1938 results about "Point set" patented technology

The invention relates to a vector-relation-based method for calibrating single-line laser radar and a CCD camera. Point set information of the laser radar for scanning a V-shaped target is extracted in a laser coordinate system, and direction vectors and intersection coordinates of straight lines in two different planes of the target are obtained by means of straight line fitting; the CCD camera is used for capturing images in a camera coordinate system, target plane equations and an equation of a plane passing through an original point and laser radar scanning lines are obtained by processing image information, a straight-line equation of laser radar scanning is built, and furthermore, the direction vectors and the intersection coordinates of the straight lines are obtained; finally, calibration is finished according to the relations between direction vectors and the intersection coordinates of the straight lines corresponding to the different coordinate systems. According to the method, no object in a calibration scene needs to be moved, collection of all calibration data can be completed at a time, and calibration efficiency is improved greatly. According to the method, the direction vectors of the straight lines of the laser scanning target planes under the coordinate systems of sensors to be calibrated are obtained directly, calibration precision is guaranteed, and meanwhile the calibration algorithm is simplified.

Methods, apparatus and computer program products provide efficient techniques for reconstructing surfaces from data point sets. These techniques include reconstructing surfaces from sets of scanned data points that have preferably undergone preprocessing operations to improve their quality by, for example, reducing noise and removing outliers. These techniques include reconstructing a dense and locally two-dimensionally distributed 3D point set (e.g., point cloud) by merging stars in two-dimensional weighted Delaunay triangulations within estimated tangent planes. The techniques include determining a plurality of stars from a plurality of points p_i in a 3D point set S that at least partially describes the 3D surface, by projecting the plurality of points p_i onto planes T_i that are each estimated to be tangent about a respective one of the plurality of points p_i. The plurality of stars are then merged into a digital model of the 3D surface.

An apparatus and method for generating a path using a limited memory size are provided. An approximate path is generated based on a reduced grid map generated by reducing an original grid map. Then, an approximate path is mapped onto the original grid map, and the mapped path is enlarged and divided into a plurality of sections based on an available memory size used for path calculation. Based on a start point and a destination point set in each of the divided sections, a detailed path in each of the sections is generated.

Method includes calculating a mean z coordinate value for points within the point cloud. An initial set of points is selected which have z coordinate values which deviate from the mean by at least an initial value. Thereafter, a triangulated irregular network (TIN) is constructed using the initial set of points. The method continues by determining if there is a significant point that exists among the points contained within an x, y extent of each triangle. If so, the TIN is updated to include the initial set of points and any significant points determined to exist within the triangles that form the TIN. Thereafter, the method continues by repeating the determining and the updating steps until there are no additional significant points found within the triangles.

The invention discloses an automatic registration method for three-dimensional point cloud data. The method comprises the steps that two point clouds to be registered are sampled to obtain feature points, rotation invariant feature factors of the feature points are calculated, and the rotation invariant feature factors of the feature points in the two point clouds are subjected to matching search to obtain an initial corresponding relation between the feature points; then, a random sample consensus algorithm is adopted to judge and remove mismatching points existing in an initial matching point set to obtain an optimized feature point corresponding relation, and a rough rigid transformation relation between the two point clouds is obtained through calculation to realize rough registration; a rigid transformation consistency detection algorithm is provided, a local coordinate system transformation relation between the matching feature points is utilized to perform binding detection on the rough registration result, and verification of the correctness of the rough registration result is completed; and an ICP algorithm is adopted to optimize the rigid transformation relation between the point cloud data to realize automatic precise registration of the point clouds finally.

Method and system for registration of a two dimensional image data set and a three-dimensional image comprising point cloud data. The method begins by cropping a three-dimensional volume of point cloud data comprising a three-dimensional image data to remove a portion of the point cloud data comprising a ground surface within a scene, and dividing the three-dimensional volume into a plurality of m sub-volumes. Thereafter, the method continues by edge-enhancing a two-dimensional image data. Then, for each qualifying sub-volume, creating a filtered density image, calculating a two-dimensional correlation surface based on the filtered density image and the two-dimensional image data that has been edge enhanced, finding a peak of the two-dimensional correlation surface, determining a corresponding location of the peak within the two-dimensional image, defining a correspondence point set; and storing the correspondence point set in a point set list. Finally, a transformation is determined that minimizes the error between a plurality of the correspondence point sets contained in the point set list.

