82results about How to "Good divisibility" patented technology

The invention discloses a vehicle detection method based on a convolutional neural network. The method includes the step S1 of collecting vehicle samples and non-vehicle samples and classifying the vehicle samples, the step S2 of preprocessing the samples, the step S3 of training a CNN vehicle detector, the step S4 calculating an average similarity table of a characteristic pattern, the step S5 of constructing a similarity characteristic pattern set, the step S6 of obtaining a CNN-OP vehicle detector, the step S7 of obtaining detection images, the step S8 of preprocessing the obtained detection images, the step S9 of constructing an image pyramid for the detection images, the step S10 of extracting characteristics, the step S11 of scanning characteristic patterns, the step S12 of classifying the characteristics, and the step S13 of combining detection windows and conducting output. An offline optimization scheme is put forward, the convolutional neural network which is completely trained is optimized, the strategy of scanning the windows after extracting the characteristics is adopted at the detection stage, and therefore the characteristics are prevented from being repeatedly calculated, and the detection speed of the system is increased.

The invention provides a liver tumor segmentation method and device based on a CT (Computed Tomography) image. The method comprises the following steps: performing Gaussian denoising on CT image data of a liver, converting the denoised CT image data into standardized data of which a gray average is 0 and a variance is 1, and performing down-sampling operation; extracting a lesion slice and a normal tissue slice from a gold standard image of the CT image of the liver, and classifying the lesion slice and the normal tissue slice into a positive sample and a negative sample; constructing a multi-level depth convolutional neural network, training a model through a stochastic gradient descent to obtain a network model, and acquiring a coarse segmentation binary image of a tumor and a pixel-classification probability image through a classifier; performing morphological erosion operation on the coarse segmentation binary image of the tumor to obtain a foreground image needed by graph cut, performing subtraction operation on the binary image of a liver and the coarse segmentation binary image of the tumor, and performing the morphological erosion operation to obtain a background image corresponding to normal tissues of the liver; and constructing an undirected graph, and obtaining a finial segmentation region of the tumor through a graph cut optimization algorithm.

The invention discloses a intra-pulse modulation and recognition method of a low signal-to-noise radar radiation source signal, which comprises the following steps of: receiving a radar radiation source pulse signal by an electronic reconnaissance receiver, after dimension reduction and A / D sampling process from radio frequency to intermediate frequency, obtaining a radar radiation source signal S(t) having different intra-pulse modulation modes, and processing the signal S(t) in a signal processing module, identifying and outputting intra-pulse modulation mode of the radar radiation source signal. With the method, the intra-pulse modulation mode of multiple radar radiation source signals can be correctly identified when the signal-to-noise is as low as -6dB; and compared with the conventional method for identifying multiple radar radiation source signals, the computational complex O (n2) or (n3) is lower.

The present invention discloses a vehicle detection method based on convolutional neural network self-adaption. The method comprises an off-line training step S1 of collecting a vehicle sample and a non-vehicle sample, forming a source sample, carrying out the pre-processing on the source sample and training a source CNN vehicle detector; an off-line self-adaption adjustment step S2 of adjusting the source CNN vehicle detector obtained in the step S1 in a self-adaption manner, improving the accuracy of the source CNN vehicle detector in a current monitoring scene, and obtaining a target CNN vehicle detector; an on-lien detection step S3 of obtaining a detection image, utilizing the target CNN vehicle detector obtained in the step S2 to carry out the vehicle detection and output a detection result. The method of the present invention adjusts the source CNN vehicle detector based on a convolutional neural network and trained on a large sample in the self-adaption manner and aiming at different monitoring scenes, enables the source CNN vehicle detector to become the target CNN vehicle detector which can finish a vehicle detection task of the current monitoring scene, can detect the vehicles accurately, and possesses the adaptability aiming at the different complicated scenes.

