682results about How to "Effective segmentation" patented technology

An untrusted component exposing a high level storage object interface within an untrusted client virtual machine accepts application level storage object operations. Responsive to a storage object operation, the untrusted component passes a message through the underlying hypervisor to an associated trusted component. The trusted component processes the message by authenticating the client virtual machine and locating an internal mapping between the client virtual machine and an associated customer-specific set of backend storage resources to which the requested storage object operation is to be applied. The trusted component uses a trust relationship with the backend storage system to securely communicate the storage object operation to the backend storage system, and passes the operation results through the hypervisor back to the untrusted component in the source client virtual machine from which the storage object request originated.

Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut.

The invention discloses a method for segmenting different objects in a three-dimensional scene. The method comprises the following steps of: establishing adjacency relations and a spatial searching mechanism of point cloud data to estimate a normal vector and a residual of each point for the outdoor scene three-dimensional point cloud data acquired by laser scanning; determining the point with the minimum residual as a seed point and performing plane clustering by using a plane consistency restrictive condition and a region growing strategy to form the state that the entire plane building is segmented from other objects in the three-dimensional scene; establishing locally connected search for a plane building region for the segmented entire building part, and clustering the points with connectivity in the same plane by using different seed point rules to realize the detailed segmentation of the plane of the building; and constructing distance label-based initial cluster blocks for the other segmented objects and establishing weighting control restriction for cluster merging to realize the optimal segmentation result of trees. Tests on a plurality of data sets show that the method can be used for effectively segmenting the trees and buildings in the three-dimensional scene.

A system is disclosed for identifying, placing and configuring a physical arrangement of a plurality of displays via image analysis of captured digital camera images depicting unique configuration images output to said displays to facilitate uniform operation of said plurality of displays as a single display area for example as a video wall. The system pairs and configures displays depicted in the captured images to individual displays within the physical arrangement through controlling and analyzing of the output of said displays captured in said images. A method and computer readable medium are also disclosed that operate in accordance with the system.

A method of image segmentation includes receiving a set of voxels, segmenting the set of voxels into a foreground group and a background group, and classifying voxels of the foreground group as either lesion voxels or normal anatomy voxels. The method also includes blocking the normal anatomy voxels and performing a second segmentation on voxels of the background group and the lesion voxels, the second segmentation forming a stage two foreground group comprising the lesion voxels and a portion of the voxels of the background group. The method further includes classifying voxels of the stage two foreground group as either stage two lesion voxels or stage two normal anatomy voxels.

The invention provides a vehicle license plate recognition method, and relates to a method for image recognition. The method comprises the following steps of preprocessing an image; partitioning a vehicle region according to color and texture characteristics; extracting a remarkable factor graph of a vehicle region diagram; extracting candidate vehicle license plates by an Adaboost classifier based on expanded Harr-like characteristic; determining the position of a real vehicle license plate from the candidate vehicle license plates; partitioning the marked vehicle license plate from the corresponding vehicle region original diagram; carrying out character segmentation according to structural characteristic; and carrying out character recognition based on the improved template matching method. With the method provided by the invention, the defects that the application scene of the traditional vehicle license plate recognition method is relatively single, some traditional vehicle license plate recognition methods are only suitably used for single vehicle license plate recognition of the single scene and difficultly used for multiple-vehicle license plate recognition of multiple scenes, and the recognition rate is easily affected by strong light, haze and weak light environments are overcome.

A system and method for monitoring resource requirements in a computer system and for adding (or subtracting) such resources as required. In a preferred embodiment, the system automatically, without user intervention, makes the resource adjustment when calculations indicate a need for such an adjustment. The system stores historical and statistical data concerning a multitude of parameters and the action taken with respect to the resources reflects a comparison against such stored data.

