62 results about "Bhattacharyya distance" patented technology

Tracking and surveillance methods and systems for monitoring objects passing in front of non-overlapping cameras. Invention finds corresponding tracks from different cameras and works out which object passing in front of the camera(s) made the tracks, in order to track the object from camera to camera. The invention uses an algorithm to learn inter-camera spatial temporal probability using Parzen windows, learns inter-camera appearance probabilities using distribution of Bhattacharyya distances between appearance models, establishes correspondences based on Maximum A Posteriori (MAP) framework combining both spatial temporal and appearance probabilities, and updates learned probabilities throughout the lifetime of the system.

The invention discloses a non-reference image quality evaluation method based on a high-quality natural image statistical magnitude model. The method includes the steps that firstly, parameters corresponding to a multi-element Gaussian model are learnt from first image blocks of a high-quality natural image; a test image is divided into second image blocks which are the same in size, and a multi-element Gaussian model of each second image block is extracted; the distances between the multi-element Gaussian models are determined through a bhattacharyya distance, and then the quality of distorted image quality blocks is determined; the quality of all the distorted image blocks are linearly weighted through visual saliency, finally the objective evaluation grade of the test image is acquired, the problem that an existing evaluation method is low in generalization ability can be well solved, and the requirements of actual application for the non-reference image quality evaluation method are met.

The invention discloses an automatic fast segmenting method of a tumor pathological image. The method comprises the following steps: firstly filtering a tumor original pathological image through the adoption of a Gaussian pyramid algorithm to respectively obtain pathological images with equal resolution, double resolution, fourfold resolution, eightfold resolution and 16-fold resolution; determining an initial region of interest containing the tumor on the equal resolution image through a RGB color model and morphological close operation; iteratively optimizing the initial regions of interest from the equal resolution to the fourfold resolution through the adoption of bhattacharyya distance; judging that the contribution of the RGB color model to the tumor region of interest has been reduced to zero when the bhattacharyya distance achieves a set threshold value; performing the self-adaptive high resolution selection of the deep precise segmentation through the adoption of a convergence exponent filtering algorithm, thereby further segmenting under the most suitable high resolution; and finally segmenting out a normal tissue and a tumor tissue in the tumor region of interest through the adoption of a bag of words model based on random projection. The method disclosed by the invention has the features of being accurate, fast and automatic.

The invention discloses a target tracking method based on multi-feature self-adaption fusion and on-line study. Target features are extracted and used as template features; three types of features are extracted from each of novel candidate target regions; a self-adaption fusion process is carried out according to distinctiveness and correlation of all the features; Bhattacharyya distances between the features obtained after fusion and the template features are calculated; the Bhattacharyya distances are subjected to uniformization and then used as weights of the novel candidate target regions; the novel candidate target region with the maximum weight, and a target region are subjected to an overlap judgment, if the overlap rate is less than an overlap rate threshold value, a multiple-time region of the novel candidate target region with the maximum weight is input to a detector, and when a recognizer outputs 'yes', the fact that target tracking succeeds is shown, and the recognizer, the template features and the target region are updated; if the recognizer outputs 'no', the fact that a novel target is found is shown; and if the overlap rate is greater than or equal to the overlap rate threshold value, the recognizer, the template features and the target region are updated. Through the target tracking method based on the multi-feature self-adaption fusion and the on-line study, the adaption ability of the target tracking under different scenarios and certain deformation conditions is enhanced, and the problem that tracking drifting is prone to occurrence after occlusion is avoided.

The invention discloses a video semantic scene segmentation method based on a convolutional neural network, which is mainly divided into two parts, wherein one part is that a convolutional neural network is built on the basis of shot segmentation, and then semantic feature vectors of video key frames are obtained by using the built convolutional neural network; and the other part is that the Bhattacharyya distance between the semantic feature vectors of two shot key frames is calculated by using the time continuity of the front and back key frames according to the semantic feature vectors, andthe semantic similarity of the shot key frames is obtained through measuring the Bhattacharyya distance. Probability estimation values of different semantics are outputted by using the convolutionalneural network to act as a semantic feature vector of the frame. Considering a time sequence problem of scene partition in the continuous time, the shot similarity is compared by combining semantic features of the two shot key frames and the time sequence feature distance between the shots, and thus a final scene segmentation result is obtained. The method disclosed by the invention has certain universality and has a good scene segmentation effect under the condition that training sets are sufficient.

