360 results about "Multiscale decomposition" patented technology

A signal processing method and system combines multi-scale decomposition, such as wavelet, pre-processing together with a compression technique, such as an auto-associative artificial neural network, operating in the multi-scale decomposition domain for signal denoising and extraction. All compressions are performed in the decomposed domain. A reverse decomposition such as an inverse discrete wavelet transform is performed on the combined outputs from all the compression modules to recover a clean signal back in the time domain. A low-cost, non-drug, non-invasive, on-demand therapy braincap system and method are pharmaceutically non-intrusive to the body for the purpose of disease diagnosis, treatment therapy, and direct mind control of external devices and systems. It is based on recognizing abnormal brainwave signatures and intervenes at the earliest moment, using magnetic and / or electric stimulations to reset the brainwaves back to normality. The feedback system is self-regulatory and the treatment stops when the brainwaves return to normal.

The invention relates to an adaptive low-illumination visible image and infrared image fusion method, and belongs to the field of digital image processing. The method comprises the steps: image preprocessing, NSCT transformation, frequency domain coefficient fusion and an NSCT inversion. The method mainly achieves the multi-scale decomposition of a bright image and an infrared visible image, extracts high-frequency components and low-frequency components, and selects different fusion rules to carry out the frequency domain fusion according to the characteristics of the high-frequency components and low-frequency components. The NSCT inversion part is mainly used for carrying out the multi-scale inversion of the obtained fusion high-frequency and low-frequency components, obtaining the gray scale image after fusion, then carrying out the weighting of the gray scale image after fusion and an original color visible image, and obtaining a color fusion image. The method can effectively keep more detail information of the original image, can improve the contrast and resolution of the fusion image, and can be widely used in the fields of intelligent traffic, video monitoring, medical diagnosis, target detection and national defense security.

The invention relates to a method for fusing multi-focus images based on wavelet transform and neighborhood characteristics, The method comprises the following steps of: firstly, performing multi-scale decomposition on the images by utilizing wavelet transform to acquire low-frequency and high-frequency information of images in different resolution ratios and directions; secondly, processing the low-frequency and the high-frequency information by adopting different fusion rules according to the characteristics of the low-frequency and the high-frequency information, wherein low-frequency subimages are processed by a neighborhood normalization gradient weighted average-based fusion method, so the defect that marginal information is ignored in the conventional low-frequency component fusion method is overcome, and high-frequency subimages are processed by a neighborhood standard deviation weighted average-based fusion method so as to retain detail information of the images furthest; and finally, performing wavelet reconfiguration to obtain the fused images. The method eliminates the phenomenon that marginal distortion exists in the conventional fusion algorithm, improves the quality and definition of the fused images, and can be applied to various military or civil multi-focus image fusion systems.

The invention discloses a multi-exposure image fusion method based on Laplacian pyramid decomposition, relating to the field of computer vision and the field of image / video processing; and the research over-emphasizes the image processing. With respect to the disadvantages of the loss of image details during multi-scale decomposition and reconstruction in the traditional fusion method based on the Laplacian pyramid decomposition, the method has the beneficial effects: the details of the input images are strengthened on a certain extent by means of an image detail strengthening method, and the partial loss of the details caused by pyramid mitigation and amplification is counteracted, so that the multi-exposure image fused images contain rich details and higher resolution.

The invention relates to a multi-exposure image fusion method. The Laplacian pyramid decomposition is utilized to perform multi-scale decomposition of an original image, so that a high frequency image and a low frequency image of the original image are obtained. Different fusion mechanisms are adopted for the high frequency image and the low frequency image to finally obtain a reconstructed image. In the Laplacian pyramid decomposition process, the size of the lower frequency image is much smaller than the size of the original image due to the processing process of down sampling of each layer, so that the time complexity of the sparse representation framework fusion method is greatly reduced, information of a specific frequency band can be highlighted, and more direction and texture information of the original image can be reserved.

An image fusing-method based on non-subsample outline wave transform includes carrying out multi-dimension decomposition on image by utilizing non-subsample outline wave transform to obtain high frequency sub-image and low frequency sub-image, using resolution selection fusion means to fuse high frequency sub-image and using relevant pixel grey scale selection regulation to fuse low frequency sub-image, applying non-subimage outline wave inverse transform on fusion results of low and high frequency sub-images for obtaining final fused result.

