350 results about "Structure light" patented technology

The invention belongs to the technical field of structured light three-dimensional measurement, and particularly relates to a super-density stripe structured light three-dimensional surface scanning method and system, and the method comprises the steps: obtaining camera parameters; projecting a super-density stripe structure light pattern formed by alternating wide bright and dark stripes to an object; acquiring an image by using a camera, and extracting a central point pixel coordinate of the stripe-structured light pattern by using a sub-pixel precision positioning method; calibrating a light plane equation of each stripe structure light pattern under a camera coordinate system by means of a plane target; reversely projecting the pixel coordinate of the central point of the stripe-structured light pattern into a ray and intersecting the ray with a corresponding light plane to obtain the three-dimensional coordinate of the ray and form an initial three-dimensional point cloud; and finally, carrying out gray scale estimation and filling on missing data caused by signal saturation or difficult positioning based on a radiation brightness physical model to obtain complete and accurate three-dimensional surface shape data. According to the invention, high-precision, high-density and high-integrity three-dimensional surface scanning is realized, and the reliability and applicability of a measurement result are remarkably improved.

The invention discloses a method for performing visual inspection on surface forming quality characteristics of a welding seam by utilizing three-dimensional reconstruction, which comprises the following steps of: S1, performing uniform-speed scanning on the welding seam along the direction of a welding bead by using linear structured light emitted by a linear laser, and performing image acquisition on linear structured light stripes formed on the surface of the welding seam by using an industrial camera; s2, converting the acquired RGB image into a gray level image frame by frame, and carrying out image distortion correction and image denoising processing; s3, carrying out ROI (Region of Interest) positioning on the formed line structured light stripe image on the surface of the welding seam by adopting a pixel point gray level distribution calculation method; s4, carrying out image segmentation on the ROI region of the weld line structured light stripe image; and S5, carrying out sub-pixel-level center line extraction on the ROI of the weld line structured light stripe image by adopting a gray extreme value weighted centroid method. Automatic detection of welding seam forming quality characteristics such as laser welding and electric arc welding can be achieved, and the operation efficiency of a production line and the welding seam quality detection precision can be greatly improved.

Disclosed in the present invention is a three-dimensional reconstruction method based on kinematic calibration for the monomerization of a line-structured light point set. The method comprises: rigidly combining an area-array camera with a linear-line-structured light emitter, and mounting same on a motion platform; using a standard radius value of a standard sphere and line-structured light scanning data to calibrate structural parameters of the motion platform of a measurement apparatus; with the calibrated spherical center position of the standard sphere and the standard radius of the standard sphere as constraints, calibrating a spatial position relationship of a line-scanned point set; controlling the motion of the five-axis motion platform, and acquiring scanning data of a measured piece in different poses; and using the scanning data and a real-time point cloud calibration matrix to complete high-quality three-dimensional model reconstruction of the measured piece from its multi-pose scanning. The system comprises: an apparatus fixing module, a calibration module, a point cloud calibration module, a scanning module, and a point cloud reconstruction module. By means of using the present invention, the reconstruction accuracy of a line-structured light three-dimensional point cloud model can be improved. The present invention can be widely applied to the field of three-dimensional reconstruction.

The embodiment of the invention discloses an MEMS structured light high-precision three-dimensional measurement method, device and equipment and a medium. The method comprises the following steps: determining first orthogonal phase distribution information of a to-be-measured target according to a surface stripe image; determining a first space linear equation of the fitting projection light of the preset projection phase; coordinates of the first space linear equation are converted to obtain a second space linear equation, a projection device coordinate system is established according to the first space linear equation, and a mapping model of the deviation angle and the projection phase is determined based on the corresponding relation between the second space linear equation and the preset projection phase; mapping the phase to obtain a first offset angle; and determining the to-be-measured target point cloud based on the first deviation angle to obtain a three-dimensional coordinate. According to the invention, the method does not depend on a high-precision calibration plate, builds the incidence relation between the phase and the angle and the ray mapping model, accurately represents the projection characteristics of the projection device, and solves a technical problem that the precision is not high when three-dimensional measurement is carried out based on an MEMS structured light system.