A speech recognition device and a speech recognition method thereof are disclosed. In the speech recognition method, a key phrase containing at least one key word is received. The speech recognition method comprises steps: receiving a sound source signal of a key word and generating a plurality of audio signals; transforming the audio signals into a plurality of frequency signals; receiving the frequency signals to obtain a space-frequency spectrum and an angular estimation value thereof; receiving the space-frequency spectrum to define and output at least one spatial eigenparameter and, and using the angular estimation value and the frequency signals to perform spotting and evaluation and outputting a Bhattacharyya distance; and receiving the spatial eigenparameter and the Bhattacharyya distance and using corresponding thresholds to determine correctness of the key phrase. Thereby this invention robustly achieves high speech recognition rate under very low SNR conditions.

The invention relates to a laser radar echo signal de-noising method based on variational mode decomposition. The method comprises the steps of according to a laser radar equation, simulating a laserradar echo signal; selecting an optimal decomposition layer number K in variational mode composition by means of detrended fluctuation analysis; performing variational mode decomposition on the laserradar echo signal; then calculating similarity between the laser radar echo signal and each mode probability density function after decomposition through Bhattacharyya distance, differentiating a correlation mode and an uncorrelated mode; then processing the uncorrelated mode by means of a moving average mode, and extracting a related signal; and finally reconstructing the correlation mode and theprocessed uncorrelated mode for realizing de-noising of the laser radar echo signal. The laser radar echo signal de-noising method can effectively filter the noise in the laser radar echo signal andimproves effective detecting distance and precision of the laser radar.

The invention provides a pedestrian identification method based on image with FHOG-LBPH feature. By statistical average of fusion HOG features (FHOG) , the optimal features are selected according to the combination with single optimal feature and the separable criterion of bhattacharyya distance, and improved FHOG-LBPH feature are obtained through fusion LBPH characteristics, fundamentally reducing the feature dimension; A classifier is obtained by using a support vector machine (SVM) to train the sample characteristics in order to obtain the classification of the test sample. The experimental results show that the method makes the pedestrian detection accuracy and real-time performance a certain improvement. Effectiveness of the method is validated by the image automatically shot, and the method has certain application value in the real pedestrian recognition.

The invention relates to a method for extracting a high-resolution SAR image building zone through multi-feature weighted fusion. The method is mainly characterized in that the strategy that feature weights are determined through a distance formula is novel. The method includes the following steps that 1, intensity images are subjected to filtering and other preprocessing; 2, features are extracted based on a gray level co-occurrence matrix texture analysis method and a variation function texture analysis method; 3, the feature weights are determined based on the Bhattacharyya distance; 4, the features obtained in the step 2 are subjected to weighted fusion; 5, the fused feature images are subjected to unsupervised classification through a k-means clustering algorithm; 6, a classification result is post-processed, small zones are removed, gaps are filled, an external contour is extracted, and the building zone is obtained. The texture features facilitating building zone extraction are fully synthesized, an established fusion feature map contains texture information richer than that of a single-feature map, the classification accuracy of the building zone and a non-building zone is improved to a certain degree accordingly, the extraction accuracy of the building zone is improved, and finally the boundary contour of the extracted building zone better fits a real building zone contour.

The present invention discloses a diagnostic quantification method with the consideration of a incomplete failure of a spacecraft control system. A diagnostic quantification problem is transformed into a multivariate distribution similarity judgment problem in mathematical statistics, and an equivalent space model of the incomplete failure is obtained. Then concrete judgment criteria of the detectability and isolability of the incomplete failure are given. Finally, according to the judgment criteria, a diagnostic quantification index of the incomplete failure is proposed by using a Bhattacharyya distance, and an analysis result is obtained based on the diagnostic quantification index. The influence of system uncertainty in spacecraft control system on-orbit actual work is considered, according to the obtained result, a designer can conveniently understand weak links of the system, the guide of the design of a diagnosis algorithm and system configuration is facilitated, thus the fault diagnosis ability of the spacecraft control system can be improved to the maximum at a ground design stage, and finally a target of improving the system overall comprehensive design ability is achieved.

