195 results about "Convolution filter" patented technology

A transmitter and corresponding method for transmitting an OFDM signal in a communications channel, including a plurality of base-band OFDM modulators, each for modulating a respective data signal onto a plurality of orthogonal sub-carriers and outputting a respective sub-channel OFDM signal; and a fast convolution filter and up-converter for applying fast convolution filtering and digital up-conversion to the sub-channel OFDM signals to output a combined OFDM signal that includes each of the sub-channel OFDM signals, the fast convolution and up-converter filtering each of the sub-channel OFDM signals and frequency shifting all of the sub-channel signals to respective designated frequencies within the combined OFDM signal. A corresponding receiver is also provided.

A technique for controlling a loudspeaker system with an artificial neural network includes filtering, with a deconvolution filter, a measured system response of a loudspeaker and a reverberant environment in which the loudspeaker is disposed to generate a filtered response, wherein the measured system response corresponds to an audio input signal applied to the loudspeaker while the loudspeaker is disposed in the reverberant environment. The techniques further include generating, via a neural network model, an initial neural network output based on the audio input signal, comparing the initial neural network output to the filtered response to determine an error value, and generating, via the neural network model, an updated neural network output based on the audio input signal and the error value.

The present invention is a method of processing seismic data in which one or more seismic vibrators are activated with one or more pilot signals and vibrator motions are recorded along with seismic data. Vibrator signatures are computed from measured vibrator motions, such as the ground force signal. A desired impulse response is specified from either a measured vibrator motion or from test data or field data from a location near the location from which the seismic data was acquired. A deconvolution filter is computed from the impulse response and the vibrator signature. Alternatively, a single separation and deconvolution filter is derived from the impulse response and from vibrator signatures from multiple vibrators and sweeps. The deconvolution or deconvolution and separation filter is used to process the seismic data. The vibrators are then moved to a new location, and the activation is repeated.

The invention discloses a neural network structured pruning compression optimization method for convolutional layers, and the method comprises the steps: (1), carrying out the sparse value distribution of each convolutional layer: (1.1) training an original model, obtaining the weight parameter of each convolutional layer capable of being pruned, and carrying out the calculation, and obtaining theimportance score of each convolutional layer; (1.2) according to the sequence of importance scores from small to large, carrying out average scale segmentation by referring to the maximum value and the minimum value, carrying out sparse value configuration from small to large on the convolution layers of all the sections in sequence, and through model training adjustment, obtaining sparse valueconfiguration of all the convolution layers capable of being pruned; (2) structured pruning: selecting a convolution filter according to the sparse value determined in the step (1.2), and carrying outstructured pruning training; Wherein only one convolution filter is used for each convolution layer. According to the optimization method provided by the invention, the deep neural network can be more conveniently operated on a resource-limited platform, so that the parameter storage space can be saved, and the model operation can be accelerated.

Soft shadows may include areas that are less clear (more blurry) than other regions. For instance, an area of shadow that is closer to the shadow caster may be clearer than a region that is farther from the shadow caster. When generating a soft shadow, the total amount of light reaching each point on the shadow receiving surface is calculated according to a spatially-varying convolution kernel of the occluder's transparency information. Ray-tracing, traditionally used to determine a spatially varying convolution, can be very CPU intensive. Instead of using ray-tracing, data structures, such as MIP-maps and summed-area tables, or separable linear filters may be used to compute the spatially-varying convolution. For example, a two-dimensional convolution may be computed as two spatially-varying, separable, linear convolution filters—one computing a horizontal component and the other a vertical component of the final 2D convolution.

The invention discloses an elimination method of slurry pulse signal pump stroke noise. The order formula (N=Fs / Fo) of a comb filter is utilized, wherein Fs is the sampling frequency of a slurry signal, and Fo is a product of the movement rate of a single slurry pump piston and the number of slurry pumps, and the order of the comb filter is determined; when the pump stroke noise is eliminated, a filtering process of a slurry pulse signal is realized by utilizing MATLAB software, and comprises the following steps: 1) collecting the slurry pulse signal on site; 2) according to the signal to noise ratio of the signal, determining the bandwidth (BW) of the comb filter, designing the required comb filter according to the BW and the determined order; 3) converting the slurry pulse signal to enable a signal value to be within an interval (-1,1), and obtaining a signal X(n); 4) loading the signal X(n) into the comb filter to carry out convolution filtering to obtain a filtered signal Y(n); and 5) plotting, and observing a signal filtering situation. The invention breaks through the restriction of a hardware circuit, the MATLAB software is utilized to effectively realize the filtering process of the slurry pulse signal, and meanwhile, the comb filter is applied to the slurry pulse signal so as to further enhance a filtering effect.

