Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

3185results about How to "Quick calculation" patented technology

Methods and apparatuses for interactive similarity searching, retrieval and browsing of video

Methods for interactive selecting video queries consisting of training images from a video for a video similarity search and for displaying the results of the similarity search are disclosed. The user selects a time interval in the video as a query definition of training images for training an image class statistical model. Time intervals can be as short as one frame or consist of disjoint segments or shots. A statistical model of the image class defined by the training images is calculated on-the-fly from feature vectors extracted from transforms of the training images. For each frame in the video, a feature vector is extracted from the transform of the frame, and a similarity measure is calculated using the feature vector and the image class statistical model. The similarity measure is derived from the likelihood of a Gaussian model producing the frame. The similarity is then presented graphically, which allows the time structure of the video to be visualized and browsed. Similarity can be rapidly calculated for other video files as well, which enables content-based retrieval by example. A content-aware video browser featuring interactive similarity measurement is presented. A method for selecting training segments involves mouse click-and-drag operations over a time bar representing the duration of the video; similarity results are displayed as shades in the time bar. Another method involves selecting periodic frames of the video as endpoints for the training segment.
Owner:FUJIFILM BUSINESS INNOVATION CORP +1

Method for quickly and accurately detecting and tracking human face based on video sequence

The invention discloses a method for quickly and accurately detecting and tracking a human face based on a video sequence, which relates to the technical field of mode identification. The method comprises the following steps of: 1, extracting a video frame image from a video stream; 2, preprocessing the video frame image, namely compensating light rays, extracting skin color areas, performing morphological processing and combining the areas; 3, detecting the human face, namely representing the human face by using Harr-like characteristics and detecting the human face by using a cascaded Adaboost algorithm with an assistant decision function; 4, establishing the characteristics of the human face, namely detecting the area characteristics of the detected human face and the shape characteristics of the edge profile of the human face; 5, tracking the human face, particularly tracking the human face by using a human face area characteristic model when an intersection does not occur in a human face area, and further matching when the intersection occurs according to the shape characteristics of the edge profile of the human face; and 6, extracting the sequence of a human face image. By the technical method, the human face can be detected and tracked quickly and accurately on the basis of the video sequence.
Owner:云南清眸科技有限公司

Image classification method capable of effectively preventing convolutional neural network from being overfit

The invention relates to an image classification method capable of effectively preventing a convolutional neural network from being overfit. The image classification method comprises the following steps: obtaining an image training set and an image test set; training a convolutional neural network model; and carrying out image classification to the image test set by adopting the trained convolutional neural network model. The step of training the convolutional neural network model comprises the following steps: carrying out pretreatment and sample amplification to image data in the image training set to form a training sample; carrying out forward propagation to the training sample to extract image features; calculating the classification probability of each sample in a Softmax classifier; according to the probability yi, calculating to obtain a training error; successively carrying out forward counterpropagation from the last layer of the convolutional neural network by the training error; and meanwhile, revising a network weight matrix W by SGD (Stochastic Gradient Descent). Compared with the prior art, the invention has the advantages of being high in classification precision, high in rate of convergence and high in calculation efficiency.
Owner:DEEPBLUE TECH (SHANGHAI) CO LTD

Optimal power flow optimization method of distributed power supplies

The invention relates to an optimal power flow optimization method of distributed power supplies. The optimal power flow optimization method of the distributed power supplies includes the following steps: A, variable in a distribution network is initialized; B, load flow calculation is carried out on the distribution network; C, lines are judged to be overloaded or not, and active output force and reactive output force of an engine and the distributed power supplies are judged to overstep the boundary or not; D, if constraint equations are all met, a step E is continued, otherwise a step F is continued; E, an objective function is judged to be the minimum or not, if the objective function is the minimum, a step J is continued, otherwise a step F is continued; F, net loss correlation coefficients are corrected; G, a Jacobean matrix and a Hessian matrix are calculated; H, a problem of sequential quadratic programming is formed and the search direction and a step size are solved; I, output force at the position of a balancing node bus and output force of each distributed power supply are corrected, and the step B is jumped to; and J, an optimal power flow result is output. The optimal power flow optimization method of the distributed power supplies provides basis of access capacity calculation for determining the distributed power supplies to be connected in a power distribution network, is simple in calculation and low in complexity, and can rapidly calculate the output force of the distributed power supplies.
Owner:CHINA ELECTRIC POWER RES INST +1

