Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

580results about How to "Improve discrimination" patented technology

Unmanned aerial vehicle multi-modal remote sensing image target detection method and device based on hybrid Mamb-CNN network

The invention provides an unmanned aerial vehicle multi-mode remote sensing image target detection method and device based on a hybrid Mamb-CNN network. The method comprises the steps of obtaining a visible light image and a thermal infrared image to be detected; inputting the visible light image and the thermal infrared image into a target detection network to obtain a remote sensing detection result; the target detection network is constructed based on a twinborn feature extraction network, the twinborn feature extraction network comprises a visible light branch network, an infrared branch network, a cross-modal fusion module, a neck layer and a detection head, the visible light branch network extracts visible light local features in a visible light image, the infrared branch network extracts infrared local features in a thermal infrared image, and the cross-modal fusion module carries out cross-modal fusion; the cross-modal fusion module fuses the visible light local features and the infrared local features to obtain multi-scale features, the neck layer is based on the multi-scale features to obtain global fusion features, and the detection head is based on the global fusion features to obtain remote sensing detection results, so that the precision and robustness of multi-modal target detection are enhanced.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Pseudo-label-based passive unsupervised domain adaptive medical image segmentation method and device

The invention discloses a passive unsupervised domain adaptive medical image segmentation method and device based on pseudo labels, and relates to the technical field of computers, and the method comprises a supervised source domain model training stage, an unsupervised adaptive target domain model training stage and a segmentation stage. The method specifically comprises the following steps of: performing pixel-level self-marking on a source domain medical image by applying pseudo-tag pixel-level uncertainty estimation to generate a reliable pseudo-tag; and on this basis, a strong and weak enhanced teacher-student target domain model is used, and a high-quality pseudo tag is fully utilized to train a target domain medical image, so that the network adapts to representation specific to the target domain medical image. According to the method, unsupervised segmentation is carried out on the target domain data graph on the premise that the source domain model and the target domain unmarked data are known, source domain data do not need to be accessed, the features of the source domain model can be reasonably utilized, and the problem existing in SFUDA can be well relieved; and the accurate segmentation capability on the target domain is still maintained under the condition that less data is available compared with the UDA method.
Owner:THE FIRST AFFILIATED HOSPITAL OF XIAMEN UNIV +1

Multi-article identification and distinguishing method, system, equipment and medium

The invention relates to a multi-article identification and distinguishing method, system and device and a medium. The method comprises the steps of obtaining multi-view image data of articles in a target area; performing object detection and instance segmentation on the multi-view image data by using a deep learning algorithm to obtain preprocessed image data; acquiring a first spatial position of the object in the target area by using a depth sensor, and performing spatial correction by combining the preprocessed image data to obtain depth information of the object in the target area; in combination with the preprocessed image data and depth information, performing secondary positioning on articles in the target area through a multi-modal data fusion algorithm, optimizing the distinguishing between the articles in the target area by using spatial correlation, confirming the identity information of each article in the target area, and generating an identification result; and matching the identification result with the article state in a preset database to generate a matching result, and feeding back the matching result to the user side. The method has the effect of improving the recognition precision of the borrowing machine.
Owner:上海视颐电子科技有限公司

Remote sensing image target dynamic detection method based on multi-kernel

The invention provides a remote sensing image target dynamic detection method based on a multi-kernel, and belongs to the field of remote sensing image detection.The method comprises the steps that a remote sensing image is collected, a YOLOv8 model is optimized, information extraction is conducted on the remote sensing image through a multi-kernel-based cross-stage feature fusion module in a backbone network of the optimized YOLOv8 model, and the remote sensing image is obtained; obtaining feature maps of different scales; performing dynamic up-sampling on the feature map by using a neck network, outputting an up-sampled feature map in response to the neck network, adding a dynamic detection head, and performing optimization and feature fusion on the up-sampled feature map by using an attention mechanism to obtain a fused feature map; and classifying the feature map to obtain a classified target detection result. According to the method, the problems of insufficient experimental effect on a multi-category data set, large number of small targets, large scale change and dense distribution of remote sensing image targets and detection conditions under a complex background in the prior art are solved.
Owner:SOUTHWEST JIAOTONG UNIV

Personalized federated confrontation cross-modal hashing method based on double prototypes

