23results about How to "Improve feature extraction" patented technology

This invention discloses a bearing remaining life prediction method based on frequency domain degradation perception. It constructs an integrated prediction system through a time-frequency decomposition dual-branch feature extraction module, a frequency domain degradation perception weight allocation module, and a life prediction loss function optimization module. First, the time-frequency decomposition dual-branch feature extraction module decomposes the original time series into high and low frequencies and inputs it into an sLSTM and mLSTM dual-branch structure for feature extraction. Second, the frequency domain degradation perception weight allocation module performs degradation perception processing on the fused features, generating dynamic weights and modulating the features to obtain the final fused features, which are then mapped to the prediction space. Finally, the life prediction loss function optimization module calculates the loss, optimizes the model output, and obtains the bearing remaining life prediction result. This invention comprehensively covers the full-stage features of bearings from healthy to severely degraded, improves the sensitivity of early fault detection, and still possesses excellent generalization and robustness under complex operating conditions.

The present application relates to a kind of forest leaf instance segmentation method and system based on deep learning, method includes: obtaining vegetation image, vegetation image is input into leaf instance segmentation model, obtains leaf instance segmentation prediction result;Leaf instance segmentation model is trained using training set;Training set includes: vegetation original image;Feature extraction and enhancement are carried out using backbone module in leaf instance segmentation model, and adaptive spatial fusion mechanism in progressive feature pyramid network is integrated to dynamically adjust feature weight, generate dynamic fusion feature;Through the dynamic asymmetric spatial perception mechanism built-in in dynamic anomaly regression head module, the corresponding multi-source deformation feature layer of dynamic fusion feature is obtained, and the feature fusion strategy of top-down cascaded decoding module is used to optimize multi-scale feature, obtain multi-source fusion feature layer, further using multi-source fusion feature layer, generate leaf instance segmentation prediction result.The present application solves the problems of data scarcity, poor adaptability and low efficiency.

The present application provides a kind of coastal water level prediction method based on multi-modal observation data, belong to coastal water level prediction technical field, the present application is by collecting the multi-modal marine observation data of different sensors, the spatial and temporal alignment of heterogeneous data is realized by establishing multi-scale space-time registration matrix, constructs marine dynamic process feature extractor to identify astronomical tide storm surge and wave characteristics and calculate nonlinear coupling parameters, using adaptive space-time fusion algorithm according to the weight of data quality dynamic adjustment generation space-time consistency dataset, establishes marine dynamic coupling strength discrimination model to determine modeling strategy, finally generates the coastal water level prediction product containing prediction value confidence interval and risk warning, solves the technical problem that multi-modal marine observation data is difficult to effectively fuse under the condition of space-time scale mismatch, resulting in insufficient coastal water level prediction accuracy.

The application discloses a coal mine image segmentation model and method based on a VMamba and multi-expert hybrid network and a construction method thereof. The coal mine image segmentation model is constructed. The image block encoding layer output of an encoder is taken as the input of the first encoding layer of a first VSS network, and the output of the first encoding layer of the first VSS network is taken as the input of the output end feature learning module. The input of the output end feature learning module is taken as the input of the first decoding layer of a decoder, and the output of the first decoding layer of the decoder is taken as the input of the second decoding layer of the decoder. The input of the second decoding layer of the decoder is taken as the input of a segmentation head, and the output of the segmentation head is taken as a segmented image. The application can significantly improve the segmentation precision and calculation efficiency of the coal image.

This invention discloses a rapid detection method and system for multiple types of hidden dangers in concrete dams based on the HDIOCNet model. First, infrared-visible dual-light images of the concrete structure surface are acquired, preprocessed, and semantically annotated to construct a training dataset integrating the dual-light images for concrete dam hidden danger detection. Second, a deep learning model, HDIOCNet, for rapid detection of multiple types of hidden dangers in concrete dams is constructed. This model employs an efficient encoder-decoder hourglass structure. The encoder part includes a lightweight edge and texture feature extraction backbone network and a multi-scale receptive field extended dilated convolutional pooling pyramid to encode the features of the input dual-light images and output feature maps at different semantic levels. Finally, the HDIOCNet model is trained based on the dual-light dataset. The trained model is used to predict the types of hidden dangers and calculate and compare the areas of hidden dangers. This invention has the advantages of high detection accuracy, fast detection speed, and intelligence, providing an efficient solution for the safety monitoring of concrete structures.

