212results about How to "Fast recognition" patented technology

The invention discloses an overhead line system cable state real-time monitoring method and sensing system based on distributed optical fiber sensing. The Mach-Zehnder interference and phi-OTDR fusion type distributed optical fiber sensing system comprises a first light source, a second light source, a Mach-Zehnder interferometer, a phi-OTDR and a data acquisition and processing module. Raman amplifiers are arranged at the two ends of the Mach-Zehnder interferometer, so that the sensing distance is prolonged; the optical fiber sensing system extracts an interference optical signal and a backward Rayleigh scattering optical signal corresponding to a fault event after phase modulation when the fault event occurs; then processing the extracted backward Rayleigh scattering light signal to obtain intensity change information of a fault event, and demodulating the position of the fault event; and sending the two-dimensional optical signal into a pre-trained Swin Transform network model to extract a time domain feature, a frequency domain feature and a spatial domain feature, and identifying the type of a fault event through a classifier.

The invention provides a coal rock recognition method and system based on image and XRF spectral information fusion, and relates to the technical field of geological rock recognition and classification, and the method comprises the steps: obtaining a to-be-detected coal rock image; inputting the coal rock image into an image detection model to obtain suspicious coal gangue and position information thereof; the method comprises the following steps: performing element testing on suspicious coal gangue, acquiring element information, inputting the element information and a suspicious coal gangue image into a fusion classification model, extracting element features through an element feature extraction module, extracting image features through an image feature extraction module, performing matrix multiplication on the image features and the element features in an initial fusion module, and performing fusion classification on the suspicious coal gangue; and performing deep fusion on the similarity matrix and the image features to obtain initial fusion features, and obtaining a classification result of the coal / coal gangue by using the initial fusion features.

The invention relates to the technical field of information security, in particular to an abnormal network traffic detection method. Comprising the following steps: S1, obtaining to-be-detected network flow data, and performing preprocessing to form a to-be-detected data set; s2, constructing an abnormal network traffic detection model, specifically, S21, acquiring original abnormal network traffic data, and performing preprocessing to form an original data set; s22, constructing a teacher model, selecting a BiLSTM model as a basic structure of the teacher model, and training the BiLSTM model by using the original data set to obtain the teacher model; s23, constructing a student model, selecting a one-way LSTM model as the student model, and training the one-way LSTM model by adopting a knowledge distillation algorithm to obtain an abnormal network traffic detection model; s3, inputting a to-be-detected data set into the abnormal network traffic detection model, and outputting a detection result; and the detection speed and the operation efficiency are improved.

The invention discloses a counting method for system terminal equipment in an NATed network based on an optical network, and belongs to the field of data communication. According to the method, Windows system terminal equipment in a home internal network is monitored and counted in real time by utilizing the high-speed transmission capability and the low-delay characteristic of an optical network; the number of the terminal devices is counted based on the change rate of the IP-ID sequence along with the arrival time of the packet, and different terminal devices are accurately distinguished by analyzing the monotonicity of the IP-ID field in the DNS request packet and the difference of the increase change rate of the IP-ID sequence between different devices. According to the invention, the number of terminal devices can be effectively identified, and the insight ability of an operator for user demands is improved, so that a more personalized service and resource allocation scheme can be provided. Meanwhile, a fixed mode algorithm is adopted, consumption of computing resources is reduced, the recognition speed is increased, the method is very suitable for the scene of recognizing the number of real-time terminal devices, and the stability and reliability of the system are further enhanced.

The invention relates to the technical field of engineering geological rock recognition and classification, and discloses a coal rock recognition method and system based on audio and vibration signal fusion, and the method comprises the steps: obtaining a vibration signal and an audio signal in a coal mining process; respectively carrying out de-noising processing on the vibration signal and the audio signal; cutting the denoised signal according to a set time interval to obtain a plurality of vibration signal segments and a plurality of audio signal segments; performing normalization processing on all the vibration signal segments and all the audio signal segments; the normalized signal segments are input into the trained coal rock recognition model at the corresponding moment according to the time sequence, the trained coal rock recognition model outputs a coal rock recognition result, and the input end of the third-class hidden layer of the coal rock recognition model at the later moment is connected with the output end of the third-class hidden layer of the coal rock recognition model at the previous moment. The method has the advantages of high automation degree, high identification speed, high lithology identification accuracy, low cost and the like.

