383 results about "Geometric relations" patented technology

The invention discloses a method and device for online detection of the size of a city rail train wheel set. A system is mainly comprises two 2D laser displacement sensors arranged along a train rail in a mirror symmetric mode, and two laser bijection switches arranged on the two sides of the same rail in a certain geometrical relation. The 2D laser displacement sensors detect and obtain tread contour lines, and the two laser bijection switches detect the wheel passing speed. The rim height and the rim thickness are worked out by extracting the tread contour lines of wheels passing through a detection system according to the geometrical relation. The coordinates of the lowest rim points of the detected tread contour lines of the wheels at different moments are extracted, the coordinates at the different moments are restored to coordinate values at the same moment on the condition that the speed is given, so that the circle where the top points of the rims of the wheels are located is fitted out, the two times of the height of the rims is subtracted from the diameter of the circle of the top points of the rims, and thus the diameters of the wheels are obtained. The method and device for online detection of the size of the city rail train wheel set are low in cost, simple in operation and high in non-contact type measurement precision.

The invention discloses a monocular vision range finding method based on geometric relation, and the method comprises the following steps: S1, calculating the distance between a section straight line of a target object and a camera lens in a horizontal plane; S2, calculating the distance between a target object and the optical axis of a monocular lens through the triangle similarity principle. According to the projection model of a camera, the method obtains the relation between a road surface coordinate system and an image coordinate system through geometric derivation, is simple in calculation process, is low in calculation complexity, and is lower in requirements for hardware. Meanwhile, the method can reach higher precision, and the error of the method is less than 0.5m. The method can effectively calculate the distance between the front vehicles or other obstacles under the conditions that the hardware configuration condition is very simple and almost no additional load and electric quantity is added, thereby achieving the effective avoidance. The method and device are good in application prospect, such as the technical field of automobile automatic driving or intelligent robot walking.

The invention relates to the technical field of three-dimensional point cloud data processing and three-dimensional scene reconstruction, and discloses a three-dimensional laser scanner and camera calibration method based on geometric constraint. The method comprises the following steps: (1) making a calibration board; (2) acquiring a three-dimensional point cloud and a two-dimensional image of the calibration plate; (3) calibrating a camera; (4) calculating a calibration board plane in a camera coordinate system; (5) building point-surface geometric constraint; (6) constructing line-point geometric constraint; (7) constructing surface-surface geometric constraint; (8) calculating a geometric mapping relation of the point cloud and the image. The method has the advantages of deeply analyzing a structure of the three-dimensional point cloud, meanwhile, solving the geometric mapping relation between the point cloud in a laser coordinate system and the image in an image coordinate systemthrough three types of thoughts including the point-surface geometric constraint, the line-point geometric constraint and the surface-surface geometric constraint, making full use of the geometric relation between the calibration board plane and a laser scanning point, and consequently making calibration of the three-dimensional laser scanner and the camera be more accurate and reliable.

It is an object of the present invention to provide a friction stir welding method and apparatus capable of maintaining a rotating tool and workpieces at a substantially constant geometrical relation for arbitrary curved surfaces having a three-dimensional shape, as well as a welded structure obtained thereby. The present invention resides in a friction stir welding method comprising joining workpieces while setting rotational angles of two rotational axes of a rotating tool which the two rotational axes are rotatable in intersecting directions or perpendicularly intersecting directions independently of rotation of the rotating tool, detecting a normal line direction with respect to joint surfaces of the workpieces and a tangential direction of a joint line, and joining the workpieces in three-dimensional directions while setting, on the basis of the detected normal line direction and tangential direction, an angle relative to a normal line direction, as well as a tangential direction, at a tip end of the rotating tool, and also resides in a friction stir welding apparatus using the said method.

The invention provides a steel rail abrasion measuring method based on a dynamic template. The method comprises the steps of installing a charge coupled device (CCD) camera and a fan-shaped laser light source above the inside of two rails respectively; demarcating each CCD camera and an optical plane parameters; obtaining space coordinates of each pixel point of rail outlines in an image according to a rail outline space computation model; extracting feature point coordinates at the lower end of a rail waist and a rail head; generating a rail outline standard template based on feature points; and contrasting a rail measurement outline to the standard template to obtain abrasion value. The method can build a measurement coordinate system by determining two feature points of a measurement rail according to geometrical relationship of a standard rail outline, can fast and accurately obtain the standard template, does not need conduct aligning analysis of the measurement outline and a standard design outline, solves the problem that method based on a static template is difficult to match, greatly improves accuracy of abrasion measurement, reduces operation quantity of image analysis and processing and has good stability.