The invention relates to a multi-scale processing method for nuclear logging data, comprising 1, reading logging data; 2, carrying out filtering for logging data; 3, carrying out normalization processing for filtered data; 4, carrying out multi-scale decomposition, amalgamation and reconstruction for logging data after normalization processing; and 5, displaying curve and image. The invention solves the limitation that collected data can be process and interpreted only in 1-D depth region in prior technology. The invention can reflect multi-scale characteristic for oil gas water distribution in multi-dimension space and improve accuracy for describing distribution of residual oil gas saturation.

Disclosed is a high-speed train driver alertness detecting method based on face image and eye movement analysis. The method includes steps of acquiring images of the head of a driver by a primary camera and a secondary camera simultaneously, extracting characteristics of the head of the driver step by step by the aid of wavelet multi-scale, recognizing the head of the driver via a neural network training method, and detecting the face of the driver via an AdaBoost arithmetic; respectively starting a Harr characteristic and a two-dimensional orthogonal Log-Gabor filtering phase characteristic to detect human eyes under different illuminations; building an adaptive non-linear level-log model of the driver; realizing eye movement tracking analysis for the driver via a strong tracking particle filter arithmetic; and finally realizing weight sum for an eye movement characteristic fatigue factor value and six face images including PERCLOS, pupilla, blinking, nodding, yawning and face inclination so as to obtain an alertness value of the driver. The calculated alertness value is high in accuracy and robustness.

The invention relates to a microscopic image fusing method based on two-dimensional empirical mode decomposition, which comprises the following steps: performing multi-scale decomposition on the acquired ordered microscopic original images by using a two-dimensional empirical mode decomposition method, thereby acquiring the multi-scale high-frequency components of original images; fusing the multi-scale high-frequency components according to local obvious standard; fusing the low-frequency components of the original images by using a principal component analysis method; and finally reversely recomposing to acquire a merged image. By using the method provided by the invention, the multi-scale decomposition is performed on the acquired ordered microscopic original images by using the two-dimensional empirical mode decomposition method and the decomposition process is adaptive; high-frequency fusing treatment is performed according to the local obvious standard based on a big area value and the relevance between adjacent coefficients is considered, so the detail information clearly focused of each original image can be supplied; and the low-frequency fusing treatment is performed by using the principal component analysis method, so the relevant information of original image pixel is utilized and the visual decoding effect of the merged image is increased, thereby increasing the quality of the fused image.

The invention provides an infrared image and visible image fusion method based on guide filtering. The method comprises the steps of: firstly, expanding the guide filtering to multiple scales, and performing multi-scale decomposition on an infrared image and a visible image by using the multi-scale guide filtering, so as to obtain a low-frequency subband and a high-frequency subband; performing nonsubsampled directional filtering on the high-frequency subband, so as to obtain a directional subband coefficient; applying different fusion rules to the directional subband coefficient and a low-frequency subband coefficient, so as to obtain the corresponding directional subband coefficient and the low-frequency subband coefficient after fusion, and finally, performing directional filtering reconstruction and multi-scale reverse transformation based on the guide filtering, so as to obtain a final fusion image. According to a fusion result obtained by adopting the method, the edge and thermal radiation characteristics of an infrared image object are preferably kept, scene details of the visible image can be preferably reserved, and the information content of a fusion image is increased, so that the edge and details of the fusion image are enriched.

The present invention provides a visible-light polarization image fusion method based on non-subsampled shearlets. At first, Strokes calculation is carried out for different polarization images captured by a multi-detector camera at the same time to obtain a polarized degree image, a polarized angle image and a light intensity image by which a polarization feature image of a target is extracted. Then, non-subsampled shearlets transform (NSST) decomposition is performed on the polarization feature image and the light intensity image separately. High and low-frequency fusion coefficients are determined separately in a frequency domain according to window energy and an average value. An initial fusion image is reconstructed by using NSST inverse transform. Finally, the initial fusion image is subjected to target enhancement to obtain final fusion image output. Compared with a conventional target detection method utilizing multi-scale decomposition, the method provided by the present invention increases means for polarization feature extraction and target enhancement, effectively increases details of the fusion image, improves target and background contrast, highlights polarization properties of the target, improves the ability of scene perception and target detection, and is suitable for a target detection system.

