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

30results about How to "Reduce training complexity" patented technology

Multi-factor-driven method for predicting concentration of multi-source harmful gas in underground cavern construction

The invention relates to the technical field of underground cavern construction safety, in particular to a multi-factor-driven underground cavern construction multi-source harmful gas concentration prediction method, which comprises the following steps: collecting underground cavern construction site data, including harmful gas concentration monitoring values and factors related to harmful gas concentration values, comprise humidity, temperature and atmospheric pressure; the collected data are preprocessed; using the preprocessed data to construct a machine learning harmful gas concentration prediction model; performing harmful gas concentration prediction based on a machine learning harmful gas concentration prediction model; and important influence factors and important time nodes of harmful gas concentration are analyzed and predicted. The prediction method can realize harmful gas concentration prediction.
Owner:CHINA THREE GORGES UNIV

360-degree whole-airspace direction-of-arrival estimation method based on space sectorization neural network

The invention discloses a 360-degree whole-airspace direction-of-arrival estimation method based on a space sectorization neural network, which mainly solves the problems of poor accuracy, high model training complexity and the like in the whole-airspace interval direction-of-arrival estimation in the prior art, and comprises the following implementation steps of: modeling a whole-airspace received signal and constructing neural network input; dividing the airspace into sectors and calculating sector indexes; mapping the direction of arrival of the whole airspace to a reference sector by using a sector index; designing a space sectorization neural network; training and reasoning a space sectorization neural network; and recovering the direction of arrival of the whole airspace by using the obtained sector information and the mapped angle value. According to the method, mapping and estimation of the full-airspace direction of arrival in a reference sector which is a high-performance interval are achieved by introducing space sector information, the method has the advantages of being high in direction of arrival estimation accuracy, high in robustness, easy to train and the like, and the method has wide prospects in practical application such as a new-generation wireless communication system, passive positioning and target detection.
Owner:ZHEJIANG UNIV

A fall warning method and system based on deep learning

The present invention proposes a fall warning method and system based on deep learning, which belongs to the technical field of fall detection and image recognition. The method includes inputting the body parameters of the monitored target person, obtaining the actual center of mass coordinates based on the body parameters, using the first radar fall estimation model to perform indoor fall phenomenon detection, and using the second video stream iterative detection model to perform outdoor fall phenomenon, and continuously updating the training sample set to update and train the second video stream iterative detection model. The system includes a first millimeter-wave radar set in an indoor environment, a second environmental vision sensor, and a third environmental vision sensor set in an outdoor environment. The present invention realizes the full-process fall detection of target persons with known features indoors and outdoors, reduces the complexity of deep learning model training, and can realize the adaptive training and update of deep learning image detection models, and improves the adaptability of the model to different environments.
Owner:KUNSHAN FIRST PEOPLES HOSPITAL

Data processing method, and training method and device of image text data quality enhancement model

The embodiment of the invention provides a data processing method and a training method and device for an image text data quality enhancement model, and the method comprises the steps: obtaining an image and initial description information, inputting the image and initial description information into the image text data quality enhancement model, and obtaining an output result of the model; the image text data quality enhancement model is used for obtaining evaluation information according to the image and the initial description information, generating enhanced description information of the image based on the image when the evaluation information indicates that the matching degree of the initial description information and the image is low, and taking the enhanced description information and the evaluation information as an output result; and when the evaluation information indicates that the matching degree between the initial description information and the image is high, taking the evaluation information as an output result. If the output result is evaluation information, determining the image and the initial description information as training data of an MLLM model; and if the output result is the evaluation information and the enhanced description information of the image, determining the image and the enhanced description information as training data of the MLLM model. The method is used for enhancing data quality and improving data utilization rate.
Owner:BAICHUAN INTELLIGENT TECHNOLOGY CO LTD

Adjusting and optimizing method and system based on large power dispatching model

