Abstract: The invention discloses a deep learning-based temporal phase unwrapping method for fringe projection profilometry. First, four sets of three-step phase-shifting fringe patterns with different frequencies (including 1, 8, 32, and 64) are projected to the tested objects. The three-step phase-shifting fringe images acquired by the camera are processed to obtain the wrapped phase map using a three-step phase-shifting algorithm. Then, a multi-frequency temporal phase unwrapping (MF-TPU) algorithm is used to unwrap the wrapped phase map to obtain a fringe order map of the high-frequency phase with 64 periods. A residual convolutional neural network is built, and its input data are set to be the wrapped phase maps with frequencies of 1 and 64, and the output data are set to be the fringe order map of the high-frequency phase with 64 periods. Finally, the training dataset and the validation dataset are built to train and validate the network.

Abstract: An image measuring apparatus includes an imager that acquires an image of a measurement target object, a touch panel display that displays the image acquired by the imager and accepts touch input operation of specifying a position in the displayed image, and an edge detector that searches for and detects an edge present in a predetermined range around the in-image specified position specified by a user's touch input operation in the image displayed on the touch panel display. When edges are found in a vicinity of the specified position, the edge detector causes a control object for selecting each of the edges to be displayed on the touch panel display not only in an aspect that prevents a wrong edge from being selected through the touch operation but in an aspect that allows visual recognition of a correspondence between each of the edges and a corresponding control object.

Abstract: A system and method for tracking an object within a surgical field are described. A system may include a lighting component to illuminate a surgical field, and a camera device to capture an image of a tracked device within the surgical field. The system may include a rotational component configured to rotate with respect to the lighting component. The camera device may couple to the rotational component to rotate with respect to the lighting component, such as in response to an obstruction of a tracked object being detected.

Abstract: To make it possible to associate a world coordinate with a coordinate of an imaging device without using a calibration board. A plurality of pattern images are generated by receiving measurement pattern light reflected from a measuring object. X coordinate, Y coordinate, and Z coordinate of a specific point are measured based on a plurality of pattern images, and a calibration target is generated from measurement result of the X coordinate, Y coordinate, and Z coordinate. Calibration is executed using the generated calibration target.

Abstract: An information processing device includes an acquisition unit that acquire measurement success/failure information indicating whether or not measurement by a measurement unit has been successful in a case where a measurement process is executed of emitting directional light, which is light having directivity, toward a subject within a specific imaging range among a plurality of imaging ranges serving as imaging targets in panoramic imaging of the subject, and receiving reflected light of the directional light to cause the measurement unit to measure a distance to the subject, and an execution unit that executes a measurement suppressing process of suppressing the measurement by the measurement unit which is performed on the subjects within the plurality of imaging ranges, in a case where the measurement success/failure information acquired by the acquisition unit indicates that the measurement by the measurement unit has been successful.

Abstract: A method is provided for reconstructing a three dimensional image, comprising: providing a pair of stereoscopic images captured by two image capturing devices; retrieving disparity data from the pair of stereoscopic images; using retrieved disparity data to determine contours of an object present in the pair of the stereoscopic images captured; selecting a pixel belonging to that object; establishing a search area at the vicinity of the selected pixel; determining values for various disparity candidates, wherein the determined values correspond to one or more chosen hypothesis associated with the search area; testing the one or more chosen hypothesis and selecting an hypothesis which best fits the selected pixel and its neighboring pixels; executing a stereo matching algorithm using data retrieved from the captured images while using the values of disparity candidates that correspond to the chosen hypothesis; and reconstructing the three dimensional image based on the results obtained.

Abstract: An image processing device includes a distance information acquisition unit and an image combination unit. Based on positions of a common subject on a plurality of images captured by a plurality of cameras for capturing surrounding images of a vehicle, the distance information acquisition unit calculates a first subject distance from a vehicle reference position to the common subject, and calculates, based on the first subject distance, a second subject distance to a subject captured by one of the plurality of cameras. Based on the first subject distance and the second subject distance, the image combination unit converts the captured images in which the plurality of cameras are employed as viewpoints to images in which the reference position is employed as a viewpoint, and combines the converted images on a single plane of projection.

Abstract: By a disparity computation unit 21, first, with respect to a block in a bottom row of a first image, a corresponding block within a second image which has a same Y-coordinate as a Y-coordinate of the block and in which an object same as or similar to an object appearing in the block appears is searched for, and, next, in the case of searching for, with respect to a block which is upward in order from the searched block of the first image, a corresponding block within the second image in which an object same as or similar to that of the block appears, the corresponding block within the second image which has a same Y-coordinate as a Y-coordinate of the block of the first image and in which an object same as or similar to that of the block of the first image appears in an X-coordinate setting range with an X-coordinate of the corresponding block of the second image corresponding to the searched block which is immediately below the block of the first image as a center is searched for.