The invention discloses a method for quickly positioning and extracting one-dimensional and two-dimensional code graphics aiming at digital images. The method comprises the following steps of: analyzing envelopes of a high-frequency component for observing an image signal, extracting a region with an obvious upper and lower envelope difference under each scale as a probable bar code region, further analyzing the probable bar code region, extracting geometric parameters from partial information and performing adaptive binarization, supplying a result to a subsequent scanning module, and sampling and decoding to output information stored by a bar code according to a geometric relation of a black and white module. Equipment required in the method is relatively simple and can be suitable for complicated backgrounds and illumination conditions; and the observed one-dimensional and two-dimensional code graphics are quickly and intelligently processed on the basis of acquisition of video signals.

A computer-implemented method and system for generation of page templates are provided. The method includes providing a document in computer memory. Using a computer processor, page elements within the document are identified and labeled. For each page of the document, a set of geometric relations between pairs of page elements co-occurring on the page is computed, and the set of geometric relations is associated with the page. The method also includes generating a set of page template candidates based at least in part on the computed geometric relations, selecting page templates from the set of page template candidates, and outputting the selected page templates.

A system and method for identifying regular geometric structures in a document page are disclosed. In the method, for a document page for which a set of page elements have been identified, the method includes identifying, where present, geometric relations among a subset of the page elements, from a predefined set of geometric relations, and a geometric structure comprising regular rows and regular columns, based on the identified geometric relations. Constraints of a definition of a regular geometric structure are applied to the identified geometric structure and, where the subset of page elements includes regular rows and regular columns forming a geometric structure which meets the constraints of the definition of a regular geometric structure, the subset of the page elements is identified as forming a regular geometric structure and may be labeled or tested to determine if it can be expanded by adding one or more rows or columns.

The invention discloses an unmanned aerial vehicle formation path planning algorithm based on a three-dimensional global artificial potential function. The algorithm is mainly used to solve problems of formation maintenance of an unmanned aerial vehicle, path planning, three-dimensional obstacle avoidance and the like under a three-dimensional space environment. The algorithm comprises the following steps of firstly establishing a mathematic model of a global potential function under a three-dimensional space; then according to an expected formation, establishing a formation geometry equation of the unmanned aerial vehicle under the three-dimensional space; and finally, establishing a formation unmanned aerial vehicle kinematics equation containing a formation constraint. In the method, through the formation geometry equation, a geometric relation of the plurality of unmanned aerial vehicles under the three-dimensional space is established; and a penalty function method is used to solve a constraint dynamics equation so as to acquire a flight path of the formation unmanned aerial vehicle. Compared to a traditional classic artificial potential function, by using the algorithm of the invention, a two-dimensional space limitation problem of a two-dimensional classic artificial potential function can be solved and problems that a local minimum value exists in a classic potential function and so on can be solved too. By using the algorithm of the invention, limitation of the two-dimensional classic potential function and path planning of the formation unmanned aerial vehicle can be effectively solved.

The invention discloses a UAV formation control algorithm based on the Lagrange's equation. An improved manual potential energy field is used in the aspect of formation UAV path programming, and motion of formation UAVs is seen as a constraint dynamic system in the formation maintaining aspect. When the constraint dynamic system is established, a spatial formation constraint equation is established according to a needed formation shape by utilizing spatial geometric relations of the UAVs relative to an inertia coordinate system, a Lagrange multiplier is introduced to establish a constraint dynamic equation set including the formation constraint formation UAVs, and certain stability is combined to eliminate the Lagrange multiplier directly and solve the Lagrange multiplier. The spatial geometric relation of the UAVs is established via the constraint equation, and the formation dynamic equation including the formation constraints is solved to obtain a flight track of the formation UAV to maintain an expected formation, and formation maintenance and transformation are relatively flexible and effective during flight of the UAV formation.

The invention discloses an omni-directional stereo vision three-dimensional reconstruction method based on Taylor series models. The method comprises the following: a step of calibrating a camera, which is to utilize a Taylor series model to calibrate an omni-directional vision sensor so as to obtain internal parameters of the camera; a step of obtaining epipolar geometric relation, which comprises the steps of calculating an essential matrix between binocular omni-directional cameras and extracting the rotation and translation component of the cameras; a step of correcting an outer polar line, which is to correct the outer polar line of a shot omni-directional stereo image so as to allow a corrected polar quadratic curve to coincide with an image scan line; and a step of three-dimensional reconstruction, which is to carry out feature point matching to the corrected stereo image and calculate the three-dimensional coordinates of points according to matching results. The method can be applicable to various omni-directional vision sensors, has the characteristics of wide application range and high precision, and can carry out effective three-dimensional reconstruction under the condition that the parameters of the omni-directional vision sensors are unknown.