The invention relates to a neighborhood normalized gradient and neighborhood standard deviation-based multi-focus image fusion method. The method comprises the following steps of: firstly, performing multi-scale decomposition on images by using wavelet transform to acquire low-frequency and high-frequency information of the images under different resolutions and different directions; secondly, processing the images by adopting different fusion rules according to the respective characteristics of the low-frequency and high-frequency information, wherein a neighborhood normalized gradient-based fusion method is adopted for the low-frequency sub images to overcome the defect that the traditional low-frequency component fusion method neglects edge information, and a neighborhood standard deviation-based fusion method is adopted for the high-frequency sub images so as to furthest keep detailed information of the images; and finally, performing wavelet reconstruction to acquire a fused image. The method overcomes of edge distortion of the traditional fusion algorithm, obviously improves the quality and the definition of the fused image, and can be applied to various military or civil multi-focus image fusion systems.

The invention discloses a power load short-term prediction method, model, device and system, and the method comprises the steps of receiving the load data, and complementing the missing data of the load data; receiving the influence factor data which comprises the air temperature data, the holiday data and the industry category data to which the power consumers belong, and quantifying the influence factors by adopting a quantification method corresponding to the load data; processing the historical load data by adopting the wavelet decomposition, carrying out the multi-scale decomposition to obtain four historical load reconstruction data sequences, and respectively carrying out correlation measurement on the four historical load reconstruction data sequences and the influence factor datato obtain a correlation characteristic data set of each reconstruction load characteristic and the influence factor; and carrying out preliminary prediction on the four sequences obtained according tothe load data by adopting a cubic exponential smoothing algorithm, further optimizing a preliminary prediction result, and finally obtaining a power short-term load prediction value as the power loadscheduling reference data.

A signal processing method and system combines multi-scale decomposition, such as wavelet, pre-processing together with a compression technique, such as an auto-associative artificial neural network, operating in the multi-scale decomposition domain for signal denoising and extraction. All compressions are performed in the decomposed domain. A reverse decomposition such as an inverse discrete wavelet transform is performed on the combined outputs from all the compression modules to recover a clean signal back in the time domain. A low-cost, non-drug, non-invasive, on-demand therapy braincap system and method are pharmaceutically non-intrusive to the body for the purpose of disease diagnosis, treatment therapy, and direct mind control of external devices and systems. It is based on recognizing abnormal brainwave signatures and intervenes at the earliest moment, using magnetic and / or electric stimulations to reset the brainwaves back to normality. The feedback system is self-regulatory and the treatment stops when the brainwaves return to normal. The braincap contains multiple sensing electrodes and microcoils; the microcoils are pairs of crossed microcoils or 3-axis triple crossed microcoils.

The invention discloses a hybrid energy storage system and a wind power generation power smooth control method. Firstly, a frequency spectrum of a wind power signal is obtained through a quick Fourier method, and amplitude-frequency characteristics of wind output power are analyzed; then, wind power is decomposed in multiple scales through an empirical mode decomposition method and then reconstructed into wind farm expected grid-connection power and high-frequency, mediate-frequency and low-frequency wind power fluctuation power; the power is distributed according to the capacity of a super-capacitor Soc, correspondingly adjusted and absorbs high-frequency, mediate-frequency and low-frequency fluctuation signal power through the super-capacitor, a storage battery and stored compressed air energy; when the output power of a wind farm is smaller than an expected grid-connection power signal, a hybrid energy storage system composed of the super-capacitor, the storage battery and an CAES is controlled to discharge through a model algorithm; when the output power of the wind farm is larger than expected grid-connection power, the hybrid energy storage system composed of the super-capacitor, the storage battery and the CAES is controlled to charge through the model algorithm. The hybrid energy storage system and the wind power generation power smooth control method improve safety and economic efficiency of grid-connection operation.