The invention discloses an adjusting and optimizing method and system based on a large power dispatching model, and belongs to the technical field of power dispatching, and the method comprises the following steps: obtaining historical power dispatching knowledge, and dividing the historical power dispatching knowledge into regional knowledge and global knowledge based on regional characteristics; constructing a first teacher model based on the difference between the global knowledge and the regional knowledge, and constructing a student model based on the lowest fluctuation cost; obtaining regional scheduling correlation according to historical power scheduling knowledge, and constructing a second teacher model according to the regional scheduling correlation; associating the first teacher model, the second teacher model and the student model based on knowledge distillation, and constructing a large power dispatching model; and outputting a tuning strategy according to the large power dispatching model and the current power data. The beneficial effects of the invention are that the output of the power tuning strategy gives consideration to pertinence and efficiency.
Owner:STATE GRID ZHEJIANG ELECTRIC POWER CO LTD

KPI (Key Performance Indicator) related fault diagnosis method and device for multi-mode manufacturing process

The invention relates to the technical field of control and monitoring of an industrial production process, in particular to a KPI (Key Performance Indicator) related fault diagnosis method and device for a multi-mode manufacturing process. The method comprises the step of using supervised variant SMGU of MGU for KPI related feature extraction. The process variables and the KPI are used as inputs of the SMGU, and the SMGU effectively keeps the relation between the process variables and the KPI information by learning potential hidden states. The sparse variant SBLS of the BLS is used for fault diagnosis, so that network structure redundancy is reduced, and model overfitting is avoided. According to the method, the problems of poor universality and low diagnosis accuracy of a traditional fault diagnosis method based on deep learning are solved, and the timeliness and precision of fault diagnosis are improved. The fault diagnosis method has good expansibility, a complete training process does not need to be repeated when new training data is added, and the fault diagnosis method can be effectively applied to multi-mode manufacturing processes such as strip steel hot rolling.
Owner:UNIV OF SCI & TECH BEIJING

Self-adaptive LDPC (Low Density Parity Check) decoding method based on model driving

The invention discloses an adaptive LDPC decoding method based on model driving, and the method specifically comprises the steps: constructing a model driving decoder of a non-full connection structure according to a base graph of a prototype graph LDPC code and an improved decoding algorithm; the method comprises the following steps: expanding a base graph of the same PB-LDPC into a plurality of check matrixes by using a plurality of lifting factors to obtain a plurality of bit sequences with different code rates and code lengths, modulating the bit sequences, passing through a channel, and taking a finally obtained log-likelihood ratio as a data set for training a network; pre-processing the obtained LLR data set, inputting the pre-processed LLR data set into a constructed model driving decoder, and training two correction factors at the same time; and obtaining a final model-driven decoder after the training is finished. According to the method, the decoding complexity is reduced, the decoding accuracy is enhanced, and a single model can have better decoding performance for codes with different code lengths and code rates through one-time training, so that better bit error rate performance can be obtained in a complex and changeable transmission system.
Owner:SOUTHWEST JIAOTONG UNIV

Multi-modal target identification method based on anti-noise contrast loss

The invention discloses a multi-modal target identification method based on anti-noise contrast loss, and the method comprises the following steps: S1, selecting different encoder architectures and decoder architectures for each modal according to the input multi-modal target information, and respectively taking the encoder architectures and the decoder architectures as a feature extraction network and a reconstruction network; s2, constructing a multi-modal target recognition network according to the number of input multi-modal target categories; s3, performing training according to the anti-noise comparison loss and the modal reconstruction loss, and updating the feature extraction network, the reconstruction network and the recognition network; s4, inputting modal data of a to-be-identified target into the feature extraction network, fusing the modal data, inputting the fused modal data into the identification network, finally obtaining dimension vectors with the same category number, and selecting the category with the maximum probability value as a prediction category of the to-be-identified target; according to the invention, the problem of low recognition accuracy in a traditional cross entropy-based multi-modal target recognition method in a noisy scene is solved, and an over-fitting phenomenon caused by tag noise is relieved.
Owner:SICHUAN UNIV