The invention discloses a personalized federal confrontation cross-modal hashing method based on double prototypes, which mainly comprises the following steps of: clustering local class-level prototypes uploaded by a client at a server side to obtain a clustering prototype, averaging to obtain an unbiased prototype, and according to gradient change, obtaining an unbiased prototype; generating personalized hierarchical weights for the client network using the super network; the client constructs an adversarial learning process by using approximate hash codes and clustering prototypes of the two modal networks, keeps the consistency between an unbiased prototype and a local class-level prototype, and further embeds the unbiased prototype into a training process of a client model; after local training is completed, all network parameters and local class-level prototypes of the client side are uploaded to the server; and after the last communication round is completed, generating a to-be-retrieved hash code based on the final client parameter, and providing an original data retrieval result according to the original data position information corresponding to the hash code with the minimum distance.
Owner:SHANDONG NORMAL UNIV

High-speed rail bearing multi-scale feature fusion fault prediction method

The invention discloses a multi-scale feature fusion fault prediction method for a high-speed rail bearing. The method comprises the following steps: acquiring a fault vibration signal of the high-speed rail bearing through a vibration signal comparison technology; noise and interference signals of the high-speed rail bearing fault original vibration signals are removed through an adaptive filter; performing multi-level decomposition on the vibration signal by using wavelet packet decomposition, extracting sub-band signals of different frequency bands, calculating instantaneous frequency and energy distribution of the sub-band signals by using Hilbert-Huang transform, and forming a time-frequency-energy three-dimensional feature map; carrying out weight distribution on each feature dimension in the three-dimensional feature map by adopting a self-adaptive weighting algorithm; constructing a training data set through the time-frequency-energy three-dimensional feature map and the fault type label; and training the long short-term memory network LSTM by using the training data set, constructing a fault prediction model, and performing fault prediction on the high-speed rail bearing. According to the invention, accurate prediction of the high-speed rail bearing fault is realized, and the accuracy of fault detection is improved.
Owner:CHUZHOU VOCATIONAL & TECHN COLLEGE

Colon polyp target detection method and system based on improved YOLOv8

The invention relates to the technical field of medical detection, and particularly discloses a colon polyp target detection method and system based on improved YOLOv8, and the method comprises the steps: obtaining an image data set of colon polyp, carrying out the preprocessing of the image data set, and dividing the preprocessed image data set into a training set, a verification set and a test set; an improved detection model is built, a first attention mechanism module is embedded in a C2f module of a network structure part of a basic model, a second attention mechanism module is embedded in a C2f module of another network structure part, a training set is input into the improved model for iterative training, and a detection result is obtained; and performing performance evaluation on the trained model based on the verification set to obtain an optimized colon polyp target inspection model. And inputting the test set into the colon polyp target inspection model to obtain a colon polyp target inspection result. The method improves the detection precision of the colon polyp target with small target detection and fuzzy boundary.
Owner:南昌大学第一附属医院

Network security situation awareness method based on artificial intelligence

The invention relates to the technical field of artificial intelligence, and discloses a network security situation awareness method based on artificial intelligence, which comprises the following steps: acquiring network security data; performing feature extraction on the network security data by adopting a full-connection neural network based on dynamic group evolution optimization to obtain a first feature; performing feature dimension reduction on the first feature by using a self-encoding neural network based on contrast entropy to obtain a second feature; constructing a classifier model by using a fractional order neural network based on complexity perception, and training the classifier model by using the second feature; and performing network security situation awareness classification by using the trained classifier model. According to the method, the capability of distinguishing the complex network security situation is improved, a more accurate classification effect can be realized, and the applicability of the model in the network security data and the classification accuracy are enhanced.
Owner:CHENGDU ANZHUN NETWORK SECURITY TECH CO LTD