This invention belongs to the field of image classification technology and relates to a method and system for tempered glass inspection based on a bi-branch inverse residual network model. The bi-branch inverse residual network model includes a preprocessing unit, a first feature extraction unit, a second feature extraction unit, a third feature extraction unit, a fourth feature extraction unit, and a classification unit connected sequentially. The feature extraction unit is composed of one or more bi-branch inverse residual modules. The model provided by this invention has advantages such as high accuracy, few parameters, and low computational cost. When used for tempered glass quality inspection, it can improve inspection efficiency and accuracy, while also ensuring non-destructive and continuous inspection, thus guaranteeing the safety and efficiency of glass production.

The application discloses a kind of power equipment defect identification and warning method and system based on deep learning.The method comprises: synchronously collecting and registering the visible light and infrared thermal imaging image on the surface of power equipment, constructs the instance segmentation network including light weight feature extraction network, multiscale feature fusion network and frequency domain mask prediction branch;Adopt the generative adversarial strategy to enhance the diversity of training sample;Based on graph neural network, analyze the association between defect and equipment topology, historical record, infer the cause-effect relationship of defect and risk level;Generate the interpretable warning information including heat map, natural language report and repair suggestion;Real-time detection and deep analysis are realized using end-edge-cloud collaborative architecture;Through closed-loop optimization mechanism, continuously improve system performance.The application realizes high-precision defect detection under multi-modal data fusion, has strong robustness and interpretability, significantly improves the intelligent level of power equipment operation and maintenance.

The application provides a kind of high-resolution image landslide detection method of combined spectrum, digital elevation model and auxiliary feature dual-branch network, including obtaining the high-resolution remote sensing image to be detected, digital elevation model and landslide true label;Extract auxiliary features, mine multiple characteristic factors from them and merge all images in channel;The image after merging is preprocessed, and landslide sample is generated;Different data enhancement means are used to increase the number and diversity of landslide data set;Residual and channel attention are added to the network model based on U-Net+++ to improve the network model;The image sample pair is respectively input into the improved U-Net+++ branch network, and the prediction result is obtained;The consistency of sample pair is mined and the model is optimized using the loss function;Based on the test sample, the model accuracy is evaluated and the landslide detection result map is output.The application provides a novel and effective landslide detection method, which can fully mine the invariance features of high-resolution landslide images and effectively improve the recognition accuracy of landslide.

The application provides a method for detecting defects in a steel pipe welding digital radiograph image, comprising the following steps: S1, collecting a plurality of DR images, expanding a sample data set, preprocessing the plurality of DR images, and constructing a training data set; S2, constructing a deep convolution network model based on image reconstruction, wherein the network model comprises at least one convolution network-based encoder and a corresponding decoder; S3, performing model parameter optimization training, using the training data set to optimize network parameters, and obtaining an optimized network model; S4, inputting the collected DR image into the optimized network model for inference to obtain a reconstructed image; performing difference operation on the reconstructed image and the input image, and binarizing the difference result to obtain a final defect position; and through the above scheme, the final defect position is obtained.

The application discloses a method and system for unmanned vehicle to identify traffic signs under extreme weather, wherein the method comprises the following steps: acquiring a traffic sign image to be identified under extreme weather; the extreme weather refers to rainy and snowy weather or fog and haze weather; for the rainy and snowy weather, the traffic sign image to be identified is subjected to rainy and snowy preprocessing; for the fog and haze weather, the traffic sign image to be identified is subjected to fog and haze preprocessing; and the preprocessed image is subjected to identification by using a trained traffic sign identification model to obtain an identified traffic sign.

This invention provides a method for tracking small targets in UAV video images based on Siamese networks. The method utilizes an improved VGG16 network to extract features from the template region and search region, obtaining feature maps for these regions and improving their expressive power. The template region feature map is then passed through channel attention and spatial attention channels to increase the proportion of effective features, resulting in an enhanced template region feature map. The enhanced template region feature map and the search region feature map are input into an RPN network, where convolution operations are performed in the classification and regression branches to obtain the target's classification response map score and regression response map score. Finally, the target's position information in the next frame is generated according to the score, achieving target tracking. This invention enhances the target feature representation capability and can adapt to situations where small targets in video images exhibit pose variations, lighting changes, and similar background interference, enabling effective and stable tracking of small targets in UAV video images.