Self-learning model system for medical image automatic segmentation

The invention relates to the technical field of image processing, and discloses a self-learning model system for medical image automatic segmentation, which comprises the following steps of: acquiring a plurality of marked data sets uploaded by a user, and performing key parameter verification and screening on data; and for the screened data samples, matching the structural parameters specified by the user with the data samples. According to the self-learning model system for medical image automatic segmentation, the training complexity of a medical image segmentation model can be reduced, non-professionals can also train the medical image segmentation model, a user does not need to pay attention to the internal complex algorithm implementation process, and the user experience is improved. And the key demand of the user for customizing the medical image segmentation domain model is met.
Owner:HEFEI HUIRUAN MEDICAL TECH CO LTD

Near infrared spectrum analysis method and system based on spectral image feature fusion

The invention relates to the technical field of near infrared spectrum analysis, in particular to a near infrared spectrum analysis method and system based on spectrum image feature fusion. The method comprises the following steps: acquiring physicochemical properties corresponding to a batch of samples, measuring near infrared spectrums of the samples and forming a modeling sample set; randomly selecting two near infrared spectrums from the sample set to construct a two-dimensional grey-scale map; extracting near infrared spectrum characteristics from the two-dimensional grey-scale map, and preprocessing the near infrared spectrum characteristics; processing the near infrared spectrum features by using a principal component analysis technology to generate feature vectors; constructing a regression model based on the feature vector and the physicochemical property data of the sample to fit the relationship between the feature vector and the physicochemical property data of the sample; and inputting the feature vector of a to-be-analyzed sample to the regression model, and outputting a prediction result of the physicochemical properties of the to-be-analyzed sample. According to the method, the near infrared spectrum analysis precision is improved by adopting a directional rapid rotation brief feature image extraction technology.
Owner:EAST CHINA UNIV OF SCI & TECH

Neural network operation methods, devices and storage media

This application provides a neural network operation method, apparatus, and storage medium, including: adding a random mask layer to a first neural network according to the type of variable dimensions to obtain a second neural network; the random mask layer is used to perform random masking processing on tensors input to the random mask layer; and training the second neural network using sample data. The neural network operation method, apparatus, and storage medium provided in this application, by adding a random mask layer to the neural network, only require training and deployment of one neural network to adapt to different input and output dimension requirements. This method has low training complexity, low storage overhead, and is easy to deploy and continuously evolve through online training.
Owner:DATANG MOBILE COMM EQUIP CO LTD

Self-processing method based on data symbolization and large model

The invention relates to a self-processing method based on data symbolization and a large model, which comprises the following steps: in the steps of performing model training and responding to input by using the large model to realize self-processing, respectively acquiring various types of sensing data acquired in the two steps and processing result data corresponding to the acquired sensing data acquired in the model training step, the method comprises the following steps of: symbolizing a plurality of different modes of sensing data, namely multi-mode sensing data, to form training data and real-time data, and further converting the plurality of different modes of sensing data into data in a symbolic form, and the information amount contained in the symbolized data is approximately equal to the sum of the information amounts contained in the plurality of different modes of sensing data. On the basis, the multi-modal sensing data can be optimized to a great extent, so that the training complexity of a large model is reduced, the training efficiency and the response efficiency are improved, and the training cost and the implementation cost are reduced.
Owner:GANZHOU YAOLING TIANHUA DIGITAL ECONOMY TECH CO LTD

Salient object detection method based on diffusion model and semantic guidance

PendingCN121788806Aquality improvementHigh quality saliency maskMathematical modelsSemantic analysis
The invention belongs to the field of computer vision and artificial intelligence, and discloses a salient object detection method based on a diffusion model and semantic guidance. Comprising the following steps: automatically generating text annotations of a saliency object data set; constructing a cross-modal saliency pseudo mask; carrying out structure optimization on an initial pseudo mask; constructing a saliency object detection framework based on a diffusion model; and training and testing the salient object detection model based on the diffusion model and the semantic guidance by using the salient object data set. According to the method, the saliency segmentation result can be effectively recovered, verification is carried out on a plurality of public data sets, and the saliency detection precision and the boundary integrity can be remarkably improved.
Owner:DALIAN UNIV OF TECH

