31results about How to "Improve feature learning ability" patented technology

The invention provides a PCBA surface defect detection method and system based on image recognition, and the method comprises the steps: collecting and constructing a multi-class PCBA overall defect image data set, and carrying out the preprocessing; constructing a pre-training neural network model, and classifying the preprocessed PCBA overall defect image data set; constructing a local target identification method based on a YOLOX network according to an overall defect classification result; and carrying out local defect detection on the PCBA surface based on a local target identification method. According to the method, the overall classification and local detection strategies are comprehensively applied to reduce the burden of the model, and the detection precision and speed are improved. And an attention mechanism is introduced to improve the performance and generalization ability of the model. Data enhancement, consistency processing, classification labeling and the like are carried out on an image data set, and the defect detection effect of the model is improved. And multiple optimization strategies such as structure improvement, loss function improvement and pruning lightweight are adopted for the network model, so that the image target detection performance is effectively improved.

The invention discloses a frequency domain enhancement fusion network method for night infrared and visible light images, and relates to the technical field of image processing. According to the method, a coarse enhancement network (CENet) is constructed, the night visible light feature extraction capability is improved through deep convolution and point-by-point convolution, a channel importance score is calculated in combination with SENet, finally, a pixel-level enhancement image is generated by using a Tanh activation function, the enhanced visible light feature image and an infrared light image are respectively sent to FDFNet, and the pixel-level enhancement image is obtained. In FDFNet, a U-shaped feature extractor is constructed based on EFA and D3FN modules of a frequency domain, visible light significant information is injected into an infrared feature map through SENet, so that the feature learning ability of a U-Net network is enhanced, finally, images passing through the FDFNet are spliced, a final fused image is obtained through image reconstruction, and the fusion effect is improved. The method provided by the invention is superior to the most advanced method in the aspect of LLVIP data set, shows the potential of further improving the fusion image precision in the future, and is helpful to promote the progress of advanced visual tasks.

The invention relates to the technical field of green power data monitoring, in particular to a green power data monitoring optimization method and system based on a particle swarm algorithm. The method comprises the following steps: acquiring green power data, namely acquiring generating capacity, power, voltage, current and environmental parameters in a green power system, performing preprocessing based on the acquired green power data, performing feature extraction on the preprocessed green power data, constructing a monitoring model by using the green power data after feature extraction, and optimizing model parameters based on the monitoring model. Comprising the steps of performing model parameter optimization by using a particle swarm optimization algorithm; and setting an early warning threshold according to the characteristics of the green power system and the monitoring target, and comparing the output of the monitoring model with the early warning threshold. According to the method, the particle swarm is divided into a plurality of sub-groups through a multi-group collaborative optimization mechanism, and information exchange is carried out, so that the search diversity can be increased, and the probability of finding a globally optimal solution is further improved.

The invention discloses an unmanned aerial vehicle image transmission signal modulation mode identification system and method based on multi-modal fusion. The method comprises the following steps: (S100) collecting and preprocessing unmanned aerial vehicle communication signal data; (S200) converting the one-dimensional time-domain signal into a two-dimensional Gramer angle field graph and estimating a two-dimensional time-frequency graph of the image transmission signal; (S300) carrying out feature merging; (S400) generating a training set and a test set; (S500) constructing a VGG-ResNet hybrid architecture deep learning network and carrying out training; and (S600) identifying the image transmission signal modulation mode of the unmanned aerial vehicle to be identified. The method disclosed by the invention is based on a multi-modal fusion technology and shows remarkable advantages, and data features of different modals can be comprehensively utilized by fusing the one-dimensional time domain signal and the two-dimensional time frequency graph information to realize more comprehensive description of data.

The invention belongs to the technical field of computer-aided diagnosis, and particularly relates to a dynamic brain network feature learning method based on Mamba, which comprises the following steps of: performing data processing, including data collection, data preprocessing, dynamic function network sequence construction and state conversion sequence construction; performing sample enhancement by taking the processed data as sample data; constructing a Mama model comprising a linear embedding layer, a Mama layer, a linear mapping layer I, an activation function and a loss function as a classification model; training the Mama model by using the state conversion sequence, and optimizing hyper-parameters of the Mama model; and based on the trained Mama model, predicting the enhanced sample data, and determining a classification result of the sample data through a label output by the Mama model. According to the method, the relation hidden in the dynamic brain network state transition sequence can be efficiently captured, and high-precision classification of each brain network sequence is realized.

