37 results about "Semi global" patented technology

Two system-level bronchoscopy guidance solutions are presented. The first incorporates a global-registration algorithm to provide the physician with updated navigational and guidance information during bronchoscopy. The system can handle general navigation to a region of interest (ROI), as well as adverse events, and it requires minimal commands so that it can be directly controlled by the physician. The second solution visualizes the global picture of all the bifurcations and their relative orientations in advance and suggests the maneuvers needed by the bronchoscope to approach the ROI. Guided bronchoscopy results using human airway-tree phantoms demonstrate the potential of the two solutions.

The invention discloses a method and a system for determining binocular scene flow based on semantic segmentation. Firstly, the scene in binocular image is semantically segmented, and the semantic optical flow is calculated by adding semantic segmentation label information, then the disparity information is calculated by semi-global matching algorithm, and then the motion parameters of countless facet regions are calculated and optimized by combining the semantic optical flow and disparity information fitting. In the process of optimization, the initial scene flow is obtained by superpixel segmentation, and then the motion of the superpixel blocks in the semantic tag is optimized, so the motion of the superpixel blocks in the semantic tag is consistent and the edge information of the moving object is protected well. Semantic information is added into the optical flow information, so that the edge of the object is protected, and the reasoning process of the occlusion problem is greatlysimplified. In addition, the motion inference at the semantic tag level makes the scene flow of pixels on the surface of the same moving object approximately consistent, and ultimately the goal of optimizing the scene flow is achieved.

A computer-implemented depth estimation method based on non-parametric Census transform with adaptive window patterns and semi-global optimization. A modified cross-based cost aggregation technique adaptively creates the shape of the cross for each pixel distinctly. In addition, a depth refinement algorithm fills holes within the estimated depth map using the surrounding background depth pixels and sharpens the object boundaries by exerting a trilateral filter to the generated depth map. The trilateral filter uses the curvature of pixels as well as texture and depth information to sharpen the edges.

The invention discloses a method for controlling a dynamic surface of a flexible joint mechanical arm. The method comprises the following steps of: 1, analyzing a flexible joint mechanical arm system model, and constructing; 2, controlling and designing the dynamic surface of the flexible joint mechanical arm; 3, inspecting tracking performance, and adjusting parameters; and 4, finishing the design. By the method, virtual control is gradually designed for a flexible joint mechanical arm control system model, a first-order low-pass filter is arranged in each step, and the dynamic surface of the flexible joint mechanical arm can be controlled, so that the phenomenon of differential explosion controlled by reverse thrust is eliminated, the semi-global stability of a closed-loop control system can be ensured, and a preset track can be quickly and accurately tracked by the angle of a connecting rod of the flexible joint mechanical arm at the same time. The method has a wide application prospect in the technical field of automatic control.

The invention relates to a docking ring circle center extraction method based on a close-range short-arc image. The docking ring circle center extraction method comprises the following steps: carrying out epipolar rectification on a binocular image containing a short-arc docking ring, dividing a threshold by using a standard deviation method, extracting a ring surface by means of regional attributes, and then extracting inner and outer edges; carrying out dense reconstruction on the extracted ring surface region by using a semi-global matching method to obtain three-dimensional point cloud in a camera coordinate system; calculating a ring surface normal vector of the point cloud, and projecting a coordinate in a plane vertical to the normal vector; distinguishing the inner and outer edges in a new plane, and respectively carrying out perfect circle fitting on the inner and outer edges; and finally, obtaining an accurate circle center coordinate of the docking ring by use of concentric ring constraint according to obtained centers and radiuses of the inner and outer edges. According to the docking ring circle center extraction method provided by the invention, from the characteristics of the docking ring, three-dimensional point cloud data are directly projected into a normal incidence spatial plan, ellipse fitting is simplified to circle fitting, and meanwhile, error points are eliminated by constraint conditions of inner and outer rings, and the docking ring circle center extraction method has the advantages of accurate result and small calculated amount.