Abstract: Compact 3D depth capture systems are based on a 3D system driver/interface, a 3D system camera, and a 3D system projector. The systems are compatible with integration in to mobile electronic devices such as smart phones and tablet computers.

Abstract: A method for representing a terrain, a method for creating terrain primitives, and an apparatus using the methods are disclosed. The terrain representation method includes: reading digital elevation model (DEM) data of a terrain; extracting feature points of the terrain from the DEM data of the terrain; creating a plurality of terrain primitives according to the feature points of the terrain; storing terrain representation model data based on the plurality of terrain primitives; and converting the terrain primitive based terrain representation model data into DEM data, and visualizing the DEM data.

Abstract: An inspection apparatus determines a location of a target object within a volume. The inspection apparatus includes a visual inspection device that determines a location of at least one reference point within the volume with respect to the visual inspection device. The visual inspection device further detects a location of the target object with respect to the visual inspection device. The visual inspection device utilizes a location of the target object with respect to the at least one reference point to determine a position of the target object within the volume. A method of locating the target object with the inspection apparatus is also provided.

Abstract: An apparatus for obtaining an image of a tooth having at least one light source providing incident light having a first spectral range for obtaining a reflectance image from the tooth and a second spectral range for exciting a fluorescence image from the tooth. A polarizing beamsplitter in the path of the incident light from both sources directs light having a first polarization state toward the tooth and directs light from the tooth having a second polarization state along a return path toward a sensor, wherein the second polarization state is orthogonal to the first polarization state. A first lens in the return path directs image-bearing light from the tooth toward the sensor, and obtains image data from the portion of the light having the second polarization state. A long-pass filter in the return path attenuates light in the second spectral range.

Abstract: The present invention aims to provide a highly reliable relief pattern detection device 1, including a slant FOP 3 having an input end surface 4 with which an object surface makes contact and an output end surface 5 substantially parallel to the input end surface 4, an irradiation light source 10 disposed on the output end surface 5 side of the slant FOP 3, for irradiating the output end surface 5 with light, and a CCD camera 11 disposed on the output end surface 5 side of the slant FOP 3, for detecting a relief pattern based on light emitted from the output end surface 5, in which optical axes Rf of optical fibers are inclined so as to create a first angle ? less than 90° in one direction from the output end surface 5 within a predetermined plane substantially perpendicular to the output end surface 5, the irradiation light source 10 irradiates the output end surface 5 with light in a direction to create a second angle ? less than 90° in the other direction from the output end surface 5 within the predetermi

Abstract: A tomographic fluorescent imaging device for imaging fluorophores in biological tissues has a scanned laser for scanning the tissue and a camera for receiving light from the biological tissue at an angle to the beam at a second wavelength ten or more nanometers greater in wavelength than the wavelength of the laser. Use of both intrinsic and extrinsic fluorophores is described. Images are obtained at each of several positions of the beam. An image processing system receives the series of images, models a path of the beam through the tissue, and determines depth of fluorophore in tissue from intersections of the modeled path of the beam and the path of the received light. The laser is of 600 nm or longer wavelength, to provide penetration of tissue. The imaging device is used during surgery to visualize lesions of various types to ensure complete removal of malignant tumors.

Abstract: An apparatus for 3D surface measurement of a target surface, the apparatus comprising: a first projector configured to project a fringe pattern onto the target surface; a second projector configured to project a fringe pattern onto the target surface; a first camera configured to capture the fringe patterns projected by the first projector and the second projector; a second camera configured to capture the fringe patterns projected by the first projector and the second projector; and a computer configured to perform fringe pattern processing of the fringe patterns captured by the first camera and the second camera and to perform data stitching and merging to obtain a 3D surface reconstruction.

Abstract: In one aspect, the present invention relates to a system evaluating a surgical margin of tumor tissues of a living subject. In one embodiment, the system includes a light source configured to emit a source light; at least one optical probe; a scanner; a spectrometer; and a controller coupled with the scanner and the spectrometer for operably controlling the scanner and the spectrometer. In operation, a working end of the optical probe is positioned proximate to a surface of a specimen of the tumor tissues. A source channel of the optical probe deliver the source light emitted by the light source from the working end to the surface of the specimen, and a plurality of collection channels collect from the working end diffused/reflected light generated from interaction of the source light with the specimen. The spectrometer receives the collected diffused/reflected light to evaluate a margin status of the specimen.