The invention discloses a personnel identification method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a face image of a target object and a feature matrix of a comparison object; performing face region extraction on the face image to obtain a face key part of the target object; performing feature extraction on the face image and the face key parts to obtain a feature point matrix; according to the feature point matrix and the feature matrix, sequentially processing based on distance similarity to obtain a similarity score of each target area of the target object and the comparison object; and carrying out integration operation on the similarity scores of all the target areas to obtain target identification scores of the target object and the comparison object. According to the method, through a multi-layer and multi-region feature extraction and similarity calculation method, the recognition accuracy and robustness of the target object and the comparison object are remarkably improved, meanwhile, the recognition efficiency is improved, and the method has good flexibility and expandability and can be widely applied to the technical field of data processing.

The invention provides heterogeneous computing hardware and a sensitive data high-speed identification method and system, and is applied to the field of sensitive data identification. The heterogeneous computing hardware comprises at least one type of programmable logic unit core, and the number of each type of programmable logic unit core is at least one; each programmable logic unit core configures different data matching rules based on the characteristics of to-be-processed network data so as to execute different data matching modes; and when the number of the programmable logic unit cores is multiple, the multiple programmable logic unit cores are mutually independent so as to realize parallel operation. According to the method and the device, multiple programmable logic unit cores are arranged, each programmable logic unit core can execute different data matching modes, so that parallel processing of different data types can be realized, the number of each programmable logic unit core is at least one, and parallel processing of the same data type can be further realized; and the sensitive data identification speed is greatly improved.

The invention relates to a deep learning-driven carbon chip automatic detection and quantitative analysis method, which comprises the following steps: (1) digital image acquisition: making a carbon chip sample subjected to experimental treatment into a microscope glass slide, and generating a digital image by using a high-resolution glass slide scanner; (2) establishing an annotation data performing format conversion and annotation on the obtained digital image, and clearly marking outlines of carbon scraps, lycopodium clavatum and other impurities in the image so as to establish the annotation database; (3) deep learning model training: dividing the annotation database into a training set, a verification set and a test set; and (4) performing automatic identification and quantitative analysis on the carbon chips: performing automatic identification on the digital image of the sample to be identified by adopting a deep learning model passing precision verification, counting the number of the carbon chips and the lycopodium spores, calculating other statistical indexes of the carbon chips, and further performing quantitative reconstruction analysis on a fire event. The method has the characteristics of high precision, high speed, high universality, simplicity and convenience in operation and suitability for statistics of a large number of samples.

The invention discloses a pavement crack real-time detection and classification method adopting a digital twin technology, and belongs to the technical field of urban intelligent operation and maintenance. In order to detect and classify pavement cracks in real time, the method comprises the following steps: performing image quality enhancement processing on an acquired image matrix to obtain a quality-enhanced image matrix; carrying out image pixel updating on the quality-enhanced image matrix to obtain a pixel-updated image matrix, and storing the pixel-updated image matrix as a pixel-updated pavement image; all images including cracks, spalling, pit slots and upheaval diseases are selected and marked, and a data set for real-time pavement crack detection is obtained; a pavement crack rapid identification method integrating multi-model features is constructed; constructing a road digital twinborn model based on a pavement crack rapid identification method integrating multi-model features; and establishing a pavement crack classification method based on the obtained road digital twin model. The pertinence and effectiveness of road repair are improved, the service life of the road is prolonged, and the total cost of road maintenance is reduced.

A portable electronic nose used for beer identification and based on a convolutional neural network is characterized in that a vertical annular gas sensor array is arranged, the gas sensor array is connected with a preprocessing module through an ADC analog-to-digital converter, and the preprocessing module is connected with a beer identification module; the gas sensor array is used for collecting beer gas signals and transmitting the beer gas signals to the preprocessing module; the preprocessing module is used for preprocessing the beer gas signal and then transmitting preprocessed beer gas data to the beer identification module; and the beer identification module is a two-dimensional convolutional neural network model CC-2DCNN based on a channel attention mechanism and a cosine annealing hot restart strategy, and is used for carrying out beer identification according to the beer gas data and outputting a beer identification result. The method has the advantages that accuracy and reliability of beer identification are improved, and a reliable solution is provided for detecting counterfeit beer and preventing beer deterioration.