The invention relates to the technical field of underwater target detection, and discloses an underwater target detection device and method based on binocular fusion line structured light, the device comprises a binocular structured light system and an information processing unit which are installed at the bow of an underwater robot, and the binocular structured light system is in communication connection with the information processing unit; the binocular structured light system comprises vertically arranged array laser and an underwater binocular camera, and the array laser is used for projecting line structured light stripes to an underwater target and forming a structured light image on the surface of the target; the underwater binocular camera is used for capturing a structured light image and sending the structured light image to the information processing unit; and the information processing unit is used for performing edge detection on the received structured light image to obtain line structured light projection stripes of the target surface, and further obtaining three-dimensional point cloud coordinates of the target surface. According to the invention, an underwater three-dimensional space can be fully covered, and three-dimensional perception and accurate identification of underwater suspended and semi-buried targets can be realized.

The invention discloses a damage detection method and system based on machine vision, and relates to the technical field of machine vision detection. A polarization structured light-thermal imaging three-mode acquisition framework of a customized machine vision array is adopted, the problems of composite noise superposition and unstable internal thermal signal diffusion caused by dynamic heterogeneity of a target surface are solved, the adaptability of damage detection to a complex environment is greatly improved, and by means of a space attention mechanism and a cascade analysis network, the damage detection accuracy is improved. According to the method, geometric measurement and heat conduction simulation technologies are combined, the problems that damage space distribution is rough in description, and there is no stable corresponding relation between surface and deep abnormity are solved, accurate space mapping and multi-dimensional quantification of damage from the surface to the interior are achieved, and through linkage of a dual optimization mechanism and an edge end improved MobileViT lightweight model, the problem that damage space distribution is rough in description is solved. Pain points where real defects and interference artifacts are difficult to distinguish are broken, stable correspondence between surface signals and deep damage is enhanced, and accuracy and practicability of damage detection in an industrial scene are guaranteed.

The invention discloses a visual inspection sorting method and system for surface defects of intelligent electric meter shell injection molded parts, and relates to the technical field of visual inspection, and the method comprises the following steps: selecting an intelligent electric meter shell as a reference part, dividing the surface of the shell into a plurality of functional partitions, collecting structured light form and brightness information, and obtaining a reference appearance map; and positioning a to-be-detected electric meter shell to a position consistent with the reference part, obtaining the online three-dimensional form and brightness response of each functional zone, mapping the online three-dimensional form and brightness response to the reference appearance map, marking a stable mirror surface with high brightness, and interpolating along an observation track to generate an online appearance map. According to the invention, through functional partition sampling layout of a window sealing area, a wiring terminal area, a stud and reinforcing rib area, a nameplate and two-dimensional code area and a general decoration side wall area, and in cooperation with double-light-source collection of diffused light and oblique incident light combined with structured light, a reference appearance map containing a highlight tolerance mask is constructed; stable characterization of mirror reflection and a transparent window is realized, and false detection caused by high brightness of the mirror surface is remarkably reduced.

The invention discloses a grasp point pose calculation method based on a geometric clustering algorithm without deep learning and a GPU (Graphics Processing Unit) and application of the grasp point pose calculation method. The grabbing point pose calculation method comprises the steps that 100, three-dimensional point cloud data of a to-be-grabbed object are obtained through an industrial-grade structured light three-dimensional camera, a geometric clustering algorithm is adopted for screening the three-dimensional point cloud data, and a unique target point cloud cluster conforming to the target form and size is extracted; step 200, performing rough matching on the target point cloud cluster and the template point cloud through the FPFH feature vector and RANSAC to obtain a rough matching result; step 300, performing fine matching on the target point cloud cluster and the template point cloud through the rough matching result and the GICP to obtain a fine registration result; step 400, judging whether a precise registration result meets a preset requirement or not according to the interior point root-mean-square error and the overlap ratio, if so, entering the next step, and otherwise, terminating the process; and 500, according to the fine registration result and coordinate transformation, the grabbing point pose of the to-be-grabbed object is obtained through calculation.