Abstract: An observing apparatus includes a lighting device for irradiating a surface of a measuring target with light having a first light source distribution, and an imaging section for imaging the surface of the measuring target. Considering a first plane passing through a measurement point, the first light source distribution is set such that: (1) a radiance L11(?) changes in a continuous or stepwise manner according to an angle ?, and (2) the radiance L11(?) is not zero in a local region of a predetermined range of ±? having a point located at a predetermined angle ?c as a center on the first plane when viewed from the measurement point, and the following equation substantially holds for arbitrary a satisfying 0<a??; L11(?c?a)+L11(?c+a)=2×L11(?c).

Abstract: The invention provides a shape measuring device, a shape measuring method, and a shape measuring program capable of easily adjusting a posture of a measuring object to a state appropriate for shape measurement before the shape measurement of the measuring object. A measuring object is irradiated with light having a pattern for posture checking by a light projecting unit before the shape measurement. An image of the measuring object captured by a light receiving unit is displayed on a display section in this state. The posture of the measuring object is adjusted with the measuring object being irradiated with the light having the pattern for posture checking by the light projecting unit.

Abstract: Even if a return beam from a work to be measured does not agree with the center of a two-piece sensor, a correction value is calculated according to a voltage difference between two sensors of the two-piece sensor if the voltage difference is within a neighborhood range. The correction value is added to an actual position of an objective lens in an up-down direction, to calculate a movement amount of the objective lens up to a focused state (a state in which the return beam agrees with the center of the two-piece sensor).

Abstract: There is provided an image analysis system which captures image data of an arbitrary pair of a first image RI and a second image LI among images obtained by color-photographing a single object from different positions into an analysis computer, wherein the computer includes corresponding point extraction means for assigning a weighing factor to a pixel information value based on the contrast size of the pixel information value in each of a first local area ROI1 set around an arbitrary reference point in RI and second local areas ROI2s at which scanning is performed on LI, calculating the similarity between ROI1 and ROI2s, and extracting a corresponding point which corresponds to the reference point from a ROI2 having the highest similarity, and depth information calculating means for calculating depth information of the object based on coordinates of the reference point and the corresponding point.

Abstract: The present invention aims to provide a highly reliable relief pattern detection device 1, including a slant FOP 3 having an input end surface 4 with which an object surface makes contact and an output end surface 5 substantially parallel to the input end surface 4, an irradiation light source 10 disposed on the output end surface 5 side of the slant FOP 3, for irradiating the output end surface 5 with light, and a CCD camera 11 disposed on the output end surface 5 side of the slant FOP 3, for detecting a relief pattern based on light emitted from the output end surface 5, in which optical axes Rf of optical fibers are inclined so as to create a first angle ? less than 90° in one direction from the output end surface 5 within a predetermined plane substantially perpendicular to the output end surface 5, the irradiation light source 10 irradiates the output end surface 5 with light in a direction to create a second angle ? less than 90° in the other direction from the output end surface 5 within the predetermi

Abstract: A system for inspecting a specimen is provided. The system includes an illumination subsystem configured to produce a plurality of channels of light energy, each channel of light energy produced having differing characteristics (type, wavelength, etc.) from at least one other channel of light energy. Optics are configured to receive the plurality of channels of light energy and combine them into a spatially separated combined light energy beam and direct it toward the specimen. A data acquisition subsystem comprising at least one detector is provided, configured to separate reflected light energy into a plurality of received channels corresponding to the plurality of channels of light energy and detect the received channels.

Abstract: A vision system that forms a map of a scene proximate a platform, e.g., a vehicle, that determines the actual ground plane form the map, and that corrects the map for differences between the actual ground plane and an assumed ground plane. The vision system may remove the actual ground plane from the map to prevent false positives. The vision system can further identify and classify objects and, if appropriate, take evasive action.

Abstract: The invention is directed to a method for illuminating an object and projecting its image on a ground glass screen. Optical comparators conventionally use incandescent illumination, either mercury arc or halogen. The use of an array of high intensity LED devices, provides many options for packaging the required optical components used in comparators.

Abstract: In a light-slit method, a first and a second measurement light projection on a surface of an object to be measured may be unambiguously identified as a first or a second measurement light projection by a camera when there is a support apparatus operating the camera and/or the measurement light projectors such that, in each light-slit recording of the camera, either the first or the second measurement light projection is visible to the camera. The possibility of unambiguous identification allows evaluating several spatially overlapping and not exactly aligned measurement light projections by means of a camera.