The invention relates to the field of intelligent image recognition, in particular to a real-time copper foil defect detection method which comprises the following steps: establishing a data set of copper foil surface defects, constructing an environment corresponding to a basic Yolo V8 model, and improving the Yolo V8 model by using a dual convolution (DualConv) structure, a deformable large kernel attention (D-LKA Attention) mechanism and a Shape IoU loss function. And training and optimizing the YOLO network model, generating weight files, storing the weight files to the local, and identifying and classifying the copper foil surface defects by using the weight files. According to the method, the accuracy of defect detection is remarkably improved, the high speed of the detection process is ensured, and the method is suitable for the real-time application requirement in an industrial production environment.

The invention discloses a photovoltaic array fault diagnosis method based on LSTM-DAE (Long Short Term Modulation-Data Acquisition Element). Collecting and preprocessing current and voltage information of the photovoltaic module; judging whether a fault occurs or not according to whether the maximum power difference value of the actual measurement curve and the reference curve exceeds a fault early warning threshold value or not; detecting a fault, reading voltage, current and voltage information, and training and testing a sample; the samples are imported into an LSTM-DAE model for feature extraction, and the model is the LSTM-DAE model constructed in an offline state by using historical photovoltaic array fault data as the samples; and transmitting the extracted feature data to an SVM-LR hybrid classifier, fitting the output of the SVM to an LR classifier through a binomial method to carry out model parameter performance optimization, and carrying out k-fold cross validation to obtain a final fault classification model. Compared with the prior art, the method can reduce the processing of label data, effectively improves the accuracy and efficiency of fault detection, and achieves the real-time monitoring and fault diagnosis in photovoltaic fault classification.

The invention discloses a digital twinning driven steel rail state transition diagnosis method, which belongs to the field of rail traffic fault diagnosis, and comprises the following steps: establishing a digital twinning model of a vehicle-rail coupling system; performing simulation by using a digital twin model to obtain a plurality of groups of vibration response signals; performing time-frequency analysis on each group of vibration response signals and each group of actually collected axle box vibration signals through wavelet transform to obtain a time-frequency diagram of each group of vibration response signals and a time-frequency diagram of each group of axle box vibration signals; taking the time-frequency diagram of each group of vibration response signals as source domain data of a sub-domain alignment migration network, and taking the time-frequency diagram of each group of axle box vibration signals as target domain data of the sub-domain alignment migration network to obtain a trained sub-domain alignment migration network; and utilizing the trained sub-domain alignment migration network to predict a to-be-detected axle box vibration signal, and completing diagnosis and identification of different steel rail states. The problem that the steel rail state diagnosis precision is insufficient under the condition that sample labels are scarce is solved.

The invention provides an aluminum electrolysis process practical training platform based on multi-modal data, an evaluation method and equipment. The evaluation method comprises the following steps: acquiring log record data and video data in an aluminum electrolysis process practical training process, and acquiring sensor data of industrial equipment in an aluminum electrolysis workshop; an LSTM network is used for processing sequence data, the long-term dependency relationship in log record data can be captured, and the sequence and logic of aluminum electrolysis process operation can be understood; processing the video data by using a CNN network, and extracting key features in the video; processing sensor data using a full connection layer; and a full connection layer is used as a fusion layer, and outputs of the networks are fused. According to the method, different deep learning networks are adopted to process different data, the extracted features are more representative, and the reliability of a result obtained through fusion is higher; the actual operation effect of the aluminum electrolysis process can be reflected and evaluated more accurately, more valuable feedback is provided, and the aluminum electrolysis process is controlled and optimized.

The invention discloses a data-driven heavy-load locomotive primary steel spring damage detection method, and belongs to the technical field of heavy-load locomotive primary spring damage detection. The detection method comprises the following steps: S1, obtaining a vertical vibration response signal of a framework of the heavy-load locomotive, and preprocessing the vertical vibration response signal to obtain a sample set; s2, dividing the sample set into a training set, a test set and a verification set, and performing standardization processing; s3, constructing a primary spring damage detection model; s4, training and adjusting the primary spring damage detection model by adopting the training set and the verification set to obtain a final primary spring damage detection model; and S5, performing evaluation verification on the final primary spring damage detection model by adopting the test set to realize primary steel spring damage detection of the target heavy-load locomotive. The method can realize intelligent grading detection of the damage of the primary spring of the heavy-duty locomotive, has the characteristics of accuracy, high efficiency, strong generalization ability and the like, and is expected to be developed into a long-term monitoring method for the damage of the primary spring.