Intelligent grade classification method based on ore image features

The invention discloses an intelligent grade classification method based on ore image features, and belongs to the technical field of machine vision, and the method comprises the steps: constructing an ore image data set, dividing the ore image data set into a training set, a verification set and a test set, and carrying out the preprocessing operation of the ore image data in each subset; constructing a residual neural network model of a multi-branch structure as an ore grade detection model; training the ore grade detection model based on the ore image data set; and detecting the grade of the to-be-detected ore by using the trained ore grade detection model. According to the method, the ore grade classification model is constructed based on the multi-branch structure and the residual error structure, the intelligent degree of the mine in the mineral separation link can be improved, guidance is provided for production and ore blending, and the method has important practical application value and significance for improving the operation efficiency of the mine.
Owner:YICHUN JIANGLI LITHIUM BATTERY NEW ENERGY IND RES INST +1

Artificial intelligence medical auxiliary data processing method and system

ActiveCN119377899AReduce training complexityImprove auxiliary efficiencyMedical data miningMedical automated diagnosisEngineeringNetwork model
The invention relates to an artificial intelligence medical auxiliary data processing method and system, and the method comprises the steps: constructing a medical data processing model which comprises a K + 1 channel feature fusion network model and a machine learning model; constructing a dynamic weight model; the input of the dynamic weight model is an L-element input vector, and the output of the dynamic weight model is a K-element output vector; the K-element output vector is input for constructing a (K + 1) th channel of the medical data processing model; acquiring to-be-processed medical data, and constructing K-mode medical data input based on the to-be-processed medical data; and inputting the auxiliary data into the 1-K channels of the medical data processing model, and obtaining corresponding auxiliary data. According to the method, through data dimension splitting, weight training is rapidly reduced, rapid training of the medical data model is realized under the condition of less medical data support and training complexity, and the medical data auxiliary efficiency is improved.
Owner:CAPITAL UNIVERSITY OF MEDICAL SCIENCES

Image generation method based on gradient noise suppression generative adversarial network

The invention discloses an image generation method based on a gradient noise suppression generative adversarial network, and the method comprises the following steps: obtaining a training set which is used for a positive sample of a discriminator; generating an image set as a negative sample; training a gradient noise sensor; training parameters are set in GNS-GAN adversarial learning, and weights of a discriminator and a generator are calculated and updated; and finally, generating an image by using a generator and carrying out pixel value scale exchange to finish the generation of a final image. The method has the advantages that the quality of the generated image and the stability of adversarial learning are improved, and the noise influence in the training process is effectively reduced through the gradient noise suppression technology; training time and computing resource consumption are reduced, and complex forward and reverse diffusion steps in a traditional diffusion model are avoided; the network structure is improved, the parameter quantity of the generator and the discriminator is less, and the training efficiency of the model is improved.
Owner:SOUTHWEAT UNIV OF SCI & TECH

Direct shear test soil parameter calibration method fusing numerical simulation and machine learning

The invention provides a direct shear test soil parameter calibration method fusing numerical simulation and machine learning, and relates to the field of geotechnical engineering. According to the direct shear test soil parameter calibration method fusing numerical simulation and machine learning, high-fidelity finite element numerical simulation, Kernel PCA dimension reduction, a PINN agent model and Bayesian parameter inversion are subjected to systematic deep fusion for the first time. The progressive damage process from the edge to the interior and non-uniform stress-strain distribution of a soil body in a direct shear test are precisely restored through high-fidelity finite element numerical simulation, low-dimensional essential characteristics of a high-dimensional response curve are extracted through a dimension reduction method, and a constitutive model and a strength criterion are embedded into an agent model to guarantee physical rationality. And finally, parameter estimation is realized through a Bayesian parameter inversion framework. The combination solves the interference of non-uniform stress and strain of the soil body in the direct shear test on parameter calibration, so that the calibration result better fits the actual mechanical property of the soil body.
Owner:BEIHANG UNIV