The invention discloses an adaptive error symbol integration robust repetitive control method for an electromechanical servo system, which comprises the steps of establishing a mathematical model of the electromechanical servo system; constructing a system design model; and designing an adaptive error symbol integration robust repetitive controller and a performance theorem and stability certification of the adaptive error symbol integration robust repetitive controller. The control method disclosed by the invention can enable the electromechanical servo system to acquire semi-global progressive tracking performance. In addition, compared with a traditional internal mold principle based linear respective control method, the adaptive error symbol integration robust repetitive control method can also effectively reduce the sensibility of the repetitive controller for noises and avoid a high memory requirement of the controller.

The invention provides a coastline super-resolution mapping method and a coastline super-resolution mapping system based on semi-global optimization. The method mainly comprises the following steps ofacquiring an initial coastline image and a reference image, performing image preprocessing, image fusion and image registration, combining the change trend of an overall coastline form and the gray level change of the periphery of an initial coastline, extracting the change control point of the coastline, and dividing the initial coastline into a plurality of coastline segments; in each of the plurality of coastline segments, acquiring a sub-pixel positioning result in a coastline neighborhood window, and fitting the sub-pixel positioning coordinates of all points in the same section into a smooth curve section; combining all curve segments together to obtain a complete coastline vector result, and completing the super-resolution mapping of the coastline. According to the invention, a sub-pixel positioning method based on a sub-pixel positioning method of a local area and capable of being adapted to a high-curvature coastline environment is provided. The method is high in positioningprecision and can be applied to coastlines with different curvatures. The result accuracy of the method is improved.

The present invention is related to the processing of stereo pairs (images obtained simultaneously from two cameras), namely, to methods and devices for processing stereo images. The technical result of the invention is creation of a method and a device for processing high-resolution stereo images with improved efficiency (performance) using a limited amount of memory with the help of a hardware accelerator for calculating the disparity map using a semi-global stereo matching algorithm with three-stage post processing (peak detection, interpolation and median filtering), which requires placing only a few strings (from 4 to 24 at different stages of calculating) in the local memory, which allows to obtain a high-quality disparity map in real time, and also by placing programmable cores of signal processors into the device, which prepare data for calculating the disparity map (rectification of images) and final processing of data using video analytics algorithms, and the hardware accelerator, which minimizes the transfer between external memory and the device, since the left and right images are fully loaded only once, and the results of the processing are data structures of a much smaller volume.

In order to meeting the requirement of binocular distance-measurement at night, the invention provides a distance-measuring system and a distance-measuring method based on a shimmer binocular camera.Considering the defect of low signal noise ratio of shimmer images, the distance-measuring method comprises the following steps: performing pretreatment to reduce image noise, fully utilizing the color and texture information of global image in a feature matching and optimizing process, reducing the error matching effect caused by the local noise; combining the calculation result of the Census descriptor and color feature with a semi-global matching optimization algorithm, the robustness of feature extraction and the accuracy of feature matching are enhanced. The distance-measuring system andthe distance-measuring method have night shimmer distance-measuring ability at night and can realize the night accurate distance-measurement.

A method for generating a block-based image histogram from data compressed by JPEG, MPEG-1, and MPEG-2, or uncompressed image data employing block-based linear quantization to generate histograms that include color, brightness, and edge components. The edge histogram, in particular, includes the global edge features, semi-global edge features, and local edge features. The global edge histogram is based on image blocks of the entire image space. The local edge histogram is based on a group of edge blocks. The semi-global edge histogram is based on the horizontally and the vertically grouped image blocks. A method for generating block-based image histogram with color information and brightness information of image data in accordance with an embodiment of the present invention extracts feature information of an image in terms of the block and updates global histogram bins on the basis of the feature information. The method for generating block-based image histogram with color information and brightness information of image data minimizes quantization error by employing linear weight and updates values of histogram bins. The error that occurs at a boundary between bins of the histograms and the linear weight depends on the distance between the histogram bins.

The invention discloses a landslide detection method based on unmanned aerial vehicle point cloud. The landslide detection method comprises the following steps: capturing a high-resolution geographicmark image of a landslide through unmanned aerial vehicle equipment; refining parameters estimated in the SFM process through an SFM program and a beam adjusting method; generating dense three-dimensional point clouds for each observation epoch by using an image captured only in the specific area through a semi-global dense matching process; calculating the normal distance between the two point clouds obtained at any different time periods, and detecting the volume surface change by adopting a point-to-point three-dimensional corresponding relation; and finally, through comparison of the pointcloud landslide steep slopes obtained at different time periods, calculating the displacement rate in the horizontal direction, and detecting the point cloud based on low-altitude, unmanned, aviationand vehicle images. According to the landslide detection method, a large amount of images from different data sources can be easily processed without a large amount of ground control point information or further processing. The research result has a certain reference value for landslide research.