A method for fault diagnosis of rotating machinery based on multi-sensor fusion and ECA-CNN, 1) Data acquisition: Collect multi-sensor vibration signals of key transmission components of rotating machinery in various health states; 2) Data preprocessing: Sampling, converting and channel fusion of multi-sensor vibration signals to obtain multi-channel images with rich and comprehensive features; 3) Model building: Introducing efficient channel attention into convolutional neural networks to construct ECA-CNN models; 4) Model training: Training the model using multi-channel image sample sets; 5) Fault diagnosis: Using the trained model to perform fault diagnosis on rotating machinery. The present invention realizes channel fusion of multi-sensor vibration signals; introduces efficient channel attention into convolutional neural networks to improve feature learning capabilities and focus attention on more sensitive features; constructs an ECA-CNN model with high computational efficiency to learn representative fault features from multi-sensor fusion data, thereby realizing fault diagnosis.

The invention discloses an unmanned aerial vehicle image transmission signal modulation mode identification system and method based on multi-dimensional feature cooperation. The method comprises the following steps: (S100) collecting and preprocessing unmanned aerial vehicle communication signal data; (S200) the one-dimensional features are extracted and remodeled into a two-dimensional feature map, and normalization processing is carried out; estimating a two-dimensional time-frequency diagram of the image transmission signal; (S300) feature combination: combining the obtained remolded graph and the time-frequency graph as four channels to form a multi-channel feature graph; (S400) generating a training set and a test set; (S500) constructing a VGGR16ChannelAttention deep learning network, and carrying out the training of the VGGR16ChannelAttention deep learning network; and (S600) identifying the image transmission signal modulation mode of the unmanned aerial vehicle to be identified. According to the method, the time-frequency analysis technology and the deep learning technology are fused, the method surpasses a traditional method through time-frequency synchronous optimization transformation, and complex signals can be accurately analyzed.

The invention discloses a model training method and a multi-scale vehicle and pedestrian detection method, and belongs to the technical field of target detection. The method comprises the steps of firstly obtaining a sample vehicle and pedestrian training set, a sample vehicle and pedestrian labeling training set and a YOLOv8 improved model, wherein an improvement method of the YOLOv8 improved model comprises the steps of replacing a traditional convolution module of a Bottleneck structure in a C2f module of a backbone network of the YOLOv8 model with a partial convolution module, introducing a lightweight cross-scale feature fusion module CCFM, and introducing a heavy parameter detection head; and then based on the sample vehicle and pedestrian training set and the sample vehicle and pedestrian labeling training set, training a YOLOv8 improved model to obtain a lightweight target vehicle and pedestrian detection model. According to the method, the parameter quantity and the calculation quantity of the model can be reduced on the basis of ensuring the detection precision of vehicles and pedestrians, and the detection effect of the model after deployment of an embedded platform is improved.

The application relates to the technical field of microwave remote sensing, and proposes an adaptive wet troposphere path delay inversion method and system fusing wind speed overlapping partition modeling, multi-scale collaborative sample balancing and model soft fusion. The method comprises the following steps: acquiring multi-source data and preprocessing the multi-source data to obtain to-be-inverted samples; according to a preset threshold, the full-range wind speed of the to-be-inverted samples is divided into a plurality of wind speed subintervals with overlapping transition zones; the to-be-inverted samples are input into trained inversion submodels, the output results of the inversion submodels are weighted and summed according to final fusion weights, and finally, wet troposphere path delay inversion results are obtained; when abnormal wind speed or invalid submodel prediction output is detected, the output result of a pre-trained global unified model is taken as the final inversion result. While guaranteeing overall inversion precision and stability, the application can significantly suppress systematic deviation under sea conditions of extremely low and extremely high wind speed.

