692 results about "Energy functional" patented technology

A method for lesion segmentation in 3-dimensional (3D) digital images, includes selecting a 2D region of interest (ROI) from a 3D image, the ROI containing a suspected lesion, extending borders of the ROI to 3D forming a volume of interest (VOI), where voxels on the borders of the VOI are initialized as background voxels and voxels in an interior of the VOI are initialized as foreground voxels, propagating a foreground and background voxel competition where for each voxel in the VOI, having each neighbor voxel in a neighborhood of the voxel attack the voxel, and, if the attack is successful, updating a label and strength of the voxel with that of the successful attacking voxel, and evolving a surface between the foreground and background voxels in 3D until an energy functional associated with the surface converges in value, where the surface segments the suspected lesion from the image.

A method for non-rigid registration of digital 3D coronary artery models with 2D fluoroscopic images during a cardiac intervention includes providing a digitized 3D centerline representation of a coronary artery tree that comprises a set of S segments composed of QS 3D control points, globally aligning the 3D centerline to at least two 2D fluoroscopic images, and non-rigidly registering the 3D centerline to the at least two 2D fluoroscopic images by minimizing an energy functional that includes a summation of square differences between reconstructed centerline points and registered centerline points, a summation of squared 3D registration vectors, a summation of squared derivative 3D registration vectors, and a myocardial branch energy. The non-rigid registration of the 3D centerline is represented as a set of 3D translation vectors rs,q that are applied to corresponding centerline points xs,q in a coordinate system of the 3D centerline.

The invention discloses a segmentation method for an image with deep image information, which is high in segmentation accuracy, and capable of still achieving a good segmentation effect under the condition of a very similar front background. The segmentation method comprises the steps of: (1) obtaining the image with deep image information via Kinect; (2) performing probability modelling on the colour information of the front background and the deep image information; (3) performing parameter estimation on the model by EM (Expectation-Maximization) algorithm; and (4) performing segmentation after the first image segmentation on the image by adopting an image segmentation algorithm, wherein an energy function is formula shown in the abstract, and according to the energy function, the smallest segmentation is evaluated by a maximum flow algorithm, so as to obtain the final segmentation object.

The present invention discloses a novel non-invasive, bedside system and method to monitor parameters associated lung changes. A novel approach for monitoring the operation of the respiratory system of a subject is provided. There is also provided a method for objectively evaluating the benefit of one mode of ventilation over another, and for assessing the differences in regional lung vibration during different modes of mechanical ventilation. The method comprises recording one or more signals from the subject, the signal varying in time according to operation of the respiratory system; and; processing the recorded signals to obtain a predetermined functional thereof presenting one or more time-varying energy functions of the subject, an abnormality in the one or more energy functions being indicative of a suspected abnormality in the operation of the respiratory system. The signals may be acoustic signals recorded by a plurality of acoustic sensors placed over the subject's thorax or back, and the at least one time-varying energy function is obtained from one or more specific regions of lung or by summing / averaging the time-dependent acoustic signals of the plurality of sensors indicative of the whole lungs.

An embodiment of the invention provides a panorama image stitching method and device which can perform good processing on a plurality of images when a camera is in non-pure rotation and displacement exists, and can allow the distortion generation rate of stitched images to be reduced. The method includes the following steps of: designing a homographic matrix according to local areas of various feature points in various images; using the designed homographic matrix to detect the feature points and delete the wrong feature points; performing meshing processing on the images; constructing a global energy function based on mesh vertices and various feature points after the wrong feature points are deleted; solving the optimized mesh vertices; performing coordinate transformation on pixel points of various images based on the optimized mesh vertices; and performing stitching processing on various images by using various transformed pixel points.

A method reconstructs at three-dimensional (3D) real-world scene from a single two-dimensional (2D) image by identifying junctions satisfying geometric constraint of the scene based on intersecting lines, vanishing points, and vanishing lines that are orthogonal to each other. Possible layouts of the scene are generated by sampling the 2D image according to the junctions. Then, an energy function is maximized to select an optimal layout from the possible layouts. The energy function use's a conditional random field (CRF) model to evaluate the possible layouts.

