67 results about "Minimum cut" patented technology

A method is disclosed to automatically segment 3D and higher-dimensional images into two subsets without user intervention, with no topological restriction on the solution, and in such a way that the solution is an optimal in a precisely defined optimization criterion, including an exactly defined degree of smoothness. A minimum-cut algorithm is used on a graph devised so that the optimization criterion translates into the minimization of the graph cut. The minimum cut thus found is interpreted as the segmentation with desired property

The invention provides a high-frequency cutting machine simulation configuration method based on frequency characteristics of a regional interconnected power grid. The high-frequency cutting machine simulation configuration method is based on the characteristics of frequency feature, a topological structure, power balance and the like of an interconnected system, determines the basic configuration principle of a high-frequency cutting machine, and then establishes a single-machine load model to perform detailed configuration on an optimal cutting machine frequency section, minimum cutting machine capacity, cutting machine rounds, cutting machine delay, cutting machine proportions of cutting machine rounds and other parameters. The high-frequency cutting machine simulation configuration method has the advantages of being good in adaptability, comprehensive in considered factors, reasonable in scheme and the like.

The invention provides a motion object real time extraction method of a Vibe improvement algorithm based on combination of graph cut. The motion object real time extraction method comprises steps of performing retreatment on video orders through a Vibe background modeling algorism, dividing the pixels in the image into a foreground, a background and an unknown type and establishing an incompletion ternary diagram, obtaining an incompletion ternary diagram according to the Vibe algorithm, establishing mapping from an image to the diagram, constructing a goal energy function by combining with a membership degree of the foreground and the background and the similarity degree characteristics of the adjacent pixels, obtaining the gather of the sides and the points which can minimize the energy function through the max-flow min-cut theory and performing image division based on the min-cut, performing a post-processing based on the division result of the graph cut algorithm, marking the motion object in the original image by an outer-connected rectangle, and further detecting the motion object through the modeling match. The invention improves the robustness and accuracy of extracting the motion object.

The invention provides an information center network (ICN) logical topology construction method based on software defined networking (SDN) and belongs to the technical field of the internet. Due to the fact that the ICN framework undergoes fundamental change compared with the TCP / IP framework, the existing network topology structure and ICN flow distribution are not matched, and in order to achieve matching between the topology structure and ICN flow distribution, by means of the method, reconstruction of network logical topology is achieved through a logic closing link mechanism and a logic adding link mechanism. To be specific, firstly, aggregation of a logic closing link is determined in real time through a hidden markov model in a spatial state transition graph which is constructed according to ICN flow distribution and has hidden markov characteristics; secondly, link aggregation and corresponding bandwidth are added through the maximum-flow minimum-cut theorem positioning logic in a weighting directed complex network constructed according to ICN flow distribution. By means of the method, an effective path is provided for further optimization of ICN flow.

The invention discloses a method for forecasting the demand of a wind generating set for spare parts based on fault tree analysis. The method comprises the steps of firstly building an abstract model of a wind generating set fault tree; then acquiring the daily annual fault probability of components corresponding to each bottom event in the fault tree; building a fault tree simulation model by using a Simulink platform, and simplifying a Boolean function expression of a top event; solving a minimum cutest of the fault tree; compiling a numerical operation sub-function for calculating the probability importance degree and key importance indexes of each bottom event; inputting the daily annual fault probability of each bottom event by a user, and calling the sub-function to output the probability importance degree and key importance indexes; and calculating the number of spare parts of each component in a future stage. The method disclosed by the invention is based on the wind generating set fault tree, adjustable in model parameter, capable of adapting to product differentiation of different manufacturers and different working conditions, fault reasons of the wind generating set are detailed, the utilization efficiency of the spare parts is improved, the inventory cost is reduced, and so that the objective of reducing the operation and maintenance cost of wind power generation enterprises is achieved.