The invention discloses an identification method of a wireless transmitter based on RF fingerprints (RFF). The method comprises the following steps: receiving a wireless signal transmitted by the wireless transmitter, wherein the wireless signal is a preamble sequence transmitted by the wireless transmitter while power is increased gradually; detecting reference time of the wireless signal; according to the detected reference time, carrying out preamble signal interception on the wireless signal; converting the intercepted preamble signal into the RFF; carrying out feature extraction on the converted RFF and carrying out identification on the wireless transmitter. According to the identification method of the wireless transmitter based on the RFF, through using advantages that RFF separability is good and a required sampling rate is low, ramp-up RFF can be used for multiple RFF identification of wireless equipment based on the preamble so that purposes of increasing wireless network physical layer safety and so on can be realized, wherein the advantages are possessed by the ramp-up RFF (radio frequency fingerprints RFF) which is obtained through converting the preamble signal transmitted during the power is obliquely ascended.

The invention discloses a method for identifying a sound fault based on a mel energy spectrum and a convolution neural network. The method comprises the following steps: first, performing pre-emphasison initially input audio data; then, performing framing and windowing processing on the data; after that, performing fast Fourier transform on framed and windowed data; extracting energy features ona frequency domain, processing an energy spectrum by using a set of mel-scale triangular filter banks; and after that, converting the data into a Mel energy spectrum by using energy in different frequency domains corresponding to each frame as a Y axis, and different frames in a time domain as an X axis. After that, the energy spectrum needs to be further framed to adapt to an input of a CNN (convolution neural network). Each frame is a sample, and one-hot coding of a label corresponding to each sample is used as an output of the CNN to train a CNN model until a network training error reachesthe minimum. During prediction, a probability value of each type of label is output, and a label with the largest probability value is taken as a final discrimination result.

The invention discloses a radar HRRP target recognition method based on a dpLVSVM model. the method includes the steps of firstly, conducting feature extraction on radar HRRP data to obtain a power spectrum feather set X; secondly, constructing the dpLVSVM model, and obtaining the probability density function of power spectrum features and the combined condition posterior distribution of all parameters; thirdly, conducting derivation to obtain the condition posterior distribution of each parameter; fourthly, conducting circulating sampling on each parameter I times; fifthly, storing the sampling result of the parameter required by the T0th test stage; sixthly, judging whether the radar HRRP is an outside-library sample or not, if yes, rejecting the judgment, and if not, executing the seventh step; seventhly, conducting sampling to obtain the cluster mark number of the power spectrum features (please see the specification); eighthly, outputting the target classification mark number (please see the specification) of the radar HRRP. The method has the advantages of being low in classifier design complexity, good in recognition performance and good in judgment rejection performance, and can be used for radar target recognition.

The invention belongs to the technical field of detection, in particular to a method for real-time detection of weld seam targets. The method comprises the following steps: building a training sampleset: welding seam images of different shapes are collected as source samples and the source samples are pretreated to form a training sample; training detector offline: the neural network is trained under different initial conditions by using the training samples, and the optimal neural network model is obtained by multiple training as a welding seam detector; performing on-line detection: a detection image is acquired, a weld detection is performed by using the weld detector and a detection result is output. The invention overcomes the problem of poor robustness of positioning the weld seam through the morphological method, realizes the accurate positioning of the weld seam of different shapes, classifies the weld seam of different kinds accurately, and has high positioning precision by adopting the weld seam detector obtained through the weld seam image training based on the line laser imaging for the different weld seams.

The invention belongs to the field of pattern recognition and particularly relates to a method for realizing remote authentication by fusing gait flow images (GFI) and head and shoulder procrustes mean shapes (HS-PMS). The method comprises the following steps of: preprocessing; estimating walking directions and determining visual angles; establishing a dynamic feature classifier for gaits; establishing a static feature for the gaits; fusing similarities between the dynamic feature classifier and the static feature according to the product rule at a matching layer to obtain decision information. According to the method for realizing remote authentication by fusing the GFIs and the HS-PMSs, the visual angles are introduced to serve as the rules of the classifiers, and thus, the problem that gait recognition is greatly influenced by the visual angle is solved. An optical flow field between adjacent two profile images is calculated by utilizing a Lacus-Kanade optical flow method, so that the real-time processing capacity of an algorithm is improved. The dynamic information and the static information of the gaits are fused, so that the separability of the method is improved, and the recognition performance is improved.