The invention relates to a new energy data frequency raising reconstruction method and device based on a generative adversarial network, equipment, a storage medium and a program product, and relates to the technical field of regional power data transmission. According to the invention, high-precision frequency raising reconstruction can be realized for different data sets under the same model parameters. The method comprises the following steps: performing normalization processing and format conversion on new energy data to obtain a new energy image; performing feature extraction on the new energy image by using a generator in the generative adversarial network model to obtain new energy image features, and obtaining a training data set and a verification data set according to the new energy image features; inputting the training data set into the generative adversarial network model for training, and adjusting hyper-parameters of the generative adversarial network model by using the verification data set to obtain a target generative adversarial network model; and inputting the new energy data into the target generative adversarial network model for frequency raising reconstruction to obtain high-resolution target new energy data.

The present invention discloses a real-time prediction method for wind power, comprising the following steps: step S1, for any wind power equipment that has been put into operation, pre-acquire the wind power and wind speed of the wind power equipment at each power generation moment after the power generation operation is completed; step S2, establish a prediction model for wind power, the prediction model for wind power is used to establish a nonlinear relationship between the wind power of the wind power equipment at a previous moment and the wind power at a later moment; step S3, collect the wind power and wind speed of the wind power equipment at the current moment in real time, and then input them into the prediction model for wind power, so as to predict and obtain the wind power of the wind power equipment at the later moment in real time. The real-time prediction method for wind power disclosed by the present invention is scientifically designed, and by establishing a prediction model for wind power, it is possible to efficiently and reliably predict the wind power of the wind power equipment in real time, and has great practical significance.

An automatic extraction method for complex event patterns based on BiGRU-CNN and Gaussian Mixture Model (GMM) includes: preprocessing the raw time series data from sensors to obtain structured time series feature data; constructing a BiGRU-CNN feature extraction model; supervised training of the BiGRU-CNN feature extraction model; extracting bottleneck features from the unlabeled sample set and generating pseudo-labels with confidence through Gaussian Mixture Model clustering; merging the high-confidence pseudo-label sample set with the labeled sample set to form an expanded training set for retraining the BiGRU-CNN feature extraction model; automatically generating CEP event pattern rules; and automatically outputting complex event detection results. This invention solves the problem of insufficient feature representation capabilities in traditional models, significantly reducing the computational overhead of subsequent GMM clustering and CEP rule matching, allowing the model to possess both strong feature learning capabilities and maintain lightweight computational characteristics, meeting the computational resource requirements of different scenarios.

This application discloses a method, system, device, and medium for long-term power consumption prediction based on an attention mechanism and frequency enhancement. A deep network structure model is constructed based on the attention mechanism and frequency enhancement. The deep network structure model includes an encoder, a frequency-enhanced hybrid attention module, and a decoder connected sequentially. The frequency-enhanced hybrid attention module includes a self-attention module and a frequency-enhanced channel attention module. Power consumption is predicted based on this deep network structure model. The power consumption prediction method provided by this invention incorporates an attention mechanism into the Transformer neural network to address the characteristics of power consumption data, making the model's prediction results more stable. The frequency-enhanced hybrid attention module enhances the model's noise resistance in the frequency domain, thereby improving the model's feature learning ability and the accuracy of long-term prediction of sequence data. An iterative prediction strategy is adopted, making multiple predictions to achieve long-term prediction.

A transmission tower defect identification method based on an improved YOLOv11 algorithm belongs to the technical field of defect identification, and designs an improved YOLOv11 network model, firstly designs and adds a HorNet high-order interactive recursive gating network module in a Backbone network, and through gating convolution and recursive structures, fuses information of different widths, and improves the capability of accurately identifying target defects; secondly, a Conv standard convolution module in the Backbone network is replaced by a GhostConv ghost convolution module, so that the calculation amount and the parameter amount are greatly reduced; and finally, a RepViTblock re-parameterization visual transformation module is added in the Neck neck network design, each pixel position in the input image is mapped to a vector space, and the precision and efficiency of target detection are improved. The method is high in identification accuracy and high in identification efficiency, and fully guarantees the safe and stable operation of the power transmission line.

The invention discloses an intelligent segmentation method for a ceramic sanitary ware point cloud working plane, and the method comprises the following steps: 1, obtaining ceramic sanitary ware point cloud data through a three-dimensional camera, and taking the data as input; the point cloud data comprises three-dimensional position information of the sanitary appliance surface and is the basis of subsequent processing and segmentation; 2, the segmentation model aggregates structural information through a Point Embedding module at a first layer of a coding stage; the method is high in feature learning capability and adaptability, the model can automatically learn feature representation in the point cloud, a feature extractor does not need to be designed manually, and the model can automatically adjust parameters in the training process for various ceramic sanitary ware point clouds, so that the training efficiency is improved. The method does not need to manually adjust parameters or design a special algorithm to adapt to different ceramic sanitary ware point cloud data like a traditional method.