Polyp image segmentation method based on boundary clue depth fusion

The invention discloses a polyp image segmentation method based on boundary clue depth fusion, and the method comprises the steps: inputting an intestinal polyp image into a backbone network through constructing a boundary clue depth fusion network, and extracting different levels of feature information, so as to guide the extraction of a polyp region; a boundary clue mining module is constructed to obtain boundary detail information by means of partial hierarchical features, and more accurate positioning of a polyp area is realized; constructing a foreground target enhancement module to enhance the learning of the network on the overall structure characteristics of the foreground target in combination with the reverse attention branch, so that the network focuses on the foreground target; and constructing a depth feature fusion module to integrate boundary information and foreground information, further improving the segmentation performance through cascade feature fusion and boundary information guidance, and finally obtaining a polyp segmentation result by using the trained model. According to the method, the limitation of the polyp in boundary uncertainty and morphological diversity is overcome, the weighted joint scale difference loss optimization model is adopted in training, and high-precision recognition and segmentation of the polyp region are realized.
Owner:CHINA JILIANG UNIV

Short message fraud identification method and system based on machine learning and computer equipment

The invention relates to the technical field of short message fraud recognition, and discloses a short message fraud recognition method and system based on machine learning and computer equipment, and the method comprises the steps: carrying out the preprocessing of collected fraud and non-fraud short message samples, and obtaining structured short message data; performing multi-dimensional feature extraction to obtain an initial feature vector; constructing a short message fraud multi-mode knowledge graph; performing feature enhancement to obtain a knowledge enhancement feature vector; inputting the knowledge enhancement feature vector into a plurality of machine learning models for training to obtain an integrated short message fraud recognition model; and performing real-time analysis on the newly received short message based on the integrated short message fraud identification model to obtain a fraud risk prediction result, so that the newly received short message can be quickly analyzed, the real-time requirement in practical application is met, and a risk threshold classification mechanism is adopted, so that the fraud risk prediction result is more interpretable and operable, and the fraud risk prediction accuracy is improved. And subsequent risk management and disposal are facilitated.
Owner:SHENZHEN GAUSS COMM CO LTD

Fault diagnosis method for engine gearbox based on PSO-VMD and multi-class support vector machine

The invention discloses an engine gearbox fault diagnosis method based on PSO-VMD and a multi-class support vector machine, and belongs to the technical field of engine gearbox fault diagnosis. The method comprises the following steps: optimizing two parameters, namely the number K of components of VMD and a penalty factor alpha, by using a PSO algorithm, and performing modal decomposition on a vibration signal by using an optimized VMD method to obtain a plurality of IMF components; selecting a sensitive mode by calculating the energy of the IMF component; and reconstructing the sensitive mode to complete noise reduction processing of the vibration signal. And extracting the reconstructed vibration signal to obtain a characteristic variable, inputting the extracted characteristic variable into a multi-class support vector machine with a maximum minimum interval, and selecting a suitable adjustable parameter p and a slack variable s to complete fault diagnosis of the engine gearbox. Simulation experiments show that the method can significantly improve the accuracy of fault diagnosis of the engine gearbox.
Owner:DALIAN UNIV OF TECH

Multi-channel attention mechanism lncRNA-miRNA association prediction method

The invention discloses an lncRNA-miRNA association prediction method of a multi-channel attention mechanism, and relates to an lncRNA-miRNA association prediction method. The method aims to solve the problem that more effective and robust feature representation may not be learned due to the fact that feature representation of multiple data sources cannot be properly fused and similarity and difference between samples cannot be learned through a contrast learning method in an existing method. According to the method, multi-source data of lncRNA and miRNA is obtained, and multiple similarity matrixes and coding matrixes are obtained through calculation; in combination with a graph convolutional network and a Transform, capturing information from a local angle and a global angle; fusing feature representations of different data sources by using a multi-channel attention mechanism; a contrast learning method is introduced to further optimize feature representation, so that the consistency between different modal features of the same lncRNA or miRNA is ensured, and the discrimination capability of the model is enhanced; in the final prediction stage, KAN is utilized to obtain a prediction score associated with lncRNA-miRNA, and the parameter and calculation efficiency are further improved.
Owner:NORTHEAST FORESTRY UNIV

Visual target tracking method based on sparse Transform

The invention provides a visual target tracking method based on sparse Transform, and relates to the technical field of visual target tracking, the method converts a target tracking problem into a sequence generation problem, firstly, a simple encoder-decoder architecture based on Transform is used, an additional header network is eliminated, and a tracking architecture is simplified; secondly, a sparse attention mechanism is added into a decoder, so that the model pays more attention to key information, and the distinction degree between a foreground and a background is improved; the method comprises the following steps: constructing a network model; constructing a sparse attention mechanism, and applying the sparse attention mechanism in a decoder in the network model; training the network model according to the loss function; and tracking a target in the video by using the trained network model. The method provided by the invention has higher accuracy and robustness when facing complex scenes with serious shielding, illumination, scale change and the like.
Owner:SHENYANG UNIV