The invention discloses a partial discharge signal denoising method based on a wavelet adaptive threshold. The partial discharge signal denoising method based on the wavelet adaptive threshold comprises the following steps of (1) inputting a partial discharge signal to be denoised, (2) carrying out wavelet multi-scale decomposition on the partial discharge signal to obtain high-frequency coefficients of decomposition scales and a low-frequency coefficient of a maximum decomposition scale, (3) using a non-negative garrote threshold function and a adaptive threshold selection method based on particle swarm optimization to carry out quantitative processing on high-frequency coefficient components obtained in the step (2) so as to remove noise components, storing the result to serve as new high-frequency coefficient components, (4) carrying out signal reconstruction through the new high-frequency coefficient components and a low-frequency coefficient component, obtained in the step (2), of the maximum decomposition scale to obtain a partial discharge signal without noise, and (5) outputting the partial discharge signal without the noise. The partial discharge signal denoising method based on the wavelet adaptive threshold achieves wavelet coefficient threshold self-adaptation selection on the premise that any priori knowledge does not exist, and is applicable to various actual partial discharge conditions and good in effect of removing white noise, and the denoised partial discharge signal with higher quality can be obtained.

The invention discloses a full-reference image quality assessment method based on an image edge difference statistical property comprising: firstly performs a multi-scale decomposition to the reference image and a distortion image; then detecting an image edge response under each scale based on the image multi-scale decomposition; obtaining a binary distribution diagram of the image edge; calculating an image edge difference statistical property by using the binary distribution diagram of the original image and the distortion image under different scales; finally mapping an image edge difference statistic to a psychological scale through a Weber-Fechner law, and carrying out normalization by using the total number of the original image edge points under each scale and obtaining a final assessment index of the image distortion. The full-reference image quality assessment method provided by the invention has advantages of stable performance, simple calculation, accurate prediction results, suitable for distinct types of distortion images, thus has great application prospect.

A signal processing method and system combines multi-scale decomposition, such as wavelet, pre-processing together with a compression technique, such as an auto-associative artificial neural network, operating in the multi-scale decomposition domain for signal denoising and extraction. All compressions are performed in the decomposed domain. A reverse decomposition such as an inverse discrete wavelet transform is performed on the combined outputs from all the compression modules to recover a clean signal back in the time domain. A low-cost, non-drug, non-invasive, on-demand therapy braincap system and method are pharmaceutically non-intrusive to the body for the purpose of disease diagnosis, treatment therapy, and direct mind control of external devices and systems. It is based on recognizing abnormal brainwave signatures and intervenes at the earliest moment, using magnetic and / or electric stimulations to reset the brainwaves back to normality. The feedback system is self-regulatory and the treatment stops when the brainwaves return to normal. The braincap contains multiple sensing electrodes and microcoils; the microcoils are pairs of crossed microcoils or 3-axis triple crossed microcoils.

The invention relates to an optical fiber distributed disturbance sensing method with disturbance property identification function. Based on double Mach-Zehnder interference type distributed disturbance sensor, the method comprises the following steps of: S1, carrying out analogue-to-digital conversion to two signals acquired by two photoelectric detectors of the double Mach-Zehnder interference type distributed disturbance sensor to obtain digital quantity signals; S2, carrying out wavelet multi-scale decomposition to the two digital quantity signals, and extracting characteristic components; S3, comparing the extracted characteristic components with a threshold value to determine what to cause disturbance; if judging that the disturbance is caused by outside noise, not giving an alarm; if judging that the disturbance is caused by outside invasion, giving an alarm, and going to step S4; S4, carrying out noise reduction to the two signals; S5, carrying out reverse wavelet transform to the two signals after noise reduction for reconfiguration to obtain recovered original signals; and S6, carrying out related operation to the two recovered original signals to obtain disturbance position, and displaying.

Through sensor of stress wave, the invention picks up signal of stress wave of malfunction in early stage. The invention mainly solves issues of data acquisition for stress wave, noise suppression, feature extraction of signal, and fault recognition and position. Based on signal character, wavelet analysis selects suitable wavelet basis function, and carries decomposition of fault signal in multiple scales. Reconstructing waveform and spectrogram from each decomposition in different scale picks up minute character so as to determine type of fault and put forward scheme of treatment. Thus, the invention reduces economic loss to minimum.