The embodiment of the invention relates to the technical field of low-altitude remote sensing target detection methods, in particular to a low-altitude remote sensing target detection method, and the method comprises the steps: obtaining a to-be-detected low-altitude remote sensing image, and processing the to-be-detected low-altitude remote sensing image through a pre-constructed sparse cross attention-based low-altitude remote sensing target detection model. The method comprises the following steps: obtaining a detection target of a low-altitude remote sensing image, outputting the detection target of the low-altitude remote sensing image, effectively extracting global feature information through a newly designed feature enhancement module, effectively fusing deep semantic information and shallow information through a newly designed small target feature fusion module, and reserving a relatively large feature size. A small target is better detected, a sparse mechanism is utilized, only correlation between most relevant feature information is considered, the efficiency is improved while the fusion effect is ensured, and the feature learning ability can be effectively enhanced through a newly designed global semantic information fusion module.

This invention discloses a method, system, and device for estimating the area of ​​the eye muscles and the backfat thickness of live pigs based on deep learning. The method includes: acquiring and constructing a dataset of live pig ultrasound images; selecting regions of interest (ROIs) in the ultrasound images, preprocessing them, and standardizing the input size; inputting the preprocessed ultrasound images into a ReAMS-UNet neural network for semantic segmentation of the eye muscle region; filtering the image contours to remove false positives and false negatives in the segmentation results; determining the upper and lower boundaries of the backfat thickness through image binarization; calculating the eye muscle area and backfat thickness, and outputting the calculation results. Based on a large-scale, highly diverse dataset of pig ultrasound images, this invention utilizes ReAMS-UNet to integrate residual learning for stable training, a hybrid attention mechanism for adaptive feature optimization, multi-scale fusion for contextual and spatial information fusion, and auxiliary supervision for enhanced gradient propagation. It achieves high segmentation accuracy, fast inference speed, accurate trait estimation, and results that reflect true carcass traits. The process is automated and suitable for high-throughput analysis applications.

This application provides a temporal sampling method and apparatus, and a speech recognition method and apparatus, relating to the field of artificial intelligence technology. The temporal sampling method includes: acquiring target speech data; and determining the temporal sampling result of the target speech data using a sampling model based on the target speech data. The sampling model includes an l-layer downsampling network and an l-layer upsampling network. Each downsampling network layer includes parallel skip modules and downsampling modules, and each upsampling network layer includes parallel skip modules and upsampling modules. The sampling model is used to match the optimal sampling path in the sampling model for the target speech data based on the skip modules and downsampling modules of each downsampling network layer and the skip modules and upsampling modules of each upsampling network layer. l is a positive integer greater than 1. The temporal sampling method in this application can improve the learning ability of acoustic features of speech data and the adaptability of modeling granularity.

The application relates to a double-layer data-driven ship trajectory prediction method and system based on a GRU network, and relates to the technical field of trajectory prediction.The application mainly obtains an observation sequence X with a length of g from an AIS data set g , inputs the observation sequence X g into a first machine learning model to obtain an intermediate feature state output with a length of l, simultaneously inputs the observation sequence X g into a second machine learning model to obtain an intermediate feature state output with a length of l, splices the intermediate feature states and to form composite training data as the input of a third machine learning model, and obtains a prediction result.The application solves the problems of insufficient multi-dimensional feature data mining and low prediction accuracy in the prior art.

The embodiment of the present application provides a privacy enhancement detection method based on a generative adversarial network. In the embodiment of the present application, a GAN including multiple generators, a discriminator and a classifier is constructed, and the GAN is trained based on a training data set to obtain a target GAN; based on this, the present embodiment generates multiple target pseudo sample data by using each generator in the target GAN, so as to use each target pseudo sample data as the training sample data of the privacy leakage detection model, so as to expand the training data set of the privacy leakage detection model, so as to avoid the problem of imbalance in the number of sample data of different data categories in the training data set, thereby improving the performance of the privacy leakage detection model and improving the accuracy of privacy leakage detection.