The invention relates to the technical field of machine vision detection, and discloses a color printed matter quality detection method which comprises the following steps: acquiring original light field response data of the surface of a printed matter in a preset structure light field; carrying out decoupling calculation on the data to generate a basic color graph representing intrinsic colors, a glossiness graph representing process characteristics and a surface normal graph representing geometrical morphology; the method is characterized in that a texture area is identified based on a surface normal graph of a standard sample, and a dynamic reference model is established for the area in combination with a basic color graph so as to provide a self-adaptive color detection threshold value; and finally, detecting color, structure and process flaws in parallel by utilizing each physical characteristic spectrum and the dynamic reference model. According to the method, through decoupling and information guidance of physical dimensions, interference of physical textures on color detection can be fundamentally inhibited, the false alarm rate is remarkably reduced, meanwhile, multi-dimensional comprehensive evaluation of flaws is achieved, and the detection result is objective and reliable.

The invention provides a light field reverse design method and system based on a bicoherent array, and the method comprises the steps: determining a target structure light field, initializing the array parameters of a bicoherent laser array in staggered distribution, and building a physical forward model of the bicoherent laser array from an emission surface near-field light field to a far-field light field; constructing a first-stage loss function by taking the generated target structure light field as a guide, optimizing amplitude, phase and tilt parameters of all sub-beams through back propagation iteration until convergence, and outputting array parameters after first-stage optimization; and introducing a light beam position penalty term on the basis of the first-stage loss function to update the loss function so as to continuously iteratively optimize the array parameters until no light beams are overlapped, and driving the dual-coherent laser array to perform coherent combination by using the finally optimized array parameters to generate a target structure light field. According to the invention, multiple typical and specific attribute structured light fields can be accurately customized, far-field side lobes are effectively inhibited, and the mode quality and the energy utilization rate are improved.

The application provides a whole tension magnetic suspension lamp tower device, relates to the magnetic suspension lamp field and comprises a plurality of superposed tension structures, and adjacent two layers of the tension structures are detachably connected through a cable. A power-on electromagnet and a magnetic suspension track matched with the power-on electromagnet are arranged in a rod in the tension structure. The power-on electromagnet is used for electrically connecting with an external power supply. A magnetic suspension lamp ball with a magnet coil wound thereon is arranged in the tension structure, and the multi-layer tension structure can be changed into various forms. The number of lamps of the application can be freely increased or decreased, and the lamps can be freely moved, the angle can be freely adjusted, and the form can be freely changed according to the scene requirement, so that the demand of customers for diversified lamps is met. The application improves the single light source form of the existing whole tension structure lamp, and the linear light source is mainly used, so that the problem that the diversified demand of people for lamps cannot be met is solved.

The application provides a motion-resistant structured illumination microscopy method based on principal component analysis (mrPCA-SIM), which can effectively compensate for non-uniform pixel offset and phase error in original illumination images. Compared with the traditional method, the application can realize more stable imaging quality under complex and unstable conditions, and is expected to realize more compatible and flexible live cell super-resolution imaging.

The utility model relates to the technical field of lighting equipment, and discloses a lamp. The lamp comprises a light guide plate which comprises a front face, a back face and a side face serving as a light inlet face, and the light inlet face is provided with a convex arc-shaped area which is provided with a concave-convex structure; the lamp strip is matched with the light guide plate in shape and surrounds the light inlet surface of the light guide plate; a containing cavity is formed in the lamp holder, the light guide plate and the lamp strip are arranged in the containing cavity, the front face of the light guide plate faces the opening direction of the containing cavity, and the back face of the light guide plate faces the bottom face of the containing cavity. The arc-shaped area is provided with the concave-convex structure, the concave-convex structure can scatter light rays, the path of the light rays entering the light guide plate is changed, and therefore light ray focusing is avoided. The direction and distribution of the light are adjusted through the concave-convex structure, it is ensured that the light can be evenly spread in the light guide plate, formation of local bright spots and virtual images is remarkably reduced, and the overall lighting uniformity and the visual comfort degree are improved.