Method for the preparation of diffractive lens with one single etching step and using one single etching mask. While the widths and intervals of the masked areas of the photo masks are decided under a geometric relation, an etching mask can be prepared on the substrate of the lens where the widths and the intervals of the masked areas can be determined. As the included angle between the etching mask and the plan of the material of the lens is in a certain ratio to the etching efficiency of the etchant to the substrate of the lens, a one step etching process can be developed whereby multilevel diffractive lens with required number, widths and heights of the levels can be obtained. This invention also provides an oxidation-isotropic etching process on the diffractive lens so prepared.

The present invention relates to an axial line correction method of a cylindrical workpiece. According to the method, the spatial relative position of the workpiece under a measurement coordinate system is determined based on the design of the reference point C0 of the end surface of the workpiece; the first correction deltax and deltay of the deviation of a positioning section ZA and a positioning section ZB of the workpiece on an X axis and a Y axis are realized through using two groups of symmetrically-correlated compensation points on the positioning section ZA and the positioning sectionZB of the workpiece; the outlines of the positioning section ZA and the positioning section ZB are resampled, so that sampling points are obtained, a center point O'A and a center point O'B are obtained through fitting calculation; with a straight line determined by the center point O'A and the center point O'B adopted as a reference axis phi of the cylindrical workpiece, a geometric relationshipwith the reference point C0 is built and is solved; and the calibration and correction of a relative deviation angle theta between the reference axis phi and the Z axis of the measurement coordinate system are realized. The present invention also provides a diameter measurement method of the sectioned section of a cylindrical workpiece. According to the diameter measurement method, a geometric relationship between the correction values deltax and deltay of positioning sections and a measured section is built; linear compensation values deltaxi and deltayi are obtained; the coordinates of a probe relative to a sampling point are calculated; integrated and automatic sampling on the outline of the measured section is realized; and a spatial projection and fitting algorithm is adopted to process sampling data to obtain the quantity value of the measured section.

The invention provides a front face image detection method which includes the steps of capturing a video image, preprocessing the image by conducting median filtering, illumination compensation and image edge processing, detecting a face based on a method combining a cascade classifier and key characteristic points, and sorting out a front face image by using the geometric relation of the key characteristic points on a two dimensional plane. The method improves the image preprocessing method in a conventional face detection process. Interference on original image characteristics is reduced on the premises of realizing illumination compensation and de-noising. The error detection rate of face detection system based on an AdaBoost cascade classifier is lowered through the improved face detection method. Weight is added to a partial gray scale model of characteristic points through gauss distribution functions, thereby increasing the efficiency of a facial key characteristic points positioning method. A front face image is sorted out based on facial characteristic points accuracy positioning and by using the planar geometric relation of the characteristic points on a two-dimensional image.

The invention discloses a method and device for recognizing image, which comprises the following procedures: detect a candidate area in an input image; divide recognition unit in the candidate area based on a basic recognition unit in a template image; the basic recognition unit refers to a partial image with much variety in the template image; the recognition unit refers to a partial image corresponding to the basic recognition unit in the template image of the candidate area; calculate a bar graph information of the recognition and/or relative geometric relation to determine the similarity between partial or all of the bar graph and/or relative geometric relation and that of basic recognition unit of the template image; judge whether there is the image of the object described in the template image in the input image according to the similarity. Therefore, the invention can be adopted to improve the accuracy for image recognition.

The invention relates to a sun vector resolving method based on a compound eye simulated multi-channel polarization sensor. The sun vector resolving method comprises the following steps: at first, designing a structure model of the compound eye simulated multi-channel polarization sensor; then designing the selection criterion of the degree of polarization, acquiring the degree of polarization information of observed points in sky by using the multi-channel polarization sensor, and selecting the degree of polarization measurement values of a certain amount according to the selection criterion,taking three values from the degree of polarization measurement values as a set of resolving inputs and determining the weight of the set of resolving inputs; next, establishing the geometrical relationship with sun vectors according to each channel mounting matrix, establishing the constrained relationship with all skylight maximal degree of polarization by measuring the degree of polarization to obtain a system of nonlinear equations; and at last, resolving corresponding sun vectors of the set of resolving inputs by the system of nonlinear equations, and resolving weighted average on the multiple groups of sun vectors, so as to resolve the sun vectors in a module system. The sun vector resolving method can be used in sunny and cloudless weather, can be applied in cloudy weather environment at the same time, and has high robustness and environmental suitability.