The invention discloses an automatic depth-image registration method, which comprises the following steps: proceeding triangularization method for depth image; transmitting point cloud data into triangle grid data; finding the boundary point in the depth image according to the triangle grid data; calculating the character value of non-boundary vertex in the depth image; extracting character point set with projected surface character; finding the mating relationship as corresponding point among character points of two depth images; finding at least three couples of corresponding vertex; calculating the estimating value of movement of two depth images according to the corresponding point; adopting modified ICP algorism to optimize the result; finishing the precise registration of two depth images. The invention improves the speed and precision of registration, which reduces the calculating quantity with simple course.

A control apparatus calculates a calibration value based on a position in the robot coordinate system 41 and a position in the vision coordinate system42, for at least three teaching points set within a calibration area. Markers 21 of two of the three teaching points have the same inclination in relation to an optical axis of a camera 3 as a visual sensor, and the two points are placed on different positions of the same plane normal to the optical axis. The remaining one of the three teaching points other than the two points is set such that the inclination of the marker 21 in relation to the optical axis is different from that of the two points. As a result, influence of a large quantization error in the optical axis direction as a measurement error of the camera 3 can be reduced.

The invention discloses a fast image recognition method of an insulator contour, comprising the following steps: (1) transforming a taken color image to a gray image through brightness calculation and extracting the edge contour of the image, and obtaining the shape of a known region after the extraction; (2) carrying out ellipse fitting on the edge contour of the known region, utilizing hough transform to detect a boundary curve and obtain each parameter of a prolate axis, a minor axis and a central point of an ellipse; (3) carrying out threshold processing on contour area, and setting a proper area threshold according to the contour area; (4) carrying out linear fitting on the center of the ellipse, and fitting a line through a two-dimensional point set by seeking sumi rho(ri); and (5) demarcating and outputting insulator pixels. The invention aims at specific requirements of patrol and examination of a helicopter or a robot to an electric transmission line, realizes real-time and precise extraction of the insulator, provides solid foundation for realizing close shot and part defect diagnosis of a follow-up camera, and has favorable theory and application prospect.

A system and method for describing local area geo-reference features and landmarks in providing high resolution asset location information. Geo-image data is integrated to a mapping application and geo-reference data to add more detailed scale levels to the map. The geo-image data includes geo-images and its features to provide more detailed references to the asset and support the larger references of the geo-reference data. To describe a geo-reference landmark, an original landmark representation is selected with a center point and a radius. The asset location points located at the original landmark representation are compiled along with the asset location points generated by events occurring at the landmark to create a point set. The point set replaces the original landmark representation when a prescribed number of points is reached. The asset location points that are within a specified distance from any of the points in the point set are added to the point set to complete the landmark representation. The geo-image data and landmark representation data are combined to provide high resolution asset location information.

The invention discloses an image searching method, which comprises a training part and a searching part, wherein the training part comprises the following steps of: the extraction of characteristic points, the supplementation of the characteristic points and the determination of matching relationships, the generation of similar point set, the clustering of the characteristic point sets and the generation of characteristic vectors of each image in an image database; and the searching part comprises the following steps of: extracting the characteristic points of a picture to be retrieved and generating the characteristic point sets; calculating distances between each characteristic point descriptor vector and corresponding cluster centers, and determining a cluster where a current characteristic point belongs by using a smallest distance; calculating the frequency ni of each cluster where the characteristic points of the picture to be retrieved belong; based on the frequency ni of the clusters where the characteristic points of the picture to be retrieved belong, and the probability logarithm wi of each cluster, generating and unitizing the characteristic vector; and calculating Euler distances between the characteristic vector of the picture to be retrieved and the characteristic vectors of each image in a picture library, and selecting the image output with the smallest distance as a searching result.