The invention provides a light-emitting earmuff structure of an RGB lamp holder headset, a manufacturing method of the light-emitting earmuff structure of the RGB lamp holder headset and the RGB lamp holder headset. The light-emitting earmuff structure of the RGB lamp holder headset comprises an earmuff body, a shading assembly and an RGB light-emitting assembly, the shading assembly comprises a first light-transmitting shading shell and a second light-transmitting shading shell, the second light-transmitting shading shell surrounds the first light-transmitting shading shell, an atmosphere light projection area is formed by the second light-transmitting shading shell, the second light-transmitting shading shell is fixedly installed on the outer side wall of the earmuff body, a first annular light blocking flange is arranged on the outer periphery of the first light-transmitting shading shell in a protruding mode, and a second annular light blocking flange is arranged on the outer periphery of the second light-transmitting shading shell. A second annular light blocking flange is arranged on the inner periphery of the second light transmitting and shading shell in a protruding mode, and the first annular light blocking flange is arranged on the outer side of the second annular light blocking flange in a surrounding mode and is opposite to the second annular light blocking flange. The light-emitting earmuff structure of the RGB lamp holder headset can effectively prevent visual interference of redundant light, and improves the use experience of a user.

The invention provides a visual guidance method and system for a large rocket cabin milling robot, and the method comprises the steps: 1, constructing a visual measurement system which comprises a hybrid robot, an area array structured light camera, a visual target, a target ball base, a product installation platform and a laser tracker, completing the system calibration, enabling the visual target to be installed on the target ball base, and enabling the visual target to be installed on the target ball base; the target ball base is fixed on the product mounting platform, and the laser tracker is used for calibrating the position of the target ball base; 2, collecting an image of a visual target through the area array structured light camera, analyzing the coordinates of the target, and resolving the relative pose of the robot relative to a product mounting platform, so as to determine the position of a theoretical cutting point according to a product design model; and 3, the area array structured light camera is used for collecting the three-dimensional shape of the surface of the to-be-machined product, the normal direction of the to-be-machined surface is calculated, and the direction of the tool is corrected according to the normal direction.

The present application relates to a kind of intelligent 3D reverse image enhancement system and method, the method therein includes the following steps: infrared structured light projector projects structured light to the area in the lower rear of vehicle, through infrared camera module synchronous acquisition infrared structured light image sequence, and the phase obtained by calculating the image collected is input into phase optimization network and is carried out image enhancement, three-dimensional reconstruction is carried out using enhanced phase information to obtain infrared structured light three-dimensional stereoscopic image;Through RGB color camera module, the long-distance background image information of the rear of vehicle is collected, and the rotation angle and translation vector of vehicle movement are obtained in real time by gyroscope;Two are input monocular depth estimation network, and the output RGB three-dimensional stereoscopic image;Finally, infrared structured light three-dimensional stereoscopic image and RGB three-dimensional stereoscopic image are depth fusion, obtain the three-dimensional stereoscopic image of complete depth and display in vehicle display, to overcome the deficiency of existing two-dimensional reverse image technology, improve the safety of reversing driving.

The three-dimensional reconstruction method of multi-view projection-imaging solves the problem of poor consistency of reconstruction results caused by calibration error and system noise, and belongs to the field of machine vision measurement. The method comprises the following steps: a projection unit projects a preset sequence of stripe coded images to a calibration board in sequence after receiving a synchronous trigger signal of the imaging unit; the position and rotating posture of the calibration board in the three-dimensional space are moved; the imaging unit and N p projection units are triggered in sequence under each posture of the calibration board until N b sets of posture sequences of the calibration board are acquired; the imaging unit and the projection unit are calibrated; the external posture parameters of the imaging unit and each projection unit are optimized based on geometric consistency constraints, the problem of poor consistency of reconstruction results is solved, the distortion-free three-dimensional coordinates of single-direction structured light projection are calculated, the depth measurement values of each projection unit p i are fused to obtain the depth information Z of the object to be detected at (X, Y), and the final three-dimensional point cloud data (X, Y, Z) is generated.

An autonomous collaborative robotic system for automatically detecting, locating, and mapping underground assets is provided. The collaborative robotic system includes two autonomous robots, each robot including a housing with extendable legs, a camera module, a laser module designed to project a structure light pattern on a pipe interior, a sensor module designed to collect images from the camera module, and a processing module designed to process and stitch data to generate a network of underground assets and identify one or more features within the asset network.