The invention relates to a deep convolutional neural network method based on information lossless pooling. The method is used for image classification, and comprises the steps of collecting different kinds of images and marking image categories as image label information; performing image set division, and dividing the collected images into a training set, a verification set and a test set; designing a convolutional neural network structure based on information lossless pooling, including the number of convolutional layers and the number of information lossless pooling layers that are used, designing the number of filters in the convolutional layers, designing Gaussian smoothing filter parameters of the information lossless pooling layers, the pooling window size and a convolutional filter structure for feature fusion, designing the number of network training loop iterations and network final convergence conditions, and initializing network parameters; and inputting training data to the network in batches for calculation and training.

A system and method for an improved convolutional layer in convolutional neural networks is provided. The convolution is performed via a transformation that includes relocating input, relocating convolution filters and performing an aggregate matrix multiply.

The invention relates to a method for improving signal display quality under the condition of low sampling rate, which comprises the following steps: digital analogy sampling is carried out to an original signal so as to obtain original sampling data; interpolating zero value supplementation is carried out to the original sampling data according to given sampling increasing times so as to obtain a data sequence after zero supplementation; a low-pass filter is designed, filtration is carried out to the data sequence after the zero supplementation by adopting the convolution filtering algorithm so as to obtain a correction signal after sampling increasing; sampling decreasing processing is carried out to the correction signal after the sampling increasing so as to obtain the correction signal. The method of the invention ensures that the available information of the signal can not be lost, thus greatly improving the display and printing effects of the signal when the analog signal frequency is comparatively high and the sampling rate is comparatively low.

A computing device for detecting an object of interest in an image is provided. The computing device includes a memory device and a processor to process image data by evaluating pixel contrast to facilitate detecting an edge transition in an image, by identifying neighboring pixels that are above a predetermined contrast value, which represent a potential object of interest, filtering the pixels based on color information to identify areas where there is a color edge transition, applying a convolution filter mask to yield regions of pixels having a localized concentration of contrast and color changes, applying a threshold filter for identifying those pixel regions having values that are greater than a predetermined threshold value and grouping the identified pixel regions into one or more groups representing an object of interest, and generating an alert to notify an operator that the object of interest in the image has been detected.

The invention relates to a real-time recognition method for a static sign language based on an improved single-time multi-objective detector, which comprises the steps of performing preprocessing on astatic sign language sample image; building a reinforced static sign language image data set; building a deep learning network based on the improved single-time multi-objective detector, wherein thedeep learning network is divided into a basic network layer and an additional convolution feature layer, the basic network layer is used for feature extraction and converting an input image into multi-dimensional feature representation, and the additional convolution layer is a feature selection strategy, the category score and the position offset of a fixed group of default bounding boxes on a feature map are predicted by using a small convolution filter, and different scales of predictions are generated from different scales of feature maps; and training the network by using the static signlanguage data set, and inputting sign language video acquired by a camera in real time into the well trained network so as to realize real-time recognition for the static sign language. The real-timerecognition method greatly improves the recognition speed while ensuring the recognition accuracy.

Disclosed are a virtual stereo synthesis method and device. The method comprises: acquiring at least one voice input signal at one side and at least one voice input signal at the other side; respectively conducting ratio processing on a left ear component of a preset head related transfer function (HRTF) and a right ear component of the preset head related transfer function (HRTF) of each of the voice input signals at the other side, so as to obtain a filter function of each of the voice input signals at the other side; respectively conducting convolution filtering on each of the voice input signals at the other side and the filter function of each of the voice input signals at the other side to obtain filtering signals at the other side; and synthesizing all the voice input signals at one side and all the filtering signals at the other side to form virtual stereo signals. By means of the above-mentioned method, the present application can improve the tonal coloration effect and reduce the calculation complexity.

A defect detection method comprising, irradiating light from a light source in an optical system and obtaining a plurality of optical images of a sample having a repeated pattern of a size smaller than a resolution of the optical system; while changing the conditions of the optical system, performing correction processing for the optical images with the use of at least one of a noise filter and a convolution filter; shifting a position of the other optical images based on any of the plurality of optical images, obtaining a relationship between shift amounts of the other optical images and a change of correlation of a gray scale value between the plurality of optical images, and performing positional alignment of the optical images based on the shift amount obtained when the correlation is highest, performing defect detection of the sample with the use of the optical images after the positional alignment.