The invention discloses a wireless Mesh network routing channel union distribution method based on topology optimization and interference reduction. During channel distribution, a routing channel union algorithm of optimizing a topological structure, routing the maximum flow, grouping links and group-distributing channels is adopted, so that the shaking problem during channel distribution and the problem about the routing efficiency can be effectively solved, and the throughput and the efficiency of a system can be further improved; network structure topology is optimized by virtue of a maximum flow minimum cut theory; the justice is kept, and the throughput is increased as much as possible; after the topological structure is optimized, the number of links participating in channel distribution is reduced, and interference and conflicts are reduced, so that the later channel distribution efficiency is improved greatly, the routing maintenance cost is reduced, and the system efficiency is improved; after routing, a routing algorithm and the channel distribution can be united effectively through a two-section channel distribution algorithm; and according to the two-section channel distribution algorithm, the integral shaking problem possibly caused by partial adjustment during channel distribution can be solved, the channel distribution efficiency is relatively high, and the performance of a network is improved greatly.

The invention request to protect a medical image segmentation method based on the combination of a cloud module and image segmentation. The method comprises the steps of: firstly, carrying out smoothing processing on an image, and removing noise points; then utilizing reverse cloud conversion to cloud characteristic constants of an image foreground and background respectively, and utilizing an X condition cloud generator to calculate membership degrees of each pixel relative to the foreground and background; calculating data items and smooth items; then establishing an energy function to construct a corresponding network figure, and utilizing a maximum flow / minimum cut algorithm to realize medical image segmentation; and finally, judging whether a segmentation result meets iteration conditions, if yes, then outputting the result, and otherwise, calculating cloud characteristic constants of a current segmentation result foreground and background again. According to the invention, the cloud module and the image segmentation algorithm are combined, the good multi-characteristic constraint capability and the global optimality of the image segmentation method are reserved, and the fuzziness and randomness of the cloud model and nondeterminacy of the association between the cloud module and the image segmentation algorithm are introduced, so that the precision of medical image segmentation can be effectively improved.

The invention discloses a method for determining the reconfigurability of a satellite control system. The method comprises the following steps of: (1) constructing a satellite control system function tree and connecting the different levels of the function tree by means of AND Gate or OR Gate according to the function implementation mode of the satellite control system; (2) according to the AND / OR relationship between different levels of the function tree, determining the cut-set family C of the function tree by using the descending method or the ascending method, wherein the elements of the cut-set family are cut-sets and the cut-sets are component sets for implementing the functions of the satellite control system; (3) performing absorption treatment on the cut-set family C determined in the step (2) to obtain the minimum cut-set family Cmin of the function tree, wherein the elements of the minimum cut-set family Cmin are minimum cut-sets cmin and the minimum cut-sets cmini are the sets of least components required for implementing the functions of the satellite control system; (4) performing failure mode effect analysis (FMEA) on the satellite control system to determine the failure mode, failure occurrence probability and failure severity of the satellite control system; (5) determining the reconfigurable degree (Gamma-i) of the failure mode i; and (6) determining the reconfigurable rate of the satellite control system.

The invention provides a circuit partitioning method for parallel circuit simulation, and belongs to the technical field of very large scale integration (VLSI) circuit design automation. The method comprises the steps as follows: better initial partition is rapidly acquired with a recursive multistage two-way partition method taking minimum cut as a target; and then minimum communication traffic and load balancing are taken as targets, and the partition is continuously improved with an iteration improvement method. The technical scheme is as follows: 1), a k-route initial partition is acquired with the recursive two-way partition method; 2), the two-way partition is performed with a multistage partition method, wherein at a roughening stage, load balancing is combined, and at an elaboration stage, iterations are limited; and 3), in an iteration improvement process, a peak which can improve the load balancing is selected to be moved preferentially each time. According to the method, an obtained partition result meets the requirements of the load balancing and less communication traffic, and the method is applicable to a circuit partition stage of an VLSI parallel circuit simulation system.