Abstract: A system and a method are provided for detecting a surface characteristic of a surface. A plurality of transponders are located on the surface for transmitting electromagnetic surface waves and for receiving the electromagnetic surface waves upon being reflected, diffracted, refracted, scattered, or otherwise altered by ice on the surface. A controller is coupled to the plurality of transponders. The controller is adapted to coordinate the plurality of transponders for imaging the surface characteristic of the surface.

Abstract: For objects with non-Lambertian surfaces, an object surface is mapped by effectively modifying the reflective properties of the object surface being sensed. By effectively making the surface Lambertian with high albedo, a calibration imaging task is achieved using a typical camera from a single or small number of camera positions. The calibration method temporarily modifies the surface properties of the imaged object by applying a thin and opaque layer, such as a coating, covering, or veneer, to the object for the duration of the calibration imaging task. The surface of this layer is a Lambertian reflector, with medium to high albedo. The layer is snugly applied, so a shape of the layer is as close as possible to that of the surface. Once the layer is applied, imaging of the layer surface essentially yields the same shape as the underlying object.

Abstract: The invention is a process for identifying an unknown object. In detail, the process includes the steps of: 1) compiling data on selected features on a plurality of segments of a plurality of known objects; 2) illuminating the unknown object with a laser radar system; 3) dividing the unknown object into a plurality segments corresponding to each of the segments of the known objects; 4) sequentially measuring selected features of each of the plurality of segments of the unknown object; and 5) comparing the sequentially measuring selected features of each of the plurality of segments of the unknown object to the selected features on the plurality of segments of the plurality of known objects.

Abstract: A substrate processing method and a substrate processing system exclude wafers W provided with a protective film having surface defects that will cause components of a resist to dissolve in an immersion liquid during an immersion exposure process, and rated abnormal from those to be processed by the immersion exposure process. The substrate processing system is provided with a protective film forming module for forming a protective film on a resist film formed on a surface of a wafer W, an exposure system 4 for processing the surface of the wafer W coated with a transparent immersion liquid layer by an immersion exposure process, and a developing module 28 for processing the wafer W by a developing process using a developer. A protective film inspecting device 33 detects surface defects in a protective film formed on a wafer W.

Abstract: A three-dimensional data processing technique is disclosed which makes natural CG reproduction of a real existing object possible with as small a data amount and as small a calculation amount as possible. Three-dimensional data processing method, program, and system acquire first data showing at least one of a surface shape or taken images of a real existing object and generate a bump map for creating a three-dimensional image of the object based on the first data.

Abstract: The invention relates to a method and apparatus for determining the topography or optical properties of a moving subject. In the method at least two images (KX1, KX2, KX3) and (KY1, KY2, KY3) of a moving subject (X) and a reference area (Y) in its immediate vicinity are taken synchronously at different moments in time, in such a way that, in each of the images taken of the subject (X), the subject (X) is illuminated mutually essentially in different ways, for example, by illuminating the subject in different ways through patterned masks, for example sine-patterned masks, and, in the images taken of the reference area (Y) in the vicinity of the subject (X), the reference area (Y) is illuminated in mutually essentially the same way, for example, through an unpatterned mask.

Abstract: Included are an illumination lamp (2) for illuminating a color filter edge (23) at a predetermined angle of incidence, a sensor (3) for taking at least two images by imaging light reflected at a predetermined angle different from the angle of incidence, an image processing section (9) for calculating a difference in luminance within a color filter in accordance with the images thus taken, and a defect determination section (13) for determining the existence of unevenness in the color filter from the difference in luminance. Provided thereby are a color filter inspection method and a color filter inspection apparatus, each for early discovering unevenness through macroscopic observation of the whole color filter by illuminating the color filter edge and by taking reflected light that is not specular reflected light, the unevenness occurring in a drying step, the color filter edge containing a boundary between a pixel and a black matrix.

Abstract: The wheel and tire assembly for running on ground includes measurement means carried by the wheel for measuring topological parameters of the inside surface of a pertinent portion of the tire. These measurement means comprise lighting and viewing means for lighting and viewing a calibrated surface pattern that is subjected to the deformation of the inside surface of the pertinent portion of the tire. The viewing means are preferably of the stereovision type or of the structured light type.