The invention relates to an intra-frame prediction method, comprising the following steps that: a 4x4 pixel luma block to be predicted is chosen to be as a current block; whether the current block is the center block is judged, if yes, energy functions of the residual error between prediction blocks of the current block and the current block in all predicting modes and a candidate predicting mode is determined according to the energy functions in different predicting modes, otherwise, a usable predicting mode is taken as the candidate predicting mode; a rate-distortion cost parameter in the candidate predicting mode is calculated, the candidate predicting mode with the minimal rate-distortion cost parameter is taken as the optimal predicting mode of the current block. The invention determines the candidate predicting mode according to the residual error energy function and determines the optimal predicting mode by calculating the rate-distortion cost parameter of the candidate predicting mode so as to decrease the number of the predicting modes which need to calculate the rate-distortion cost parameter, thereby reducing the amount of computation.

The invention discloses a method and a device for detecting tissue boundaries by use of ultrasonic images. The method comprises a search step and a detection step, wherein the search step is used for searching an ultrasonic image of a detection target for an initial center point of a target region and determining an initial region boundary curve according to the initial center point; the detection step takes the initial center point as a pole, starts searching for the position of a target region boundary along a polar line passing the pole from an initial region boundary, and calculates the energy functional of gray-scale distribution in different positions, wherein a position corresponding to the minimum value of the energy functional of gray-scale distribution is the boundary of the target region. As the invention first detects the center point and then rapidly detects the boundaries along the polar line, the invention is simpler and rapider in detection. Region segmentation functional adopted in the invention can effectively avoid the influence of ultrasonic image noise and effectively detects weak boundaries. In addition, grey scale correction along the polar line can eliminate the influence of non-uniform fields of image gray-scale distribution.

A method for automatically segmenting a liver in digital medical images includes providing a 3-dimensional (3D) digital image I and a set of N training shapes {φi}i=1, . . . , N for a liver trained from a set of manually segmented images, selecting a seed point to initialize the segmentation, representing a level set function φα(θx+h) of a liver boundary Γ in the image asφα(x)=φ0+∑i=1nαiVi(x),whereφ0(x)=1N∑i=1Nφi(x)is a mean shape, {Vi(x)}i=1, . . . , n are eigenmodes where n<N, αi are shape parameters, and h ε R3 and θε [0,2π]3 are translation and rotation parameters that align the training shapes, minimizing a first energy functional to determine the shape, translation, and rotation parameters to determine a shape template for the liver segmentation, defining a second energy functional of the shape template and a registration mapping weighted by image intensity histogram functions inside and outside the boundary, and minimizing the second energy functional to determine the registration mapping, where the registration mapping recovers local deformations of the liver.

The invention discloses an automatic digging method for remarkable objects of color images. The automatic digging method for the remarkable objects of the color images is characterized by comprising the steps of changing a red green blue (RGB) color space of the images into a hue saturation value (HSV) color space and calculating significance of targets in the aspects of hue, saturation and warm color gain; obtaining a rectangular frame surrounding a significance region according to a significance level image and performing rectangular frame expansion, wherein images surrounded by the expanded rectangular frame serve as follow-up processing images; using an improved watershed algorithm to pre-divide input image contents, using pre-divided super pixel subregions to replace weighted graphs formed by dividing pixel point structural graph, and adopting a maximum flow-minimum dividing strategy to perform division till energy functions are converged to obtain divided images. By means of an automatic image digging technology, the remarkable objects in scene can be quickly and effectively dug, and digging efficiency, the quality and the like are improved remarkably.

A method that facilitates identification of features in a scene enables enhanced detail to be displayed. One embodiment incorporates a multi-grid Gibbs-based algorithm to partition sets of endmembers of an image into smaller sets upon which spatial consistency is imposed. At each site within an imaged scene, not necessarily a site entirely within one of the small sets, the parameters of a linear mixture model are estimated based on the small set of endmembers in the partition associated with that site. An, enhanced spectral mixing process (SMP) is then computed. One embodiment employs a simulated annealing method of partitioning hyperspectral imagery, initialized by a supervised classification method to provide spatially smooth class labeling for terrain mapping applications. One estimate of the model is a Gibbs distribution defined over a symmetric spatial neighborhood system that is based on an energy function characterizing spectral disparities in both Euclidean distance and spectral angle.

An image editing application (or a blur classification module thereof) may automatically estimate a coherent defocus blur map from a single input image. The application may represent the blur spectrum as a differentiable function of radius r, and the optimal radius may be estimated by optimizing the likelihood function through a gradient descent algorithm. The application may generate the spectrum function over r through polynomial-based fitting. After fitting, the application may generate look-up tables to store values for the spectrum and for its first and second order derivatives, respectively. The use of these tables in the likelihood optimization process may significantly reduce the computational costs of a given blur estimation exercise. The application may minimize an energy function that includes a data term, a smoothness term, and a smoothness parameter that is adaptive to local image content. The output blur map may be used for image object depth estimation.