The embodiment of the invention provides an image quality evaluation method and system. The method comprises the steps of: obtaining gray contrast of an image to be measured according to a Bhattacharyya distance between a grey level histogram of an area of interest and a grey level histogram of a peripheral area; obtaining first texture features according to average texture features of the area ofinterest after filtering and polarity texture features of the area of interest after filtering; obtaining second texture features according to average texture features of the peripheral area after filtering and polarity texture features of the peripheral area after filtering; obtaining texture contrast of the image to be measured according to a Bhattacharyya distance between the first texture features and the second texture features; and obtaining the probability of detecting a target in the image to be detected according to the gray contrast and the texture contrast. Starting from the gray features and the texture features of the image, the image quality evaluation method and system comprehensively consider the detection conditions of tiny target features and employ gray and texture features to enhance the robustness and the applicability of the image evaluation method.

The invention provides a UI test method for a control. The method comprises: intercepting a target picture and a source picture, and calculating a color histogram of the target picture and the source picture to obtain a Bhattacharyya distance; when the Bhattacharyya distance is greater than a predetermined threshold, obtaining positions and first pixel values of a plurality of mutation pixel points on the target picture and second pixel values of pixel points, in the positions, on the source picture, wherein the mutation pixel points are pixel points on a UI profile; and outputting a test result according to a variance or a standard deviation of difference values of the first pixel values and the second pixel values. The invention furthermore provides a UI test system for the control. According to the UI test method and system for the control, a UI of the control can be automatically verified to test the display effect of the UI.

The invention discloses a method for building a multi-classification support vector machine classifier based on the Bhattacharyya distance and a directed acyclic graph, belonging to the field of mode identification. The method aims to solve the problems that the training speed is lowered when the number of training samples or the number of classes is increased and the calculation amount is large because the traditional multi-classification strategy can not utilize prior information with different separabilities among classes because of the fixed structure. The method disclosed by the invention comprises the following steps: 1. respectively calculating the Bhattacharyya distance between every two classes in a training sample for a multi-classification object; 2. building an initial operation form according to the Bhattacharyya distance between the every two classes in the training sample, which is obtained in the step 1; 3. according to the initial operation form obtained in the step 2, building a multiple classifier based on the directed acyclic graph structure; and 4. adopting a support vector machine as a binary classifier, and carrying out multi-classification based on the directed acyclic graph structure.

The invention provides an automatic retrieval method of a key frame in an IVUS (Intravascular Ultrasound) video. According to the method, firstly, each frame of image is subjected to SRAD (Speckle Reducing Anisotropic Diffusion) filtering; then, on the basis of performing grayscale stretch on the filtered images, a grey level histogram of each frame of image is calculated to obtain a 256-dimension normalized grayscale feature vector; then, the Bhattacharyya distance between the adjacent frame of scale feature vectors is calculated to be used as the measure on the similarity of adjacent frames of images; and finally, the Bhattacharyya distance between the adjacent frame grayscale feature vectors is compared with a set threshold value, and the extraction of the key frame is completed. The automatic retrieval method has the advantages that the fast extraction of the key frame in the IVUS video is realized through analyzing the grayscale features of the IVUS images; a tester can be helped to fast locate the variation or foreign object implanted position; and reliable information is provided for the processing and the evaluation of vascular mutation.

The invention belongs to the technical field of radar technology and discloses a multi-station radar signal fusion detection method based on Bhattacharyya distance quantization, and the communication bandwidth between radars and a signal fusion center in multi-station radar signal fusion detection can be reduced. The method comprises a step of setting a multi-station radar system which comprises a signal fusion detection center and N radar stations, a step of determining the quantization bit b of each radar station to a received echo signal and obtaining a quantization interval number M=2b according to the quantization bit b, a step of carrying out quantization of the received echo signal by each radar station, determining the quantization interval to which a quantized signal belongs, and transmitting a label number corresponding to the quantization interval to the signal fusion detection center, and a step of setting an expected false alarm probability, wherein the signal fusion detection center detects a target according to the expected false alarm probability and the label number corresponding to each quantization interval sent by N radar stations.