Abstract: The invention provides a measuring apparatus that can efficiently analyze a three-dimensional image by simultaneously recording a circular streak image and a straight-line streak image at a measured point, even when a large number of circular streak images are present. A measuring apparatus includes: a 3CCD camera; a cubic beam splitter that combines optical images incident from plural routes; a mirror that shifts an image focusing position of an optical image at a measured point by a predetermined distance; a coloring unit that applies a predetermined color to an optical image incident to a route of the beam splitter; a motor that rotates the beam splitter and the mirror in a direction of an arrowhead; and a PC that calculates a three-dimensional position of the measured point based on the optical image recorded by a camera.

Abstract: A method for inspecting geometrical shapes of objects to determine selected dimensions thereof based on data characterizing such objects obtained through stereoscopic photographs taken by a pair of cameras with fields of view intersecting to thereby provide a photographic event measurement volume that includes at least a portion of each of such objects being photographed. The method involves using previously specified procedures to check on the cameras performance consistency in photographing from different positions, preparing the object to be inspected including providing reference point targets thereon, scanning that object with the cameras from different camera pair positions, processing the resulting data to represent the scan basis geometrical shape of the object, and orient it to compare with the dimensional specifications therefor.

Abstract: After calibration for three-dimensional measurement has been completed, specification of a range of height to be measured is accepted, and using a homography matrix corresponding to the specified range on each of the images A0 and A1 from respective cameras, a range is extracted where a point included in the viewing fields of both of the cameras appears among points in the specified height range. Further, the extracted range is color-displayed as a measurable range on each of the images A0 and A1.

Abstract: In a light-slit method, a first and a second measurement light projection on a surface of an object to be measured may be unambiguously identified as a first or a second measurement light projection by a camera when there is a support apparatus operating the camera and/or the measurement light projectors such that, in each light-slit recording of the camera, either the first or the second measurement light projection is visible to the camera. The possibility of unambiguous identification allows evaluating several spatially overlapping and not exactly aligned measurement light projections by means of a camera.

Abstract: An image processing system recovers 3-D depth information for pixels of a base image representing a view of a scene. The system detects a plurality of pixels in a base image that represents a first view of a scene. The system the determines 3-D depth of the plurality of pixels in the base image by matching correspondence to a plurality of pixels in a plurality of images representing a plurality of views of the scene. The system then traces pixels in a virtual piecewise continuous depth surface by spatial propagation starting from the detected pixels in the base image by using the matching and corresponding plurality of pixels in the plurality of images to create the virtual piecewise continuous depth surface viewed from the base image, each successfully traced pixel being associated with a depth in the scene viewed from the base image.

Abstract: An apparatus and method for obtaining surface texture information using photometric stereo. The material for which surface height and reflectance function information is desired (“the material”) is illuminated with an illumination source emitting electromagnetic waves, preferably in the form of white light, which is consequently reflected by the material to be scanned into an imaging sensor. The position and orientation of the illumination source relative to the sensor is constant. The material is placed within or on top of a holding apparatus, such as a pane of glass, which is oriented in order to keep the illumination vector constant with respect to the imaged surface. The illumination source and sensor are moved in unison across the surface in order to progressively capture a complete image of the surface; this operation may be facilitated in practice through the use of hardware such as a flatbed scanner.

Abstract: A structured light pattern digitizing method is combined with photogrammetry to determine a 3D model of an object. The structured light digitizing operation generates a 3D model of the object being scanned, and this model is then used to compute a higher accuracy model using photogrammetry.

Abstract: An optical scanner for three-dimensional scanning comprises: a support bed; a flat, transparent plate; guide rails under the transparent plate; a carriage slidably attached to the guide rails; and one or more sensors attached to the bed/case or carriage. For three-dimensional imaging, multiple scanned images of the object are obtained, each of which is from light reflecting off the object at a different angle with respect to the path of the carriage. This is done by shining light on the object and appropriately channeling reflected light, from at least two different directions, into the sensor(s). In one embodiment, the carriage has three CCD sensors, one oriented rearwards (with respect to the path of travel of the carriage), one oriented vertically, and one oriented forwards—each effectively “sees” the object from a different orientation. The multiple scanned images can be used for stereoscopic viewing and/or three-dimensional rendering using a computer.

Abstract: In one embodiment, an apparatus for three-dimensional (3-D) image acquisition can include: (i) first and second lenses configured to receive light from a scene; (ii) first, second, third, and fourth sensors; (iii) a first beam splitter arranged proximate to the first lens, where the first beam splitter can provide a first split beam to the first sensor, and a second split beam to the second sensor; and (iv) a second beam splitter arranged proximate to the second lens, where the second beam splitter can provide a third split beam to the third sensor, and a fourth and split beam to the fourth sensor. For example, the sensors can include charge-coupled devices (CCDs) or CMOS sensors.