The application discloses a highway construction safety intelligent monitoring and early warning system and method, which is integrated in a mobile working vehicle and comprises a support device, a double camera with night vision and zooming functions, a data processing device with an embedded Yolo-v5 improved algorithm model, an alarm device combining sound and light with vibration, and a power supply device. The camera is used for collecting video of a construction area in real time, the collected video is preprocessed through scene characteristic enhancement, a CSPDarknet53 backbone network with an introduced CBAM attention mechanism is used for identifying safety cones and construction personnel, a virtual boundary line is dynamically generated, the Euclidean distance of personnel to the boundary line is calculated, a multi-parameter weighted correction model is used for dynamically adjusting a safety threshold, and dangerous judgment is performed in combination with multi-frame fusion trajectory analysis and Kalman filter prediction. The application realizes all-weather accurate monitoring, dynamic boundary sensing, early warning and evidence reservation, and significantly improves the intelligent safety management level of highway construction.

The application discloses a hyperspectral remote sensing image classification method based on unsupervised multi-view image contrast learning, first, data preprocessing is performed on the obtained hyperspectral remote sensing image X to obtain superpixels and corresponding labels and a segmentation matrix; then, according to the segmentation matrix, a spatial adjacency matrix and a spectral adjacency matrix are respectively established from the multi-view angle to obtain multi-views; finally, the multi-views are input into an adaptive data enhancement module to obtain deep features for classification; the application fully utilizes unsupervised deep contrast learning for image classification, combines a multi-view form of graph construction, fully considers various representations of samples, comprehensively considers various levels of features, and improves the classification precision.

The present disclosure provides a text retrieval model training method, a text retrieval method and related devices, and relates to the technical field of artificial intelligence. The method comprises: compressing each pair of query word samples and candidate text samples into string samples; processing the string samples by using a feature extraction sub-model in a text retrieval model to obtain hidden layer features; performing a relevance score calculation operation on the hidden layer features by using a similarity calculation sub-model in the text retrieval model; performing up-sampling mapping on the hidden layer features to obtain up-sampled features, and performing feature filtering on the up-sampled features to obtain filtered features; performing down-sampling mapping on the filtered features and the up-sampled features to obtain down-sampled features; calculating the relevance scores between the query word samples and the candidate text samples based on the down-sampled features; and training the text retrieval model in a contrast learning manner based on the relevance scores. The method can improve the training stability and training efficiency of the text retrieval model.

The present application relates to an X-ray security image contraband detection method based on improved YOLOv7, belonging to the field of target detection, comprising the following steps: S1: preprocessing the security data set and randomly dividing it into a training set and a validation set; S2: combining a multi-dimensional efficient channel attention module with a backbone network to construct an efficient backbone network; S3: constructing a transition network between the backbone network and the neck network through a multi-scale feature aggregation module; S4: designing a precise bounding box regression loss EIoUer Loss as the positioning loss of the model; S5: constructing an MME-YOLO security image contraband detection network model through an image preprocessing module, an efficient backbone network, a transition network, a neck network and a detection head; S6: training the MME-YOLO model; S7: verifying the MME-YOLO model.

This invention discloses a training method for an image classification model, an image classification method, and an apparatus. The training method for the image classification model includes: acquiring a pre-constructed image-text reconstruction pre-trained network; the image-text reconstruction pre-trained network includes a text reconstruction network and an image reconstruction network, the image reconstruction network including a corresponding first encoding network branch and a first decoding network branch; acquiring a training dataset for the image-text reconstruction pre-trained network; the training dataset consists of training data pairs formed by image data and corresponding text data; training the image-text reconstruction pre-trained network based on the training dataset to obtain a target image-text reconstruction network; and determining an image classification model based on the encoding network branch of the image reconstruction network in the target image-text reconstruction network and a pre-set image classification model. This invention eliminates the need for labeling the training data, thereby improving the feature extraction capability of the image classification model and thus increasing the accuracy of the image classification model.

The application discloses a rotating machinery cross-domain fault diagnosis method based on dynamic evolution and wavelet double-path structure, and relates to the technical field of fault diagnosis. The method comprises the following steps: obtaining labeled vibration signals under a certain working condition of rotating machinery and a large number of unlabeled vibration signal samples under an actual variable-speed working condition to be measured. Firstly, batch normalization processing is performed on the input original vibration signals to reduce signal distribution differences caused by speed changes. Secondly, a double-path feature extraction structure is constructed based on wavelet packet transformation, low-frequency global and high-frequency detail features are fused, and the model cross-domain fault feature extraction capability is improved. Then, a domain self-adaptive method based on a dynamic evolution mechanism is adopted to construct a series of mixed domains evolving from a source domain to a target domain, the domain offset mutation problem in the migration process is relieved through gradual transition and gradual migration, and finally the trained model is saved to realize the rotating machinery cross-domain fault diagnosis by using a small amount of labeled samples in the source domain and a large amount of unlabeled samples in the target domain.