The invention discloses a target tracking method for judging occlusion and repositioning a target, and belongs to the field of target detection and tracking. The method comprises the following steps:for any target tracking process, roughly judging whether occlusion occurs or not by utilizing the change of a confidence coefficient function; calculating the Bhattacharyya distance between the targetLocal Binary Pattern feature and the Local Binary Pattern feature of the pre-selected box for the area which is preliminarily judged to be shielded, and further confirming whether the target Local Binary Pattern feature is shielded or not; for the condition of local occlusion, adopting a multi-peak repositioning method to perform positioning after target occlusion; and for severe shielding or long-time shielding, adopting an SVM (Support Vector Machine) detection repositioning method to carry out accurate positioning. According to the method, the target shielding condition can be accurately judged, and the problem of target repositioning after shielding is effectively solved.

The invention relates to a human body motion data similarity automatic evaluation method. First of all, by use of human body skeleton structure based motion data acquired by a motion capture device, distances between attitude are defined based on a data format, then statistical information of motion is established by aggregating various time-space attitude, finally, a distance between two motions is calculated based on a Bhattacharyya distance, segmented motion comparison is performed, and motion similarity is evaluated through the distance. The method concretely comprises the following steps: 1, performing human body motion acquisition by use of a Vicon motion capture suite; 2, decomposing motion into sub-motion of a time sequence; 3, performing similarity comparison on the sub-motion; and 4, obtaining the similarity between motion A and motion B by calculating Cos t<*>(h0,h0). The method has the following advantages: by taking attitude data of motion capture as input, the statistical information of the motion is established by aggregating the various time-space attitude such that the motion evaluation accuracy is improved and the real-time performance is improved.

The invention discloses a transient electromagnetic signal noise separation and recognition method based on improved variational mode decomposition, which comprises the steps of: carrying out the global search and optimization of a mode number K and a penalty factor alpha in a variational mode decomposition algorithm through employing a whale optimization (WOA) algorithm to obtain an optimal parameter combination; carrying out variational mode decomposition (VMD) on a transient electromagnetic signal by utilizing the obtained optimal parameter combination to realize signal-to-noise separation;and identifying a noise mode in a mode component through an improved Bhattacharyya distance algorithm to realize noise elimination. According to the optimization method, parameter setting is simple,required operators are few, and the workload of a traditional optimization method is greatly reduced; transient electromagnetic signals can be decomposed into a series of modal components with frequencies from low to high more accurately according to optimized parameters, and the modal aliasing problem caused by traditional artificial subjective parameter selection is greatly reduced; and the calculation is simple and convenient, the identification is convenient, and subsequent signal reconstruction is facilitated.

The invention provides a texture distribution weak hypothesis and regularization strategy-based natural image matting method. An improvement is made aiming at the defects of the Bayesian matting algorithm. Firstly, aiming at the problem that an original method is too strong in hypothesis, the hypothesis is weakened; and a calculation measure and a correction coefficient for carrying out correction on a Gaussian distribution variance are defined and designed on the basis of a histogram and the bhattacharyya distance, so that an adaptive variance Gaussian distribution model of considering texture complexity is provided; and complicated texture distribution of natural images is effectively coped with. Secondly, aiming at a calculation model of the original method, a regularization strategy-based matting algorithm model is provided on the basis that an ideal corrective color estimation optimization model and a solving problem thereof are provided, namely a data constraint term and a penalty term are added to a basic model through an augmented lagrangian multiplier method; and a solving model, in a regular form, of an ideal optimization model is obtained.