The invention discloses an on-line monitoring and inhibiting system applied to cold convertor station valve hall air conditioner waterway corrosion, and relates to the technical field of power transformation on-line monitoring and overhauling. The system comprises an ethylene glycol concentration management module, a corrosion inhibitor management module, an ion concentration management module and an operation and maintenance data analysis module; the operation and maintenance data analysis module is used for judging whether ethylene glycol needs to be added or not according to the concentration of the ethylene glycol, calculating to obtain a first target quantity when the first judgment result is that the ethylene glycol needs to be added, judging whether a corrosion inhibitor needs to be added or not according to the PH value of the solution, and calculating to obtain a second target quantity when the second judgment result is that the corrosion inhibitor needs to be added; the controller is also used for judging a corrosion judgment result of the corrosion degree according to the iron ion content and the oxygen content of the solution; in this way, operation and maintenance personnel can be helped to find the corrosion state of the valve hall air-conditioning waterway system of the cold convertor station in time, automatic adding of the anti-freezing solution and the slow-release agent is achieved, and time and labor are saved in monitoring and restraining of corrosion of the valve hall air-conditioning waterway system.

The invention discloses a 3D object classification continuous learning method and system based on a parameter level mask adapter, and the method comprises the steps: obtaining to-be-detected 3D point cloud data, and extracting the 2D features, original 3D features and text features of the 3D point cloud data; fusing the 2D features and the 3D features through a parameter-level mask adapter to obtain global features; performing comparative learning on the global features and the text features to obtain a 3D object classification result; wherein when the parameter level mask adapter continuously learns a plurality of 3D object classification tasks, the most relevant parameters of the learned tasks are frozen, and the most relevant parameters of the learned tasks are not updated any more in subsequent tasks. According to the method, the prior knowledge of the CLIP model is adapted to a 3D object classification task through multi-modal feature fusion, and continuous learning based on parameter isolation is realized by using a mask of a parameter level, so that disastrous forgetting is effectively reduced, and the classification performance is improved. The invention further provides a new model continuous learning ability evaluation index, and a more comprehensive evaluation framework is provided for 3D object classification continuous learning.

The invention relates to the technical field of computer visual recognition, in particular to an asynchronous event stream processing method and device based on a graph model and a storage medium. The method comprises the following steps: sampling an ambient light intensity change value through an event camera, and outputting to obtain an asynchronous event stream, the asynchronous event stream being used for indicating light intensity changes corresponding to a plurality of asynchronously sampled pixels; and feature learning is carried out on the asynchronous event flow through a graph convolutional network model, feature data is output and obtained, the graph convolutional network model is used for indicating setting of parameters of an asynchronous event flow generation graph according to a connectivity index, and the connectivity index indicates connectivity of the graph. According to the embodiment of the invention, the connectivity index is provided for describing the connectivity of the graph, the parameter setting of the asynchronous event flow generation graph is guided through the connectivity, the scale of the generation graph, the number of nodes and the number of edges are controlled, data preparation is made for an end-to-end deep learning algorithm, and the processing effect of the asynchronous event flow based on the graph model is improved.

The embodiment of the invention provides a privacy enhancement detection method based on a generative adversarial network. In the embodiment of the invention, a GAN comprising a plurality of generators, a discriminator and a classifier is constructed, and the GAN is trained based on a training data set to obtain a target GAN; based on this, according to the embodiment of the invention, a plurality of target pseudo sample data are generated by utilizing each generator in the target GAN, and each target pseudo sample data is used as the training sample data of the privacy leakage detection model, so that the training data set of the privacy leakage detection model can be expanded; the problem that the number of sample data of different data categories in a training data set is unbalanced is solved, so that the performance of a privacy leakage detection model is improved, and the accuracy of privacy leakage detection is improved.

The present invention relates to the technical field of human posture estimation, solves the technical problem that the traditional method does not perform spatial feature extraction with the same resolution in multiple identical spaces, and particularly relates to a parallel space internal and external interaction system and method for human posture estimation, the system comprising a downsampling module for acquiring an input image and quickly downsampling the input image to obtain a downsampled image feature, a channel adjustment module for expanding the channel size of the downsampled image feature to obtain a channel expansion feature, and separating the channels of the channel expansion feature to obtain four parallel space features with the same spatial size and adjacent channels. The present invention explores the influence of parallel space interaction on human posture estimation by performing spatial interaction within and between parallel spaces, and completes global feature interaction both internally and externally, which is of great benefit to capturing the relationship between key points of human posture estimation and ensures the high efficiency of human posture estimation.