The invention provides a gesture recognition method, a palm virtual keyboard using same, and an input method; the palm virtual keyboard comprises a signal acquisition unit, a signal pretreatment unit, a signal segmentation unit, a feature extraction unit, a feature fusion unit, a gesture recognition unit, and a character mapping unit; a bioelectrical sensor arranged on a wrist and a position sensor arranged on a thumb can respectively obtain a gesture signal; the gesture signal is processed, features are extracted, and gesture recognition is carried out so as to recognize a user gesture motion, thus obtaining the characters corresponding to the gesture motion, and realizing input of the palm virtual keyboard; the two sensors arranged on the wrist and thumb can recognize the gesture so as to use the palm as the virtual keyboard for inputting, thus solving the technical problems that a virtual keyboard in the prior art needs a camera to collect images, and the camera is not easy to install, easy to be blocked, and inaccurate in recognition.

The invention discloses a remote sensing image variation detecting method on the basis of weighted Gabor wavelet characteristics and two-stage clusters. The processed objects include optical remote sensing images and SAR (synthetic aperture radar) images and the remote sensing image variation detecting method includes (1) generating difference images according to remote sensing image types; (2) subjecting the difference images to Gabor wavelet transform; (3) extracting multiscale and multidirectional characteristics of the Gabor wavelet transform of the difference images; (4) designing the weighting coefficient and acquiring the weighted Gabor wavelet characteristics; (5) clustering the weight Gabor wavelet characteristics by means of the two-stage cluster strategy; (6) acquiring variation detecting results. By the remote sensing image variation detecting method, loss of marginal information is reduced, stronger, weak and slight varying areas can be detected at the same time, the total mistake pixel number is decreased, more detail information is reserved and variation results can be effectively extracted.

The invention discloses a high-resolution range profile target recognition method for kernel adaptive mean value discriminant analysis. The method comprises the steps that an original HRRP signal training set is acquired, l<2> norm normalization is performed to extract power spectrum features, and a feature sample set after preprocessing is obtained; a kernel function is adopted to perform mappingto a high-dimensional feature space; an adaptive dispersion matrix is configured; an optimal projection direction is solved; a new non-linear dimension reduction training feature set is obtained; anSVM classifier is trained; and SVM classification recognition is performed on a to-be-tested original HRRP signal. Through the method, global information of training samples is utilized in a kernel mapping space, local information is adaptively fused during information extraction, low-dimensional features with higher separability compared with common feature extraction and data dimension reductionmethods can be obtained, and recognition precision is improved. The method is also suitable for feature extraction and classification of other signals, such as classification of crack types and sizesthrough a magnetic flux leakage signal in nondestructive testing and audio signal classification.

The invention relates to a radar signal feature extraction method based on residual depth learning. With a designed residual depth learning network, deep-level feature extraction is carried out on a radar radiation source signal in a complex electromagnetic environment. The method is implemented as follows: parameters of the residual depth network are trained by using the existing radar data in adatabase; the intercepted data are sent to the input terminal of the residual depth network and results are outputted after mapping of multiple hidden layers, wherein the outputted results are used asthe depth features of the pulse string; with a clustering method, the obtained depth features are clustered, and the correlation degree of each two radiation sources after clustering is calculated and processed according to a correlation criterion; and then the parameter of each radiation source after fusion is calculated and sorting is completed. Therefore, the depth features among data can be dug; the sorting precision is high; and the radar signal feature extraction method can be applied to fields of target reconnaissance and interference source localization.

The invention relates to a battery management system for a battery having a plurality of battery cells connected in series, comprising a battery control unit, a plurality of low-voltage measuring devices, by means of which the voltage of one or more battery cells can be measured, and comprising one or more high-voltage measuring devices for a voltage across a plurality or all the battery cells, and / or at least one current measuring device, by means of which a current from or through the battery can be measured, and / or at least one a measuring module comprising a high-voltage measuring device, and a current measuring device, characterized by a signal transmission device, by way of which signals from low-voltage measuring devices and from at least one of the high-voltage measuring devices and / or the current measuring device and / or the measuring module can be transmitted to the battery control unit.