The invention discloses a visible light image and infrared image registering method which comprises the following steps: performing multi-scale decomposition on a visible light image and an infrared image to obtain low-resolution visible light image and infrared image; extracting SIFT (scale invariant feature transform) features, multi-scale corner features and surface point features from the low-resolution image pair; matching the SIFT features and removing exterior points; obtaining an initial transformation model by use of the matched SIFT feature pair, wherein the transformation model refers to any geometric transformation relationship between the infrared image and a high-spectrum image; extracting the multi-scale angular point features and the surface point features based on an image block pair on the original image pair by use of the geometric constraint provided by the initial transformation model; determining a more accurate transformation model according to the initial transformation model and the multi-scale angular point features and surface point features; and transforming the infrared image according to the transformation model to obtain the transformed infrared image.

A method for rapid hierarchical image segmentation based on perceptually driven contour completion and scene statistics is disclosed. The method begins with an initial fine-scale segmentation of an image, such as obtained by perceptual completion of partial contours into polygonal regions using region-contour correspondences established by Delaunay triangulation of edge pixels as implemented in VISTA. The resulting polygons are analyzed with respect to their size and color / intensity distributions and the structural properties of their boundaries. Statistical estimates of granularity of size, similarity of color, texture, and saliency of intervening boundaries are computed and formulated into logical (Boolean) predicates. The combined satisfiability of these Boolean predicates by a pair of adjacent polygons at a given segmentation level qualifies them for merging into a larger polygon representing a coarser, larger-scale feature of the pixel image and collectively obtains the next level of polygonal segments in a hierarchy of fine-to-coarse segmentations. The iterative application of this process precipitates textured regions as polygons with highly convolved boundaries and helps distinguish them from objects which typically have more regular boundaries. The method yields a multiscale decomposition of an image into constituent features that enjoy a hierarchical relationship with features at finer and coarser scales. This provides a traversable graph structure from which feature content and context in terms of other features can be derived, aiding in automated image understanding tasks. The method disclosed is highly efficient and can be used to decompose and analyze large images.

This invention relates to a method for interfusing fuzzy images based on region characters including the following steps: 1, applying small wave frames to carry out multi-dimension resolutions to being interfused images to get a series of high frequency components and a lowest component, 2, carrying out K average clustering to the low frequency part of the infrared images and dividing it to three kinds, 3, expressing the three kinds to an important target region, a second important region and a background region to make a decision to the interfusion based on the fuzzy region character and measurement target of the HF part of a sensor multi-image, 4, sending the final multi-resolution images into a filter made up of a same small wave basic function to be filtered and summing up the filtered image signals, lowering the transformation layer number of the small wave frame by one, carrying out a process of the fall-sample to the filter then to transform the next layer inversely and repeating the process till finishing the inverse transformation to the entire wave frames to get a final fused image.

A signal processing method and system combines multi-scale decomposition, such as wavelet, pre-processing together with a compression technique, such as an auto-associative artificial neural network, operating in the multi-scale decomposition domain for signal denoising and extraction. All compressions are performed in the decomposed domain. A reverse decomposition such as an inverse discrete wavelet transform is performed on the combined outputs from all the compression modules to recover a clean signal back in the time domain. A low-cost, non-drug, non-invasive, on-demand therapy braincap system and method are pharmaceutically non-intrusive to the body for the purpose of disease diagnosis, treatment therapy, and direct mind control of external devices and systems. It is based on recognizing abnormal brainwave signatures and intervenes at the earliest moment, using magnetic and / or electric stimulations to reset the brainwaves back to normality. The feedback system is self-regulatory and the treatment stops when the brainwaves return to normal. The braincap contains multiple sensing electrodes and microcoils; the microcoils are pairs of crossed microcoils or 3-axis triple crossed microcoils.

