10results about How to "Improve feature extraction efficiency" patented technology

The application provides a facial expression recognition method based on a double attention mechanism, named Adaptive Spatio-Excitation Transformer (ASET). This method introduces Adaptive Squeeze-and-Excitation (ASE) attention mechanism and spatial attention mechanism, and combines with Transformer network, which significantly improves the accuracy and efficiency of facial expression recognition. The core of the application is to recalibrate the channels of feature maps through ASE mechanism, and focus on the key areas of the face through spatial attention mechanism, so as to more efficiently extract expression features. In addition, the application also introduces visualization technology to highlight the key areas in the face image, helping to understand the decision-making process of the model. Experimental results show that the application has achieved excellent performance on multiple standard datasets such as FER2013, CK+ and JAFFE, and has significantly improved performance compared with existing technology. The application can be widely used in human-computer interaction, sentiment analysis and other fields, providing an efficient and accurate solution for facial expression recognition.

This invention provides an automatic SAR target detection method and apparatus based on adaptive feature focusing, belonging to the field of SAR image detection. The method includes: constructing a lightweight EOD-Net; after the backbone network extracts multi-scale features, the latent target perception branch PTBranch outputs a mask to coarsely locate the target region; and using a no-overlap feature map cropping NOFC to iteratively remove overlapping blocks, retaining only non-overlapping target feature blocks for the detection head to regress. During the training phase, a Gaussian-binary hybrid mask supervises PTBranch, and the focus loss and DICE loss are jointly optimized. This invention outperforms comparable methods such as YOLOv11 and Faster RCNN, achieving high-precision and efficient SAR image detection.

The invention discloses an ultra-high voltage power transmission line channel unmanned aerial vehicle inspection optimization and improvement method. The method comprises the following steps: S1, carrying out real-time image acquisition on a power transmission line channel based on an unmanned aerial vehicle aerial survey technology; s2, an adaptive median filtering and bilateral filtering combined algorithm is adopted to pre-process the image; s3, performing brightness equalization processing on the image and adjusting the image contrast; s4, performing multi-level feature extraction on the power transmission line channel image; s5, targets in the transmission line channel are detected based on the stable features and the dynamic features; according to the invention, optimization processing can be carried out on the unmanned aerial vehicle inspection image, multi-level feature extraction is carried out, a detection model is constructed, target detection and change detection of a power transmission line channel are realized, and hidden dangers are rapidly identified.

The application discloses a tomato disease and pest identification method based on an improved ControlNeXt lightweight classification model, and comprises the following steps: 1) model structure optimization; 2) lightweight module integration; 3) training strategy optimization; 4) performance verification; and 5) disease and pest identification. The tomato disease and pest identification method solves the outstanding problems in model complexity, calculation efficiency and actual deployment adaptability by improving the YOLOv8s-CLS model, and realizes the balance between accuracy and lightweight.

The application discloses a pipeline leakage detection method and device, the method comprises the following steps: acquiring video images and pressure data of multiple continuous time steps in a pipeline, fusing the video images and the pressure data to obtain fusion information; performing space-time feature extraction on the fusion information by using a space-time feature extraction network to obtain a feature vector; performing classification prediction on the feature vector by using each classification head in a trained multi-heterogeneous structure classification model to obtain pipeline state categories output by each classification head; and determining a final pipeline state category by using an entropy balance decision function according to the pipeline state categories output by each classification head and weights of each classification head, so that the accuracy of pipeline leakage detection is improved.

The application discloses a game performance analysis and running stability prediction system based on artificial intelligence, relates to the cross technical field of machine learning and game technology, and comprises a data acquisition and preprocessing module, a causal feature extraction module, a stability prediction module and a causal root cause positioning module; the data acquisition and preprocessing module collects game performance data in multiple channels and completes standardized processing to generate frame-level feature vectors, the causal feature extraction module builds a causal graph by improving a PC algorithm, filters features, and adaptively adjusts feature weights, the stability prediction module predicts abnormal probability by means of a causal time series convolution network and triggers early warning, and the causal root cause positioning module completes root cause searching and hierarchical judgment by relying on virtual causal intervention, wherein the application replaces the traditional experience-based feature filtering and correlation analysis mode by means of causal logic, saves the complicated operation of manual index filtering, can position multi-level performance causes layer by layer, and captures game lag and crash hidden dangers early.

This invention relates to a feature extraction model training and feature extraction method and apparatus, comprising: inputting a training image set into an initial model; extracting several local features from the training images by a local feature extraction layer; enhancing the several local features using an attention mechanism by a feature enhancement layer to obtain several enhanced local features; a global feature extraction layer aggregating features based on the several enhanced local features to obtain global features; and a classifier obtaining predicted classification parameters for the training images based on the global features. The model parameters of the initial model are adjusted according to the label parameters and predicted classification parameters of the training images to obtain a trained classification model. A feature extraction model for extracting global features is constructed based on the local feature extraction layer, feature enhancement layer, and global feature extraction layer in the classification model. This provides an end-to-end global feature extraction scheme, reducing algorithm complexity.

The application discloses a kind of diagnostic methods and systems for glenoid and humeral head defect area, belong to image processing technical field, the method includes: obtaining the medical image data of the glenoid and humeral head to be processed;The medical image data is input into the segmentation model of pre-setting, and the segmentation result of glenoid and humeral head is obtained;Based on the segmentation result, the defect area and defect proportion of glenoid are calculated;Based on the defect proportion, the defect degree of humeral head is determined.The diagnostic method and system for glenoid and humeral head defect area of the application provide a kind of efficient, accurate intelligent diagnostic auxiliary tool for clinic, with good application prospect and popularization value.

The application discloses a precoding matrix indication selection method based on a neural network. In the method, a user end first acquires a channel matrix of a downlink; then, the channel matrix is preprocessed by downsampling, segmented discrete Fourier transform and number domain conversion, so that input features suitable for neural network processing are obtained; then, the neural network is used for feature extraction and code word mapping on the preprocessed channel features, corresponding code word numbers are output for each subband, and the code word numbers are converted into precoding matrix indication (PMI) parameters; subsequently, the user end feeds back the PMI to a base station; and the base station maps corresponding precoding matrices according to the same predefined codebook and the received PMI, and the precoding matrices are used for downlink beamforming transmission. The application uses the neural network to replace a conventional traversal search type PMI selection process, reduces the calculation complexity of the user end under the premise of keeping compatibility with an existing codebook feedback mechanism, and improves the PMI selection efficiency.

The embodiment of the application provides a text feature extraction method and system, wherein the method comprises: obtaining a text string to be processed; performing word segmentation processing on the text string to obtain a word segmentation result; generating a phoneme sequence according to the word segmentation result; separating the phoneme sequence into a phoneme feature combination; and generating feature data of the text string according to the phoneme feature combination. The embodiment of the application generates a phoneme sequence and separates a phoneme feature combination, accurately extracts phoneme-level features of the text, directly adapts to the analysis requirement of a pronunciation correction scene on speech details, and overcomes the insufficient applicability of a traditional method due to focusing on speech signal processing or semantic understanding. Meanwhile, the embodiment of the application does not need to rely on complex speech synthesis or signal processing, significantly reduces the computational complexity, and improves the efficiency of feature extraction.