The present invention discloses an indoor scene layout estimation and target region extraction method based on RGB-D images. The method comprises the following steps: performing scene layout estimation; using a graph-based segmentation algorithm and a constraint parameter minimum-cut algorithm to perform over segmentation of the processed depth map and RGB images to get the region sets of different sizes; performing over-segmentation level grouping, using four different similarity measurement modes to perform regional combination to complete the regional level grouping, so as to access to target regions of all sizes; and performing target boundary-box matching. The method realizes the target region extraction of the indoor scene with high efficiency and high recall rate.

The invention discloses a GraphCut-based interactive target extraction method in a complicated background remote-sensing image. The GraphCut-based interactive target extraction method in the complicated background remote-sensing image comprises the following steps: (1) selecting an interested image region; (2) appointing the foreground and the background of the interested image region; (3) obtaining the color distribution histogram of a foreground region and a background region; (4) establishing a graph model G=<V,E>; (5) respectively calculating regional item energy R(A) and edge item energy B(A); (6) calculating an adaptive weight lambda, and constructing an energy function; (7) optimizing the energy function by a maximum flow and minimum cut algorithm to obtain a preliminary segmentation result; (8) by aiming at a region which is wrongly segmented, forcedly appointing a foreground and a background; (9) according to an enforced constraint input by an operator, revising the graph model; (10) optimizing the energy function again to obtain a final segmentation result. According to the GraphCut-based interactive target extraction method in the complicated background remote-sensing image, which is disclosed by the invention, the statistics accuracy of color distribution information can be improved, meanwhile, the adaptation of a GraphCut algorithm in the complicated background remote-sensing image can be enhanced, the segmentation accuracy can be effectively improved, and interaction times are reduced.

The invention relates to a data-driven fault-tree analysis method, a data-driven fault-tree analysis device and data-driven fault-tree analysis equipment. The data-driven fault-tree analysis method can include the steps of: generating a fault tree, which corresponds to a fault top event, according to historical fault data of the fault top event, wherein the fault tree includes multiple layer bottom events; quantitatively processing the fault tree to obtain fault probability corresponding to each layer bottom event and a Fussell-Vesely importance degree of each minimum cut set, wherein the minimum cut sets are cut sets which are obtained by qualitatively processing the fault tree and correspond to the fault top event; and generating state evaluation data of to-be-analyzed equipment according to each fault probability and each Fussell-Vesely importance degree. By adopting the method, fault management efficiency is improved, and reliability of equipment fault management is also improved.

Methods and apparatus for locating a dense and isolated sub-graph from a weighted graph having multiple nodes and multiple weighted edges are described. Each node in the weighted graph represents an object. Each weighted edge in the weighted graph connects two nodes and represents the relationship between the two objects represented by the two corresponding nodes. To located the sub-graph, first, an auxiliary weighted graph is constructed using the weighted graph and three coefficients: α, β, and γ, where α, β, and γ are greater than 0, α influences the number of nodes inside the sub-graph, β influences the sum of the weights associated with the edges connecting a node inside the sub-graph and a node outside the sub-graph, and γ influences the sum of the weights associated with the edges connecting two nodes both inside the sub-graph, and by adding a source node s and a sink node t. Next, the auxiliary weighted graph is partitioned into two parts using the s-t minimum cut algorithm. The sub-graph is the part associated with the sink node t in its original form, with the original undirected edges and unmodified edge weights and excluding the sink node t and all the new edges added during the construction of the auxiliary weighted graph.

