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

14results about How to "Enhanced feature information" patented technology

Optical remote sensing image building change detection method based on deep learning

The invention discloses an optical remote sensing image building change detection method based on deep learning, and belongs to the field of remote sensing image change detection. The method comprises the following steps: firstly, acquiring optical remote sensing image data from high-resolution No.2, preprocessing the optical remote sensing image data, and labeling a change information label Label; and then the image is input into the change detection model, and a detection result graph is output through calculation. The problems that an existing change detection method is low in detection precision and incomplete in detection edge, and a change detection algorithm is poor in universality on different data sets are effectively optimized and improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Target detection method and device, vehicle and storage medium

The invention relates to a target detection method and device, a vehicle and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a to-be-detected target image; the target image comprises a plurality of target objects to be detected; inputting the target image into a target detection model to obtain a detection result of the target image; the target detection model comprises a feature fusion network of a channel fusion space attention mechanism; the detection result comprises a plurality of bounding boxes and a plurality of labels; the bounding box is used for marking the positions of the multiple target objects in the target image; the labels are used for representing categories of the multiple target objects of the bounding box. Therefore, the target detection model can more accurately capture the features of the small target object and the shielded target object in the target image based on a channel fusion space attention mechanism, and more effectively fuses the features of each target object in the target image at different levels, thereby improving the precision of target detection.
Owner:CHONGQING CHANGAN TECH CO LTD

Gesture interaction method and system, readable storage medium and computer

The invention provides a gesture interaction method and system, a readable storage medium and a computer. The method comprises the following steps: acquiring a sight focusing area of a user for a virtual marker; inputting the hand image into a convolutional neural network model for convolution operation to obtain a convolutional feature image; performing pixel processing based on the hand coding image of the hand image to obtain a corresponding pixel feature image; importing the multi-scale fusion unit into a multi-resolution network model for model optimization to obtain a network optimization model; and inputting the convolutional feature image and the pixel feature image into a network optimization model to output a hand posture estimation result of the user, and performing collision judgment according to the hand posture estimation result and the sight focusing area to realize gesture interaction of the user. According to the method, attitude estimation is carried out on the convolution feature image and the pixel feature image by using the network optimization model, and the influence of network parameter quantity on hand attitude estimation is reduced, so that the detection error of hand joint points is reduced.
Owner:HUIZHI WORLD (HANGZHOU) TECHNOLOGY CO LTD

Government purchase commodity transaction price prediction method and device based on CMPSOLSTMTLM model

The invention provides a government purchase commodity transaction price prediction method and device based on a CMPSOLSTMTLM model, and belongs to the technical field of data analysis. The method comprises the following steps: acquiring purchase price historical data of the same commodity in an administration and acquisition contract, preprocessing and normalizing the purchase price historical data, and dividing the purchase price historical data into a training set and a test set; constructing a government purchase commodity transaction price prediction model; adopting an improved algorithm CMPSO based on particle swarm optimization to carry out parameter optimization on the government purchase commodity transaction price prediction model; and segmenting data of the test set, inputting the segmented data into the trained government purchase commodity transaction price prediction model for prediction, and carrying out reverse normalization on an output result to obtain a commodity price prediction result. According to the method, the advantages of the LSTM and the Transform model are combined, and the particle swarm optimization algorithm is used for parameter adjustment and optimization, so that the price prediction precision and efficiency are improved.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +2

Abnormal sound detection method and device

PendingCN119533958Anarrow detection rangeEnhanced feature informationVehicle testingVibration measurement in solidsSound detectionNoise
The invention relates to an abnormal sound detection method, which comprises the following steps of: installing an abnormal sound detection device at a to-be-detected position of an automobile part, and detecting a vibration signal at an abnormal sound occurrence moment by using the abnormal sound detection device; and analyzing the vibration signal, determining an abnormal sound frequency band, performing noise reduction on the abnormal sound frequency band, and analyzing the to-be-detected position according to the vibration signal after noise reduction. The abnormal sound detection device is installed at the to-be-detected position of the automobile part, the abnormal sound detection device is used for detecting the vibration signal at the abnormal sound occurrence moment, then the vibration signal is analyzed, the abnormal sound frequency band is determined, the detection range of the vibration signal is reduced, noise reduction is conducted on the abnormal sound frequency band, the signal-to-noise ratio of the signal of the abnormal sound frequency band is increased, and the abnormal sound detection accuracy is improved. The interference of external noise is reduced, the feature information of the vibration signal is improved, and the technical problem that the fault position cannot be accurately judged due to the fact that the abnormal sound signal detected by the abnormal sound stethoscope in the vehicle driving process is interfered by other irrelevant signals in the related technology is solved.
Owner:DONGFENG MOTOR GRP