The invention discloses a method for measuring spherical object geometric parameters by use of lasers and a monocular camera. The method comprises the following steps: arranging the camera and the more than three lasers, enabling laser beams emitted by the lasers to irradiate on an object, wherein the laser beams are not coplanar and the orientation of the camera is the same as the directions of the lasers; defining a world coordinate system Ow and a camera coordinate system Oc, and determining an internal parameter matrix of the camera and a conversion relation between the camera coordinate system and the world coordinate system; defining an image two-dimensional coordinate system, enabling the camera to acquire points formed when the laser beams are irradiated on the object, and obtaining coordinates of the laser points under an the image coordinate system and circle center coordinates of the object on an image; and calculating geometric parameters of the object through a geometric relation and a camera-image conversion relation. Compared to a conventional monocular measurement method, the method provided by the invention has the following advantages: object information does not have to be obtained in advance, and the method is applied to measurement of non-texture non-cooperative object. Compared to a conventional binocular measurement method, the method provided by the invention has the advantages of higher efficiency and stability and better fault tolerance and robustness.

A method and a system are disclosed for querying a document collection based on the layout of only a fragment of the content of a document, specified as a query zone. The method includes providing an index for a collection of documents. In the index, content of a document page in the collection that has been decomposed into layout blocks is indexed according to representations of the blocks and one or more geometric relations between the blocks. A query is generated which is based on representations of blocks determined to be within the query zone and geometric relations between them. This is used to query the index to retrieve pages of documents in the collection which can each be expected to include a layout zone somewhere in the page that is similar in layout to the query zone.

The invention discloses a device and a method for measuring the liquid level height of molten silicon in a single crystal furnace, belonging to the technical field of semiconductor material detection. The device is characterized in that a crucible is arranged in a single crystal pulling furnace body; a conical heat insulation screen is arranged on the crucible in the single crystal pulling furnace body; an observation hole is formed in the top surface of the single crystal pulling furnace body, and through the observation hole, laser can enter the single crystal pulling furnace body and a photoelectric sensor can acquire an image; the optical axis of a lens is set to be perpendicular to the projection of a laser stripe on silicon liquid, the sum d' of the distance between one reference point and the laser stripe and the distance between the other reference point and the laser stripe is calculated, and the distance d between the lower edge of the heat insulation screen and the silicon liquid is calculated according to a geometric relation. According to the device and the method, laser is adopted as reference of measurement, and the laser stripe can be processed to be narrower, so that the measurement precision can be improved; the measurement precision is higher due to adoption of double reflection laser measurement; the laser incidence and the CCD (charge coupled device) imaging are carried out in a same incident hole, the laser is fixed together with a CCD, and the device disclosed by the invention lowers complexity in comparison with a method in which laser enters the single crystal pulling furnace body from a window and is received by the CCD from another window.

The invention discloses a vehicle collision prevention early warning method based on vision. The method comprises steps that two determination conditions including a lane line length and a gradient are added to a detection lane line to carry out Hough transform, and a lane line of a self vehicle is extracted; at a detection target vehicle portion, in combination with a normal distribution function, an OTSU method is employed to combine an improved method of a genetic algorithm (GA) to separate a target and the background; at a distance measurement portion, a method combining geometric relation projection with camera calibration is employed, danger determination is carried out according to a relative distance, and collision prevention early warning is realized. According to the method, the distance between the self vehicle and a front vehicle can be more accurately estimated, a driver is prompted through alarming to adopt measures for processing, and road traffic accidents can be greatly reduced.

The invention discloses a vision-based pose stabilization control method of a moving trolley, which fully considers about a kinematics model and a dynamics model of a trolley and a camera model. The vision-based pose stabilization control method comprises the following steps of: respectively obtaining an initial image and an expected image at a starting pose position and an expected pose position through a camera, and obtaining an existing image in a movement process in real time; by utilizing an antipode geometric relation and a trilinear restrain relation among shot images, designing three independent ordered kinematics controllers based on Epipolar geometry and 1D trifocal tensor by utilizing a three-step conversion control policy; finally designing a dynamic conversion control rule by taking outputs of the kinematics controllers as the inputs of the kinematics controllers by utilizing an retrieval method so that the trolley quickly and stably reaches an expected pose along a shortest path. The invention solves problems in the traditional vision servo method that the dynamics characteristic of the trolley is not considered during pose stability control and slow servo speed is slow, and the vision-based pose stabilization control method is practical and can enable the trolley to quickly and stably reach the expected pose.