The present invention relates to the technical field of power operation and maintenance alarm and more particularly relates to a power operation and maintenance alarm data fusion method based on the evidence theory. The method comprises the steps of (S1) obtaining basic probability allocation BPA according to an evidence confidence level, and (S2) fusing data to obtain a fusion result according toan improved fusion rule. Through introducing the evidence confidence level and using a Bhattacharyya distance, the BPA is adjusted, at the same time, a D-S combination rule is improved, and a new fusion rule is proposed to fuse the data. According to the method, a problem of evidence conflict in the D-S evidence theory is solved well, information contained in conflict evidence is not ignored, theaccuracy of the fusion result is improved, and a fault diagnosis speed and fault handling efficiency of a power communication network are improved.

The invention relates to a Bhattacharyya-distance-algorithm-based excitation inrush current and fault differential current identification method of a transformer. The method comprises: collecting secondary currents of current transformers arranged at two sides under differential protection of a transformer according to N points of each cycle and forming a differential current signal sequence I; determining whether the value of the differential current signal sequence I exceeds a setting value of a differential protection starting component; if so, starting a provided criterion to carry out fault differential current and excitation inrush current determination; processing the differential current signal sequence by using a 1 / 2 cycle data window and predicting a corresponding sinusoidal wave, converting the differential current and a predicted sinusoidal sequence into a probability distribution function of sampled values similar to the image grayscale in the data window, and then carrying out matching calculation based on a Bhattacharyya distance; comparing a calculated Bhattacharyya coefficient Bc with a set threshold value Bcset and taking a protection action under the condition ofbeing higher than the threshold by the Bhattacharyya coefficient; and otherwise, locking protection. With the method, the in-zone fault, inrush current, the in-zone and out-zone fault CT saturation and the like can be determined accurately; and thus the reliability of the differential protection is ensured.

The invention discloses a manual initial box correction method and system based on background distinguishing. The method comprises the following steps: preprocessing a received target image; judging whether the target image is larger than 100 pixels or not, and if so, receiving an instruction for manually framing the rectangular frame as an initial rectangular frame; receiving and executing an instruction of enlarging the initial rectangular frame by 1.5 times, and obtaining an extraction area of a candidate initial frame; calculating a Bhattacharyya coefficient BC1 of the foreground histogramand the background histogram of the candidate initial rectangular frame; calculating the Bhattacharyya distance between the initial rectangular frame foreground histogram and the background histogramaccording to the Bhattacharyya coefficient; correcting the manual initial rectangular frame according to the Bhattacharyya distance; and if not, receiving and executing a morphological processing instruction, and obtaining a corrected initial rectangular frame. The accuracy of the initial area can be improved, the deviation between the rectangular frame and the real target rectangular frame during initialization of the tracking algorithm is reduced, the algorithm accuracy is improved, and the target tracking accuracy is further improved.

The invention relates to the technical field of target tracking, in particular to a moving target automatic tracking method and system under the condition that a target and a background are similar incolor, and overcomes the defect when a CAMshift algorithm is directly adopted for target tracking. The method comprises the following steps: S1, processing a video stream to obtain a denoised sequence frame image; S2, processing the sequence frame image to obtain a foreground target in the first frame image; removing shadows in the foreground target to obtain a moving target area of the first frame image; s3, reading a next frame of image, taking the next frame of image as a current frame of image, obtaining and processing color-curvature probability distribution maps of moving target areas of the current frame of image and a previous frame of image, and obtaining a candidate area of the current frame of image; s4, if the Bhattacharyya distance between the candidate region of the currentframe of image and the moving target region of the previous frame of image is greater than a distance threshold, taking the candidate region as the moving target region of the current frame of image;and repeating the step S3 and the step S4 to realize tracking of the moving target.

The invention discloses a rotor winding image detection method fusing region distribution characteristics and edge scale angle information. The method comprises the steps that 1, graying, filtering and threshold preprocessing operation are performed on a to-be-detected image respectively to complete winding region image preprocessing, and the to-be-detected image becomes a binary image; 2, the similarity between spatial distribution characteristics of a winding region contour between the to-be-detected image and a template is calculated to perform template retrieval; 3, through calculation ofrelative angle information of vectors formed by a sampling point on a contour edge of the to-be-detected image and a centroid of the region contour and gradient vectors at the point as well as scale information of the vectors, description of the contour form is realized; and 4, the similarity between angle and scale distribution information of the to-be-detected image and the template is calculated through a Bhattacharyya distance, and then detection of the to-be-detected image is realized. Therefore, the influence of template selection contingency on detection precision is effectively avoided, detection time is shortened, and detection accuracy is improved.