Approaches for optimizing computation of minimum cut or maximum flow on graphs comprising a plurality of nodes and edges with grid-like topologies are disclosed. Embodiments exploit the regular structure of input graphs to reduce the memory bandwidth—a main bottleneck of popular max-flow / min-cut algorithms based on finding augmenting paths on a residual graph (such as Ford-Fulkerson [1956] or Boykov-Kolmogorov [2004]). Disclosed embodiments allow more than 200% speed-up without sacrificing optimality of the final solution, which is crucial for many computer vision and graphics applications. Method and system embodiments replace standard linked list representation of general graphs with a set of compact data structures with blocked memory layout that enables fixed ordering of edges and implicit branchless addressing of nodes. The embodiments are orthogonal to other optimizations such as parallel processing or hierarchical methods and can be readily plugged into existing min-cut / max-flow computation systems to further improve their performance.

The invention discloses a shopping image collaborative segmenting method for performing collaborative segmentation on a plurality of input shopping images containing one piece of garment automatically and extracting garment areas in the images. According to the invention, foreground (garment) areas and background areas in the shopping images are positioned by using an upper body detection algorithm and an image distinctive area detecting algorithm; a Gaussianmixed model is adopted for performing unified modeling on the foreground and the background of all the garment images and a collaborative segmentation objective function is established; then a minimum cut algorithm is used for performing iteration solving of the objective function; and finally the segmentation results of all the images are obtained. The method is suitable for being applied to e-commerce websites and online shopping websites. Interference on image retrieval caused by complex background can be eliminated and searching accuracy of searching engines can be improved.

The invention provides an image defogging method, which comprises the following steps: calculating the atmospheric light component of a foggy image to be processed; constructing each pixel of the foggy image and added source points and focal points into an undirected graph represented by an edge set and a vertex set, and solving a minimum cut in the undirected graph to carry out image segmentation processing to the foggy image so as to obtain a plurality of segmented image areas; and according to the atmospheric light component, independently carrying out defogging processing to each segmented image area by adopting a dark channel prior defogging method to obtain a defogged image. Firstly, the foggy image is subjected to the image segmentation processing by adopting an image segmentation method based on image segmentation to obtain a plurality of segmented image areas, then, each segmented image area is subjected to the defogging processing independently by adopting the dark channel prior defogging method, so that the obtained defogged image avoids from generating an obvious halo effect defect on an edge, and the obtained defogged image is clear and undistorted. The invention also provides an image defogging system.

The invention relates to a predication method for a dynamic tail-escaping amount of strip steel. The method is characterized by comprising the following steps: (1) collecting strip shape flatness data of section measuring points of the strip steel in a width direction and data information of the distance away from a strip steel head corresponding each set of the data, and forming a data file with a text format; (2) carrying out effective data extraction on each independent strip steel strip shape data file and carrying out meshing distributed processing; (3) fitting a partial waveform of the strip steel and formulating a judgment standard; (4) carrying out wave shape judgment on certain length data of the tail part of the strip steel section by section and combining a wave shape severe degree to judge whether tail escaping is needed or not; and (5) carrying out process correction on a predicated length and correcting an undersize tail-escaping amount in tail-escaping amount predication according to a minimum cutting length requirement of the process. According to the method, the tail-escaping amount of the strip steel of an application set is reduced and the yield of the application set is improved; a production accident is prevented from occurring; the method is simple and easy to operate.

The invention discloses an image foreground extraction method based on a graph cut model. The method is used for accurate segmentation of a human eye area in an image and belongs to the field of image recognition based on machine vision, and the method is suitable for automatic detection driving fatigue state of a driver. According to the invention, the problem that a present detection system cannot accurately recognize human eye opening and closing states in a complex driving environment is solved. According to the method, a graph cut model is firstly established on an original image; then, based on a segmentation target, an energy function of the graph cut model is constructed; and finally, the function is solved by a max-flow min-cut method so as to obtain the final segmentation result. By the segmentation algorithm, a binary image with a white background and a black eye area is constructed, thus providing stable feature description for follow-up human eye state recognition. It proves validity of the extraction method through experiments. The method provided by the invention can be widely applied in automatic detection of fatigue state of drivers of trains, interurban coaches and ''three danger'' vehicles.