This invention relates to the field of oil and gas reservoir exploration technology, specifically a method, apparatus, electronic device, and storage medium for predicting the content of multiple minerals. The method includes acquiring input features of the well section to be predicted; inputting these features into a multi-component mineral content prediction model; and outputting the corresponding prediction results for the content of each mineral component. The multi-component mineral content prediction model is trained using multiple samples on a pre-set deep learning model, which employs a strategy of bidirectional multi-scale feature extraction and cross-scale attention fusion. The model constructed by this invention can not only efficiently capture the global long-term trend and local abrupt fluctuations of logging curves, but also automatically learn the mutual constraints between minerals, achieving accurate mapping between multi-scale logging features and specific mineral categories. Therefore, the multi-component mineral content prediction model enables efficient and collaborative prediction of multiple minerals, providing an effective data foundation for oil and gas exploration and development, reservoir evaluation, and production capacity prediction.

This invention belongs to the field of character recognition technology and provides a handwritten letter recognition method based on piezoresistive signal detection, including the following steps: collecting the temporal piezoresistive signal during the letter writing process as raw data; preprocessing the raw data to obtain training data; constructing a recognition model, inputting the training data into the recognition model to extract temporal feature vectors, and performing classification training; using the trained recognition model for forward inference to confirm the letter category; this invention accurately captures changes in writing force and temporal logic based on piezoresistive electrical signals, significantly improving the accuracy of handwritten letter recognition.

This invention provides a method for detecting small infrared targets in a single frame, comprising the following steps: acquiring a dataset of single-frame infrared small target images and preprocessing the dataset to obtain a training set; constructing a deep learning network model based on a multi-scale local contrast enhancement module and a pyramid max pooling module; training the deep learning model based on the training set of single-frame infrared small targets to obtain a single-frame infrared small target detection model; acquiring the single-frame infrared small target image to be detected; inputting the image into the single-frame infrared small target detection model and outputting the detection result image. This invention utilizes the good generalization and robustness of deep learning methods, applying a deep learning network model to single-frame infrared small target detection, and using a multi-scale local contrast enhancement module and a pyramid max pooling module to enhance the feature extraction capability of the deep learning network for single-frame infrared small targets, thereby achieving high accuracy and high robustness in single-frame infrared small target detection.

This invention discloses a multi-objective optimization method based on a GCN proxy model, which mainly addresses the problems of high computational complexity, low optimization efficiency, and low prediction accuracy in cascading failure simulation during critical node detection in complex networks. First, initialization and objective function construction are performed, setting relevant algorithm and model parameters, and constructing a dual objective function for attack cost and attack failure effect. A complex network dataset is generated, downloaded, and preprocessed. Second, addressing the low computational and optimization efficiency caused by multiple traversals of the entire network in each evaluation of cascading simulations during critical node detection in complex networks, this invention constructs and trains a multi-branch attention GCN proxy model. Through multi-dimensional feature extraction, multi-task learning, and group calibration, the prediction accuracy of the number of cascading failure nodes is ensured. Then, a multi-objective optimization algorithm fusing GA and PSO is used iteratively, combined with the GCN proxy model to predict the objective function, improving optimization efficiency. The convergence and diversity of solutions are balanced through GA global search and PSO local optimization. Next, the Pareto optimal solution is calibrated and verified to ensure the relative error is within a reasonable range and to verify accuracy. Finally, the experimental results are output and archived. This invention utilizes the GCN proxy model to assist in the fusion of multi-objective optimization algorithms, significantly improving optimization efficiency and prediction accuracy, and enabling precise detection of key nodes in complex networks.

The application discloses a multi-target respiratory signal separation method, system, device and storage medium, which is applied to the technical field of non-contact vital sign monitoring, and the method comprises the steps of: acquiring a training data set, wherein the training data set is generated by linear superposition of multiple respiratory source signals in a complex domain; constructing a deep learning separation model, wherein the deep learning separation model comprises a radar encoder module, a radar separator module and a radar decoder module which are connected in sequence; training the deep learning separation model based on the training data set by using a permutation-invariant training strategy; inputting the acquired respiratory phase signal into the trained deep learning separation model, and outputting separated target independent respiratory waveforms; and the application can separate and reconstruct the target independent respiratory waveforms in a complex scene with multiple people overlapping in space and similar respiratory frequencies, has strong noise robustness, and provides an effective solution for low-cost and non-contact health monitoring.