The invention discloses a method for judging occlusion in a target tracking process. The method comprises the following steps that step 1, reading a tracking target image sequence, extracting a firstframe of image in the image sequence, selecting a to-be-tracked target frame on the first frame of image, extracting an LBP feature vector LBP1 of the target frame wherein the first frame of image isa selected tracking target image in a completely unshielded state; step 2, reading a next frame of image, and performing coarse shielding judgment on the frame of image; step 3, if the step 2 is judged to be shielding, performing accurate shielding judgment t by utilizing a Bhattacharyya distance; step 4, judging whether the image sequence is the last frame of the tracking target image sequence ornot, and if so, ending; and if not, returning to the step 2. According to the invention, a more robust occlusion coarse judgment method is designed, the concept of the Bhattacharyya distance is combined, the interference of target deformation on occlusion judgment is eliminated, and whether the target is occluded or not can be judged more accurately.

The invention discloses a thermal infrared image super-resolution reconstruction evaluation method, which is used for evaluating the performance of a super-resolution reconstruction algorithm at a thermal infrared image application level, and comprises the following steps of: performing temperature inversion on a thermal infrared image at a first stage, and converting the thermal infrared image into a temperature image representing temperature; and utilizing the obtained temperature image for comparing the similarity between the temperature image of the thermal infrared image after super division and a temperature image of a real high-resolution thermal infrared image by calculating the Bhattacharyya distance of the temperature image at a second stage, and therefore evaluation can be givenon the application level of thermal infrared image temperature inversion. According to the thermal infrared image super-resolution reconstruction evaluation method, evaluation indexes of the thermalinfrared image super-resolution reconstruction algorithm are provided at the application level by utilizing the application characteristics of the thermal infrared image, so that the super-resolutionreconstruction algorithm evaluation and application are combined, the method has more practical significance, the method is not limited by the size of the image, and calculation can further be carriedout due to different sizes of temperature maps.

The present invention discloses a SAR image road detection method based on ratio features. The problems are mainly solved that road edge positioning is not accurate and a false alarm rate is high in the prior art. The method comprises the steps of: 1) performing speckle reduction of an SAR image and extracting 9 texture features; 2) screening 3 texture features having the greatest contribution onclassification from the 9 texture features according to a Bhattacharyya distance; 3) calculating comparison ratio features R1 and similar ratio features R2 in the image point by point after speckle reduction; 4) constructing a road dictionary D1 and a background dictionary D2 by employing samples with results of the step 2) and the step 3); 5) solving one average difference value E1 of the road dictionary D1 and one average mean value E2 of the background dictionary D2 for each pixel point, performing classification of the pixel points through the difference values, and obtaining a preliminarydetection result; and 6) performing optimization of the preliminary detection result, and obtaining a final detection result. The SAR image road detection method based on ratio features can completely and clearly detect roads in the SAR image, and is suitable for detection of roads with different directions and different widths in the SAR image.

The invention relates to the technical field of weaving, and provides a method for online detection of chromatic aberration of warp knitted cloth, comprising the following steps: setting an encoder, so that the encoder generates a trigger signal as the warp knitted cloth is transmitted; acquiring an image of the warp knitted cloth in real time through a color line scan camera; processing the imageto obtain a standard color image and a histogram cross method standard picture; dividing the image into multiple sub-pictures, and calculating chromatic aberration values between the multiple sub-pictures and the standard color image; dividing the image of the warp knitted cloth into N * N sub-pictures; calculating Bhattacharyya distance values of the chromatic aberration between the N * N sub-pictures and the histogram cross method standard picture, judging whether the chromatic aberration exists, and calculating pass rates of the sub-pictures. The method provided by the invention can realize the online detection of the chromatic aberration, and involves both the overall chromatic aberration pass rate of the cloth and the chromatic aberration fluctuation of the cloth, thereby intuitivelyand accurately reflecting the chromatic aberration of the whole cloth.