of specific implementation cases are provided. A multi-dimensional optical information detection system is used to detect multi-dimensional light. The multi-electrode thermoelectric thin film detector in the detection system is an 8-electrode system, and the bias voltage is modulated in steps of 0.02V, with a modulation range from -0.1V to 0.1V. Then M is 11 and N is 8.

[0083] Step 1: Use a multi-dimensional optical detection system based on the photothermal effect to collect reference optical information from multiple single-wavelength polarization-modulated optical signals, and obtain the photocurrent response matrix of the electrode thermoelectric thin film detector ;

[0084] As Figure 3 shown, it is the polarization response characteristic curve of the thermoelectric thin film detector; it can be seen from the figure the normalized response characteristics of the 8-electrode thermoelectric thin film detector to polarized light modulated at different angles by a λ / 4 polarizer with a central wavelength of 1550nm, indicating that the 8-electrode thermoelectric thin film detector has the ability to detect the polarization state of light;

[0085] where the reference optical information of the i-th incident light beam is ; The photocurrent response matrix is expressed as follows:

[0086] ,

[0087] The reference optical information is the wavelength λ and polarization S of the single-wavelength polarization-modulated optical signal.

[0088] Step 2: Take the reference light information as the tag set and the photocurrent response matrix as the signal set, and establish a multi-layer perceptron model (MLP) to output multi-dimensional light information. Among them, the multi-dimensional light information for decoding the i-th incident light is:

[0089] ,

[0090] where is the multi-layer perceptron, is the photocurrent response matrix;

[0091] Then input the photocurrent response matrix into the multi-layer perceptron as shown in Figure 4 . In the multi-layer perceptron with only 3 hidden layers and 256 neurons in each hidden layer, the multi-layer perceptron model consists of an input layer, an output layer, and hidden layers. Each hidden layer includes a fully connected layer and an optimization model layer. The ReLU activation function is used in the hidden layers, and the Sigmoid and Softmax functions are used as the activation functions in the output layer;

[0092] The input layer is:

[0093] ,

[0094] The neural activity in the L-th layer:

[0095] ,

[0096] where is the connection matrix from the (L - 1)-th layer to the L-th layer, is the activation function of the L-th layer, is the bias of the hidden layer;

[0097] The output layer is:

[0098] ,

[0099] where is the read matrix, is the activation function of the output layer, is the bias of the output unit, used to correct the bias of the output layer.

[0100] Step 3: According to the same random seed function, randomly sample the corresponding dataset composed of the tag set and the signal set and divide it into a training set, a test set, and a validation set according to a ratio of 4:3:3;

[0101] Step 4: Train the multi-layer perceptron (MLP) model, and the loss function is as follows:

[0102] ,

[0103] Among them, S is the reference polarization information, and λ is the reference wavelength information. is the polarization information predicted by the model. is the wavelength information predicted by the model. is the L2 regularization equation, and β is the regularization factor. In this embodiment, the role of using a multi-layer perceptron (MLP) model for training is to enhance network optimization and prevent the network from overfitting.

[0104] When the minimum value of the loss function obtained after training with the training set is less than the set threshold, it is output as a model file. In this embodiment, as Figure 5 shown, it is a schematic diagram of the training loss curve of the deep learning framework in the multi-dimensional optical information detection method of the present invention. In this example, through 5000 iterations of training, the threshold is 0.0001, and finally a model file is obtained.

[0105] Step Five: Use the validation set to verify the trained model file. If the obtained accuracy rate is greater than 98.6%, it is qualified; otherwise, repeat Steps Three to Four using a new random seed function for iterative model training and verification until the accuracy rate is greater than 98.6%.

[0106] According to the multi-dimensional optical information detection method of the embodiment of the present invention, through the polarization light sensitivity and wavelength sensitivity generated by the lattice symmetry breaking at the interface between the thermoelectric thin film and the substrate, combined with a deep learning neural network, high-precision detection of multi-dimensional optical information such as polarization and wavelength is achieved. This system does not require complex optical elements and spectrometer structures, is applicable to the detection of multi-dimensional optical information from the visible light to the mid-infrared band, and has the characteristics of simple structure, low cost, and high measurement accuracy. At the same time, using a deep learning algorithm for optical information decoding significantly improves the measurement accuracy and data processing efficiency, and effectively solves the limitation that traditional detection systems can only achieve two-dimensional parameter detection.

[0107] Embodiment 2

[0108] As Figure 2 shown, this embodiment provides a multi-dimensional optical information detection system for implementing the multi-dimensional optical information detection method as described above. Among them, it includes:

[0109] A light source for emitting a light beam. In this embodiment, the light source is a broadband light source that covers the light source from the visible light to the mid-infrared band, and can be a thermal radiation light source or a laser, and its polarization state can be modulated by a polarizer.

[0110] An optical component for modulating the polarization state of the light beam.

[0111] A multi-electrode thermoelectric thin film detector that receives light beams with different polarization states to obtain reference optical information and generates current signals of different electrodes according to the reference optical information.