The invention relates to an in-vehicle gesture recognition method and system based on a directional loudspeaker, and the method comprises the following steps: collecting gesture data through the directional loudspeaker, and extracting an audio clip containing a gesture, thereby obtaining a gesture waveform; preprocessing the gesture waveform; sTFT transformation is carried out on the preprocessed gesture waveform, the gesture waveform is converted into a spectrogram, and the spectrogram is evenly cut and then serves as input of a gesture recognition model; and gesture recognition is carried out by using a gesture recognition model constructed based on the ResNet network. Compared with the prior art, the method has the advantages of high recognition accuracy, high recognition speed and the like.

The invention relates to the technical field of risk early warning, and particularly discloses a substation risk early warning method and system based on an edge AI analyzer, and the method comprises the steps: determining the position of the edge AI analyzer and the application range of the edge AI analyzer according to a determined gunlock position; the method comprises the following steps: receiving a video acquired by a gun camera regularly based on an edge AI analyzer, performing target positioning on the video, determining a target frame, identifying contents in the target frame based on a preset convolution feature table, and outputting a risk type; and when the output of identifying the content in the target frame based on the preset convolution feature table is null, identifying the content in the target frame based on an AI identification model in the edge AI analyzer, and outputting a risk type. The local identification module based on the convolution kernel table and the AI identification module based on the AI model are arranged in the edge AI analyzer, the transformer substation risk is identified in a gradient mode, the identification speed is high, and the identification range is large.

The embodiment of the invention discloses a parameter identification method for a photovoltaic cell. The method comprises the following steps: constructing an equivalent circuit model and an objective function of a double-diode photovoltaic cell; identifying the parameters of the photovoltaic cell according to an NOA algorithm, and determining a current optimal parameter combination; based on the objective function, determining an output voltage and an output current corresponding to the current optimal parameter combination, fitting the output voltage and the output current with corresponding actual measurement values, and determining a fitting degree value; and when the fitting degree value meets a threshold range and the NOA algorithm converges, determining an optimal photovoltaic cell parameter according to a corresponding current optimal parameter combination when the NOA algorithm converges. According to the method, the accurate photovoltaic cell model is constructed, the efficient NOA algorithm is adopted for parameter identification, the target function is combined for error evaluation and optimization, and rapid and accurate identification of the photovoltaic cell parameters is effectively achieved.

The invention provides a transformer substation planning and site selection method based on artificial intelligence. The method comprises the following steps: (1) designing a real-time topographic feature recognition model and deeply researching an activation function and an optimization strategy; a1, setting a plurality of specific scenes; obtaining a real-time topographic feature recognition model; a2, storing an activation function; a3, establishing an optimization strategy for reducing the complexity and calculation amount of the model; a4, evaluating the performance of the real-time topographic feature recognition model; (2) formulating a diversified training strategy and a data enhancement scheme; (3) performing data processing in combination with unmanned aerial vehicle data, and extracting landform and ground feature category features in a complex terrain environment; (4) identifying and analyzing unknown landform data through the real-time topographic feature identification model; (5) constructing an adaptive scoring model; and (6) providing a substation site selection strategy according to the landform data and the adaptive scoring model system. The invention provides an efficient substation planning and site selection method by using an artificial intelligence technology.

The invention provides a live broadcast content auditing method, device and equipment and a computer readable medium, and the method comprises the steps: extracting a cut frame from a live broadcast video stream, taking the extracted cut frame as a to-be-audited image, calling a text detection model to carry out text detection on the to-be-audited image, and cutting the to-be-audited image according to the detected text. The method comprises the following steps: acquiring a to-be-audited image to obtain at least one character image, calling a lightweight text recognition model to perform text recognition on the character image for each character image to obtain a text recognition result, and performing violation judgment according to all the text recognition results corresponding to the to-be-audited image to obtain a violation judgment result. And then processing the live broadcast video stream which is judged to be illegal and / or the live broadcast room of the live broadcast video stream according to a preset illegal live broadcast processing rule, thereby realizing automatic auditing and processing of text content in a live broadcast picture, and effectively preventing spreading of illegal content.