Orthogonal frequency division multiplexing system signal recovery method and device and electronic equipment

ActiveCN116915562BReduce training complexityprocessing speed
The application relates to the technical field of wireless communication, and provides a signal recovery method and device for an orthogonal frequency division multiplexing system and electronic equipment. The method comprises the following steps: collecting a received signal; the received signal is obtained by receiving a transmitted signal of the orthogonal frequency division multiplexing system; determining a signal recovery result of the received signal; inputting the received signal and a pilot sequence into a conditional generative adversarial network to obtain a signal recovery result output by the conditional generative adversarial network. In the application, the conditional generative adversarial network is used for signal detection and signal recovery of the received signal of the orthogonal frequency division multiplexing system; the multiple cascaded sub-layers of the generator in the conditional generative adversarial network are used for gradient updating based on a rank restriction reverse transmission method with a constant matrix rank during training; the multiple cascaded sub-layers are trained as a whole, and the training of a large dense layer is replaced by the training of a lightweight sub-layer, so that the network training complexity is reduced, the data processing speed is improved, and the calculation efficiency is improved.
Owner:CHINA MOBILE COMM LTD RES INST +3

Establishment method and application of ponding image day and night bidirectional conversion model based on reflection map consistency

The invention provides a ponding image day and night bidirectional conversion model construction method based on reflection map consistency and application, and the method comprises the following steps: obtaining a plurality of groups of real day and night ponding image pairs comprising real daytime ponding images and real night ponding images, and generating daytime scene cues for each real daytime ponding image, generating a night scene prompt word for each real night ponding image; constructing a waterlogging image day and night bidirectional conversion framework comprising a brightening conversion unit and a darkening conversion unit, wherein the waterlogging image day and night bidirectional conversion framework generates a simulated night waterlogging image and a simulated daytime waterlogging image; and performing iterative training on the ponding image day and night bidirectional conversion architecture by using a plurality of groups of real day and night ponding images to obtain a ponding image day and night bidirectional conversion model. According to the scheme, the reflection consistency decoder is constructed to extract the reflection maps of various ponding images and calculate the reflection consistency loss, the conversion process is constrained without changing the essential attribute of the ponding area, and semantic distortion is effectively prevented.
Owner:HANGZHOU SOUNDBEI SOFTWARE TECH CO LTD

Long-term and short-term interest fused user preference prediction method and device

The invention provides a long-term and short-term interest fused user preference prediction method and device, and the method comprises the steps: obtaining a data set from a social platform, and carrying out the preprocessing, and the data set comprises user data, video data, and historical interaction data of a user and a video; extracting a short-term historical interaction behavior sequence of the user according to interaction data of the user and the video in the short-term time T, and inputting the short-term historical interaction behavior sequence into a short-term interest capture module to obtain short-term interest features of the user; the user data, the video data and historical interaction data of the user and the video data are input into a long-term interest capture module according to a feature domain composition sequence to extract long-term interest features of the user; and splicing the short-term interest features of the user and the long-term interest features of the user, and inputting the spliced features into a prediction module to obtain a video preference result of the user. According to the method, the long-term interest capture module and the short-term interest capture module are constructed to learn different feature interactions, so that the problem of isomerism of long-term and short-term interest features is solved, and the user preference prediction effect is improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Model life cycle management method and system, central node and distributed nodes

The invention relates to a model life cycle management method and system, a central node and distributed nodes. The model life cycle management method is executed by a center node and comprises the steps that all distributed nodes are clustered to form at least one training group, and each training group comprises a plurality of distributed nodes; and in each training group, training a clustering federated learning model together with the plurality of distributed nodes of the training group to obtain a trained clustering federated learning model. According to the method, the clustering federation learning method is adopted, the model training complexity is reduced, the model training efficiency is improved, and the model training cost is reduced.
Owner:CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER +1