The present invention is a minimum cut set calculation system for calculating minimum cut sets of a fault tree with binary decision diagram (BDD), comprising: subtracting means for, from one of two sub-BDDs of an input BDD, removing redundant paths included in the other sub-BDD using a recursive function comprised of a recursive case and a base case, wherein said subtracting means comprises equivalence removing means for, when said two sub-BDDs are equivalent, outputting a terminal node 0 in said base case.

The invention discloses a method and a device for achieving interactive image segmentation, and a terminal. The method comprises steps of forming a smearing trajectory as a skeleton to form a mark area, determining an area of interest including the mark area, and generating an input mask image for the image segmentation algorithm: using the pixel in the mark area as a foreground point in the mask image, and taking the pixels outside the mark area in the area of interest as background points in the mask image; and acquiring a depth image including target object depth information, determining the segmentation parameter of each pixel on the mask image according to the depth image and the mask image, constructing an undirected image and mapping the segmentation parameter of each pixel in the mask image into the undirected image, processing the undirected image according to the minimum cut-maximum flow algorithm to obtain a fine segmented mask image, and dividing images corresponding to the foreground point in the fine segmented mask image from the original image. The operation time of the algorithm can be shortened, and the image segmentation effect can be improved by the depth information of the image.

The invention provides a method for determining importance degree of components of a satellite control system. The method includes: (1) a satellite control system function tree is established, and different levels of the function tree are connected through a conjunction gate or a disjunction gate according to function realization ways of the satellite control system; (2) a cut set family C of the function tree is determined by adopting a descending method or an ascending method according to the conjunction or disjunction relationship among the different levels of the function tree, elements in the cut set family are cut sets, and the cut sets are sets of components for achieving functions of the satellite control system; (3) absorption processing is performed on the cut set family C determined in the step (2), a minimum cut set family (Cmin) of the function tree is obtained, elements in the minimum cut set family (Cmin) are minimum cut sets cmin, and the minimum cut sets cmin are sets of minimum components required for achieving the functions of the satellite control system; and (4) the importance degree of each component in the function tree is determined. The method overcomes the defect that a failure mode and effects analysis (FMEA) technique can only show single point failure and can provide a basis for design of reliability and reconfigurability of a satellite.

The present invention provides a method for changing a node control category in a complex network. The method comprises: for a to-be-processed redundant node n, acquiring all unsaturated nodes in thenetwork that can arrive at the redundant node n through a staggered path; constructing a staggered network by taking the redundant node n as the starting point; using the minimum cut algorithm to process the staggered network to obtain a set of minimum edges that requires to be deleted when the redundant node n is disconnected from all the unsaturated nodes on the staggered path; identifying the alternative ring including the redundant node n in the network, and based on the identified alternative ring, determining contiguous edges that are required to destroy the alternative ring; deleting all the contiguous edges in the set of the minimum edges, and deleting the determined contiguous edges that require to be deleted in order to destroy the alternative ring; and selecting one staggered path from the redundant node n, and deleting a matched edge in the selected staggered path, so that the redundant node n is converted into an input node. The method provided by the present invention greatly reduces the conversion cost and has higher efficiency.

The invention provides a curve cutting system of a cutting bed. The curve cutting system of the cutting bed comprises one locating point selection module, one locating point radius computation module,one maximum radius speed definition module, one minimum radius speed definition module and one cutting speed execution module. The cutting speed execution module is used for selecting a continuouslyvariable speed value in a range of a maximum cutting speed value and a minimum cutting speed value and cutting the cloth, and the continuously variable speed value follows an equation that V is equalto KRf+d, wherein V is corresponding speed when radius is R, and K, f and d are variables. The curve cutting system of the cutting bed has the advantages that various curve speed optimization schemescan be designed according to actual requirements and are converted into mathematical formulas, so that only an appropriate speed scheme needs to be selected when the cloth is cut, and further the aimof simplification is achieved; meanwhile, cutting can be carried out at different speeds according to curves with different radians, and the effect of optimization is achieved, so that cutting qualitycan be improved.