The invention relates to a combustion gas index automatic identification method based on images and belongs to the technical field of image identification. The method is characterized in that a conventional scheme in a dial positioning and character identification process is improved, the robustness of combustion gas meter image noise is improved, and a more accurate character sub-image which does not contain other impurities can be obtained; in addition, the structure information of images are utilized to describe characteristics of different character images, a classifier is constructed by a 3-neighbour method, the information separability of 10 extracted character characteristics from 0-9 is good, and the combustion gas index can be accurately extracted without a complex identification process, so that the method is much better than an existing combustion gas index identification method in efficiency, and the whole process from image collection to successful characteristic identification is no longer than 0.08s, and the combustion gas index can be integrated to a combustion gas index identification system having real-time requirements; and the method does not depend on any third party software and can be transplanted to any platform in demand such as a PC platform or an intelligent mobile phone client.

The invention discloses a cross-granularity sheet metal part identification system and method based on a machine vision technology and belongs to the technical field of machine vision. For structuralappearance characteristics of sheet metal parts, a machine vision related technology is used, shape factors and rotation invariant moments of sheet metal part images are calculated to serve as coarse-grained characteristic information, sheet metal part graph contour data are extracted to serve as fine-grained characteristic information, and side face images and related characteristics of the sideface images are combined to serve as auxiliary information to construct a sheet metal part database; during detection, Euclidean distances among coarse-grained feature information are compared, similarity calculation is performed on fine-grained feature information, and cross-grained sheet metal part classification and recognition are realized; before the similarity of the fine-grained feature information is calculated, auxiliary information is compared through a template matching method and other methods, matched alternative parts are screened, the calculation complexity can be further reduced, the classification precision is ensured, and the method has good applicability to sheet metal parts with high similarity characteristics.

The invention relates to the fields of pattern recognition, machine learning and computer vision, and provides a zero sample classification method based on semantic enhancement of encyclopedic knowledge, which aims to solve the problem that the existing zero sample image classification method cannot give consideration to both word vector language information range and processing efficiency. The zero sample classification method comprises the steps of: S1, classifying unknown-class images by means of a trained convolutional neural network classifier, and subjecting semantic features of classification result tags to convex combination to serve as semantic features of the unknown-class images; S2, and classifying the semantic features of the unknown-class images obtained in the step S1 and semantic features in a pre-constructed semantic feature space by means of a nearest neighbor classifier, so as to obtain final classes of the unknown-class images. The zero sample classification method and a zero sample classification device provided by the invention enhance the global information of word vectors, so as to improve the accuracy of image zero sample classification.

The invention relates to a mechanical vibration signal feature extraction method based on combination of stochastic resonance and kernel principal component analysis. The method comprises the steps that firstly, the stochastic resonance method is applied for conducting pretreatment on rotor oscillation original signals measured by a sensor, the signal periodicity is improved, and the oscillation signal to noise ratio is improved; then, a time domain feature set is extracted for the pretreated output signals; then the kernel principal component analysis method is adopted for conducting nonlinear feature transformation for the extracted time domain feature set, and therefore the final needed feature set is obtained. The method is applied to feature extraction and failure diagnosis of simulated failure of an engine rotor, the result shows that the feature set extracted through the method is of linear independence, the number of dimensions is smaller, the separability is higher, the precision and efficiency of the failure diagnosis can be effectively improved, and application in engineering practice is facilitated.

The invention belongs to the technical field of radars, and discloses a radar high-resolution range profile target recognition method based on an iMMFA (infinite max-margin factor analysis) model so as to improve classification performance of the radar and reduce solving complexity of the model. The method comprises steps: radar high-resolution range profiles of M categories of targets; feature extraction is carried out on each radar high-resolution range profile; an iMMFA model is built; an initial value of each parameter of the iMMFA model is set, according to a Gibbs sampling rule, after a preheating process of I0 times of iteration, sampling values of each parameter at T0 times are stored respectively; a final FA model, a final TSB-DPM model and a final LVSVM classifier are determined, and a final iMMFA model is formed; a radar high-resolution range profile of a test target is acquired, and feature extraction is carried out on the radar high-resolution range profile of the test target; and according to a clustering label of a test hidden variable as described in the description, a target category to which the test target belongs is determined.