Aero-engine performance interval prediction method considering maintenance factors

The invention provides an aero-engine performance interval prediction method comprehensively considering maintenance factors. At present, prediction results of most aero-engine performance degradation prediction methods are point prediction, only future performance reference values are provided, and performance recovery caused by maintenance factors is often ignored. On the basis, the invention designs a brand-new QCformer method. According to the method, Pinball loss is adopted as a loss function, and performance interval prediction of the aero-engine is achieved. And the method adopts event coding to model maintenance activities so as to predict possible performance recovery brought by different maintenance strategies in the future. According to the prediction mode, airline companies and maintenance teams can have deeper understanding of the performance change trend of the engine in the service period, reference is provided for making a maintenance strategy, the flight safety and reliability can be ensured, and the maintenance cost is reduced.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Domain-adaptive span-level aspect emotion triple extraction model establishment method and application thereof

The invention discloses a domain-adaptive span-level aspect emotion triple extraction model establishment method and application thereof, and belongs to the technical field of emotion analysis, and the method comprises the following steps: extracting semantic information by adopting a span-level feature extraction method combining syntactic and semantic information, and shielding the expression of a prediction enhancement feature on syntactic information through part-of-speech tagging to obtain a domain-adaptive span-level aspect emotion triple extraction model; syntactic information and semantic information are fully utilized by span features; the domain invariant features of the span are enhanced by taking the dependency relationship tree as the core, the feature distribution is optimized by utilizing a mutual information maximization loss function, the features aiming at the specific field are transferred to be field-independent, and the cross-field prediction is realized on the premise of not increasing the labeling cost; according to the method, simple span-level tags are designed and only comprise six tags, so that under the condition of ensuring accurate extraction of an emotion triple in the aspect of span level, the calculation burden in the training process is reduced, and a clearer learning target is provided. According to the method, on the premise that the labeling cost is not increased, cross-domain span-level aspect emotion triple extraction can be realized.
Owner:HUAZHONG UNIV OF SCI & TECH

A highly robust image tampering detection method

The application belongs to the field of information security, and provides a high-robustness image tampering detection method, which comprises the following steps: 1) obtaining multi-scale feature extraction by using a hole convolution, and using Concat to obtain a global feature representation, so that the loss of shallow layer features after multiple convolutions can be prevented, and a larger receptive field can be obtained, and the effect of small target tampering detection is improved; 2) extracting noise by using BayarConv, and the noise extractor is better than an SRM filter, and Bayarconv is developed to enhance the noise inconsistency between the manipulated area and the real area in a given image; 3) using a residual block, batch normalization and an activation function to capture spatial features, and the structure is a conventional encoder, and the main purpose is to cross-fuse with semantic features; 4) using a cross-attention mechanism to fuse spatial features and semantic features, and the fused features are input into an up-sampling layer and a convolution layer for detection, and a hybrid loss function is used to train the model. Experimental data on a large number of public data sets show that the cross-attention mechanism provided in the application can not only accurately predict the tampering position, but also more accurately identify the tampering type.
Owner:ANHUI UNIV OF SCI & TECH

Data expansion and exoskeleton joint end-to-end torque estimation method based on diffusion model

The invention discloses a data expansion and exoskeleton joint end-to-end torque estimation method based on a diffusion model, and the method comprises the steps: carrying out the normalization processing of time series data from a multi-source sensor, carrying out the fragmentation according to a fixed length, and constructing a training sample with a motion class label; then, training a classifier-free conditional diffusion model by adopting a sample, and simultaneously learning conditional and unconditional denoising mapping relationships in a manner of randomly inactivating category conditions; in the generation stage, based on a classifier-free condition guidance mechanism, multi-modal time series data with specified motion category features are gradually generated from random noise; and finally, fusing the generated synthetic data with real acquired data to train a joint torque end-to-end prediction network, thereby realizing joint torque estimation of input sensor time sequence data. The method improves the prediction precision, generalization ability and stability of the end-to-end torque estimation model in a multi-action and few-sample scene, and has a good engineering application value.
Owner:杭州智元研究院有限公司

