147 results about "Energy diagram" patented technology

The invention discloses an active detection and recognition system and method for a human gait behavior based on semantic folding. Embedded gait behavior detection and recognition system hardware with low power consumption is built by using a three-dimensional sound field positioning system, a sole force field positioning system, an HDMI high-definition camera, a high-definition video acquisition system, a microcomputer Raspberry and the like. Gait semantic energy diagrams with timing characteristics provided by the invention contain gait time information under different situations, and the learning and prediction ability of a gait behavior cognition system can be enhanced according to a lot of gait semantic energy diagrams with timing characteristics. Meanwhile, the active detection and recognition technology for a human gait behavior based on semantic folding has extensive application prospects in various fields which mainly comprises the fields such as long-distance identity recognition, abnormal gait behavior detection, pedestrian behavior prediction and mass video retrieval, and has excellent economical and social benefits.

The invention provides a gait recognition method based on a partitioned matrix. Firstly, extracting single-frame images from a video, then carrying out grey scale transformation on the single-frame images, using the background subtraction method to extract person body targets, using mathematical morphology to fill the holes of binary images, and extracting profiles of the person by means of single connection analysis so that the person bodies are positioned in the middle and are uniformly in the size of 64 * 64 pixels; observing the periodic change of the gait according to elliptical short axis and eccentricity fitted in image regions after the standard centralization of each frame image in a gait video sequence; using a gait energy diagram to extract the integral characteristic of the gait in the one period, dividing GEI into sub-blocks by means of the partitioned matrix, eliminating the sub-blocks which are useless to classification in a self-adapting manner, and adopting the method, which combines the two-dimensional principal component analysis of a sub-block mode with the two-dimensional linear discriminant analysis, to further extract local characteristics; and integrating the characteristics of each effective sub-block into a whole during the classification recognition, and adopting a nearest neighbor classifier to perform identification judgment. The method is effective for the recognition of the gait of knapsack change.

The invention discloses an adaptive characteristic block selection-based gait identification method in the technical field of image processing. By blocking a human body region in a gait energy diagram, acquiring statistical information of each region according to the training data of no clothes and carried object state interference and calculating the statistical information through blocks duringtesting to automatically select characteristic blocks in accordance with the statistical information laws of the training data, the adverse effects of pedestrian clothes and carried object state change on gait identification are effectively overcome, meanwhile, the characteristics of the parts such as head, shoulders and the like of a person are kept, and the effectiveness of the gait identification is improved. Any priori knowledge is not needed, the calculation complexity of characteristic selection is reduced by 28 percent compared with the conventional gait identification method for non-supervision characteristic selection, and meanwhile, the average identification rate is comparable in the conventional supervision characteristic selection-based gait identification method.

The invention provides a micro-expression recognition method based on a difference slice energy diagram and Gabor transformation. The micro-expression recognition method comprises the following steps: constructing a micro-expression sequence difference slice energy diagram, calculating micro-expression frames containing change regions in a micro-expression periodic sequence, graying the micro-expression sequence to extract micro-expression difference slices, and overlapping micro-expression difference slice frame sequences to obtain a micro-expression difference energy diagram; extracting the characteristics of the difference slice energy diagram, constructing a Gabor filter kernel function, performing Gabor characteristic extraction on the difference slice energy diagram, sampling the extracted characteristics, writing the characteristics of each sample in a column vector form, maximizing the quotient of inter-class divergence and intra-class divergence through linear discriminant analysis with supervisory information, and further extracting the characteristics of each sample; performing classification and identification, training a model according to training data, and predicting and classifying test samples according to the model. The method provided by the invention has general applicability. Compared with an existing method, the method provided by the invention has a higher identification rate.

The invention is applied to the field of video detection, and provides a video significance detection method. The method comprises the steps that superpixel segmentation is conducted on a to-be-detected current frame to obtain a current frame after superpixel segmentation, optical flow field motion estimation is calculated according the current frame and a previous frame, motion distribution energy and motion edge energy are calculated, motion history energy is calculated according to the current frame and the previous frame, and a hybrid motion energy diagram is generated according to the above-mentioned features and a significance diagram of the previous frame; and an initial target segmentation area of the hybrid motion energy diagram is obtained, a reliable target area and a reliable background area are extracted, and a significance global optimization model is constructed according to the reliable target area, the reliable background area and the hybrid motion energy diagram and then solved to obtain a significance diagram of the current frame. According to the video significance detection method, by adopting multiple motion features and space features such as the motion distribution energy of an area layer, the motion edge energy of an edge layer, the motion history energy of a pixel layer and the significance diagram of the previous frame, and the robustness and stability of significance detection are enhanced.