Pointer instrument reading identification method

The invention discloses a pointer instrument reading identification method. The method comprises the steps of extracting a dial plate, removing interference, and correcting the dial plate by using affine transformation; performing circle detection and straight line detection on the dial plate to obtain predicted circle center and pointer angle; based on features of a scale connected domain on thedial plate, screening out the scale connected domain, performing linear fitting on the scale connected domain, calculating an intersection point of every two fitting straight lines, and performing screening verification on a to-be-selected circle center by utilizing the predicted circle center and pointer angle to obtain the circle center of the dial plate, wherein a distance from the centroid ofthe scale connected domain to the circle center on the dial plate is the radius of the dial plate; and according to information such as the circle center of the dial plate, the radius of the dial plate, the straight lines of a pointer, extracting an arc scale bar of the dial plate, expanding the arc scale bar in a rectangular shape, then according to horizontal coordinate distribution of scale onthe rectangular scale bar, performing minimum and maximum scale detection, noisy point removal and scale insertion, and finally in combination with the pointer angle, calculating reading of the dial plate. The method is high in universality and high in timeliness; and the reading has relatively high accuracy.
Owner:HUAZHONG UNIV OF SCI & TECH

Simulation system and simulation method for three-dimensional comprehensive situations of space mission

The invention discloses a simulation system and a simulation method for three-dimensional comprehensive situations of a space mission. The simulation system comprises a space satellite trail and posture modeling module, a satellite frame modeling module, a coverage area analysis and modeling module, a data tracking and receiving modeling module, a time management module, a coordinate system management module and a three-dimensional visualizing simulation module, wherein the time management module is used for providing simulation time and various time standards of astronomical time for simulation of the space mission; the coordinate system management module is used for providing various coordinate systems such as a celestial coordinate system, an earth fixed connection coordinate system, a moving coordinate system and the like to describe moving rules of moving objects; and the three-dimensional visualizing simulation module is used for three-dimensional visual display, playback and deduction for situation analysis and modeling results, capable of controlling acceleration, deceleration, pause and start of a simulation process according to the simulation mission or a demonstration script, and capable of providing a powerful guarantee for display of the space comprehensive situations and analysis and demonstration of a focused simulation stage.
Owner:THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP

Electromyographic signal gait recognition method for optimizing support vector machine based on genetic algorithm

InactiveCN104537382AWith global search capabilityQuick calculationCharacter and pattern recognitionHuman bodyTime domain
The invention relates to an electromyographic signal gait recognition method for optimizing a support vector machine based on a genetic algorithm. According to the electromyographic signal gait recognition method, the penalty parameter and the kernel function parameter of the support vector machine are optimized with the genetic algorithm, the performance of the support vector machine is accordingly optimized, and the efficiency and the accuracy of the support vector machine for recognizing lower limb movement gaits based on electromyographic signals are improved. The electromyographic signal gait recognition method includes the steps of firstly, carrying out de-noising processing on the collected lower limb electromyographic signals with a wavelet modulus maximum de-noising method; secondly, extracting the time domain characteristics of the de-noised electromyographic signals to form characteristic samples; thirdly, optimizing parameters of the support vector machine with the genetic algorithm to obtain a set of optimal parameters with the minimum errors, and constructing a classifier through the parameters; finally, inputting a characteristic sample set into the optimized classifier for gait recognition. The electromyographic signal gait recognition method is easy to operate, rapid in calculation and high in recognition rate, and has the application value and the broad prospects in the human body lower limb gait recognition field.
Owner:HANGZHOU DIANZI UNIV

Online evaluation method of electric power system dynamic stability

The invention discloses an online evaluation method of electric power system dynamic stability. The online evaluation method comprises the steps of step 1, carrying out high-frequency sampling by utilizing a PMU (Power Management Unit), and extracting an oscillation mode for sampling data by utilizing a matrix pencil identification method; step 2, detecting low-frequency oscillation, and emitting low-frequency oscillation warning if a damping ratio of the detected oscillation mode is lower than a set threshold value; step 3, carrying out small perturbation calculation on a system model in a current running mode through a frequency domain analysis method, and obtaining a characteristic value, a characteristic vector, a corresponding unit and participated factor information; and step 4, screening out information of a low-frequency oscillation mode from a small perturbation calculation result according to the low-frequency oscillation mode which is determined by the matrix pencil identification method, regulating a related electric power generator to output, and obtaining tide stability limit of call lines between related domains through time-domain simulation at the same time. According to the online evaluation method disclosed by the invention, the influence of noise is effectively avoided, the identification accuracy is improved, the calculating speed and the calculating efficiency are increased, and the online dynamic safety evaluation effect of the electric power system is obviously improved.
Owner:SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products