The invention provides an infrared images method for detecting targets at sea, which relates to a method for detecting the targets at sea. The invention aims to provide the method for detecting the targets at sea, which not only can well inhibit sea clutters to obtain reasonable image segmentations, but also can extract out the fractal characteristics at a high speed to remove false targets so as to achieve effective detections. The method comprises the following steps: performing preprocessing on the obtained infrared images; performing self-adapting iteration threshold segmentation; detecting whether the part of a sea-sky line has a region of interest (ROI); extracting the ROI at the background part of the sea-sky line; extracting the ROI at the background part of a non-sea-sky line; and combining the regions of interest to obtain an image of interest to be further processed, and extracting the fractal characteristics of each ROI to perform target detections. The method can quickly and effectively segment out the regions of interest in the infrared images, and not only reduces the amount of calculation to extract out the fractal characteristics at a higher speed because the extracted regions of interest is far smaller than the original images, but also can remove the false targets appearing in the threshold segmentation through the fractal characteristics.

The invention discloses a method and module for extracting and interpreting information of a remote-sensing image, and provides a geographical element object based automatic interpreting method based on SRMMHR and random forest. The module extracts and interprets the information of the remote-sensing image by the adoption of the method. The method and module for extracting and interpreting the information of the remote-sensing image can achieve effective segmentation of the remote-sensing image, automatic optimization of characteristics, and automatic establishment of a classification rule set; a means which is little in manual intervention, high in degree of automation and high in interpreting precision is provided for extracting and interpreting the information of the remote-sensing image.

There is provided a method for splitting a split type conjugate fiber. The method includes four steps. Firstly, there is provided a first polymer with crystallization of 40% to 95% and a second polymer with crystallization of 1% to 25%. Secondly, a conjugate fiber is made of the first and second polymers by conjugate spinning. Thirdly, the conjugate fiber is submerged in water so that the conjugate fiber contains water. Finally, the conjugate fiber is heated and split into fine fibers.

A method and apparatus for recovering a three-dimensional (3D) scene from two-dimensional (2D) images. A sequence of images is divided into a number of smaller segments and a 3D reconstruction is performed on each segment individually. All the reconstructed segments are then combined together through an efficient bundle adjustment to complete the 3D reconstruction. Segmenting may be achieved by dividing the segments based on the number of feature points that are in each frame. The number of frames per segment is reduced by creating virtual key frames. The virtual key frames encode the 3D structure for each segment, but are only a small subset of the original frames in the segment. A final bundle adjustment is performed on the virtual key frames, rather than all of the original frames. Thus, the final bundle adjustment is two orders of magnitude faster than a conventional bundle adjustment.

The invention discloses an intelligent wheelchair dynamic gesture recognition method based on Kinect depth information and relates to the field of intelligent wheelchairs. A method of dynamic gesture recognition based on Kinect depth image information is adopted, and the intelligent wheelchair dynamic gesture recognition method has strong expansibility, can solve problems of influence on gesture detection caused by complex backgrounds, large-area skin color interference and the like and can accurately and effectively separates hands. Subsequently, a method combining Camshift and Kalman filtering is adopted to fast and effectively track gestures, a fused feature extraction method is adopted, and accuracy of dynamic gesture recognition is improved. When the intelligent wheelchair dynamic gesture recognition method is applied to an intelligent wheelchair control system based on dynamic gesture recognition, fast and accurate dynamic gesture command recognition can be achieved, the intelligent wheelchairs can be safely and stably controlled, and the natural and visual man-machine interaction mode between people and the intelligent wheelchairs is achieved.

A split torque gearbox system provides a multiple path, three stage power gear train that transmits torque from a high-speed engine to a low speed output shaft, while providing equal gear load distribution with a floating pinion in the second stage of reduction. The number of the split modules in the gearbox depends on gearbox configuration, number of high speed input shafts, and transmitted power. The split modules are located around a last stage output gear that combines power from each module and transmits the power to an output such as a main rotor system.

An MOS device includes first and second source/drain regions of a first conductivity type formed in a semiconductor layer of a second conductivity type proximate an upper surface of the semiconductor layer, the first and second source/drain regions being spaced apart relative to one another. A non-uniformly doped channel region of the first conductivity type is formed in the semiconductor layer proximate the upper surface of the semiconductor layer and at least partially between the first and second source/drain regions. An insulating layer is formed on the upper surface of the semiconductor layer. A first gate is formed on the insulating layer at least partially between the first and second source/drain regions and above at least a portion of the channel region, and at least a second gate formed on the insulating layer above at least a portion of the channel region and between the first gate and the second source/drain region. The second gate has a length which is substantially greater than a length of the first gate, the first and second gates being electrically isolated from one another.