The utility model discloses a connecting structure of a lampshade and a lamp pole of a high-altitude single-arm street lamp, four conical columns which are distributed in a rectangular shape are arranged on a lower lamp shell at a lampshade connecting hole, fixing screw holes are formed in the columns, and transverse and longitudinal reinforcing plates are arranged among the columns; the lamp pole connecting end mounting plate is provided with corresponding conical fixing holes and is fixed through bolts after being in interference fit with the conical columns, and clamping plate clamping grooves in the bottom of the mounting plate clamp the two sides of the longitudinal reinforcing plate. According to the structure, through interference fit of the conical columns and dual fixation of the bolts and reinforcement of the reinforcing plates and the clamping plates, the connection strength of the lampshade and the lamp pole is remarkably enhanced, external force such as wind power and vibration is effectively resisted, and loosening and shaking are prevented; the installation process is simplified, maintenance and repair are convenient, and the technical effects of stable and reliable connection, high structural strength and convenient installation and maintenance are achieved.

The present application relates to a kind of micro air compressor interface installation and surface marking integrated equipment and method, belong to air compressor auxiliary production equipment field.Structure light detection and transmission module is vertically connected with large rack and fixed on ground, and unqualified product removal module is vertically and closely connected with conveying belt;Micro air compressor transport module is fixed on the large platform of rack shell, and torsion gun movement mechanism is fixed on the large platform, and torsion gun adjustment module is fixedly connected with torsion gun movement mechanism;Interface pickup module is fixed on the frame of shell by pin shaft, surface marking mechanism is fixed on the large platform, and rack shell is fixed on ground;Automatic unloading mechanism is fixed by magnetic attraction device of rack shell and rack shell.The advantages are that the equipment integrates feeding, detection, installation, waste removal and product collection, saves a lot of production time and human resources, reduces the increase rate of misdelivery, miswaste or unqualified products caused by manual detection and installation, and greatly improves production efficiency.

The invention discloses an event-based high dynamic range structured light three-dimensional reconstruction method, which comprises the following steps: S1, establishing an event camera structured light simulator based on Blender, and providing a first event camera HDR structured light data set; s1.1, a physical projector based on a node tree system is realized in the simulator, so that the optical characteristics of the physical projector can be accurately controlled; s1.2, an HDR scene is constructed by high-fidelity texture grids, the models are derived from an OmniObject 3D data set, and reflection characteristics of a real HDR surface are simulated by adjusting parameters of an object; according to the event-based high dynamic range structured light three-dimensional reconstruction method, the problems of reconstruction precision reduction and reconstruction failure caused by overexposure, underexposure and reflectivity difference of an existing structured light system in a complex HDR scene are solved, so that high-precision and robust three-dimensional reconstruction of high-reflection, weak-reflection and complex surfaces is realized.

The application relates to the technical field of light beam scanning, in particular to a dot matrix structured light scanning method and device based on a superstructure surface, wherein the method comprises the following steps: acquiring array light beams of incident light beams during dot matrix structured light scanning based on at least one array unit in a first-order superstructure surface; generating outgoing light beams of the incident light beams based on the array light beams and a second-order superstructure surface which satisfies a certain interval condition with the first-order superstructure surface; and generating a scanning result of the dot matrix structured light scanning based on the outgoing light beams. Therefore, the problems that the long-distance detection precision is limited when a static dot matrix structured light projection is realized based on a superstructure surface and the detection field of view and detection efficiency are limited when a dynamic adjustable laser beam scanning is realized based on the superstructure surface are solved.

The application belongs to the technical field of optical three-dimensional measurement, and discloses a two-division iteration sub-pixel matching method and system for phase structured light three-dimensional measurement, which comprises the following steps: obtaining a phase map; performing legality marking and pixel-level initial matching on the phase map; determining a sub-pixel search area based on the pixel-level initial matching; and performing sub-pixel matching point search based on the sub-pixel search area by using a two-division iteration method to obtain a sub-pixel matching point. The application can improve the precision of binocular matching in phase structured light three-dimensional measurement, thereby improving the precision of three-dimensional reconstruction.