Multi-modal data fusion crop yield prediction method, device and medium

The invention discloses a multi-modal data fusion crop yield prediction method and device and a medium, and relates to the field of crop yield assessment, and the method comprises the steps: collecting an original image of a target farmland; preprocessing the original image of the target farmland to obtain preprocessed images of a plurality of quadrat areas; based on the preprocessed image of each quadrat region, extracting crop parameters of each quadrat region; determining feature information of each quadrat region based on the preprocessed image and crop parameters of each quadrat region; respectively inputting the feature information of each quadrat region into a multi-modal data fusion prediction model to obtain a crop yield prediction value of each quadrat region; and summing the crop yield predicted values of all the quadrat areas to obtain a crop yield predicted value of the target farmland. According to the invention, manual intervention is reduced, and the crop yield prediction efficiency and accuracy are improved.
Owner:CHINA AGRI UNIV

Target detection method combining multi-branch decoupling head and feature enhancement

The invention provides a target detection method and device combining a multi-branch decoupling head and feature enhancement. According to the method, a YOLOv5 model is selected as a reference framework to design a target detection network for target detection; the target detection network includes a backbone network, a neck network, and a head module. The method comprises the following steps: firstly, performing feature extraction on an input image by using a convolutional neural network through a backbone network to obtain three feature maps of different levels; the neck network performs feature enhancement on the three feature maps of different levels and then performs feature fusion so as to further extract features; the feature enhancement is added into cavity convolution processing to enlarge a receptive field; the head module adopts a three-branch decoupling head, independently divides category prediction, prediction frame positioning and confidence calculation in target detection into three network branches, performs convolution operation on extracted features, and outputs category prediction, prediction frame positioning and confidence calculation results. By using the method, the small-scale target detection precision of the remote sensing image can be improved.
Owner:BEIJING INST OF TECH

Industrial control system anomaly detection method based on differential switching value coding

PendingCN119416054AEnhanced feature informationSolve the detection accuracy is not highProgramme controlComputer controlData setAnomaly detection
The invention discloses an industrial control system anomaly detection method based on differential switching value coding, and relates to the technical field of industrial control system safety, and the method comprises the steps: carrying out the probability conversion of a switching value numerical value (0 or 1) in a training data set, obtaining a switching change probability value, and capturing the probability information of the state change of a switching device; therefore, the feature information of the numerical vector of the device is expanded, and a differential switching value coding technology is designed. The industrial control system anomaly detection method based on differential switching value coding solves the problem that an existing industrial control anomaly detection method based on deep learning is not sensitive to numerical value changes of a switching device in an industrial control system, and consequently the detection accuracy is not high, and the industrial control system anomaly detection method based on differential switching value coding is provided.
Owner:SOUTHERN XINJIANG ELECTRICITY SUPPLY COMPANY OF STATE GRID XINJIANG ELECTRIC POWER

A lane detection method based on multi-dimensional collaborative attention and feature aggregation

The present invention discloses a lane line detection method based on multi-dimensional collaborative attention and feature aggregation, comprising the following steps: constructing a lane line detection model, including a feature extraction network module, an auxiliary segmentation network module, a feature information transmission module and an existence branch module; inputting a lane picture into the feature extraction network module for feature extraction, and outputting a multi-layer scale feature map; using the auxiliary segmentation network module to fuse the multi-layer feature map to provide local details when the model is trained; using the feature information transmission module to transmit information to the feature map so that each pixel can obtain global information, and finally excluding non-existent lane lines and outputting lane lines through the existence positioning module; the method of the present invention introduces multi-dimensional collaborative attention and feature information transmission modules to respectively improve the model's ability to extract features and perceive global information, while improving the accuracy in complex environments, the detection speed also has advantages, and meets the real-time requirements.
Owner:ANHUI ANZHIXIN TECHNOLOGY GROUP CO LTD