The invention discloses an incomplete projection CT image reconstruction method based on VAEGAN. The method comprises the following steps: firstly, a sinusoidal image of complete projection data is used for training a VAEGAN model to obtain a VAEGAN model capable of generating a high-quality sinusoidal image; secondly, using the trained model to predict the missing part of sinusoidal graph of incomplete projection data, the completed projection data can be obtained. Finally, the CT image is reconstructed from the completed projection data using the convolution filtered back projection (FBP) method. The invention can predict the missing projection data and further reconstruct the CT image with high quality in accordance with clinical diagnosis.

Imaging apparatus (26) is provided for use with an image sensor (24). The apparatus includes a non-linear mapping circuit (42), which is configured to receive a raw stream of input pixel values generated by the image sensor and to perform a non-linear mapping of the input pixel values. to generate a mapped stream of mapped pixel values, and a linear convolution filter (44), which is arranged to filter the mapped stream of mapped pixel values to generate a filtered stream of filtered pixel values. Other embodiments are also described.

A finger vein image recognition method based on fusion of local coding and CNN model is proposed. The method comprises the following steps: extracting the finger vein image from the finger vein image;using the encoder based on weighted symmetric local graph structure to encode the image: the reconstructed encoded convolutional filter is obtained; establishing an improved convolution neural network mode; performing feature extraction of a digital vein ROI image; measuring the similarity of the ROI images of digital veins to be matched. The finger vein image recognition method integrating the local coding and the CNN model provided by the invention can not only solve the problem of variable finger posture to a certain extent; experimental results on two finger vein databases show that the proposed method is feasible to some extent, which not only has good matching effect, but also reduces the number of parameters that can be learned, reduces the learning cost and improves the matching efficiency.

The invention relates to a deep neural network method based on space fusion pooling. The method, which is used in image classification, includes the following steps: collecting images of various categories, and marking the category of each image as image tag information; carrying out image set division: dividing the collected images into a training set, a verification set and a test set, wherein the training set is used to train a convolutional neural network; designing a deep neural network structure for image classification (including the number of convolution layers and the number of space fusion pooling layers used), designing the number of filters in the convolution layers, designing the fusion function form, space sliding step length, pooling function, pooling window size and step length in the space fusion pooling layers, designing a convolutional filter structure for feature fusion, designing the number of network training loop iterations and the network convergence conditions, and initializing the network parameters; and inputting training data to the network in batches for calculating and training.

A method of object recognition trains a convolutional neural network (CNN) with a set of training images, then classifies an image of an object using the trained CNN. A first layer of the CNN is trained by generating a set of first convolutional filters from eigenvectors produced from linear principal component analysis of patches of the training images. The training of each of multiple hidden layers CNN includes generating a set of convolutional filters from a selected subset of eigenvectors produced from linear principal component analysis of patches of an affinity matrix constructed using a set of prior convolutional filters from a prior layer of the CNN, where the affinity matrix represents correlations of feature vectors associated with the prior layer. The last layer of the CNN is trained with a regular classifier by error back-propagation using the training images and labels associated with the training images.

A technique for an equalizer filter with dynamically configurable convolution filter is described. The input to a transmitter chain is modified by an equalizer filter, prior to being applied to the transmitter. The equalizer filter modifies and smoothen the amplitude of the signal. The modified and smoothen signal has its peaks reduced which results in lower Crest Factor. The input to the reconditioning equalizer filter could be a baseband, an intermediate frequency (IF) or radio frequency (RF) signal. In the case of an IF or RF signal, it needs to be down converted to baseband before applied to the equalizer filter.

The invention discloses a realization method of a missile radio altimeter height signal simulator based on DRFM (Digital Radio Frequency Memory) technology. The method applies the DRFM technology to the radio altimeter signal simulating since the DRFM technology can retain the subtle features of the radio frequency signal. According to the method provided by the invention, continuous sampling cycle storage technology, address register cycle reset and pulse delay precision control technology are adopted, and as the method is based on DRFM system digital noise modulation technology and digital convolution filter technology, a series of technical problems of applying the DRFM technology to the altimeter signal environment are solved, highly numerical simulation precision control and continuous adjustable are realized and a plurality of interference signals of the radio altimeter can be simulated. And as the method is under use in a certain testing system developed in our institution, the effectiveness and the validity of the method is tested and verified.

The invention discloses a test paper surface texture defect detection method based on gray scale gradient clustering, which comprises the following steps: collecting a frame of image of test paper, and carrying out graying and median filtering preprocessing on the image; performing binary segmentation on the image based on a four-point gray scale dynamic threshold, and extracting a test paper areathrough a difference method; carrying out Gama gray scale enhancement on the image and filtering out part of periodic textures by adopting a Gaussian low-pass filter; constructing a single-directionGaussian kernel function to carry out convolution filtering on the image in the vertical direction; calculating the gradient grad _ x of the image in the horizontal direction; dividing the test paperarea into n columns of subareas along the horizontal direction, and calculating the position of a gradient maximum value area of each subarea; carrying out clustering calculation on the position of the gradient maximum value area of each sub-area in the vertical direction, and marking the area with the area clustering number reaching the threshold range as a texture defect area; and judging whether the test paper is qualified according to the marked area. The method has the advantages of high detection speed, high detection precision, good robustness and the like.