[0112] A signal acquisition and control unit for modulating the bias voltage of the multi-electrode thermoelectric thin film detector and collecting current signals to form a photocurrent response matrix;

[0113] A building module for using the reference optical information as a tag set and the photocurrent response matrix as a signal set to build a multi-layer perceptron model. The multi-dimensional optical information of the i-th incident light beam is decoded as:

[0114] ,

[0115] where is a multi-layer perceptron, is the photocurrent response matrix;

[0116] A sorting module for randomly sampling and dividing the corresponding data set into a training set, a test set, and a validation set according to the same random seed function in a first range ratio;

[0117] A training module for training the multi-layer perceptron model. The loss function is as follows:

[0118] ,

[0119] where S is the reference polarization information, λ is the reference wavelength information, is the polarization information predicted by the model, is the wavelength information predicted by the model, is the L2 regularization equation, and β is the regularization factor. The role of using the multi-layer perceptron (MLP) model for training is to enhance network optimization and prevent the network from overfitting.

[0120] When the minimum value of the loss function obtained by training with the training set is less than the set threshold, it is output as a model file;

[0121] A verification module for verifying the trained model file. If the obtained accuracy rate is greater than the first threshold range, it is qualified; otherwise, the iterative model training and verification are repeated using a new random seed function until the accuracy rate is greater than the first threshold range;

[0122] An output unit for outputting multi-dimensional optical information.

[0123] It should be noted that in this embodiment, the optical components include:

[0124] A polarizer for selecting light with a specific polarization direction, allowing light in one direction to pass through and blocking light in other directions;

[0125] A wave plate for changing the polarization state of light through the birefringence effect, such as converting linearly polarized light into circularly polarized light or adjusting the polarization direction. Preferably, a λ / 4 wave plate or a λ / 2 wave plate is used;

[0126] A filter is used to select light of a specific wavelength, allowing a certain wavelength band to pass through while blocking other bands. By combining the above optical components, the polarization state and wavelength of the incident light are modulated.

[0127] It should be noted that in this embodiment, the multi-electrode thermoelectric thin film detector uses anisotropic thermoelectric materials and has the characteristic of being sensitive to light of different polarizations and wavelengths.

[0128] As a further preference of this embodiment, the material of the multi-electrode thermoelectric thin film detector is lead selenide (PbSe), and the substrate material is strontium titanate (SrTiO 3 ). The multi-electrode thermoelectric thin film detector is a single crystal thin film detector with thermoelectric effect and lattice symmetry breaking at the interface with the substrate material. It has N signal output electrodes (N > 3), a bias electrode, and a common ground electrode, and is modulated by M biases with a certain step size.

[0129] It should be noted that during the training process of the deep learning neural network, it includes:

[0130] Dataset classification: Shuffle the sequence of the labeled set signal set through the same random seed function, and sample the training set, test set, and validation set.

[0131] Deep learning training: Train based on the deep learning framework that combines data-driven and physical models to obtain a training model, and test it through the test set.

[0132] Verification test: Use the validation set to verify the trained model. If the accuracy is greater than 99%, it is qualified; otherwise, extract the unqualified data in the validation set into the training set for iterative verification.

[0133] It should be noted that in this embodiment, the signal acquisition and control unit includes:

[0134] A bias modulation circuit for modulating the bias of the multi-electrode thermoelectric thin film detector.

[0135] A current signal acquisition module for acquiring current signals.

[0136] A multi-dimensional optical information detection system in the embodiment of the present application is applicable to the detection of multi-dimensional optical information from visible light to mid-infrared bands, and has the advantages of simple structure, low cost, and high measurement accuracy.

[0137] A multi-dimensional optical information detection system in an embodiment of the present application may be a device, or a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a palmtop computer, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a personal computer (PC), etc. The embodiments of the present application do not make specific limitations.

[0138] A multi-dimensional optical information detection system in an embodiment of the present application may be a device with an operating system. The operating system may be the Android operating system, the iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0139] A multi-dimensional optical information detection system provided in an embodiment of the present application can implement Figure 1 each process implemented by a method embodiment of a multi-dimensional optical information detection method. To avoid repetition, it will not be elaborated here.

[0140] According to the multi-dimensional optical information detection system of an embodiment of the present invention, through the polarization light sensitivity and wavelength sensitivity generated by the lattice symmetry breaking at the interface between the thermoelectric thin film and the substrate, combined with a deep learning neural network, high-precision detection of multi-dimensional optical information such as polarization and wavelength is achieved. The system does not require complex optical elements and spectrometer structures, is applicable to the detection of multi-dimensional optical information from the visible light band to the mid-infrared band, and has the characteristics of simple structure, low cost, and high measurement accuracy. At the same time, a deep learning algorithm is used for optical information decoding, significantly improving the measurement accuracy and data processing efficiency, and effectively solving the limitation that traditional detection systems can only achieve two-dimensional parameter detection.

[0141] Optionally, an embodiment of the present application further provides an electronic device, including a processor, a memory, a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements each process of the above method embodiment of a multi-dimensional optical information detection method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0142] The embodiments of the present application further provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiments of the multi-dimensional optical information detection method and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0143] Wherein, the processor is the processor in the electronic device in the above-mentioned embodiment. 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, etc.

