Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

7126results about How to "Improve generalization ability" patented technology

Unmanned aerial vehicle patrol detection image power small component identification method and system based on Faster R-CNN

The invention discloses an unmanned aerial vehicle patrol detection image power small component identification method and system based on Faster R-CNN. The method comprises the following steps: carrying out pre-training on a ZFnet model, and extracting a feature graph of an unmanned aerial vehicle patrol detection image; training an RPN region proposed network model obtained through initialization to obtain a region extraction network, generating a candidate region frame on the feature graph of the image by utilizing the region extraction network, and carrying out feature extraction on the candidate region frame to extract position features and in-depth features of a target; carrying out training on a Faster R-CNN detection network obtained after initialization by utilizing the position features and in-depth features of the target and the feature graph to obtain a power small component detection model; and carrying out actual power small component identification detection by utilizing the power small component detection model. The beneficial effects are that Faster R-CNN is utilized to realize identification and positioning of a plurality of types of power small components, so that identification speed of about 80 ms per picture and 92.7% accuracy can be achieved.
Owner:STATE GRID INTELLIGENCE TECH CO LTD

Zero sample image classification method based on combination of variational autocoder and adversarial network

ActiveCN108875818AImplement classificationMake up for the problem of missing training samples of unknown categoriesCharacter and pattern recognitionPhysical realisationClassification methodsSample image
The invention discloses a zero sample image classification method based on combination of a variational autocoder and an adversarial network. Samples of a known category are input during model training; category mapping of samples of a training set serves as a condition for guidance; the network is subjected to back propagation of optimization parameters through five loss functions of reconstruction loss, generation loss, discrimination loss, divergence loss and classification loss; pseudo-samples of a corresponding unknown category are generated through guidance of category mapping of the unknown category; and a pseudo-sample training classifier is used for testing on the samples of the unknown category. The high-quality samples beneficial to image classification are generated through theguidance of the category mapping, so that the problem of lack of the training samples of the unknown category in a zero sample scene is solved; and zero sample learning is converted into supervised learning in traditional machine learning, so that the classification accuracy of traditional zero sample learning is improved, the classification accuracy is obviously improved in generalized zero sample learning, and an idea for efficiently generating the samples to improve the classification accuracy is provided for the zero sample learning.
Owner:XI AN JIAOTONG UNIV

Urban rail transit panoramic monitoring video fault detection method based on depth learning

The invention provides an urban rail transit panoramic monitoring video fault detection method based on depth learning. The method comprises a data set construction process, a model training generation process and an image classification recognition process. The data set construction process processes a definition abnormity video, a colour cast abnormity video and a normal video in an urban rail transit panoramic monitoring video. A training set and a test set are classified. The model training generation process comprises model training and model test. The model training is to train a fault video image recognition model based on a convolution neural network. The convolutional neural network comprises a plurality of convolution layers and a plurality of full connection layers. The model test is to calculate the test accuracy. If expectation is not fulfilled, the fault video image recognition model is optimized. The image classification recognition process comprises the steps that a single-frame image to be recognized is input into the model, and the fault video image recognition model outputs an image classification result to complete the fault image detection of the urban rail transit panoramic monitoring video.
Owner:HUAZHONG NORMAL UNIV +1

Automotive exhaust emission data fusion system

The invention discloses an automotive exhaust emission data fusion system. The automotive exhaust emission data fusion system comprises a roadside air pollutant concentration estimation module, a roadside air pollutant concentration prediction module, a city global atmospheric environment prediction module, an automotive exhaust emission factor estimation module and an automotive exhaust emission feather analysis module, wherein the five modules are used for respectively realizing different data analysis functions, and the different functions can be realized by virtue of the different modules; the modules can be independently used, or two or more modules can be combined for use, so as to realize the storage, analysis and fusion of automotive exhaust telemetering data, automotive attributes, driving working stations, detection time and meteorological condition data; and by combining with a vehicle-mounted diagnosis system database, a portable emission test system database, a vehicle inspection station offline database, a traffic information database and a geographic information database, automotive exhaust telemetering data is analyzed, and the highest discriminatory key indexes and statistical data are acquired, so that effective supports are provided for the formulation of relevant decisions of government departments.
Owner:UNIV OF SCI & TECH OF CHINA

Image classification method based on confrontation network generated through feature recalibration