The invention discloses an estimation method of a multi-component non-stationary signal instantaneous frequency based on focusing S-transform, and mainly solves the problems that the multi-component non-stationary signal instantaneous frequency with high precision cannot be realized because the energy aggregation is not high and the time frequency resolution ratio cannot be flexible to adjust and cannot realize high precision. The estimation method comprises the realizing steps: 1, inputting a to-be-analyzed non-stationary signal; 2, optimizing a control parameter of a window function in the focusing S-transform according to an aggregation criterion; 3, calculating the optimized focusing S-transform and acquiring a signal time frequency distribution energy diagram; 4, carrying out binarization processing on the time frequency distribution energy diagram of the non-stationary signal; and 5, obtaining the instantaneous frequency estimation on a signal according to a binaryzation time frequency diagram after the binarization processing. According to the method provided by the invention, the self-adaption adjustment of the control parameter of the window function can be realized by improving the S-transform window function, and the time frequency distribution energy aggregation and the instantaneous frequency estimation accuracy can be improved, therefore the method can be used for radar interception, communication countermeasure, voice identification, and medical brain wave signal analysis.

The invention discloses a maneuvering target radial acceleration and speed estimation method based on an orthogonal match pursuit, belonging to the field of radar signal processing. According to the maneuvering target radial acceleration and speed estimation method, a radial acceleration and a radial speed of a high-speed and large-maneuvering target can be rapidly accurately determined, the tracking performance and the recognition capability of a radar to the high-speed and large-maneuvering target are effectively improved, the response time of a weapon system is increased, and the attacking capacity to the target is enhanced. The maneuvering target radial acceleration and speed estimation method provided by the invention comprises the following steps of: 1, sampling a signal received by a radar, establishing a complete atom library; 2, carrying out orthogonal match pursuit decomposition on the signal; and 3, searching a sparse solution energy diagram peak value, determining a radial acceleration and a radial speed of the signal according to peak value coordinates. The maneuvering target radial acceleration and speed estimation method has the advantages of high instantaneity, accuracy in radial acceleration and speed estimation, easy realization of engineering, stronger engineering application value and popularization prospect, and can be used in the fields of improving high-maneuvering target real-time accurate pursuit and radar target type recognition, and the like.

The invention relates to a method for extracting and identifying small sample character contour features which comprises the following steps: firstly extracting body contour images in a target character video; secondly dividing gait cycles, unifying the size of the body contour images, and extracting feature factors of the body contour; and then working out a gait energy diagram and feature factors of each gait cycle, and obtaining contour feature data of the character by multiplying a gray-scale histogram of the gait energy diagram by the feature factors of the gait energy diagram; and then putting the contour feature data of a well-trained target character into a training library; finally working out the contour feature data of the character to be identified, carrying out improved nearest neighbor matching with the character in the training library, wherein the character in the training library which has a minimum distance with the character is identified to be the character to be identified, and finishing the character identification. The invention eliminates the influence of a great deal of noises in actual complex environments, shows body contour information, extracts effective character features and can be used for identifying the characters in household scenes.

The invention belongs to the technical field of radar and discloses a fast simulation method of a high resolution SAR image. The SAR image of a needed target scene can be efficiently and quickly simulated. The method is used for SAR image interpretation and automatic target recognition. The method comprises the steps that the three-dimensional model of the target scene is established; the imaging geometry of the target scene and the starting point and the direction vector of a needed sampling ray are determined; for the target scene, an SAH-BVH bin dividing structure based on bin is established; the BVH structure is used to carry out rapid ray tracing, and intersection information is acquired; an acquired backscattering energy diagram is determined; a final SAR image is synthesized; and corresponding noise is added.

The invention discloses a connected region labeling-based frequency hopping signal dynamic clustering extraction method. The method comprises the following steps that: a received signal model is constructed; a morphological method is adopted to perform de-noising and segmentation processing on received signals; connected region labeling is performed on a processed image; the lasting durations of connected region labeling signals and labels corresponding to the lasting durations of the connected region labeling signals are dynamically clustered; secondary dynamic clustering is performed on the appearing time points of the connected region labeling signals and the labels corresponding to the appearing time points of the connected region labeling signals according to a dynamical clustering result; frequency hopping signal detection and extraction are performed according to a dynamical clustering result; and frequency hopping signal verification and quality evaluation extraction are performed on the extracted signals, and a frequency hopping energy diagram can be obtained. With the connected region labeling-based frequency hopping signal based dynamic clustering extraction method adopted, accurate extraction of the energy diagram of required frequency hopping signals can be realized when low-signal noise ratio strong interference exists, and different-time duration interference of which the period is identical with a hopping period exists, or another kind of frequency hopping signals of which the period is identical with the period of required frequency hopping signals exist.