The invention discloses a method and a device used for making a map. The method comprises the following steps of responding to the operation of detecting that a user is in a selected area to be markedon the map to be marked, and finding geographical position information corresponding to the area to be marked in the geographical position information list corresponding to the stored map to be marked; acquiring a road image sequence and a track point set collected by a in-vehicle camera, wherein each track point in the track point set is recorded when the in-vehicle camera collects each frame ofroad images in the road image sequence; according to the geographical position information of the area to be marked and the track point set corresponding to the road image sequence, extracting a target image frame corresponding to the area to be marked from the road image sequence; and responding to a condition that that a marking operation which is performed by a user reference target image frame on a marked object in the area to be marked is detected and generating a marked file used for storing the position parameter of the marked object. In the invention, map marking efficiency can be increased.

The invention provides a SRP-PHAT multi-source spatial positioning method. The method comprises the steps that the number and spatial positions of all microphones in a uniform circular microphone array are assumed to be unchanged in the data obtaining process at first, the isotropous microphones are evenly distributed on a circumference which has the radius r and is located on an x-y plane, the direction of arrival of a plane wave s is expressed by polar coordinates, the original point of the coordinate system is located on a circle center position of the circular array, multiple sound source signals are divided into non-overlapped time frequency point sets, each time frequency window contains only one movable source signal, and weak W orthogonal separation conditions are met; a Hamming window is selected, a controllable response power function is calculated and a target function is obtained through a SRP-PHAT algorithm, wave beams are controlled to carry out scanning in all the possible receiving directions, and the wave beams output the direction value with the maximum power to obtain the direction of a sound source, so that the DOA estimation of the multiple sound sources has the better separating performance in the strong noise and moderate reverberation acoustic environment, the real peak value is obviously outstanding, and high positioning precision is achieved.

The present invention provides an intersection condition-orientated unmanned vehicle trajectory planning method based on the Bezier curve and the VFH algorithm. The method includes the following steps that: 1) the starting point pose P0 (x0,y0,theta0) and destination point pose P3 (x3,y3,theta3) of current trajectory planning are acquired; 2) a trajectory cluster A1 from the starting point pose P0 (x0,y0,theta0) to the destination point pose P3 (x3,y3,theta3) is generated through adopting a three-order Bezier curve model; 3) the trajectory cluster A1 is screened according to a maximum curvature constraint, so that a trajectory cluster A2 is obtained, collision detection is performed on A2, so that a collision-free trajectory cluster A3 is obtained; 4) if A3 is not empty, an optimal trajectory is selected from A3 according to a trajectory smoothest principle and is outputted to a control layer, and the method is terminated, otherwise, the method shifts to step 5; 5) a movement region in the original VFH algorithm is improved, so that a fan-shaped movement region is built; 6) obstacle information is utilized to establish a grid map; 7) the fan-shaped movement region is divided into a plurality of fan-shaped regions, and whether an obstacle exists is judged; 8) the Bezier curve is used in combination, and optimal trajectory points are selected; and 9) with a discrete point set generated in the step 8 adopted as control points, a B-spline curve is generated, and the B-spline curve is adopted as the final trajectory of an unmanned vehicle.

A lane robust identification method for warning departure is that first conducts conditional edge detection on the left and right local windows, and constructs the corresponding gradient direction map. Then, according to the histogram processing method, the gradient direction range of lane edge points on every local window. Aiming at the continuity features of direction and space of lane edge points, the filtering algorithm of the candidate and effect point collection is put forward and every window is filtered. Finally, according to the established effective point collection corresponding to each window, the rapid and accurate extraction of lane symbol is realized though the Kalman filter method based on scalar processing.

The invention discloses a non-overlapping field-of-view camera gesture calibration method based on point cloud feature map registration. The method comprises the following steps that: (1) carrying outbasic calibration on a plurality of cameras of a non-overlapping field of view to obtain an internal reference; (2) utilizing the plurality of cameras to carry out environment detection and synchronous positioning and mapping, constructing a point cloud map, and extracting a key frame to solve the pose matrix of the camera; (3) extracting an image frame from the key frame of one camera, carryingout similarity detection on the key frames of other cameras, constructing a matching frame point set and a matching point pair set, and carrying out projection error minimization on the projection ofthe point cloud map point on the image frame and the practical pixel coordinate; and (4) carrying out feature matching on a frame near the matched frame, blending all feature points, carrying out global optimization and iterative solution on a relative pose matrix, selecting a correction parameter according to a practical situation, and carrying out final gesture calibration on the camera. By useof the method, the problems of high calibration work intensity, low work efficiency and low accuracy of a traditional calibration method are solved.