The application relates to a three-dimensional spectrum combined PCB detection method and system based on multi-modal fusion. The detection method comprises the following steps: acquiring three-dimensional topographic data and multi-band spectral reflection data, and collecting the three-dimensional topographic data after structure light projection; performing cross-modal space registration processing according to the three-dimensional topographic data and the spectral reflection data to generate corresponding registration feature data; determining the defect state of the PCB surface; when the defect state is an appearance similar defect state and a material attribute difference state, corresponding fusion feature encoding signals are generated, spectral set consistency verification is performed, and a direct output defect recognition action is performed or dynamic compensation processing is performed until the conditions for the direct output defect recognition action are met. The same detection area can be described from two physical dimensions of geometric height change and material optical reflection difference, and the difference can be distinguished, so that more comprehensive and more reliable defect determination results can be obtained.

The invention discloses a core-shell structure light conversion agent, a photovoltaic glass light conversion coating liquid and a preparation method of the photovoltaic glass light conversion coating liquid, and belongs to the technical field of photovoltaic packaging. The core-shell structure light conversion agent comprises a core layer and a shell layer, wherein the core layer comprises a light conversion agent luminescent molecular material; the shell layer comprises a silicon dioxide material; the particle size of the core-shell structure light conversion agent is 20-200 nm; and the thickness of the shell layer is 10-50% of the particle size of the core-shell structure light conversion agent. By designing the core-shell structure with the inorganic silicon dioxide shell layer, effective packaging of light conversion agent molecules is realized, so that high light transmittance is maintained, the ultraviolet stability of the light conversion film layer is improved, and the service life of the coating film layer in an outdoor environment is prolonged.

This application relates to a method and system for detecting wafer parameters. The detection method includes providing multi-wavelength sequential illumination; modulating the illumination light into multi-step phase-shifting structured light using a spatial light modulator and projecting it onto the wafer surface; acquiring the multi-step phase-shifting structured light reflected from the wafer surface using a broadband imaging unit to obtain a structured light image sequence, ensuring consistent pixel positions in the images under multi-wavelength sequential illumination; synchronously controlling the timing of wavelength switching of the illumination light, structured light modulation, and image acquisition to obtain a multi-wavelength structured light image sequence; performing multi-spectral film thickness inversion on the multi-wavelength structured light image sequence to obtain a film thickness distribution map; and performing multi-wavelength phase fusion three-dimensional reconstruction on the multi-wavelength structured light image sequence to obtain three-dimensional topography data. The detection system includes an illumination module, a spatial light modulator, a broadband imaging unit, and a data processing module. This invention can acquire the three-dimensional topography and surface film thickness of wafers, and is also suitable for topography detection of etching trenches with aspect ratios.

Embodiments of the present application disclose an imaging method and device, a storage medium and a terminal. The method comprises: acquiring each initial image of a target corresponding to a multi-step phase shift structured light collected by a camera at at least two exposure times; acquiring, for each step of phase shift, a phase shift vector composed of pixel values of a same pixel point in different exposure times in the initial images; performing linear correction on each pixel value in each phase shift vector to obtain a corrected target phase shift vector; determining a target exposure time in each exposure time based on each target phase shift vector; taking a pixel value corresponding to the target exposure time in each target phase shift vector as a target pixel value; and composing a target image corresponding to each step of phase shift of the target by each target pixel value. The present application can effectively suppress random noise fluctuating with time in the imaging process, and can improve the imaging quality in the structured light measurement technology.

The application discloses a kind of structure light three-dimensional measurement method based on continuous phase constraint, including constructing encoding stripe, project the encoding stripe and obtain corresponding image, project periodic stripe pattern with preset phase offset and obtain multiple images, and the phase information of each pixel is calculated by the multiple images;Determine the stripe period interval to which the pixel belongs based on the phase information, and based on the continuity of phase on space, the initial stripe order is corrected consistently, and the three-dimensional appearance of the measured object is recovered according to the corrected stripe order and phase information.The present application encodes by time domain, space domain and color domain, the present method significantly reduces the number of patterns that need to be projected, while ensuring measurement accuracy through color adaptation and phase-assisted decoding, and has stronger robustness for color surfaces.