The invention discloses a gait recognition method and system in combination with subspace learning and tensor neural network and belongs to the field of intelligent recognition. The method includes the following steps: acquiring gait data, obtaining a gait data set, and processing the gait data set to obtain a silhouette set, and further obtaining a gait energy diagram; taking 80% of the silhouettes as a training set and conducting dimensionality reduction on the training set, taking the rest 20% of the silhouettes as testing set data and testing the result of the training, then extracting features from the gait energy diagram and a data tensor neural network module which is subject to dimensionality reduction, then classifying the features through a support vector machine which acts as a classifier, finally comparing the training set and the result of the test set to obtain the result from identifying and verifying the identity of passenger. According to the invention, the method is easy to implement and has low cost. The method can automatically conduct identity authorization and fake identity verification in a certain venue, and effectively increase the effectiveness of identity verification for security and protection and other conditions in a monitored venue.

The invention relates to a human behavior identification method based on multi-feature fusion, which comprises the following steps of: acquiring a human body behavior video by using a camera, extracting a foreground image of each frame of image, and carrying out cavity filling and interference filtering to obtain a human body silhouette image sequence; Calculating the similarity between adjacent frames in the image sequence, and obtaining the weight of each frame of image representing the behavior posture; According to each frame of image in the human body silhouette image sequence and the corresponding weight thereof, obtaining an action energy diagram representing a behavior process through weighted average; And extracting a Zernike moment, a gray histogram and a texture feature of the action energy diagram to form a multi-dimensional feature fusion vector containing behavior space-time characteristics; Constructing feature vector template libraries of different standard behaviors; And in the behavior identification process, extracting feature vectors of to-be-identified behaviors according to the to-be-identified videos, matching the feature vectors of the to-be-identified behaviors with the feature vectors of the standard behavior template library one by one, determining behavior types according to matching results, and realizing accurate identification of human body behaviors. According to the method, the time change and spatial attitude characteristics of human body behaviors are represented by constructing the action energy diagram, the behavior recognition accuracyand real-time performance can be improved, and certain practical value is achieved.

The invention discloses a road traffic sign detecting method based on phase symmetry. The flows of the method comprise red-blue standardization pretreatment, phase symmetry detection, morphological filtering, and maximally stable extremal region (MSER) feature detection. Specifically, the method comprises: performing color pre-segmentation on an image by a red-blue standardization method according to the characteristic red or blue of a traffic sign; computing a highlight prominent traffic sign candidate region by using phase symmetry according to the symmetry of the external shape of the traffic sign; and extracting a sign candidate region from a phase symmetry energy diagram by using MSER features. The method is suitable for detection of road traffic signs in complex natural environment and has better detection effects. Further, compared with a conventional detection method just based on color or shape information, the method has better robustness in complex road scenarios by using the color and shape characteristics of the traffic signs.

The invention belongs to the technical field of pattern recognition, relates to computer technology, digital image processing technology, biological feature recognition technology and the like, and provides an image contour based novel human face recognition method. The method comprises the following steps: firstly, extracting a human face image contour by using a binarization method and a mathematical morphology method, followed by further optimizing to obtain the human face contour with interior boundary as few as possible, and calculating human face contour energy diagram of each training sample; then, calculating the similarity between the test sample and each kind of the human face contour energy diagram; and finally, classifying and recognizing the test sample according to the similarity standard. The method provided by the invention is a similarity matching method, can make full advantage of image structure information, avoids characteristic value solving problem in a traditional method and Euclidean distance-based classification algorithm, and can effectively improve classification and recognition performance through applying a matrix logic and operation into the classification and recognition.