Disclosed is a method and apparatus to provide for fingerprint minutiae matching using scoring techniques. A plurality of minutiae in a fingerprint image is defined. A score associated with each minutia corresponding to the validity of each minutia is estimated. The fingerprint image is then matched against one or more sample fingerprint images utilizing a partial point set pattern matching (PSPM) algorithm.

The invention discloses a calculation method for force feedback in a virtual system, which comprises the following steps: step 1: a virtual environment comprising a virtual space, a virtual object and a virtual tool is established, attributes of the virtual tool are set, and a point set model which includes a plurality of mass points and surrounds the virtual tool is constructed; step 2: the virtual tool and a force feedback device are bound, the motion states of the virtual tool and the virtual object in the virtual space are tracked, whether the virtual tool and the virtual object collide or not is judged, if yes, step 3 is implemented; the step 3: the line speeds and the motion speeds before and after the collision of all the collision mass points of the virtual tool during the collision are respectively calculated, and the received impact during the collision process is also calculated; step 4: the resultant forces and the resultant moments of forces of all the collision mass points of the virtual tool are calculated and sent to the force feedback device. The calculation method takes full account of the self-rotation features of a virtual surgical instrument and can be applied in a surface model or a body model adopted in the virtual surgery.

The invention discloses a semi-supervised multi-spectral remote sensing image segmentation method based on spectral clustering; the segmentation process includes that: (1) the characteristics inputted to the multi-spectral sensing image are extracted; (2) N points without labels and M points with labels are randomly and evenly sampled from a multi-spectral sensing image with S pixel points to form a set n which is the summation of N and M, wherein M points with labels are used for creating pairing limit information Must-link and Cannot-link sets; (3) the sampled point set is analyzed through semi-supervised spectral clustering to obtain the class labels of the n (n=N+M) points; (4) the sampled n (n=N+M) points are used as the training sample to classify the rest (S-N-M) points through nearest-neighbor rule, each pixel point is assigned with a class label according to the class of the pixel point and is used as the segmentation result of the inputted image. Compared with prior art, the invention has good image segmentation effect, strong operability, improves the classification accuracy, avoids searching the optimum parameters through repeated test, has small limit on image size and is better applicable to the segmentation of multi-class multi-spectral sensing images.

The invention discloses a unmanned aerial vehicle (UAV) path determination method and apparatus for reconstructing a three-dimensional model, the method comprising the steps of: constructing a three-dimensional point model forming an outline of a captured building; determining a photographing points of a flight path of the UAV around the building so that a camera on the UAV can capture a corresponding point set covering the three-dimensional point model at each photographing point and the overlap ratio of the point sets captured by the camera at adjacent photographing points is greater than an overlap ratio threshold; instructing the UAV to fly along the flight path and instructing the camera to photograph the building at corresponding photographing points. The method can calculate minimum photographing point sets satisfying a three-dimensional reconstruction requirement just by acquiring the height and the two-dimensional orthograph of a three-dimensional reconstructed target, so as to provide guidance for a three-dimensional reconstruction data acquisition process, to ensure that the acquired images meet the three-dimensional reconstruction requirement, to avoid the collection of redundant image information, and to improve the efficiency of the three-dimensional reconstruction process.

A medical diagnostic imaging apparatus is provided that is capable of accurately tracking motions of a moving organ that moves periodically over a plurality of periods.

The medical diagnostic imaging apparatus includes a matching computation unit for performing a matching computation between a template extracted containing a tracking point on one image and another image, and a template extracting unit for extracting, from the other image, a region correlated with the template as a template of the other image by the matching computation, whereby a movement of the tracking point is tracked based on the extracted template. The template extracting unit extracts, as a key template, a region containing one or more tracking points set on an image at least one time phase within a motion cycle of the moving organ. The matching computation unit performs the matching computation using the key template in the vicinity of the time phase at which the key template is extracted.

The invention discloses an electrical power system dynamic state estimation method based on an unscented transformation Kalman filter, which comprises the following steps: selecting a sigma point sampling strategy according to statistics of input variable to obtain a sigma point set of the input variable and corresponding weight; secondly, performing non-linear transformation on each sigma point in the sampled sigma point set of the input variable to obtain a transformed sigma point set; and finally, performing weight processing on the transformed sigma point set to obtain the statistics of output variable. The method reduces the application difficulty, and simultaneously can obtain higher accuracy and robustness.