The invention discloses a method for positioning and identifying a laser character of a beer bottle cap, which comprises the following steps: step 1, character positioning which comprises coarse positioning and fine positioning, that is, carrying out binaryzation, corrosion expansion, edge detection, contour tracing and Hough transform processing on a positioning character image, searching an angle between the straight lines on which two edges of the positioned character A are positioned, calculating a rotating angle of the character, searching coordinates of the center of the bottle cap, translating the center of the bottle cap to the center of an original bottle cap image, aligning the bottle cap image according to the calculated rotating angle of the character and repositioning the character; and step 2, character division and identification, wherein the character identification comprises the steps of extracting a 13 characteristic, extracting a protection statistical characteristic, extracting a coarse grid characteristic and finally carrying out matched identification on the character on the basis of the three character characteristics by utilizing a template matching method. The method disclosed by the invention aims at the character image of the bottle cap, which has a complex background and nonuniform illumination and implements the positioning on the laser character of the beer bottle cap, which rotates at a random angle.

The current invention concerns a method for detecting cancerous cells and/or classifying cells in a cell sample comprising the following steps: providing a cell sample; obtaining holographic information from said cell sample by digital holographic microscopy (DHM); deriving at least one cellular parameter from said holographic information, and; classifying said cells of cells sample; characterized in that said classification occurs by appointing a Scoring Factor to said cells of cell sample, based on said cellular parameters. In a second aspect, a system for the detection of cancerous cells and/or classification of cells in a cell sample is provided, employing the method as disclosed in the invention. In a final aspect, a method for updating and/or improving a database comprising thresholds linked to holographic information and the database related thereof is equally disclosed.

The invention relates to a method of quickly segmenting a moving target in a non-restrictive scene based on a full convolution network, which belongs to the technical field of video object segmentation. The method comprises steps: firstly, framing is carried out on the video, and a result after framing is used for making a Ground Truth set S for a sample image; a full convolution neural network trained through a PASCAL VOC standard library is adopted to predict a target in each frame of the video, a deep feature estimator for an image foreground target is acquired, target maximum intra-class likelihood mapping information in all frames is obtained hereby, and initial prediction on the foreground and the background in the video frames is realized; and then, through a Markov random field, deep feature estimators for the foreground and the background are refined, and thus, segmentation on the video foreground moving target in the non-restrictive scene video can be realized. The information of the moving target can be effectively acquired, high-efficiency and accurate segmentation on the moving target can be realized, and the analysis precision of the video foreground-background information is improved.

The present invention discloses a tensor-based user track mining method. The tensor-based user track mining method comprises: (1) acquiring history track data of a user; (2) dividing data with time difference exceeding a predetermined time threshold in the history track data to form a plurality of segments of continuous track data; (3) extracting an arrest point of the user in each segment of track on account of each segment of continuous track data; (4) dividing the arrest point into a start point and a destination point and acquiring a corresponding road segment in sequence by a map matching method; (5) building a three-dimensional tensor by using the arrest point and the road segment sequence; (6) finding a related hotspot road segment between the start point and the destination point for a user search request (S,Q); and (7) calculating a recommended path according to a road segment weight set. The tensor-based user track mining method according to the present invention has the advantages as follows: only longitude and latitude of each of the start point and the destination point are provided for searching the hotspot recommended path between the start point and the destination point for the user search request; and the user does not need to understand the background implied data structure.