The invention discloses a road detection method based on bimodal data fusion. The method comprises the following steps: transferring axes of laser radar three-dimensional points; obtaining a laser radar three-dimensional point set in a camera image range; setting a height threshold value, obtaining a subset of laser radar three-dimensional points of a barrier; obtaining a subset of laser radar three-dimensional points of a passable road area; obtaining color Gaussian mixture models of a non-road area and a passable road area; obtaining an area-of-interest of road detection on an image; structuring an energy function based on the Markov random field, calculating the minimum value of the energy function, and obtaining a global optimal image road detection result. By the adoption of the road detection method based on the bimodal data fusion, robust of complex environment is achieved, the detection result is not influenced by shadows of road surface, fine barriers in an environment sensed by a sensor can be distinguished from the passable road area; an area without laser radar data returning and the non-road can be judged, and the road detection method based on the bimodal data fusion is suitable for fields such as autonomous vehicle guidance.

The invention discloses an image partition method of synthetic aperture radars (SAR) which is based on a level set and relates to the application technology of radar remote sensing. The method comprises the following procedures: an SAR echoed signal is acquired by a receiver and a hybrid probability model of an SAR image is computed; a boundary detection operator is computed according to the hybrid probability model; an energy functional based on a boundary information is acquired by combining a geodesic active contour model with the boundary detection operator; the energy functional based on a region information is computed and a partition model is defined as the weighted sum of the energy functional which are based on the region information and the boundary information; the partition model is minimized by a variation method, so as to acquire the partition result of the SAR image. As the invention uses the level set method for transforming curve movement into curved surface movement, even if the target boundary is disunited or merged in the image partition, the topology structure of the curved surfaces does not change, and simultaneously the invention does not need a noise preprocessing procedure, thus improving the precision and the applicability of the SAR image partition.

A level set polarization SAR image segmentation method based on polarization characteristic decomposition, belonging to the radar remote sensing technology or the image processing technology. In the invention, a polarization characteristic vector v which is composed of three polarization characteristics: H, alpha and A is obtained by the polarization characteristic decomposition of each pixel point of the original polarization SAR image; the polarization characteristic vectors v of all the pixel points are combined into a polarization characteristic matrix omega so as to convert the segmentation problem of the polarization SAR image from data space to polarization characteristic vector space; and the condition that the characteristic vector definition is suitable for energy functional of the polarization SAR image segmentation is utilized and a level set method is adopted to realize the numerical value solution of partial differential equation, thus realizing the polarization SAR image segmentation. The method provided by the invention takes full use of the polarization information of the polarization SAR image; therefore, the image edge obtained by segmentation is relatively complete so that the local characteristic is maintained better, the robustness for noise is stronger, the stability of the arithmetic is higher and the segmentation result is accurate; and the invention reduces the complexity of data and can effectively improve the image segmentation speed.

A method of deformable image registration for thoracic 4-D computed tomography (CT) images includes: receiving, by a processing device, a set of thoracic 4-D CT images; and iteratively solving, by the processing device, an energy function applied to subsequent images of the set of thoracic 4-D CT images to transform the subsequent images into respective optical flow fields between the subsequent images, the energy function enforcing the following constraints on the subsequent images: intensity constancy; mass conservation; gradient constancy; and spatio-temporal smoothness. A method of determining regional lung function includes: receiving, by a processing device, a set of thoracic 4-D CT images of a lung; transforming, by the processing device, the set of 4-D CT images of the lung into respective spatial voxel-wise deformation maps; and transforming, by the processing device, the spatial voxel-wise deformation maps into respective spatial voxel-wise strain maps of the lung indicating regional mechanics of the lung.

The embodiment of the invention provides an electrical power system load prediction method and device based on a depth belief network (DBN) and relates to the field of electric power systems. Through the method and device, the convergence rate can be increased, and the prediction error can be lowered. According to the specific scheme, the method comprises the steps that a training sample and a test sample are acquired; an energy function of an RBM model is constructed; the training sample is utilized to perform layer-by-layer training on at least one hidden layer and visible layer to obtain weights of the training sample among nodes of the hidden layers and the visible layers; and a prediction value of an electrical power system load is obtained according to output data obtained through the training sample and the DBN obtained after test sample input is trained. The method and device are used for electrical power system load prediction.