[0144] Embodiment 3

[0145] This embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the multi-dimensional optical information detection method as described above.

[0146] Embodiment 4

[0147] This embodiment provides a computer storage medium, wherein an instruction is stored in the computer storage medium. When the instruction is executed on a computer, the computer is enabled to execute the multi-dimensional optical information detection method as described above.

[0148] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention.

[0149] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example.

[0150] Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The mention of "embodiments" in this text means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. Those skilled in the art can explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0151] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A multi-dimensional optical information detection method, characterized in that: include: S1, obtaining reference light information and a photocurrent response matrix of multiple target light signals, wherein each element in the photocurrent response matrix is ​​determined by the polarization information S and the wavelength information λ of the reference light information, and by applying different bias voltages and collecting the current signals of each electrode of the multi-electrode thermoelectric thin film detector, a photocurrent response matrix representing multi-dimensional light information is formed; S2, using the reference light information as a label set and the photocurrent response matrix as a signal set, and establishing a multilayer perceptron model to output multidimensional light information; S3, according to the same random seed function, randomly sampling the corresponding data set consisting of the label set and the signal set in a first range ratio and dividing them into a training set, a test set and a validation set; S4, training the multilayer perceptron model, when the minimum value of the loss function obtained after training the training set is less than the set threshold, output it as a model file; S5, use the verification set to verify the trained model file, if the accuracy is greater than the first threshold range, it is qualified, otherwise use a new random seed function to repeat S3 to S4 for iterative model training and verification until the accuracy is greater than the first threshold range.

2. The multi-dimensional optical information detection method according to claim 1, characterized in that: In S2, in the multi-layer perceptron model, the input layer receives the vectorized data of the photocurrent response matrix; each hidden layer contains a connection matrix, an activation function, and a bias term, where the neural activity of the Lth layer is obtained by the output of the previous layer through the weighting of the connection matrix, superimposing the bias, and then passing through the activation function; The output layer reads the matrix and the activation function mapping, and finally outputs multi-dimensional light information.

3. The multi-dimensional optical information detection method according to claim 1, characterized in that: In S1, the reference light information of the i-th incident light is , the photocurrent response matrix It is expressed as follows: ， Where S is the polarization information of the reference light information, λ is the wavelength information of the reference light information; U1, U2, ..., U M are different bias voltage values; I1, I2, I3, ..., I N is the current signal collected by the detector, and M and N are the electrode numbers.

4. The multi-dimensional optical information detection method according to claim 2, characterized in that: In S2, the multilayer perceptron model includes an input layer, an output layer, and multiple hidden layers. for: ， The neural activity in the Lth layer in the hidden layer is expressed as: ， in is the connection matrix from layer L-1 to layer L, is the activation function of the Lth layer, is the bias of the adjacent hidden layer, is the neural activity in layer L-1; The output layer is: in To read the matrix, is the activation function of the output layer, is the bias of the output unit, which is used to correct the bias of the output layer.

5. A multi-dimensional optical information detection system, used to implement the multi-dimensional optical information detection method according to any one of claims 1 to 4, characterized in that: include: A light source for emitting a light beam; An optical component for modulating the polarization state of the light beam; A multi-electrode pyroelectric thin film detector receives light beams of different polarization states to obtain reference light information, and generates current signals of different electrodes according to the reference light information; A signal acquisition and control unit, used for bias modulating the multi-electrode pyroelectric thin film detector and collecting current signals to form a photocurrent response matrix; A building module, used to use the reference light information as a label set and the photocurrent response matrix as a signal set to build a multilayer perceptron model; A sorting module is used to randomly sample the corresponding data set according to the same random seed function and divide it into a training set, a test set and a validation set in a first range ratio; The training module is used to train the multi-layer perceptron model. When the minimum value of the loss function obtained through training of the training set is less than the set threshold, the model file is output; A verification module is used to verify the trained model file. If the accuracy rate is greater than the first threshold range, the model is qualified. Otherwise, a new random seed function is used to repeat iterative model training and verification until the accuracy rate is greater than the first threshold range. An output unit outputs multi-dimensional light information.

6. The multi-dimensional optical information detection system according to claim 5, characterized in that: The multi-electrode thermoelectric thin film detector is a single crystal thin film detector with thermoelectric effect and lattice symmetry breaking at the interface with the substrate material. It has N signal output electrodes: N>3, a bias electrode and a common ground electrode, and is modulated by M biases of a certain step length.

7. The multi-dimensional optical information detection system according to claim 5, characterized in that: The signal acquisition and control unit comprises: A bias modulation circuit is used for bias modulation of a multi-electrode pyroelectric thin film detector; The current signal acquisition module is used to acquire current signals.

8. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the multi-dimensional optical information detection method as claimed in any one of claims 1 to 4 when executing the computer program.

9. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the multi-dimensional optical information detection method according to any one of claims 1 to 4.

Images