The present invention discloses a composite texture feature extraction method for a flotation froth image. The method comprises: firstly, in a grayscale quantization matrix of a froth image, acquiring a face neighborhood set of all central pixel points; then, for all the central pixel points, constructing a three-dimensional data table and obtaining a nested grayscale frequency table; again, acquiring an improved neighborhood grayscale correlation matrix; and finally, obtaining a new composite texture feature, wherein the feature integrates a size, a texture and a roughness degree of froth, and has relatively high stability and separability in reflecting a texture of flotation froth; and according to the extracted composite texture feature, it is easy to distinguish flotation froth images with different operating conditions in different ore grades, thereby having a relatively high accuracy rate of recognizing operating conditions. The composite texture feature extraction method for the flotation froth image provided by the present invention is simple and effective, and is very important to guide the recognition of froth operating conditions in a mineral flotation site.

The invention discloses a dermatoscope image retrieval method based on end-to-end depth hashing. The dermatoscope image retrieval method comprises the steps of 1, establishing a dermatoscope image database; 2, designing an end-to-end deep hash network model; 3, carrying out network training; 4, extracting a deep hash code, and constructing a retrieval database; And 5, retrieving the dermatoscope image. The method has the advantages that by designing a Res-DenseNet50 deep hashing structure, the fusion capability between high-level features and low-level features is improved, and the loss of information in the transmission process between layers is avoided. And the extracted high-level features have better separability, so that higher retrieval accuracy is achieved. The end-to-end deep hash-based retrieval method is realized. According to the method, the original image is directly learned, and the deep hash code corresponding to the input image can be directly obtained from the penultimate layer of the network, so that the dermatoscope image retrieval process is simplified, and the accumulative error between the front step and the rear step in the traditional retrieval process is avoided.

The invention provides a log output method and a system for a distributed software system. The log output method for the distributed software system comprises confirming current types of software users; extracting log information which is corresponding to the current types of software users from a log database according to corresponding relationships between preset types of software users and the log information; outputting the log information which is corresponding to the current types of the software users. The log database stores files recording generated information during operation of the distributed software system or files recording the log information which is corresponding to the types of the software users and every file records the log information which is corresponding to one type of software users. The log output method for the distributed software system has the advantages of solving the problem that the analyzability of logs output from the existing distributed software system is poor, improving the analyzability of the logs output form the distributed software system, relieving the workload of the software users and providing convenience for work carrying out of later software users.

The invention discloses an adaptive spectral focusing band selection method for a hyperspectral image. The method comprises the steps of firstly processing whole spectral domain hyperspectral originaldata of a ground object by utilizing three band selection algorithms, arranging results of the algorithms according to a sequence from large to small, and selecting out first N bands as optimal bandcombinations; and secondly assessing the optimal band combinations selected out by the three band selection algorithms by utilizing an independent component analysis (ICA) band assessment function, setting a J threshold, calculating out assessment results of the band combinations, and selecting the band combination with the maximum result as the optimal band combination. By utilizing an adaptive spectral focusing technology, automatic wavelength selection of wave bands can be realized during imaging of a spectrograph; a tunable light filtering component in an imaging control system is adaptively tuned to multiple spectral channels most favorable for detection and identification; spectral adaptive detection is realized; redundant and disorderly spectral information is deleted; the spectralimaging information utilization efficiency is improved; and the resource demand of information processing is reduced.