A robust self-adaptive dynamic surface control method for an adjustable metal cutting system is characterized by comprising the steps of description of an adjustable metal cutting system mathematical model, a hysteresis model and a neural network system, design of a self-adaptive dynamic surface controller and the like. By means of an introduced error transformation function, control accuracy can be specified at will, so that accurate control over the cutting depth of a cutter is realized; under the condition that a system model is not completely known, approach to unknown terms is realized through an RBF neural network; estimation of the norm of an unknown parameter vector is used for replacing estimation of an unknown parameter ground vector, so that the computation burden of the system is greatly relieved; by the adoption of the strategy that the self-adaptive dynamic surface technology is combined with the error transformation function and an RBF, the hypothesis of time lag is relaxed, it is guaranteed that tracking errors and the transient process can be within any specified index at the same time, the problem of 'differential explosion' of the inverse method is eliminated, semi-global uniform ultimate boundedness of system signals is guaranteed, and the robust self-adaptive dynamic surface control method has the advantages of being scientific and reasonable, high in control accuracy, applicable and the like.

Systems and methods are provided for intrusion detection, specifically, identifying masquerade attacks in large scale, multiuser systems, which improves the scoring systems over conventional masquerade detection systems by adopting distinct alignment parameters for each user. For example, the use of DDSGA may result in a masquerade intrusion detection hit ratio of approximately 88.4% with a small false positive rate of approximately 1.7%. DDSGA may also improve the masquerade intrusion detection hit ratio by about 21.9% over convention masquerade detection techniques and lower the Maxion-Townsend cost by approximately 22.5%. It will also improve the computational overhead.

A method for generating a block-based image histogram from data compressed by JPEG, MPEG-1, and MPEG-2, or uncompressed image data employing block-based linear quantization to generate histograms that include color, brightness, and edge components. The edge histogram, in particular, includes the global edge features, semi-global edge features, and local edge features. The global edge histogram is based on image blocks of the entire image space. The local edge histogram is based on a group of edge blocks. The semi-global edge histogram is based on the horizontally and the vertically grouped image blocks. A method for generating block-based image histogram with color information and brightness information of image data in accordance with an embodiment of the present invention extracts feature information of an image in terms of the block and updates global histogram bins on the basis of the feature information. The method for generating block-based image histogram with color information and brightness information of image data minimizes quantization error by employing linear weight and updates values of histogram bins. The error that occurs at a boundary between bins of the histograms and the linear weight depends on the distance between the histogram bins.

As a key component of 4D products, a digital surface model (DSM) has a wide use range and use value in the field of national basic mapping. In order to accurately, stably and efficiently generate a digital surface model, the present invention discloses a dense DSM generation method based on object-side semi-global multi-view image matching. The method uses feature matching and triangulation network (TIN) interpolation to establish an initial DSM, introduces multi-view image matching of object-side geometric constraints through object-side space grid division, forms the DSM by matching cost aggregation of object-side space three-dimensional coordinates, and finally uses a series of data post-processing to remove the mismatched area and fill the default elevation area. After a lot of experiments, the method greatly improves the accuracy, reliability and efficiency of digital surface model matching.

To improve the performance for determining obstruction of a stereoscopic system using two cameras or more, a hybrid of local and semi-global methods is provided. For each stereoscopic image formed from simultaneous left and right images, a breakdown of each left and right image into corresponding sectors is applied. Obstruction level is determined by a disparity map by sector, based on left or right images, and in which a disparity is assigned to each pixel corresponding to the best matching score. A determination of density by sector of the disparity map is carried out by reference to a fraction of pixels with a disparity considered to be valid. A state of obstruction of at least one camera is determined based on a weighted average of the probabilities of obscuring of the sectors of the disparity map obtained by comparison between the density of the sectors and a predefined density level.