The invention discloses an image classification method based on a confrontation network generated through feature recalibration. The image classification method based on the confrontation network generated through feature recalibration is suitable for the field of machine learning and comprises the steps that to-be-classified image data are input into a confrontation network model for network training; a generator and a discriminator which are constituted by a convolutional network are constructed; random noise is initialized and input into the generator; the random noise is subjected to multilevel deconvolution operation in the generator through the convolutional network, and finally, generated samples are obtained; the generated samples and authentic samples are input into the discriminator; and the input samples are subjected to convolution and pooling operation in the discriminator through the convolutional network, thus a feature graph is obtained, a compressed and activated SENetmodule is imported into an intermediate layer of the convolutional network to calibrate the feature graph, thus the calibrated feature graph is obtained, global average pooling is used, and finally,image data classification is output. The SENet module is imported into the intermediate layer of the discriminator, the importance degree of each feature channel is automatically learned, useful features relevant to a task are extracted, features irrelevant to the task are restrained, and thus semi-supervised learning performance is improved.
Owner:JIANGSU YUNYI ELECTRIC

An aluminum material surface defect detection algorithm based on deep learning

The invention relates to an aluminum material surface defect detection algorithm based on deep learning, and the algorithm comprises the steps: (1) employing a camera to shoot the surface of an aluminum material, obtaining a related data set, employing a labelImg tool to label an image, and obtaining label information; (2) dividing the image into a training set and a test set, and performing dataenhancement on the training set; (3) inputting a defective image, a non-defective image and label information of the defective image into the network at the same time every time to carry out model training; and (4) inputting the test image into the trained aluminum material surface defect detection model, and obtaining the position and the corresponding category of the defect. According to the method, a defective image and a non-defective image can be effectively utilized; the generalization ability and the detection precision of the model are improved, the detection performance is further improved by fully utilizing context information around the candidate region, the detection performance of dense small defects can be improved by utilizing a soft non-maximum suppression algorithm, and the method is an efficient aluminum material surface defect detection algorithm.
Owner:SUN YAT SEN UNIV

Artificial intelligent training platform for intelligent networking vehicle plan decision-making module

The invention, which relates to the technical field of an intelligent vehicle automatic driving and traffic simulation, relates to an artificial intelligent training platform for an intelligent networking vehicle plan decision-making module and aims at improving the intelligent level of the intelligent vehicle plan decision-making module based on enriched and vivid traffic scenes. The artificial intelligent training platform comprises a simulation environment layer, a data transmission layer, and a plan decision-making layer. The simulation environment layer is used for generating a true traffic scene based on a traffic simulation module and simulating sensing and reaction situations to the environment by an intelligent vehicle, thereby realizing multi-scene loading. The plan decision-making layer outputs a decision-making behavior of the intelligent vehicle by using environment sensing information as an input based on a deep reinforcement learning algorithm, thereby realizing training optimization of network parameters. And the data transmission layer connects the traffic environment module with a deep reinforcement learning frame based on a TCP / IP protocol to realize transmission of sensing information and vehicle control information between the simulated environment layer and the plan decision-making layer.
Owner:TONGJI UNIV

Depth convolution wavelet neural network expression identification method based on auxiliary task

The invention discloses a depth convolution wavelet neural network expression identification method based on auxiliary tasks, and solves problems that an existing feature selection operator cannot efficiently learn expression features and cannot extract more image expression information classification features. The method comprises: establishing a depth convolution wavelet neural network; establishing a face expression set and a corresponding expression sensitive area image set; inputting a face expression image to the network; training the depth convolution wavelet neural network; propagating network errors in a back direction; updating each convolution kernel and bias vector of the network; inputting an expression sensitive area image to the trained network; learning weighting proportion of an auxiliary task; obtaining network global classification labels; and according to the global labels, counting identification accuracy rate. The method gives both considerations on abstractness and detail information of expression images, enhances influence of the expression sensitive area in expression feature learning, obviously improves accuracy rate of expression identification, and can be applied in expression identification of face expression images.
Owner:XIDIAN UNIV

Special audio event layered and generalized identification method based on SVM (Support Vector Machine) and GMM (Gaussian Mixture Model)

The invention relates to a special audio event layered and generalized identification method based on a combination of an SVM (Support Vector Machine) and a GMM (Gaussian Mixture Model), and belongs to the technical field of a computer and audio event identification. The special audio event layered and generalized identification method comprises the following steps of: firstly, obtaining an audio characteristic vector file of a training sample; secondly, respectively carrying out model training on a great quantity of audio characteristic vector files (of the training samples) with various types by using a GMM method and an SVM method, so as to obtain the GMM model with generalization capability and an SVM classifier, and complete offline training; and finally, carrying out layered identification on the audio characteristic vector files to be identified by using the GMM model and the SVM classifier. With the adoption of the method provided by the invention, the problems that the conventional special audio event identification is low in identification efficiency on a continuous audio stream, very short in continuing time, high in audio event false dismissal probability can be solved. The method can be applied to searching a special audio and monitoring a network audio based on contents.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