The invention discloses a data processing method for a heterogeneous distributed storage system. Storage nodes in the distributed storage system are divided into two parts including a coding repairingnode set and a replica repairing node set; after being coded, original data is put in the storage codes, which are composed of multiple coding repairing nodes and replica repairing nodes; according to the maximum-flow minimum-cut theorem, the fact that various nodes satisfy the basic condition of reconstructing an original data file is determined; the downloading cost as low as possible is obtained under the limitation of the basic condition; a minimum repairing bandwidth point and a minimum storage point are obtained by calculation; and thus, reconstruction is completed.

In high dynamic range (HDR) image creation, a ghost artifact detection method divides the images (brackets) into multiple tiles, and selects one bracket for each tile as the local reference bracket. The local reference brackets are selected via optimization of an objective function which includes both a component that measures exposure quality of individual tiles and a component that measures correlation between neighboring tiles. The minimization can be realized by constructing a graph for the objective function and calculating a minimum cut of the graph using a graph cut algorithm. Graph examples for three and four image sets are given. Ghost artifact detection is then performed on a tile-by-tile basis by using the local reference bracket for each tile. Ghost maps are generated this way and used for HDR image creation. This method minimizes artifacts due to inconsistencies in local reference bracket selection in areas involved in ghost-inducing objects.

The invention provides an image processing method and device suitable for the field of image processing. The method comprises that an original image is obtained; a first selection instruction is received, a first pixel set assigned by the first selection instruction is obtained from the original image, and a first Gaussian mixture model is established for the first pixel set; a second selection instruction is received, a second pixel set assigned by the second selection instruction is obtained from the original image, and a second Gaussian mixture model is established for the second pixel set; and a foreground side weight is determined according to the first Gaussian mixture model, a background side weight is determined according to the second Gaussian mixture model, a maximum-flow minimum-cut model is established according to the determined foreground side weight and background side weight, and a foreground of the original image is determined according to the established maximum-flow minimum-cut model. Compared with an image segmentation manner combining K-means algorithm and maximum-flow minimum-cut algorithm, the method can be used to extract the foreground from the original image more accurately by fully utilizing each obtained pixel.

A method of multispectral decomposition for the removal of out-of-band effects. A band of a multispectral radiance is measured using at least one optical filter, upon scanning a plurality of original radiances. A spectral range of an integral is partitioned between a maximum cut-off wavelength of the band and a minimum cut-off wavelength of the band into a plurality of sub-ranges. A multispectral radiance vector is generated from the measured band-averaged spectral radiances. The pre-calculated multispectral decomposition transform matrix corresponding to the optical filter and the measured multispectral radiance vector are matrix-multiplied to generate a band-averaged spectral radiances image vector representing a plurality of recovered band-averaged spectral radiances. The plurality of recovered band-averaged spectral radiances is outputted, for example to a display, thereby generating a plurality of recovered radiances free of out-of-band effects and which approximate the plurality of original radiances.

The invention discloses a bilateral video target segmentation method and system. According to the method, a video sequence with a key frame mark is mapped to a high-dimensional bilateral space, the video data to be processed is reduced, and then the non-empty grid unit is taken as the node of the graph and the graph cut optimization model is constructed; the method is characterized in that a confidence dynamic appearance model is constructed by analyzing a Gaussian distribution rule, and the possibility that each grid unit belongs to a foreground / background is accurately estimated; a high-order item is introduced into the energy function to enhance the space-time correlation of non-adjacent nodes with similar appearance characteristics; and finally, the energy function is solved by using amaximum flow / minimum cut algorithm to obtain a label value corresponding to each grid unit, and finally label distribution of the video pixel points is achieved. According to the method, interferenceof adverse factors on segmentation can be well eliminated, and video target segmentation with a complex scene can be rapidly processed with high precision.