A glass surface stain image recognition method applied to a window-cleaning robot relates to the technical field of image recognition, and comprises the following steps: acquiring image data, environmental perception data and tactile data of a target glass area according to a sensor terminal of the window-cleaning robot; constructing a shooting parameter lookup table, and updating shooting parameters of the sensor terminal in real time according to the environment sensing data in the current acquisition period and the shooting parameter lookup table; constructing a stain feature recognition model, and performing pre-estimated stain type labeling on the image data of the current acquisition period according to the stain feature recognition model; and performing correctness detection on the estimated stain type marked in the target glass area according to the tactile data of the current acquisition period, if a wrong stain type exists in the target glass area, obtaining the recognition correct rate of the stain feature recognition model, and performing local feature enhanced recognition operation or retraining operation according to the recognition correct rate. And the stain identification capability of the window cleaning robot is obviously improved.

The invention relates to the field of computer vision, in particular to a traffic target recognition method based on 4D millimeter wave radar and vision fusion, which comprises the following steps: clustering radar point cloud data by adopting a density-based clustering algorithm, and expanding the center coordinate of each cluster output by the clustering algorithm to obtain an expansion frame; converting the extension value into a two-dimensional visual coordinate system based on a conversion matrix between a radar coordinate and a camera coordinate to obtain an interested target frame under the visual coordinate system; fusing the interested target frame in the visual coordinate system with image data collected by a camera, and taking a fused feature map as the input of a YOLOV8 target detection model; the YOLOV8 target detection model establishes detection branches according to the number of interested target frames, and each branch detects an image of one interested frame part in the fused feature map; according to the method, all-weather sensing work can be realized, the traffic target identification speed is high, and the precision is high.

The invention provides a vehicle target detection method based on YOLOv7, relates to the field of image processing technology and automatic driving, and is used for solving the problems of low detection accuracy, poor real-time performance and the like of automatic driving in a complex environment. The method comprises the following steps: step 1, improving a backbone network structure of YOLOv7, and replacing a convolutional layer in the YOLOv7 with PConv so as to reduce calculation redundancy of an algorithm; 2, optimizing a feature extraction module, and designing an SPPFCSPC module to reduce the receptive field and improve the model speed and the feature information extraction capability; and 3, introducing an ECA attention mechanism, and enhancing the feature extraction capability of the model. And a fourth step of adjusting a feature output stage, removing a 20 * 20 feature layer, and replacing the 20 * 20 feature layer with a 160 * 160 small target detection layer so as to improve the detection capability of a small target and strengthen shallow feature extraction. And finally, using an EIOU loss function to accelerate the convergence speed of the model.

The invention provides a feeder line terminal equipment short circuit fault rapid identification method, which utilizes a first half wave breaking phenomenon to carry out instant fault detection and identification, and comprises the following steps: establishing a fault database in a fault identification process, a longitudinal coordinate ifind at a curve intersection point of the shortest operation time t1 necessary for terminal equipment and a fault current waveform curve i2 is taken as a current instantaneous setting value S2, an absolute value of a curve slope of an intersection point p of the ifind and the fault current waveform curve i2 is taken as a setting value K2 = di2 (t) / dt of a current change rate, and fault current characteristic information (S2, K2) is stored in a fault library as a rapid identification criterion. The short-circuit fault database is continuously updated along with the fault identification process, and the short-circuit fault database is compared with the criterion stored in the fault database when the fault occurs, so that the fault identification can be completed in a 1 / 4 period, that is, the identification of the fault current can be completed in t2 time.

The invention relates to the technical field of indoor energy consumption supervision, and particularly discloses a water, electricity and gas security centralized management method and system in an Internet of Things vision field, and the method comprises the steps: determining the data integrity of each management unit according to monitoring equipment installed in each building unit; determining energy consumption data of each management unit based on monitoring equipment, analyzing the energy consumption data, and determining the core degree of each management unit; and receiving a management request containing a management level input by a management party, determining a monitoring data volume according to the management level, selecting a monitoring data volume management unit based on the data integrity and the core degree, and obtaining energy consumption data of the monitoring data volume management unit. According to the method, several limited management units are randomly selected in combination with two parameters of data integrity and core degree, data acquisition and identification are carried out, an original global scheme is converted into a sampling scheme, and the identification speed is greatly improved on the basis of ensuring certain identification accuracy.