Aviation data bus signal encryption method and system based on FPGA

The invention relates to the technical field of signal encryption, in particular to an aviation data bus signal encryption method and system based on a field programmable gate array (FPGA), which comprises the following steps of: based on input three-dimensional tensor signal data, extracting slices from a time index of an aviation data bus according to a fixed interval, progressively sequencing amplitudes of signal channels, and then segmenting; according to the method, through processing logic of matrix decomposition and feature curve generation, the feature extraction and dimension reduction process is optimized, the distinction degree and the expression capacity of feature information are improved, the randomness and the anti-cracking capacity of a key are enhanced through a key generation mode combining a dynamic disturbance factor and an encryption parameter, and the safety of signal transmission is guaranteed; through combination of amplitude superposition and frame-by-frame storage, dynamism and high efficiency of a signal encryption process are realized, signal tampering and eavesdropping risks are reduced, and through feature reconstruction and point-by-point matching processing in a decryption stage, accurate restoration of signal amplitude is ensured, and data integrity and anti-interference capability are guaranteed.
Owner:XIAN JANGHO ELECTRONIC TECH CO LTD

Paper innovation quality measurement index generation method based on large language model

The invention provides a method for generating a measurement index of thesis innovation quality based on a big language model, and relates to the technical field of thesis innovation quality measurement, and the method comprises the steps: firstly obtaining to-be-tested thesis data; the to-be-tested paper data is input into a preset science and technology paper innovation quality measurement model, the science and technology paper innovation quality measurement model comprises a novelty measurement module, a usefulness score calculation module and a measurement index calculation module, and the novelty measurement module carries out keyword extraction on the to-be-tested paper data through a constructed large language model; calculating to obtain a novelty score according to the keyword; the usefulness score calculation module calculates a usefulness score according to the to-be-tested paper data; and inputting the novelty score and the usefulness score into a measurement index calculation module, wherein a measurement index is used for measuring the innovation quality of the to-be-measured paper. According to the method, the distinction degree of innovative measurement of the paper is effectively improved, the comprehensiveness of prediction dimensions is ensured, measurement index generation is performed on the paper from an objective angle, and the reliability of a measurement result is ensured.
Owner:SUN YAT SEN UNIV

Image segmentation method and device, computer equipment and storage medium

The invention provides an image segmentation method and device, computer equipment and a storage medium, and belongs to the field of image processing, and the method comprises the steps: obtaining a to-be-segmented target medical image, and determining a two-dimensional histogram of the target medical image; representing the Renyi entropy of the target medical image through a plurality of gray threshold values in the two-dimensional histogram; stepwise strengthening is introduced into the bat algorithm, the exploration capability and the algorithm development capability of the bat algorithm are strengthened, and the improved bat algorithm is obtained; taking maximization of the Renyi entropy as a target, and performing iterative optimization on the plurality of gray threshold values through an improved bat algorithm to obtain an optimal threshold value set; and segmenting the target medical image based on the optimal threshold set to obtain a segmentation result. Therefore, the Renyi entropy is introduced to preliminarily quantify the quality of image segmentation, the maximization of the Renyi entropy is taken as a target, iteration is carried out through the improved bat algorithm, the optimal solution of the gray threshold is effectively found, and finally segmentation is carried out through the optimal solution, so that the segmented image provides better information retentivity and discrimination.
Owner:BIG DATA & INFORMATION TECH RES INST OF WENZHOU UNIV

All-electric drive aircraft tractor control system and method

The invention relates to the field of electric digital data processing, in particular to a control system and method for an all-electric drive aircraft tractor. The method mainly comprises nine steps from S1 to S9. The system comprises a data storage module, a data acquisition module, a data expansion module, a data processing module, a tractor control module and an execution module. An existing full-electric drive aircraft tractor control system has the problems that the data processing capacity is poor and the decision-making accuracy is low. The control system and method for the all-electric drive aircraft tractor are high in data processing capacity and high in decision-making accuracy.
Owner:XIAN RVNUO NEW ENERGY