Abstract: The invention relates to a system for the combined shadow-free illumination of a pre-definable area and for referencing three-dimensional spatial co-ordinates, and to an active or passive referencing system, each in particular for referencing surgical or medical instruments. The system is characterized in that at least two cameras and the light source (operation lamp) are held together such that the optical signals detected by the cameras, for referencing three-dimensional spatial co-ordinates in the area illuminated by the light source, can be evaluated. Since the field of view of the light source, in its conventional use, is not obscured or only negligibly obscured, this field of view can simultaneously be used for optical navigation by the cameras held together with the light source. In accordance with the invention, the cameras are automatically aligned optimally for optical navigation. The cameras can be rigidly or flexibly connected to the light source.

Abstract: A surface shape measuring apparatus, comprising: a stereo-photographing part 3 for photographing an object 1 in stereo; a relative position changing part 4 for changing the positional relation between the stereo-photographing part 3 and the object 1; means 5 for storing stereo-photographing parameters in a plurality of directions from which the stereo-photographing part 3 photographs the object 1; a stereo-image generating means 6 for controlling the stereo-photographing part 3 to photograph the object 1 from the plurality of directions with the stored stereo-photographing parameters and generating stereo images of the object 1; and a surface shape processing means 7 for measuring the surface shape of the object 1 based on the stereo images of the object 1.

Abstract: A method for use with a non-contact range finding and measurement system for generating a template guide representative of the surface of a observed object, and for utilizing the template guide to improve laser stripe signal to noise ratios and to compensate for corrupted regions in images of the observed object to improve measurement accuracy.

Abstract: The apparatus is comprised by a three-dimensional measurement device for measuring an object and generating three-dimensional data of the object; a control device for changing a position or a posture of the object; a three-dimensional position sensor for measuring a relative position or a relative posture between the three-dimensional measurement device and the object; and a computer device for integrating plural sets of three-dimensional data based on a measurement result of the three-dimensional position sensor.

Abstract: A system and method for acquiring three-dimensional (3-D) images of a scene. The system includes a projection device for projecting a locally unique pattern (LUP) onto a scene, and sensors for imaging the scene containing the LUP at two or more viewpoints. A computing device matches corresponding pixels in the images by using the local uniqueness of the pattern to produce a disparity map. A range map can then be generated by triangulating points in the imaged scene.

Abstract: Systems and methods that improve process control in semiconductor manufacturing are disclosed. According to an aspect of the invention, conditions in a cluster tool environment and/or a wafer therein can be monitored in-situ via, for example, a scatterometry system, to determine whether parameters associated with wafer production are within control limits. A cluster tool environment can include, for example, a lithography track, a stepper, a plasma etcher, a cleaning tool, a chemical bath, etc. If an out-of-control condition is detected, either associated with a tool in the cluster tool environment or with the wafer itself, compensatory measures can be taken to correct the out-of-control condition. The invention can further employ feedback/feed-forward loop(s) to facilitate compensatory action in order to improve process control.

Abstract: The invention relates to connection of corresponding points measured by a computer vision system. The points are indicated by an illuminator (LASER), by means of which several points can be illuminated on the surface of the object at the same time. A camera system (CAM1, CAM2) measures the positions of the points. Using a data system (DTE), projection images are generated from a three-dimensional model of the object, in which images the positions of the points are calculated. To locate the actual point in the image perceived by the cameras, a search is performed in an area in the neighborhood of coordinates calculated from the point in the projection image. The point thus located can be connected to the perceptions of the other cameras by the aid of the projection images. After the corresponding points have been found, the actual three-dimensional coordinates of the measured point are calculated.

Abstract: The invention provides a measuring apparatus that can efficiently analyze a three-dimensional image by simultaneously recording a circular streak image and a straight-line streak image at a measured point, even when a large number of circular streak images are present. A measuring apparatus includes: a 3CCD camera; a cubic beam splitter that combines optical images incident from plural routes; a mirror that shifts an image focusing position of an optical image at a measured point by a predetermined distance; a coloring unit that applies a predetermined color to an optical image incident to a route of the beam splitter; a motor that rotates the beam splitter and the mirror in a direction of an arrowhead; and a PC that calculates a three-dimensional position of the measured point based on the optical image recorded by a camera.