The invention discloses a three-dimensional image quality objective evaluation method based on energy diagrams. The three-dimensional image quality objective evaluation method includes: firstly respectively calculating energy diagrams on different scales and directions of original undistorted three-dimensional images and energy diagrams on different scales and directions of fuzzy three-dimensional images to be evaluated to obtain the objective evaluation metrics of each pixel point of the fuzzy three-dimensional images to be evaluated, and then performing fusion on the objective evaluation metrics of each pixel point of the fuzzy three-dimensional images to be evaluated according to the energy diagrams and binocular minimum perceptible changing images to obtain image quality objective evaluation predicted values of the fuzzy three-dimensional images to be evaluated. The three-dimensional image quality objective evaluation method has the advantages of being capable of well reflecting visual perception characteristics of human visual systems by obtaining the energy diagrams of different scales and directions, performing fusion on the energy diagrams and the minimum perceptible changing images, and being capable of effectively improving objective evaluation results and correlation of subjective perception.

The invention discloses a gait recognition method, particularly the gait recognition method based on two-dimension wavelet packet decomposition and complete PCA (Principal Component Analysis), which belongs to the technical field of pattern recognition. The method comprises the following steps of: pretreatment (morphologic treatment, target extraction and image normalization), feature extraction (gait cycle, gait energy image and fusion of WPD plus (2D) 2 PCA selection feature) and classification of the test samples to a corresponding class according to the nearest neighbor classification principle. the method integrates periodic frames in one mean chart by utilizing the gait energy diagram so as to eliminate the influence of difference of periodic frame numbers on the feature extraction, thereby reducing the computational complexity; and besides, the method extracts and selects gait features by initially adopting the method of fusing WPD with (2D) 2 PCA so as to solve the problems of loosing of high-frequency components or excessive dimensionality due to the simple adoption of all data of the existing gait recognition method based on wavelet transformation, and has higher recognition rate as well as higher robustness of vision angle change.

The invention discloses a no-reference image blur degree evaluation method based on multiresolution DCT edge gradient statistics. The method includes the following steps: 1), dividing a target image into more than one 8x8 blocks and performing DCT conversion; 2), sequentially combining subblocks, identical in position, in each 8x8 DCT matrix to acquire a DCT conversion diagram containing three levels of resolution; 3), performing square summation on coefficient values of identical positions in three corresponding DCT coefficient matrixes to acquire an energy diagram identical in size; 4), performing local maximum value extraction on the energy diagram acquired on each level of resolution to acquire three edge diagrams identical in size; 5), performing gradient calculation on each edge diagram to acquire an edge gradient diagram, and performing variance statistics to acquire standard deviation S1, S2 and S3 of the edge gradient diagrams; 6), calculating to acquire a blue degree value B equal to 1/(S1*a/(S3+e)+S2*b/(S3+e). By the method, accuracy and stability in objective evaluation of no-reference blur degree can be improved.

The invention discloses a self-adaption image scaling method for the visual-saliency detection based on DCT-domain. The method comprises the following steps: decoding part of a JPEG image to a DCT domain and obtaining a visual-saliency detecting diagram; performing threshold segmentation on the visual-saliency detecting diagram so as to obtain a spacial energy distributing diagram; extracting a visual salient region from the energy distributing diagram so as to obtain the size and the location of a protective frame and an energy distributing diagram containing the protective frame; calculating the number of clipping lines required to be deleted according to the size of the protective frame, and performing line clipping based on DCT blocks according to the number of the clipping lines required o be deleted and the protected energy diagram, finally, performing fine adjustment according to the resolution ratio of a user terminal, so as to obtain the output of an image satisfying the size requirement of the user terminal. Through the implementation of the method disclosed by the invention, visual salience content can be detected and protected, so that the quality of the image scaling technique is improved.

The invention discloses a hand swing motion direction judging method based on direction motion historigram and competition mechanism. The method comprises the following steps of: A1. obtaining the current motion image from video stream, establishing a skin color probability model, and obtaining four light stream directional diagrams; A3. respectively calculating four direction motion historigrams according to the four light stream directional diagrams in step A2; A4. obtaining four direction motion energy diagrams according to a gesture motion historigram; A5. calculating and encoding the motion direction of each frame of image; A6. judging the motion direction of the whole motion sequence; and an interested region is extracted by frame difference and skin color cooperatively to reduce the interference of background and the skin color of a human face. The integral motion direction is calculated by the four motion historigrams and the energy diagrams in a statistic mode to effectively overcome the motion coverage problem. The motion direction is determined by the action competition mechanism to greatly reduce the noise effect and improve the judging accuracy and stability of the motion direction.