Hysteroscope image color feature transformation method based on deep learning

The invention discloses a hysteroscope image color feature transformation method based on deep learning, particularly relates to the field of medical image processing, solves the problem of insufficient analysis accuracy caused by color feature redundancy in a hysteroscope image, and ensures high-quality image data through multi-level accurate screening. Extracting multi-dimensional color features by using nonlinear mapping and structural analysis, and enhancing the expression and discrimination of the features; the constructed multi-level index system is combined with spectral analysis and graph theory operation, and the macroscopic distribution difference and the microcosmic robustness of the features are accurately measured; the method comprises the following steps: successfully extracting a key candidate dimension subset with high discrimination and robustness in a complex scene through a Pareto-like leading edge search and topological data analysis technology, multi-round iteration and graph theory clustering screening; therefore, the problems of color feature redundancy, insufficient stability and poor adaptability are effectively solved, and the accuracy and reliability of hysteroscope image analysis are remarkably improved.
Owner:SHANGHAI YODO MEDICAL TECH

Intelligent coal gangue and coal quality sorting method and system based on image hyperspectral technology

The invention belongs to the technical field of coal processing, and particularly discloses an intelligent coal gangue and coal quality sorting method and system based on an image hyperspectral technology, and the method comprises the steps: obtaining a hyperspectral image on a to-be-detected sample transmission line, converting the hyperspectral image into a grayscale image, and extracting the edge information of a to-be-detected sample; segmenting a spectral image of each to-be-detected sample, and extracting position information of each to-be-detected sample at the same time; determining the dynamic position of each sample to be detected; transmitting sound waves to each to-be-tested sample, and receiving sound wave signals passing through each to-be-tested sample; preprocessing the spectral image and the sound wave signal of each to-be-detected sample, and respectively extracting spectral features, texture features, spatial features and sound wave features to form a comprehensive feature vector; and inputting the comprehensive feature vector into a trained coal gangue recognition model to obtain a coal gangue and coal recognition result. According to the method, the sorting precision of the coal gangue and the coal quality is remarkably improved, so that the model can still keep relatively high recognition precision in a complex environment.
Owner:SHANDONG UNIV

Multi-factor network security authentication method and system based on SDN (Software Defined Network)

The invention discloses a multi-factor network security authentication method and system based on an SDN (Software Defined Network). The method comprises the following steps: constructing a multi-dimensional authentication space comprising an identity feature dimension, a behavior feature dimension and an environment feature dimension in an SDN controller; decomposing the eigenvalues into deterministic sequence components and random sequence components by adopting a dynamic sequence decomposition method, and calculating the correlation degree of the eigenvalues among dimensions; according to the method, the stability index is calculated based on the feature stability evaluation function, the fusion authentication decision function is constructed to carry out authentication decision, safe and reliable network authentication is achieved through the technical means of multi-dimensional feature fusion analysis, dynamic sequence decomposition, self-adaptive decision and the like, and the method has high practical value.
Owner:HUANENG LANCANG RIVER HYDROPOWER CO LTD

Visual inspection method and system for appearance defects of IC package carrier

The invention relates to the technical field of image processing, in particular to a visual inspection method and system for appearance defects of an IC package carrier, and the method comprises the steps: according to the regional concentration ratio of each super-pixel block in each convex hull, the color brightness difference value and the area of all connected domains in each super-pixel block in each convex hull, carrying out visual inspection on the appearance defects of each super-pixel block in each convex hull; and determining a region feature value of each superpixel block in each convex hull, determining a filtering window of each pixel point in the package carrier gray-scale map, and detecting the filtered package carrier. According to the method and the device, the window size of each pixel point on the IC package substrate in a filtering algorithm is determined by analyzing the normal texture region and the oxidation defect region in the gold surface region on the IC package substrate and the characteristics of the noise appearing in the acquired image, so that the accuracy of detecting the oxidation defect in the gold surface region on the IC package substrate is improved.
Owner:SUPER TECH IND (GUANGDONG) CO LTD +1