The invention relates to an efficient porous structure design and optimization method based on a three-period minimal surface, belonging to the computer-aided design field. Firstly, the functional representation of porous structure based on three-period minimal curved surface and the corresponding porous structure design method are presented. Then, under the given external constraints, the energyfunction model is constructed to model the porous structure design, and the corresponding discretization form is given. Finally, topology initialization and geometry optimization are carried out to obtain the optimal porous structure under given constraints. The invention greatly shortens the design and optimization period of the cavity structure, and can give the optimal result in theory. The porous structure designed by the invention has the characteristics of smoothness, full connectivity, controllability, quasi-self-support and the like, and is suitable for the common 3D printing manufacturing method, and the internal structure of the printing process does not need additional support, so that the printing time and the printing material can be saved.

The invention provides a method for segmenting an image with non-uniform gray scale based on a level set function. The method comprises the following steps: constructing the level set function; constructing image segmentation energy functional; and carrying out level set function evolution so that the energy functional is minimized so as to obtain an image segmentation boundary, wherein, the energy functional comprises a global energy statistical item, a local energy statistical item and an energy penalty item. In the invention, on the basis of a C-V (Chan-Vese) model, a Gaussian kernel function is introduced and the local statistical information for the image with the non-uniform gray scale is fully utilized so as to optimize the 'energy' functional for a minimized closed curve; and by adding the energy penalty item, convergence of a signed distance function (SDF) is ensured and the time-consuming reinitialization process is avoided. Experiments prove that by adopting the method for segmenting the image with the non-uniform gray scale, clear and accurate segmentation results can be obtained and the segmentation accuracy and efficiency for the image with the non-uniform gray scale can be improved.

The invention discloses a method for designing MIMO radar waveforms. The method mainly solves the problem in the prior art that tolerance of Doppler is poor in the process of waveform design. The implementation steps of the method include the first step of fixing a set of waveform center frequency sequences of a radar and setting an initial phase to be zero, the second step of searching a frequency interval initial variable to find out a frequency interval initial value which satisfies the requirement that the 3dB bandwidth of an emitted energy function equals to the 3dB bandwidth of an ideal emitted energy function, the third step of setting a frequency interval according to the frequency interval initial value, the fourth step of inputting the frequency interval and the initial phase and outputting an emitted energy function difference value, emitting direction sidelobe gain and the sidelobe magnitude of signals after pulse synthesis to construct a cost function, the fifth step of calling the cost function and optimizing the cost function through the minimax method to obtain the frequency interval and the initial phase meeting the requirement, and the sixth step of obtaining a set of final signals according to the frequency interval and the initial phase and completing the design of the waveforms. The waveforms designed through the method have the advantages of being good in the tolerance of the Doppler and applicable to target detection.

The invention provides a three-dimensional non-rigid body reconstruction method based on multiple depth maps. The method comprises the following steps: performing multi-depth map photographing on a non-rigid body according to different angles and different postures so as to obtain multiple depth maps; converting each depth map into a group of three-dimensional point clouds, and acquiring multiple matching dotted pairs among the multiple groups of three-dimensional point clouds; performing position change on each matching point, and solving a conversion parameter corresponding to each matching point of which the position is changed; splicing all conversion parameters, and constructing an energy function according to the splicing result; and solving the energy function so as to reconstruct a three-dimensional non-rigid body model according to the solution result. According to the method, the required input information is simple and is easily acquired, and a high-precision complete three-dimensional model can be obtained. The method is accurate and robust in solution, the influence brought by the accumulating is eliminated, and the method is high in operating speed and has wide application prospect. The invention also provides a three-dimensional non-rigid body reconstruction system based on multiple depth maps.

A method for multimodal image registration includes providing a pair of images acquired from differing imaging modalities, defining an intensity correction function that corrects the intensities of a first image in terms of the intensities of the second image, defining a registration transformation function that registers the second image with the first image, wherein said intensity correction function and transformation function are functions of a plurality of parameters, obtaining corrections to the plurality of parameters by minimizing an energy functional of a square difference of the intensity corrected first image and the registration transformed second image, and updating the intensity correction function and the registration transformation function based on the corrected plurality of parameters.