Digital intermediate frequency predistortion system and method based on direct learning network

A digital intermediate frequency predistortion system and method based on a direct learning network comprises: a digital intermediate frequency predistortion network unit, radio frequency transmitters respectively connected thereto, a transmitter network parameter extraction unit and an end-to-end network construction and predistortion network parameter extraction unit, and a feedback link unit respectively connected to the radio frequency transmitter output end and the transmitter network parameter extraction unit input end. The present invention utilizes the optimization idea in analog predistortion, introduces a nonlinear neural network structure, and reduces the algorithm complexity by sharing network parameters. A predistortion technology more suitable for digital intermediate frequency signals is designed by jointly optimizing mean square error and intermodulation interference indicators, so that the digital intermediate frequency predistortion module achieves better performance.
Owner:SHANGHAI UNIV

Radio frequency device output prediction method based on autoregressive network

The invention discloses an autoregressive network-based radio frequency device output prediction method, which comprises the following steps of: generating a random noise signal by using an arbitrary waveform generator, and recording an input signal set and an output signal set by combining an oscilloscope and a radio frequency device; preprocessing the collected data to obtain an input feature vector and a label for model training; and then constructing and training a full-connection autoregressive neural network based on an automatic encoder architecture, and predicting the output of the radio frequency device by using the trained full-connection autoregressive neural network.
Owner:UESTC (SHENZHEN) ADVANCED RES INST

Identification method of citrus red spider pests based on deep learning

The present invention relates to the field of crop pest identification, and discloses a method for identifying citrus red spider pests based on deep learning, comprising: collecting citrus red spider pest images, and preprocessing the citrus red spider pest images; calibrating image data labels to produce a deep learning data set; training the deep learning data set in a convolutional neural network to obtain a trained citrus red spider pest identification model; inputting the image to be identified into the citrus red spider pest identification model to obtain the identification result of the citrus red spider pest identification model. The present invention solves the problem that the existing crop pest identification relies on human eye identification, which is easily disturbed and has low identification accuracy.
Owner:SICHUAN TECH & BUSINESS UNIV

A Text-Driven Immersive Open-Scene Neural Rendering and Hybrid Enhancement Approach

ActiveCN116563459BReduce training complexityCoordinate colorsImage analysisBiological models
This invention relates to a text-driven immersive large-scene neural rendering and blending enhancement method, comprising: 1. Creating a dataset; 2. Reconstructing the large scene based on an improved progressive neural radiation field; 3. Predicting the foreground and background matte values ​​of the rendered image based on a convolutional neural network; 4. Generating the background from text using a stable diffusion model; 5. Calculating background motion through changes in camera parameters between adjacent frames; 6. Blending the rendered foreground and background and coordinating lighting. This invention achieves real-time text-driven, editable large-scene background enhancement, allowing rendering of immersive large scenes at any observation position at a city scale, generating observation images with effects consistent with the real scene, and enabling mixed reality on this basis. It can satisfy users' personalized customization of the scene and achieve visual effects at the level of film and television special effects. This technology can be applied to fields such as 3D visualization, digital mapping, and virtual reality games.
Owner:BEIHANG UNIV

Grape leaf disease image recognition method based on machine learning model

The invention belongs to the technical field of agricultural information, and provides a grape leaf disease image recognition method based on a machine learning model, and the method comprises the steps: collection of a to-be-detected grape leaf disease image and recognition of a SingleFormer model, and the construction process of the SingleFormer model comprises the steps: image collection and division, image expansion and enhancement, and SingleFormer network training. According to the SingleFormer network, the complexity of model training is reduced, and the recognition precision and the SOTA evaluation effect of the model are improved.
Owner:CHINA AGRI UNIV