Elevator fault prediction method and system based on sound and vibration fusion

The invention discloses an elevator fault prediction method and system based on sound and vibration fusion, and the method comprises the steps: carrying out the weighted fusion of a vibration signal and a sound signal according to a signal-to-noise ratio, and then combining with a feature matrix composed of a wavelet packet transformation normalized energy value, a time domain and a frequency domain, applying a Sodat swarm algorithm to an optimization support vector machine model, and carrying out the prediction of an elevator fault. And carrying out feature classification on the feature matrix by using the model. According to the invention, the accuracy of fault prediction can be improved, and the risk of sudden faults is reduced, so that the maintenance efficiency is optimized and the fault rate is reduced.
Owner:NANJING KANGNI MECHANICAL & ELECTRICAL

Database visualization method based on single cell

The invention relates to the technical field of single cell data processing, in particular to a database visualization method based on single cells. The method comprises the following steps: acquiring a single cell data set; standardizing the single cell data set to obtain standardized single cell data; performing high-dimensional feature extraction on the standardized single-cell data to obtain single-cell high-dimensional feature data; and performing nonlinear dimension reduction processing on the single-cell high-dimensional feature data to obtain single-cell dimension reduction data. Performing data clustering on the single cell dimension reduction data to obtain single cell clustering data; performing gene differential expression extraction on the single cell clustering data to obtain differential expression gene data; multi-modal data fusion analysis is carried out on single cell data through a data processing technology, a feature mapping technology and a visualization technology; and dynamic weight division is carried out on the single cell database, so that the effect of visualization of the single cell database is enhanced.
Owner:ZEBRAFISH (BEIJING) TECHNOLOGY CO LTD

Low-slow small unmanned aerial vehicle detection method based on acoustic fusion features

The invention discloses a low-slow-small unmanned aerial vehicle detection method based on acoustic fusion features, relates to an unmanned aerial vehicle detection method, and belongs to the field of signal processing technologies and deep learning. The objective of the invention is to solve the problem that the traditional unmanned aerial vehicle detection method mainly depends on radar, vision, infrared and other technologies, but the detection accuracy of a low-speed small unmanned aerial vehicle is low in a complex urban environment. The method comprises the following steps: establishing an unmanned aerial vehicle audio signal data set in an urban environment; constructing an unmanned aerial vehicle detection network model; taking the unmanned aerial vehicle audio signal in the urban environment as the input of the unmanned aerial vehicle detection network model, and taking the detection result as the output of the unmanned aerial vehicle detection network model; the detection result is whether the unmanned aerial vehicle exists; obtaining a trained unmanned aerial vehicle detection network model; and inputting an audio signal in a to-be-detected urban environment into the trained unmanned aerial vehicle detection network model, and outputting a detection result by the trained unmanned aerial vehicle detection network model.
Owner:JILIN UNIVERSITY

Multi-modal emotion recognition method based on deep learning

PendingCN119150165AReduce training overheadSimplify Design ComplexitySpeech analysisBiological modelsPattern recognitionSpeech sound
The invention relates to the technical field of emotion recognition, in particular to a multi-modal emotion recognition method based on deep learning, which comprises the following steps: constructing and training a multi-modal emotion recognition model, and inputting to-be-recognized data into the trained multi-modal emotion recognition model to output a recognition result; the multi-modal emotion recognition model comprises a self-attention encoder, a first cross attention encoder, a second cross attention encoder, a gating unit and an MLP classifier; according to the method, comprehensive learning and interaction are carried out by combining two modal data of voice and text, the emotion information is more comprehensive, the inherent defect of a single feature is made up, and the robustness of the model is higher and the accuracy is higher.
Owner:CHONGQING XIAOYI ZHILIAN INTELLIGENT TECH CO LTD

Vehicle re-identification method, device, equipment and product based on multi-modal pre-training

The invention discloses a vehicle re-identification method, device, equipment and product based on multi-modal pre-training. The method comprises the following steps: acquiring vehicle data of a target vehicle; wherein the vehicle data at least comprises one of vehicle image data or text description information of the target vehicle; performing feature extraction on the vehicle data by adopting a trained multi-modal vehicle re-identification model to obtain final features of the vehicle data, and outputting information of the target vehicle according to the final features; wherein the trained multi-modal vehicle re-identification model comprises a pre-trained visual converter model, a pre-trained text graph model and a visual converter main network. According to the method, multiple query modes and text information embedding can be supported, capturing of image text information and understanding of image semantics are improved, the robustness and discrimination of extracted features are enhanced through pre-training, and therefore the vehicle re-recognition performance is improved.
Owner:GUANGDONG SCI & TECH INFRASTRUCTURE CENT +2