The invention discloses a multi-perspective gait classification method based on multiple regression. The method comprises the steps that 1 a human body contour is extracted from a gait data set to be classified; two human body area images of inner point representation and boundary representation are constructed, and a hub energy diagram is further generated; 2 a multi-period hybrid gait energy matrix corresponding to each gait image sequence is calculated as a gait feature based on the hub energy diagram of the previous step; and 3 multi-perspective gait classification is converted into multiple regression, and a convolution neural network is constructed for solving. According to the invention, the multi-perspective gait classification method based on multiple regression uses the multi-period hybrid gait energy matrix as the gait feature; accurate gait period segmentation is eliminated; the reliance on gait period segmentation is reduced; multi-perspective gait classification is converted into multiple regression; the convolution neural network is constructed for solving; and the gait classification accuracy is improved.

The invention provides a multi-source remote sensing image feature matching method based on directional phase consistency, and the method achieves the high-precision matching of multi-source remote sensing images based on the directional phase consistency, and comprises the steps: carrying out the image ortho-rectification of a reference image and a target image; Carrying out partitioning and feature point extraction on the reference image; Respectively calculating direction phase consistency energy diagrams of the reference image and the target image in multiple directions to obtain a direction phase consistency vector of each pixel point; Constructing feature description vectors of the feature points based on dense combination of the direction phase consistency vectors; Image matching iscarried out, gross error elimination is carried out, and wrong matching points are removed. The invention provides an effective multi-source remote sensing image matching method, reliable and high-precision homonymous points can be obtained among images of multiple sources, and practice shows that the method is feasible and effective, and the matching process is high in efficiency and reliable inprecision.

The present invention relates to a free viewpoint image quality evaluation method based on ray space. The invention uses the edge pixel direction consistency parameter of lines which have same direction in ray space for elevating the ray space quality obtained by three different interpolation methods. Firstly the high-frequency energy diagrams of all pixel direction angles in the ray space are obtained from three interpolation methods. Simultaneously the edge graph of ray space, which has low noise and same direction, is obtained. Then the average high frequency energy value of pixel direction angle in the edge graph is calculated, and the value is used as an important criterion which is used for evaluating the consistency of ray space edge pixel direction obtained through interpolation. Finally whether the evaluated high-quality ray space can generate high-quality viewpoint picture is checked. The test shows that when the ray space obtained through fixed-direction interpolation, ray space obtained through bilinear interpolation and ray space obtained through most adjacent interpolation are executed with quality evaluation, the obtained parameter variation is more uniform and is more adjacent with the variation characteristic of PSNR evaluation result compared with the prior art.

A method for testing acoustic emission signal transmission characteristics of a helicopter component based on a harmonic wavelet packet belongs to the technical field of acoustic emission detection for mechanical helicopter components, and solves the problems of energy leakage and inflexibility of frequency band selection when the acoustic emission signal transmission characteristics are analyzed by a traditional wavelet packet. The method includes: acquiring testing signals obtained by an acoustic emission sensor; determining a decomposition layer number j and a frequency bandwidth B and computing an upper limiting frequency m and a lower limiting frequency n; computing frequency domain and frequency band values of harmonic wavelets; transforming the testing signals by means of FFT (fast Fourier transform) algorithm to obtain frequency domain discrete values; computing wavelet transform of the frequency domain and frequency band values; computing time-domain signals xl (r); obtaining energy E1 by means of transforming; and normalizing the energy E1 to obtain average energy and an energy diagram of the testing signals of the helicopter component to be tested, thereby obtaining the acoustic emission signal transmission characteristics of the helicopter component to be tested. The method is applicable to testing of the acoustic emission signal transmission characteristics of the helicopter component.

The invention discloses a three-dimensional video repositioning method. The three-dimensional video repositioning method comprises the step of firstly extracting an image saliency map, a gradient energy diagram and a motion saliency map of each frame of a color image in a color video sequence respectively, mixing with depth information of a scene to obtain a visual attention map of each frame of the color image in the color video sequence, and calculating an intra-frame consistency energy diagram and an inter-frame consistency energy diagram of each frame of the color image in the color video sequence; finding out all the vertical gaps of each frame of the color image in the color video sequence by adopting a dynamic planning method; and then removing pixels falling in all the vertical gaps of each frame of the color image in the color video sequence and pixels falling in the same vertical gaps of each frame of a depth image in a depth video sequence to obtain a repositioned color video sequence and a repositioned depth video sequence. The three-dimensional video repositioning method has the advantages that the image deformation of the obtained repositioned three-dimensional video can be reduced, time domain jitter of the obtained repositioned three-dimensional video can be avoided, outstanding content of the obtained repositioned three-dimensional video can be highlighted, and accordingly relatively high visual comfort is kept.