The invention relates to the technical field of computers, and provides a method for searching interest points in a designated area of a map by a hand-drawing way. The method comprises the following steps: step 1 of providing a drawing interface on a client electronic map surface to provide a hand-drawing area for users; step 2 of judging type of the hand-drawing area; step 3 of acquiring a screen pixel point set in the hand-drawing area; step 4 of converting the screen pixel point set into a map longitude-latitude point set; step 5 of transmitting the map longitude-latitude point set to a background server; step 6 of calculating an external rectangle and a centre point according to the map longitude-latitude point set by the server, and searching interest points of the external rectangle; step 7 of screening the interest points in the hand-drawing area to form a searching result set. According to the method provided by the invention, users can randomly designate areas by the hand-drawing way on an electronic map of the client to search interest points.

The invention relates to the quantitative analysis and/or visualization of the relative motion of objects in particular of the relative motion of one or several objects inside a living entity, for instance the human body or a living cell. The invented system and method allow to quantify and visualize the motion of these objects with respect to the parts of the living entity, which can deform and move itself with respect to each other. Furthermore, the method allows to identify movements and deformations which correspond to situations with a particular meaning for the living entity, for instance predicting complications in a disease progress, etc. An important application is the analysis of motion and deformation of stent-grafts introduced after endovascular repair of aneurysms. Here, the occurrence of deformations leading to graft-limb occlusions and of migrations of the stent-graft leading to so-called endoleaks can be predicted in an early stage. This allows an early intervention, hence, avoiding more severe problems. The motion is calculated from pairs of images corresponding to different points in time using semi-automatic steps to extract point sets (or binary images) and an automatic procedure to determine the motion and deformation of the point sets and to describe it quantitatively. An important part of the method is the visualization allowing the user to have an immediate impression of the occurring movements and deformations.

The invention discloses a vehicle tracking method based on machine learning and optical flow. A vehicle model is obtained through one-off off-line training and used for detecting vehicle block mass Blobs in a video flow in real time, bidirectional pyramid optical flow tracking is performed on calculation characteristic point sets of all the vehicle mass block Blobs, and results of optical flow tracking in the forward direction and the backward direction are analyzed and filtered, so that multiple targets are stably and accurately tracked to form vehicle tracks. According to the complete vehicle tracking solution, the vehicle tracking method based on machine learning and optical flow can be widely applied to the fields of intelligent traffic, electronic polices, video monitoring, unmanned driving and others; by the utilization of the tracking method, a user can solve the classic problems in an existing tracking algorithm well, the multiple targets, such as long-period vehicle staying, size scale changing, shadowing, local shielding and touching, can be stably and accurately tracked; particularly, the vehicle tracking method has the good effects under the conditions of severe weather, a low illumination level and a high noisy point.

The subject matter discloses a method of determining whether a point in a computerized image is visible from a viewpoint; said image is represented as a point cloud, the method comprising: performing inversion on a the vicinity of the point thus creating a computerized inversed objects each point in the vicinity of the point is related to a parallel point in the computerized inversed object and obtaining a convex hull of the inversed object; the point is likely to be visible from the viewpoint in case it belongs to the point set composing the convex hull. The method is also useful for shadow casting and for determining the location of an image-capturing device within a volume

A program parallelizing apparatus, a program parallelizing method and a program parallelizing program capable of creating a parallelized program of higher parallel execution performance. A fork point determination section converts an instruction sequence in part of an input sequential processing program into another instruction sequence to produce at least one sequential processing program. With respect to each of the input sequential processing program and the one or more programs obtained by the conversion, the fork point determination section obtains a set of fork points and an index of parallel execution performance to select a sequential processing program for parallelization and a fork point set with the best parallel execution performance index. A fork point combination determination section determines an optimal combination of fork points included in the fork point set determined by the fork point determination section. A parallelized program output section creates a parallelized program for a multithreading parallel processor from the sequential processing program for parallelization based on the optimal combination of fork points determined by the fork point combination determination section.