Medical image segmentation method based on multiple extended recursive attention

A medical image segmentation method based on multi-extended recursive attention belongs to the technical field of image segmentation, and comprises the following steps: a coding part: coding input features by a multi-extended recursive attention block and a feature merging layer; in the decoding part, firstly, the feature data of the multi-extended recursive attention block encoding part are input into a decoder; secondly, the decoder gradually recovers the original resolution of the image through up-sampling, and semantic information obtained through up-sampling and features output by the encoder of the first part are subjected to feature interaction through jump connection; thirdly, inputting the interacted features into the decoding part of the recursive attention block, and restoring the original information of the image to the maximum extent; and finally, through a linear mapping layer, obtaining a pixel-level segmentation prediction result according to the extracted image feature marks. By adopting the method, the model can show better overall performance and robustness in a segmentation task, and the method has important significance in practical application in the fields of medical images and the like.
Owner:HUAIBEI NORMAL UNIVERSITY

Drug target affinity prediction method based on sequence modality and graph modality

The invention provides a drug target affinity prediction method based on a graph mode and a sequence mode, and aims to solve the problems of single-mode limitation and local and overall structure capture of an existing graph neural network and realize multi-mode feature fusion. The method comprises the following steps: data preprocessing: converting a protein sequence and a molecular SMILES sequence into a Graph form; extracting features of a graph mode and a sequence mode, and respectively designing feature extraction modules; multi-modal feature fusion: carrying out feature fusion through a specific module; and carrying out regression prediction by using a deep neural network (DNN). In the model training, the prediction performance is improved by optimizing parameters and structures, and comparison experiment verification is performed, so that the reliability is shown, and the application potential in drug research and development is indicated.
Owner:HUZHOU UNIVERSITY

Pedestrian re-identification method, device and system based on attitude estimation and storage medium

The invention discloses a pedestrian re-recognition method, device and system based on attitude estimation and a storage medium, and relates to the technical field of image recognition. The method comprises the following steps: acquiring original modal data, and extracting exclusive features to obtain a visible light modal feature map and an infrared modal feature map; extracting common features based on a multi-head self-attention mechanism to obtain a shared feature map; processing the original modal data based on attitude estimation to obtain a key point thermodynamic diagram of the original modal data; performing score diagram processing on the key point thermodynamic diagram to obtain a score diagram and score confidence of the key point thermodynamic diagram; performing multi-head batch normalization weighting processing on the score map, the score confidence coefficient and the shared feature map to obtain a feature vector set; and carrying out distance measurement matching on the feature vector set to obtain a pedestrian re-identification result. According to the embodiment of the invention, the robustness and adaptability of the system are improved, the capability of processing the shielding problem is improved, and the accuracy and efficiency of pedestrian re-identification are improved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Method for acquiring optimal grabbing pose of plug seedling

The invention discloses a method for acquiring an optimal grabbing pose of a plug seedling. The method depends on a two-finger clamping jaw of graded transplanting equipment. The two-finger clamping jaw is positioned above the hole tray; the method comprises the following steps: 1, representing a grabbing pose: # imgabs0 # 2, constructing a data set: shooting a hole tray image from a vertically downward visual angle; the shot images are segmented and zoomed according to plug grids, and pixel-level capture pose labeling is carried out on each image; 3, training a neural network: inputting a required original image into the real-time grabbing detection network, and outputting the grabbing confidence degree, the grabbing angle and the grabbing width of each pixel point in the image by the real-time grabbing detection network; according to the method, the optimal grabbing pose of each seedling in the plug is obtained by fusing machine vision and deep learning, the seedlings are grabbed based on the optimal grabbing poses, leaves and stalks of the seedlings can be effectively avoided, the damage rate in the plug seedling grabbing process is reduced, and the survival rate of the transplanted seedlings is increased.
Owner:NANHUA UNIV