The invention discloses a complex scene traffic network congestion identification method based on an unmanned aerial vehicle and data fusion, and belongs to the technical field of traffic network congestion identification. The problem that a traditional traffic jam identification method in the prior art is low in identification efficiency and is difficult to adapt to complex traffic scenes is solved. According to the method, a visible light image and an infrared image in a complex traffic scene are collected, image feature extraction and matching are carried out, and a fused image is obtained; constructing a data set, inputting the data set into the established basic model, auxiliary model and strengthening model for training, fusing loss functions of the three models, and training the three models by adopting an overall loss function to obtain an optimal model; and adjusting the enhancement coefficient and optimizing the optimal model to obtain the optimal model with the maximum accuracy rate, namely the final optimal model, and outputting congestion area positioning by the optimal model. The method effectively improves the recognition performance of the traffic network congestion recognition model, and can be applied to traffic network congestion recognition in complex scenes.

The invention relates to a signal control scheme identification method, system and device based on vehicle passing data, and a medium. The method comprises the following steps: obtaining vehicle passing data classified according to a traffic flow direction; carrying out self-correlation analysis processing on the vehicle passing data in each flow direction, and carrying out grouping processing on the obtained signal period data to obtain a division scheme of a signal control time period; performing curve fitting on the vehicle passing data of each flow direction in each signal control time period in each intersection, and identifying a maximum value point and corresponding moment data of each fitted curve; by comparing the time data of the maximum value point of the fitting curve of each flow direction in the same time period, the traffic flows of different flow directions with deviations smaller than a set threshold value are classified into the same signal phase, and graph superposition is carried out on the fitting curves of different signal phases in the same signal period. And determining the phase sequence and the phase duration of each signal phase based on the maximum value point and the intersection point of the fitted curve after superposition. The technical problem that in the prior art, a signal control scheme is poor in recognition effect is solved.

The invention relates to a method for early warning of the development state of road internal voids, an electronic device and a storage medium, and belongs to the technical field of road internal monitoring. In order to solve the problem of timely and accurate early warning of road internal voids, the invention includes using a three-dimensional ground penetrating radar to collect road internal images, annotating the collected images, obtaining a data set for road internal void identification, constructing a road internal void identification model, constructing a loss function between a basic model, an auxiliary model, a first reinforcement model and a second reinforcement model for road internal void identification, and constructing an overall loss function; using the data set for road internal void identification to train the basic model, the auxiliary model, the first reinforcement model and the second reinforcement model for road internal void identification, and obtaining a trained basic model for road internal void identification as a road internal void intelligent identification model; constructing a digital twin model based on the road internal void intelligent identification model; and establishing a method for early warning of the development state of road internal voids.

This invention discloses a hybrid quantization method for image recognition models based on bit-flipping attacks, comprising: Step 1, performing initial quantization on the image recognition model to convert it into an initial quantized model; starting from the first layer of the initial quantized model, performing bit-flipping attacks layer by layer, and recording the sensitivity of each layer under attack; forming a sensitivity set of the initial quantized model from the sensitivities of all layers; constructing an optimization objective function and determining optimization constraints, and determining the optimal hybrid precision quantization strategy for the image recognition model based on the optimization objective function and the optimization constraints; Step 3, setting the bit width for storing the parameters of each layer of the image recognition model according to the optimal hybrid precision quantization strategy, thereby obtaining the optimal hybrid quantization model; Step 4, acquiring the image to be recognized and performing image recognition using the optimal hybrid quantization model.

The present invention relates to the field of image recognition technology, and in particular to a face recognition method, device, equipment and storage medium for RGB-NIR different imaging for intelligent networked face lock. The method comprises: obtaining RGB image data, performing face detection and face feature extraction in the cloud, obtaining high-dimensional features that can represent the face, and binding the high-dimensional features with flags according to binding information; unbinding the high-dimensional features according to the binding information, and storing them in the feature access stack of the face lock end; activating the face lock camera and obtaining camera data, and performing face detection and feature extraction on the NIR image data, obtaining high-dimensional features to be identified that represent the face, and calculating the similarity between the high-dimensional features to be identified and the high-dimensional features stored in the feature access stack of the face lock end to obtain the similarity. Finally, an update mechanism for the feature access stack of the face lock end is added. The present invention can improve the recognition accuracy of the face lock.