The invention discloses a contact network failure detection and diagnosis method based on an unmanned aerial vehicle, which comprises the following steps: (1) image acquisition: carrying a video camera to shoot along a contact network by an unmanned aerial vehicle so as to respectively acquire contact network images under visible light and infrared light; (2) image graying; (3) image enhancement; (4) image segmentation; (5) image dissection; (6) image fusion: fusing Laplacian pyramid layers under visible light with corresponding Laplacian pyramid layers under infrared light, and carrying out image reconstruction on the fused Laplacian pyramid to obtain a contact network component image after the visible light image and the infrared light image are fused; and (7) carrying out image identification and failure judgment by a BP (back-propagation) neural network. The method can be used for effectively acquiring a contact network image in the operation process of a locomotive in a multidirectional multiangular real-time mode, automatically identifying the contact network component in the image, and judging whether the contact network fails and the type of the failure; and the judgment result is more accurate and reliable, and can better ensure the safety of railway transportation.

The invention relates to a binary method for a low-quality document image based on local contract and estimation of stroke width. The method comprises the steps that the scanned document image is obtained; the colored document image u (x, y) is grayed in a minimum mean method; character stroke pixel is detected based on the local contrast; global optimal thresholding is carried out on the obtained local contract image in an Otsu method; edge detection is carried out on the binary image via a Canny operator, the amount nfg of the character foreground pixels and the amount nedge of the character edge pixels are calculated respectively, the contour proportion lambda is calculated by dividing the nfg by the nedge, and the character stroke width is estimated via the contour proportion; and image local binarization is carried out in a sliding neighborhood method. According to the method, details of character strokes are reserved effectively, the character foreground is effectively segmented, and phenomena including ink marks infiltration, spot of pages, textured background, and non-uniform illumination can be inhibited.

The invention belongs to the technical field of laser radars, and discloses a depth map-based three-dimensional laser radar point cloud target segmentation method, which comprises the following stepsof: converting three-dimensional point cloud data acquired by a three-dimensional laser radar into a two-dimensional depth map; calculating an angle value formed by two adjacent points in each columnin the depth map, and traversing to obtain an angle matrix corresponding to the depth map; traversing the depth map through a breadth-first search algorithm, if the angle difference between two pointson adjacent positions of the depth map is smaller than a specified threshold value, marking the depth map as the same type, thereby finding out the part, belonging to the ground, in the depth map, and removing ground point cloud data according to the mapping relation between the point cloud and the depth map; and carrying out target segmentation on the non-ground point cloud based on an improvedDBSCAN algorithm, and judging whether the point cloud is a core point or not according to an adaptive parameter eps while considering a spatial Euclidean distance and an angle distance. According to the method, the segmentation efficiency on the depth map is improved, the real-time requirement is met, and the problems of under-segmentation and over-segmentation are effectively solved.

The invention brings forward an identification method for an information carrier comprising multi-type identifications. The information carrier can be a product label. By use of auxiliary positioning identification and a corresponding positioning identification detection identification algorithm, auxiliary positioning identifications on the information carrier are automatically identified, such that automatic positioning of multi-type data is realized. By use of an image identification algorithm, such information as characters, bar codes, display contents of display screens, two-dimensional codes, images and the like can be simultaneously identified, and the electronic display screens can display such contents as the characters, the bar codes, the two-dimensional codes, the images and the like, such that the information carrier has abundant information, and the identification results are accurate and reliable. Compared to bar code identification, two-dimensional code identification and image identification, character identification is smaller in characters and high in character segmentation and character identification difficulty. In order to ensure the accuracy of the character identification, the identification results are verified for the character identification by use of already known character lengths.

The embodiment of the invention provides a method for segmenting a vasa sanguinea retinae image. The method mainly comprises the steps of carrying out double-scale matched filtering processing on the vasa sanguinea retinae image to obtain a fine scale matched filtering response image and a coarse scale matched filtering response image; segmenting out vessel support regions from the fine scale matched filtering response image, carrying out binarization processing on each vessel support region by use of a local self-adaptive thresholding method and segmenting out fine blood vessel sections; segmenting the coarse scale matched filtering response image by use of a fixed proportioning thresholding algorithm to obtain large blood vessel sections. Segmentation results of the fine blood vessel sections and large blood vessel sections are fused to obtain a complete vasa sanguinea retinae segmentation result, and the accurate rate of the segmentation result is high.