The invention discloses a module transfer method based on multiscale modeling. The method comprises the following steps: collecting original spectra of a host instrument and a slave instrument; by combining the characteristic of wavelet basis and the characteristic of the original spectrum of a sample, selecting the optimal wavelet basis to carry out wavelet multiscale decomposition on the spectrum to obtain wavelet coefficient; reconstructing the wavelet coefficient; respectively performing multivariate calibration on each layer of reconstructed spectrum; setting up a prediction model based on partial least squares method and leaving one cross-validation method for the spectrum after performing multivariate calibration to obtain a cross-validation root-mean-square error of the prediction model; performing model fusion on the prediction model by using weight number, and calculating the prediction root-mean-square error and related coefficient to evaluate the model transfer effect. Compared with a conventional model transfer method, the method greatly improves the model transfer efficiency and performance, and can be widely applied to fields of near-infrared and Raman spectrum.

The invention relates to a rapid tone mapping system and method based on multi-scale Gauss filters. The system comprises a multi-scale decomposition module, a rough layer module, a detail layer module, a fusion module, a chroma processing module, a gamma correction module and a terminal display module. The multi-scale Gauss filters are used to decompose images of high dynamic range to obtain rough images and detail images; the fusion module combines the rough images with the detail images linearly to form novel images of low dynamic range; the chroma processing module compensates chroma information; and the gamma correction module uses gamma correction to compensate the nonlinear relation between input signals and output signals of a display system in advance. According to the invention, the image of high dynamic range can be effectively compressed, image information is effectively reserved, the algorithm efficiency is high, consumption time is short, and the tone mapping system and method are suitable for mobile phones.

The invention relates to a wind-speed time series forecasting method for a wind power station. The wind-speed time series forecasting method is characterized by comprising the following steps that: a wind-speed collecting instrument is used for data of wind speed of same area once per hour, and the collected original wind speed data is organized to form a wind-speed time series for analyzing and forecasting; a rapid independent component analysis algorithm is utilized for carrying out multiple-scale decomposition on the wind-speed time series, so as to obtain a plurality of independent components; the delay time and the embedding dimension of the independent components are calculated, and a phase-space reconfiguration theory is adopted for carrying out phase space reconfiguration on the independent components; a least squares support vector machine regression model is utilized for carrying out modeling forecasting on the independent components after phase space reconfiguration; and the forecasting results are superposed to obtain the final forecasting result of the wind-speed time series. The method is scientific, reasonable, accurate and reliable in wind-speed time series forecasting, and has strong adaptivity.

The invention relates to a super-high voltage direct-current power transmission line region internal and external fault identification method, and belongs to the field of high voltage direct-current power transmission system relay protection. The method comprises the steps of: firstly collecting fault voltage data; carrying out wavelet multi-scale decomposition on detected fault voltage signals to obtain a wavelet reconstruction high frequency coefficient of each layer, forming a characteristic vector matrix with singular-spectrum entropy of the high frequency coefficients of all layers, and dividing the data in the characteristic vector matrix into a training set and a testing set; then setting a training set label and a testing set label; carrying out training on the training set; then setting storage positions of prediction labels and prediction precision; inputting the testing set to an SVM classifier for testing, and obtaining a classification result and prediction precision; and then determining whether the classification result stored in a prediction label storage space is correct. By adopting the method provided by the invention, faults at three different positions can be identified at the same time; in addition, the method is simple and effective, the calculating time is short, and automation is realized in the whole classification process.

The invention discloses an image segmentation method based on feature selection and hidden Markov model, which comprises the processes that: an image block corresponding to the texture of an image to be segmented is extracted, and a corresponding training feature set is extracted; a model parameter theta j<c> is obtained; a likelihood value corresponding to data blocks of various scales corresponding to scale analysis of the image to be segmented and a likelihood value corresponding to the pixel points of the image to be segmented are respectively obtained and combined together to obtain likelihood value k<c> that is required in final fusion; the initial segmentation results of various scales are obtained; context-2 and context-6 are adopted in sequence to carry out the multi-scale post fusion segmentation to the image; the result of scale 0 is taken as a final segmentation result; the image segmentation method aims at solving the defects that the traditional image segmentation method based on hidden Markov model does not make full use of image information and background guiding the segmentation of the image when in post fusion can not completely retain edge information on fine scales, and can be used for the segmentation of synthetic aperture radar (SAR) images, remote sensing images and textured images.