The invention discloses a robot positioning method and system based on deep learning. Relates to the technical field of artificial intelligence. The method comprises the following steps: sending an obtained global environment map and a local environment map under the global environment map into a trained deep neural network model to obtain an accurate candidate pose of a robot; fine correction is conducted on the candidate poses through robot motion, and finally the optimal robot pose is obtained; the deep neural network model comprises a convolutional layer conv0, a maximum value pooling layer maxpool, a convolutional layer conv, a cross attention layer crossattn and a candidate pose acquisition layer Maxop; the maximum pooling layer maxpool and the convolution layer conv are connected in sequence to form a layer group, the multiple layer groups are connected in sequence, the layer group located on the uppermost layer serves as the shallowest scale to be connected to the output of the convolution layer conv0, and the output of the convolution layer conv0 and the output of all the layer groups are connected to the cross attention layer crossattn and the candidate pose obtaining layer Maxop in sequence so as to output the optimal pose of the robot; according to the robot positioning method and system, the accuracy and robustness of robot positioning are improved.

The invention discloses a modulation identification method, device and equipment based on a pulse convolutional neural network, and relates to the technical field of wireless communication, and the method comprises the steps: connecting and combining a plurality of pulse residual blocks fusing an attention mechanism, and constructing a convolutional layer and a full connection layer of the pulse residual blocks through LIF neurons; based on the pulse residual blocks of the connection combination, creating a deep network model which takes a pulse residual neural network as a backbone network framework and is fused with an attention mechanism; and obtaining an IQ signal data set to train the created deep network model, thereby realizing modulation identification classification of the IQ signal data to be identified based on the trained deep network model. The wireless signals are modulated and identified through the improved deep network model, the effects of improving the identification speed and reducing the operation power consumption are achieved, and improvement of the performance of a wireless communication system is facilitated.

The invention discloses a human body behavior recognition device and method based on an infrared image, and the method comprises the following steps: S1, collection of the infrared image: employing a single-chip microcomputer to drive an infrared sensor, enabling detected temperature data to form an 80 * 64 * n digital matrix, transmitting the 80 * 64 * n digital matrix to the single-chip microcomputer through an SPI, and storing the 80 * 64 * n digital matrix, then the temperature digital matrix is transmitted to a PC end in a UART communication mode; s2, preprocessing the infrared image; s3, making a human body behavior data set: designing and collecting infrared images of seven behavior actions of bending down, falling down, lying flat, standing, sitting still, standing-to-sitting and walking; s4, designing a behavior recognition algorithm; s5, behavior recognition algorithm training; and S6, identifying seven behavior actions. According to the method, the accuracy is higher, the recognition speed is higher, terminal deployment with limited computing resources is facilitated, and the actual application requirement is met.

The invention discloses an electric power external insulation equipment typical defect fault identification method based on ultraviolet imaging, and belongs to the technical field of electric power grids. The invention aims to solve the problem of low efficiency of identifying corona discharge defect faults through an ultraviolet spectrum in the prior art. The method comprises the following steps: simulating external insulation defects of power equipment, and acquiring an ultraviolet spectrum of corona discharge of the power equipment with the simulated defects by adopting an ultraviolet imaging technology; establishing a neural network, training the neural network by using the ultraviolet spectrum and the defect fault corresponding to the discharge, and obtaining a fault recognition model based on the ultraviolet discharge spectrum; and collecting the ultraviolet discharge spectrum of the to-be-detected electric power external insulation equipment, inputting the collected ultraviolet discharge spectrum into the fault identification model based on the ultraviolet discharge spectrum, and obtaining the fault defect of the to-be-detected electric power external insulation equipment. The method is suitable for typical defect fault identification of the power external insulation equipment.

The present invention discloses an image recognition method, device, equipment and storage medium, and relates to the field of image processing technology. The present invention includes a camera, an image recognition device and a display module, wherein the image recognition device includes, obtaining a sample image and a corresponding recognition result; filtering the sample image using a series of filters to obtain image component features of each sample image in multiple frequency bands; inputting the multiple image component features and the corresponding recognition results of each sample image into the input layer and output layer of different recognition networks according to the corresponding different frequency bands and training and converging to obtain a recognition network for each frequency band; obtaining a target image; extracting the image analysis features of the target image in order from low to high according to the frequency band; inputting the image analysis features of the target image in order from low to high according to the corresponding frequency size into the input layer of the recognition network of the corresponding frequency band until the recognition result of the target image is obtained. The present invention takes into account both the accuracy and speed of image recognition.