A computer-implemented depth estimation method based on non-parametric Census transform with adaptive window patterns and semi-global optimization. A modified cross-based cost aggregation technique adaptively creates the shape of the cross for each pixel distinctly. In addition, a depth refinement algorithm fills holes within the estimated depth map using the surrounding background depth pixels and sharpens the object boundaries by exerting a trilateral filter to the generated depth map. The trilateral filter uses the curvature of pixels as well as texture and depth information to sharpen the edges.

The invention provides a semi-global self-adaptive control method aiming at non-standard nonlinear aircrafts. The semi-global self-adaptive control method comprises the steps that (1) a rigid aircraftlongitudinal dynamic system model is given; (2) a stable operating point is determined, and a local linearized system model of an aircraft system is obtained, a T-S fuzzy intelligent approximation technology is utilized to establish a T-S fuzzy intelligent aircraft dynamics model: and (3) the T-S fuzzy intelligent aircraft dynamics model is dynamically reconstructed to derive a T-S fuzzy intelligent aircraft system standard form based on relative degree; and (4) an effective self-adaptive controller is designed, the ideal performance of a controlled system is realized, that is, closed-loop stability and asymptotic output tracking.

The invention discloses an adaptive fuzzy dynamic surface control method for a time-delay interconnected large-scale system. According to the invention, a fuzzy logic system is used to approximate an unknown time-delay function in the system, and reference signals are used to replace unknown time-delay signals in input of an approximator. The adaptive fuzzy dynamic surface control method provided by the invention for the time-delay interconnected large-scale system can process completely unknown time-varying time delay in system output, can ensure all signals in the system to be semi-global uniformly bounded, and can enable the tracking error to be converged within a small neighborhood comprising an original point.

The invention discloses a dual camera based automatic focusing method. The method includes the following steps: adopting a binocular camera that only has horizontal displacement to obtain a pair of binocular images at a default alignment plane, adopting a semi-global stereo matching method to solve the parallax of the binocular images, and partitioning the parallax to obtain a preliminary parallaxdiagram; correcting the parallax by using a weighted median filtering method, and removing a singular value in the parallax diagram to obtain a final parallax diagram; after a user selects a focusingarea, extracting a parallax value of the focusing area by using a focusing strategy in which a large screen priority mode and a close-range priority mode are combined, and calculating a focusing distance by using a trigonometric ranging method based on the parallax value and internal and external parameters of the binocular camera to achieve one-step focusing. The invention proposes the focusingstrategy in which the large screen priority mode and the close-range priority mode are combined for a single picture, the main body of the picture can be highlighted, and the one-step focusing can beachieved by using only a single pair of binocular images; and the method disclosed by the invention is small in calculation amount and good in real-time performance, and greatly improves the focusingspeed.

The invention discloses a dynamic surface control method for the opening of a main throttle valve of a steam turbine generator. The method comprises the following steps of: 1, analyzing a main throttle valve opening control system model, and constructing; 2, performing dynamic surface control and design on the opening of the main throttle valve of the steam turbine generator; 3, inspecting tracking performance, and adjusting parameters; and 4, finishing the design. The dynamic surface control method for the opening of the main throttle valve of the steam turbine generator is provided for the main throttle valve opening control system model, so that a preset track can be quickly and accurately tracked by the power angle of the steam turbine generator of a closed-loop system on the basis of ensuring the stability of a closed-loop semi-global system. The method has high practical value and a wide application prospect in the technical field of automatic control.

A method and system for generating a disparity map, a storage medium, and a computer program product are provided. The method for generating a disparity map includes the steps: acquiring a first leftview and a first right view; generating a first initial disparity map through an SGM (semi-global matching) acceleration algorithm according to the first left view and the first right view; generatinga second left view and a second right view according to the first left view and the first right view, wherein the second left view and the second right view are respectively identical to the views obtained after the first left view and the first right view are rotated by 180 degrees, or the second left view and the second right view are respectively identical to the views obtained after the firstright view and the first left view are rotated by 180 degrees; according to the second left view and the second right view, generating a second initial disparity map through the SGM acceleration algorithm; and according to the first initial disparity map and the second initial disparity map, determining a target disparity map. By using the SGM acceleration algorithm for multiple times, the methodfor generating a disparity map can realize the computational performance similar to the SGM algorithm on the premise of not increasing the memory pressure.