A method for predicting the remaining life of rolling bearings

The invention discloses a method for predicting the remaining life of a rolling bearing, and relates to the field of rolling bearing life prediction. The invention aims to solve the problem of low prediction accuracy in existing bearing remaining prediction methods. The invention decomposes and reconstructs the noise-reduced signal into a short-time series matrix, extracts features through a multi-scale fusion permutation entropy method, and inputs the extracted feature data into a neural network to obtain the remaining life trend of the rolling bearing prediction. The invention can reflect the trend of more bearing remaining life changing over time, and has good remaining life prediction accuracy.
Owner:HARBIN UNIV OF SCI & TECH

Marine vessel detection method based on feature extraction and feature weighting selection fusion

The application discloses a marine ship detection method based on feature extraction and feature weighting selection fusion. First, remote sensing ship images are collected to construct a data set. Then, a ship detection model is constructed, the remote sensing ship images are input into the model to obtain fusion features, and then the fusion features are input into a detection head of the model for detection to obtain a detection result. Then, the model is trained, the remote sensing ship images are input into the model, and after multiple rounds of training, a final model is obtained. Finally, the remote sensing ship images are input into the trained model to output ship types and positioning information. The application utilizes dynamic learning sampling point offset and modulation factors to enable convolution kernels to change according to ship shapes and enhance feature information. In the feature fusion stage, feature pyramid networks based on hierarchical scales are developed to fully utilize feature maps from different scales and enhance the feature expression capability of the model.
Owner:SANYA SCI & EDUCATION INNOVATION PARK WUHAN UNIV OF TECH

Method and device for segmenting fine objects based on super-resolution technology

The present invention discloses a method and device for segmenting fine objects based on super-resolution technology, which can be used for segmenting three-dimensional micro-vessels. The method comprises the following steps: 1) constructing a super-resolution network, proposing a structure-preserving super-resolution network, and performing super-resolution operations on micro-vessels on the basis of maintaining the vascular structure information to obtain more detailed information; 2) constructing a three-dimensional vascular segmentation network, which adopts a U-shaped network structure, extracting features layer by layer in the convolution layer while connecting the two symmetrical layers at the head and tail to achieve full feature extraction; 3) using super-resolution to process data, and using the super-resolution data to train the segmentation network, so as to achieve better segmentation effect. The present invention enhances the vascular characteristic information through super-resolution technology, thereby significantly improving the original network and achieving efficient and accurate segmentation effect.
Owner:ZHEJIANG GONGSHANG UNIVERSITY

Data classification method and apparatus, storage medium, and electronic device

PendingCN122712211Aincrease diversityEnhanced feature information
The present disclosure provides a data classification method, device, storage medium and electronic equipment. The method comprises: obtaining first generated content data to be classified, and performing feature extraction on the first generated content data based on a first neural network model to obtain first features; obtaining a generated content reference feature set, the generated content reference feature set comprising a plurality of generated content feature pairs, each generated content feature pair comprising a key feature and a value feature, the key feature being extracted based on the first neural network model, and the value feature being extracted based on a second neural network model; determining a plurality of target generated content feature pairs in the generated content reference feature set according to a first similarity between the first features and the key features; performing feature fusion on the first features and the value features in the plurality of target generated content feature pairs to obtain second features; and determining a classification label of the first generated content data according to the second features. The method can improve the accuracy of data classification.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Lane detection method based on decoupled representation network and slope consistency loss

The present invention discloses a lane line detection method based on a decoupled representation network and slope consistency loss, which performs scene induction and division on lane image data to obtain lane images in five scenes; constructs a decoupled representation network, which includes a multi-branch module and a feature aggregation layer; uses a three-stage training strategy to train lane images in five scenes, and constructs a loss function to constrain network learning. The loss function includes a slope consistency loss function, a smooth L1 loss function, and a line intersection loss function. The slope consistency loss function includes a global slope consistency loss function and a local slope consistency loss function. The present invention adopts a lane detection framework with a decoupled representation network and slope consistency loss, decouples lane features in different scenes, and then implements feature adaptive aggregation to enhance the feature information of the corresponding branch of the input image and suppress the noise features of other branches.
Owner:WUHU SIMBA NETWORK TECH CO LTD