The invention provides a method for detecting old and new as well as deformity of paper currency by a sorting machine based on a paper currency degeneration energy function. The aim of the method provided by the invention is realized through the following steps: firstly establishing a reference image template; then registering paper currency images; carrying out global registration by utilizing geometrical characteristics in the process of image registration; carrying out partial registration by utilizing a color diffusion model; and detecting the deformity as well as old and new characteristics according to the registration result, and estimating the old and new as well as deformity of the paper currency according to a BDE (basic data exchange) function. The method provided by the invention comprises the following steps: establishment of the reference image template, global registration of images, partial registration of images, and estimation on the old and new as well as deformity of the paper currency according to the BDE function. The method for detecting the old and new as well as deformity of the paper currency by the sorting machine based on the paper currency degeneration energy function has the advantages of high recognition rate, stability and reliability; and the method provided by the invention can meet practical requirements and is applied to a practical paper currency sorting system.

A method and related system for automatically and efficiently isolating the heart in Computer Tomography (CT) or Magnetic Resonance Imaging cardiac scans is disclosed. The method involves segmenting a heart within a set of volumetric data. In accordance with one aspect of the present invention, the set of volumetric data is processed to determine the minimum value of an energy function having a first term, a second term and a third term. The heart is segmented based on the processing of the set of volumetric data.

Analog processors such as quantum processors are employed to predict the native structures of proteins based on a primary structure of a protein. A target graph may be created of sufficient size to permit embedding of all possible native multi-dimensional topologies of the protein. At least one location in a target graph may be assigned to represent a respective amino acid forming the protein. An energy function is generated based assigned locations in the target graph. The energy function is mapped onto an analog processor, which is evolved from an initial state to a final state, the final state predicting a native structure of the protein.

The invention relates to an automatic generation method of an interactive three dimensional city panoramic map. Based on city morphology and gestalt theory, the method combines roads widening, viewpoint raising, building displacement and building height reducing with optimization method through establishing energy function deviating argument and shielding argument for estimating city space cognition and uses linearization constrained condition energy function to solve minimizing energy function in real time, therefore automatic generation of the interactive three dimensional city panoramic map is achieved. The making method of the three-dimensional digital city panoramic map is characterized by fast visualization speed and little deformation of city scenes, having broad application prospect in city navigation, space position service and the like.

The invention provides an image stretching distortion adaptive correction method comprising: dividing an image into uniform square grids and establishing an input-output coordinate; determining a person area and a background area by using a face detection algorithm, establishing homographic constraint for each grid in order to correct the stretching distortion appearing in the person area, establishing homographic compatible constraint for adjacent grids in order to guarantee the continuity of the grids; determining a linear area by using a linear detection algorithm and establishing linear maintaining constraint for the linear area in order to protect a corrected line against bending; guaranteeing the uniform continuity of the whole image by means of global coordinate smoothness and uniformity constraint; using an energy function to express the constraint, adding weights and adding the energy equations, computing a coordinate value with the minimum energy by using a least square method so as to obtain a corrected image coordinate value; performing rendering by using bilinear mapping to obtain a final corrected image.

The invention discloses a method for extracting a target object from an interactive video, comprising the following steps of: obtaining the frame difference image of three adjacent frames of images by a frame difference method as a rough estimate of the target object; then combining with the coordinate position of the rectangular region of the front frame of image to determine the rectangular region containing the target object in the present frame of image; after that, structuring the energy function of each frame of image in an original video, and realizing the accurate extraction of the target object; adequately utilizing the coordinate position of the rectangular region of the front frame of image during the process of determining the rectangular region containing the target object inthe frame of image, thus, the target object region of the present frame can be accurately determined even if aiming at the conditions of target object suddenly turning to static or background shakingand the like; and finally establishing a fraction model for each frame of image after the target object region is determined, wherein the target object can be accurately extracted by a graph cut method, thereby greatly improving the extraction accuracy.

The invention relates to a modeling method of plate rolling in an online control model, which carries out the modeling by a rigid-plastic finite element method. The modeling method comprises the following steps: taking a central line of a plate as an x shaft and the thickness direction of the plate as a y shaft to build a two-dimension plane strain rolling model; inputting rolling conditions and parameters; dividing finite element grids in a rolling deformation region at the lower side of the rolling contact region by adopting a quadratic element and carrying out finite element pretreatment; setting the initial speed field of the finite element; building a rigid-plastic finite element energy functional by taking the initial speed field as an initial value, iterating and solving a minimum value point of the energy functional by adopting the damping Newton method, and obtaining the actual speed field; calculating the strain field and the strain field according to the actual speed field, further calculating online control parameters of the rolling force, the rolling torque and the forward slip value, and obtaining the plate rolling model. The invention improves the calculation speed of the finite element, realizes the online rapid calculation and control of the rigid-plastic finite element of the plate rolling and has strong antijamming capacity and good stability.