The invention discloses an acoustic target radiation noise classification method and system based on EMD (Empirical Mode Decomposition) and compressed sensing. The method comprises the following stepsof firstly, carrying out EMD decomposition on an obtained ship radiation noise signal and carrying out line spectrum component extraction on a basic mode component by utilizing compressed sensing; and utilizing the maximum mutual information coefficient to select the line spectrum component obtained by the maximum correlation coefficient of the basic mode component and the original signal to resynthesize the signal line spectrum. According to the method, the line spectrum with relatively low amplitude in the signal can be extracted; sparse dictionary training being carried out on the extracted line spectrums, sparse coding matrixes obtained after sparse representation is carried out on different signals being distributed at different positions, subsequent classification being more facilitated, time domain, frequency domain and sparse domain feature extraction being carried out on the signal line spectrums to form an accurate feature set capable of serving as a classification basis, and classification accuracy being improved; the line spectrum of the signal can be extracted more accurately; the extracted sparse features have better separability, and have a good application prospectin identification of radiation noise classification of underwater acoustic targets such as ships and warships.

The present invention concerns a synchronous generator of a gearless wind power installation, comprising a stator and a multi-part external rotor. The invention also concerns a wind power installation having such a generator. Furthermore the present invention concerns a transport arrangement for transporting a synchronous generator of a gearless wind power installation.

The invention discloses a remote-sensing image under-segmentation object recognition method. The method comprises the following steps: data dimension reduction is performed on an image to obtain a segmentation object; clustering is performed on the segmentation object; a mixing degree index of the segmentation object is calculated according to the clustering; and the under-segmentation object is recognized in the segmentation object according to the mixing degree index. According to the judgment method of the invention, space texture and spectrum dimension information is combined, the obtained image segmentation result is more aligned with the distribution of real objects, and the under-segmentation object recognition speed and the recognition result accuracy can be improved.

The invention belongs to the technical field of prestress, and particularly relates to a grouting-free adhesive-bonded prestressed steel bar and a preparation and construction method thereof. The adhesive-bonded prestressed steel bar comprises a corrugated pipe, structural adhesive and a prestressed steel bar. The preparation method comprises the following steps: after filling the corrugated pipe with structural adhesive, inserting the prestressed steel bar in the corrugated pipe; erasing the superfluous structural adhesive so as to enable the prestressed steel bar to be capable of freely expanding and contracting in the corrugated pipe. Compared with the prior art, the grouting-free adhesive-bonded prestressed steel bar disclosed by the invention has the advantages that concentrated factory production can be adopted, the quality controllability is good, the separability of types is high, and the on-site usage and the quality control are convenient. Experiments prove that the grouting-free adhesive-bonded prestressed steel bar is high in bonding strength with concrete members, is good in compactness and is high in capability of resisting corrosion, so that the overall working properties and the durability of a prestressed concrete structure are greatly improved, and the service life of the prestressed concrete structure is prolonged. The grouting-free adhesive-bonded prestressed steel bar disclosed by the invention can play an important role on the technical field of the prestress, and has an extensive market prospect.

The invention discloses a supervised neighborhood preserving embedding method based on a kernel function. According to the method, compared with a discriminant neighborhood embedding algorithm, the problem of unbalanced distribution of data samples can be processed, and the recognition rate is high; and training and test samples are transformed to a non-linear space through the kernel function, and a dimension reduction characteristic matrix is obtained through learning and training by employing category information of the known training samples so that the samples have better separability in the discrimination subspace.

The invention relates to a photovoltaic array working state analysis and fault diagnosis method based on linear judgment analysis. The method comprises the following steps: step S1, generating photovoltaic array simulation data and colleting a plurality of electric feature parameters and environment parameters of the maximum power point of a photovoltaic generation array in daily work, thereby obtaining a feature parameter testing sample matrix; step S2, performing linear judgement analysis on a feature parameter standard matrix to obtain a projection matrix, and multiplying the standard matrix with the projection matrix to obtain a standard classification matrix; step S3, serving the standard classification matrix as a training set, and training a classification model through a support vector machine; step S4, multiplying the testing sample matrix with the projection matrix to obtain a new sample matrix; and step S5, classifying the new sample matrix obtained in the step S4 by using the classification model obtained in the step S3, and identifying the class of the data. Through the method disclosed by the invention, the accurate diagnosis on the fault can be realized by performinglinear judgment analysis and classification on the daily running data of the photovoltaic system.