Methods and systems for extracting formation properties from formation logging data is disclosed. A method includes obtaining a deconvolution filter; and processing the formation logging data using the deconvolution filter to produce estimates of the formation properties. The estimates of the formation properties may be further processed with a diffusion filter, which may be an anisotropic diffusion filter. A system for extracting formation properties from formation logging data includes a central processing unit and a memory, wherein the memory stores a program having instructions for performing a method that includes designing a deconvolution filter; and processing the formation logging data using the deconvolution filter to produce estimates of the formation properties.

The invention discloses a fabric defect detection method based on a single-classification support vector machine (SVM). The method comprises the following steps: obtaining a defect-free fabric image, optimizing parameters of a Gabor filter by use of an RDPSO algorithm, and constructing a single optimal Gabor filter most adapted to a defect-free fabric image texture feature; optimizing parameters of the single-classification SVM by use of the RDPSO algorithm; performing Gabor convolution filtering on a fabric image to be detected; extracting one group of texture features on the image after filtering on the basis of GLCM; and performing defect determining by use of the single-classification SVM. According to the invention, by use of the single optimal Gabor filter, the detection speed can be effectively improved and the requirement for real-time performance of a system is ensured; and by taking the single-classification SVM as a defect determining method, the problems of local extreme values, over-learning, under-learning and the like by use of a conventional statistical mode identification method can be avoided, the generalization capability of a system can be effectively improved, and the requirement for detection accuracy of the system can be guaranteed.

The invention discloses a deep convolutional neural network method based on deterministic discarding connection. The method comprises the following steps: step one, collecting a training data set and carrying out tag marking on the data; step two, setting a structure of a convolutional neural network; step three, determining a threshold t that needs to be discarded by a convolution filter weight, initializing the convolution filter weight and determining an iteration frequency; step four, carrying out convolution operation to obtain a feature maps of all convolution layers and inputting the feature map of the last convolution layer into a classifier to obtain a data classification result so as to complete forward calculation; step five, carrying out updating and convolution filter weight optimization continuously by using a back propagation algorithm from the last convolution layer to the first convolution layer to reduce a training error; and step six, repeating the steps four and five and carrying out iteration to optimize parameters of the convolutional neural network continuously till meeting of a terminal condition.

The lane line type detection method comprises the following steps: (1) shooting a road surface in front of a vehicle body to obtain a road surface image; (2) obtaining a region-of-interest image fromthe pavement image, and performing the following two operations on the region-of-interest image: 1, converting the region-of-interest image into a grayscale image, and then performing image convolution filtering on the grayscale image so as to obtain an edge grayscale image; 2, converting an original RGB image of the region-of-interest image into a Lab color space image; (3) performing line segmentation on the edge grayscale image to obtain multiple lines of segmented images; and respectively identifying lane line marks for each row of segmented images, combining the lane line marks into a complete fitting lane line, and finally performing lane line classification according to the fitting lane line and the Lab color space image. According to the method, various illumination environments can be dealt with, the efficiency can be improved, the calculated amount can be reduced, the error rate can be reduced, an actual lane can be fitted more accurately than a straight line, yellow and white can be distinguished well, the lane line category recognition rate can be improved, and lane lines with different features can be recognized.

The invention discloses a convolution neural network learning algorithm based on a limit learning machine, the algorithm is based on the idea of self-encoding to learn the convolutional filter with bias. Firstly, the data matrix is used to generate the standardized training data with the mean value of 0 and variance of 1. Secondly, the data matrix is used to generate the standardized training datawith the mean value of 0 and variance of 1. Then the convolution deviation is processed, the intercept term is added, and the normalized input and intercept terms are reconstructed so that the objective matrix becomes a formula shown in the specification. Given input and objective matrix, and reshaping matrix are used to obtain a filter. The invention is based on an automatic coding limit learning machine, which learns a convolution filter, and is used for training arbitrary convolution neural network to work, dealing with the deviation of the filter, and reconstructing a standardized input with an intercept term. The invention is a hierarchical training process, does not need the entire classification model to extract arbitrary features, improves the training speed, realizes a competitive result in the generalization performance, and exceeds the BP in the training speed. CNN; while memory consumption is reduced.