Convolutional neural network based crowd density distribution estimation method

The invention relates to a convolutional neural network based crowd density distribution heat map generation method, which comprises the steps of dividing a crowd picture set into a training sample set and a test sample set, performing crowd label image segmentation by using convolutional neural network architecture, and carrying out number regression by using a convolutional neural network; correcting a density map through a multi-scale template operation, generating a crowd density distribution heat map according to the corrected density map and the regression number, and completing crowd density distribution estimation. According to the invention, deep characteristics of an image are extracted by using a powerful learning ability of the full convolutional neural network so as to perform accurate crowd segmentation, and low efficiency and blindness of density calculation of a traditional method for full image characteristics are overcome; a crowd near-far perspective effect is overcome to a certain extent through multi-scale template correction; and mapping is performed in allusion to the estimated number of people, lateral comparison can be performed on heat maps of different cameras, the method is applicable to various crowd scenes, and the crowd density distribution heat map can be acquired in real time.
Owner:ZHENGZHOU JINHUI COMP SYST ENG

Network constructing method for human face identification, identification method and system

The invention discloses a deeper layer network constructing method used for gender identification or age estimation based on human face. The method includes a step (101) dividing all training pictures into a plurality of groups; (102) extracting high layer features of a group of pictures based on a convolution neural network and thereby obtaining a first matrix composed of the high layer feature vectors, and extracting low layer and global features of the same group of the training images based on an artificial neural network and thereby obtaining a second matrix composed of the low layer feature vectors, obtaining a group of gender identification or age estimation results based on the extract first matrix, the second matrix and the defined judgment formula, wherein the values of a first weight matrix W1, a second weight matrix w2, an offset matrix b and an adjusting weight beta in the defined judgment formula are updated by utilizing an error back propagation algorithm and the final values of the parameters are obtained and the network construction is completed. Judgment of age and gender of a human face is performed based on the judgment formula determined according to the values of the parameters when the network construction is completed.
Owner:HENGFENG INFORMATION TECH CO LTD

Method for remain useful life prognostic of lithium ion battery with model active updating strategy

InactiveCN103778280AEasy Adaptive AcquisitionFlexible inferenceElectrical testingSpecial data processing applicationsHealth indexEngineering
The invention relates to a method for remain useful life prognostic of a lithium ion battery with a model active updating strategy. According to a time series obtained through a voltage range of a discharge curve, conversion is conducted so that an equivalent discharge difference series obtained by discharge circulation at each time can be obtained, and therefore a health index time series of the ion battery is obtained; according to correspondence of a discharge voltage series and a time series, prognostic is conducted on the health index series to determine the remain useful life of the battery. Sampling entropy characteristic extraction and modeling are conducted on a charge voltage curve so that a relationship between a complete and accurate charge / discharge process and a battery performance index can be provided. On the basis of a performance index model, a short-term time series prognostic result is continuously updated to a known performance index data series and correlation analysis is conducted. According to the difference of the correlation degrees, retraining is conducted in the mode of training set expansion. The method is different from an existing iteration updating draining method, the prognostic model is updated dynamically, and therefore the prognostic precision is improved.
Owner:SHANGHAI JIAO TONG UNIV

Analogue circuit fault diagnosis neural network method based on particle swarm algorithm

The invention discloses a neural network method for diagnosing analog circuit failures which is based on a particle swarm algorithm, and comprises the following steps: imposing an actuating signal to an analog circuit to be tested, measuring an actuating response signal in the testing nodes of the circuit, extracting the candidate signal of failure characteristics by implementing noise elimination and then wavelet packet transformation on the measured actuating response signal, extracting the failure characteristics information by further implementing orthogonal principal component analysis and normalization processing on the candidate signal of failure characteristics, and sending the failure characteristics information as samples to the neural network for implementing classification. The method adopts the particle swarm algorithm instead of a gradient descent method in traditional BP algorithms, thus leading the improved algorithm to be characterized in that the algorithm avoids the local minimum problem and has better generalization performance. The BP neural network method for diagnosing the analog circuit failures which is optimized on the basis of particle swarm can obviously reduce iteration times in the algorithm, improve the precision of network convergence, and improve diagnosis speed and precision.
Owner:HUNAN UNIV

Improved CNN-based facial expression recognition method

The invention provides an improved CNN-based facial expression recognition method, and relates to the field of image classification and identification. The improved CNN-based facial expression recognition method comprises the following steps: s1, acquiring a facial expression image from a video stream by using a face detection alignment algorithm JDA algorithm integrating the face detection and alignment functions; s2, correcting the human face posture in a real environment by using the face according to the facial expression image obtained in the step s1, removing the background information irrelevant to the expression information and adopting the scale normalization; s3, training the convolutional neural network model to obtain and store an optimal network parameter before extracting feature of the normalized facial expression image obtained in the step s2; s4 loading a CNN model and the optimal network parameters obtained by s3 for the optimal network parameters obtained in the steps3, and performing feature extraction on the normalized facial expression images obtained in the step s2; s5, classifying and recognizing the facial expression features obtained in the step s4 by using an SVM classifier. The method has high robustness and good generalization performance.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products