The present invention discloses a semi-global stereo matching method based on surface orientation priority, which solves the problem that the matching effect of the large-scale untextured indoor sceneis not ideal in the existing stereo matching technology. The method comprises the following steps: S1, the SGM algorithm; S2, the two-dimensional direction prior; S3, the three-dimensional directionprior; and S4, the surface normal prior. The method disclosed by the present invention is the prior on a simple surface, and can also be significantly improved in the matching of complex scenes containing bevels and weaker textures.

The present invention discloses a dense matching method using confidence weight-based bilateral filtering. The method comprises the following steps that: 1, a reference image and a reference image are selected according to a stereo image pair, and a traditional window operator is adopted to calculate a matching cost matrix; 2, the cost reliability of a central pixel is judged according to the distribution of gray level in a cost calculation window; 3, confidence weight-based bilateral filtering is performed on cost suspicious pixels, so that matching cost is obtained; and 4, a traditional semi-global dense matching method is adopted to quickly obtain an accurate disparity map according to the new matching cost. The dense matching method using confidence weight-based bilateral filtering of the invention is high in filtering speed and can effectively eliminate the problem of disparity edge mismatch commonly existing in a traditional stereo image dense matching algorithm. In the generated matching disparity map, the line features of the edges of ground object are obvious, and therefore, three-dimensional reconstruction accuracy is high.

To improve the performance for determining obstruction of a stereoscopic system using two cameras or more, a hybrid of local and semi-global methods is provided. For each stereoscopic image formed from simultaneous left and right images, a breakdown of each left and right image into corresponding sectors is applied. Obstruction level is determined by a disparity map by sector, based on left or right images, and in which a disparity is assigned to each pixel corresponding to the best matching score. A determination of density by sector of the disparity map is carried out by reference to a fraction of pixels with a disparity considered to be valid. A state of obstruction of at least one camera is determined based on a weighted average of the probabilities of obscuring of the sectors of the disparity map obtained by comparison between the density of the sectors and a predefined density level.

In order to meet the needs of binocular ranging at night, the present invention provides a ranging system and ranging method based on a low-light binocular camera. Taking into account the shortcomings of low signal-to-noise ratio of low-light images, the image noise is reduced through preprocessing. It also makes full use of the global color and texture information of the image during the feature matching and optimization process, weakening the impact of false matching caused by local noise; combining the results of Census descriptor and color feature calculations with the semi-global matching optimization algorithm to enhance the feature Extraction robustness and feature matching accuracy. The invention has the capability of low-light ranging at night and can achieve accurate ranging at night.

The invention discloses an information processing method and an electronic device. The electronic device comprises a first acquisition unit and a second acquisition unit. The information processing method comprises following steps: utilizing a first acquisition unit and a second acquisition unit to respectively acquire a first image and a second image of an object; setting up an energy function according to parallax field of the first image relative to the second image; calculating all pixel points and gradient values thereof within the first preset scope of pixel points; sequentially selecting N gradient values in a smallest order and utilizing pixel points corresponding to N gradient values as the direction for optimizing paths; calculating matching cost of each optimization path; setting up a semi-global energy function based on matching cost and an energy function; and calculating the parallax field corresponding to the object based on the semi-global energy function.

The invention provides a quick semi-global dense matching method and device. The quick semi-global dense matching method includes the steps that a base image and a matching image which are to be matched and have a epipolar line relation are obtained; matching calculation is carried out on the base image and the matching image according to a dense matching algorithm and the epipolar line relation; an obtained base image disparity map and an obtained matching image disparity map are denoised and refined; consistency detection is conducted on the base image disparity map and the matching image disparity map obtained through denoising and refining processing to obtain a matching base image disparity map. According to the method, the base image and the matching image are calculated according to the dense matching algorithm and the epipolar line relation, the two obtained disparity maps are denoised and refined, noise in the disparity maps is filtered out, consistency between the object boundary in the disparity maps and the object boundary in the original images is kept, left-right consistency detection is realized fast, and it is unnecessary to conduct two individual left-right image matching; the matching time is shortened on the premise of considering matching quality and matching speed at the same time.