5407 results about "Optical polarization" patented technology

A right-hand circularly-polarized patch antenna comprising a ground plane and a patch connected to each other with one or more wires for which the wire shape and location of the end points are selected such that they do not cause an antenna mismatch, and the electrical current carried in the wires produces an extra electromagnetic field subtracted from the patch field in the nadir direction.

The present invention relates to a solar azimuth estimation method and system based on multi-channel feature enhancement and region-aware attention, belonging to the technical field of intelligent navigation for low-altitude economy unmanned systems. Aiming at the problem of decreased accuracy in solar azimuth estimation based on polarization images under complex cloud cover conditions, the present invention proposes a deep learning framework integrating multi-channel features and direction-aware attention. First, based on polarization light field information acquired by a division-of-focal-plane polarization camera, a three-channel composite input feature composed of a polarization intensity map, an adaptive threshold gradient map, and high-frequency residual edge information is constructed. Second, a ResNet backbone network embedded with a squeeze-and-excitation mechanism is adopted, and a direction-aware polarization attention module is introduced to achieve adaptive fusion of multi-scale features through luminance guidance, deep feature enhancement, and a gradient edge branch.

The invention relates to the technical field of optical fiber communication monitoring, in particular to a passive optical fiber multi-parameter digital twin drive abnormal root cause positioning method and system. Collecting temperature, stress, acoustics and polarization signals, and constructing a time domain, frequency domain and energy domain coupling feature tensor and time sequence data set; performing nonlinear dimension reduction and feature decoupling by using a beta-VAE model, and dynamically quantifying contribution of each parameter to anomaly by using an integral gradient to form a contribution degree vector group; constructing a PINN digital twinborn model embedded with heat conduction and elasto-optical effects, and predicting a normal fluctuation range under contribution vector weighting and data-physics dual constraints; modeling measurement and prediction deviations under the guidance of contribution vectors, and outputting an abnormal measurement score, confidence, a position and a time sequence; and a causal graph neural network is constructed, topology and abnormal events are fused for tracing causes, a fault source is identified, and the model is subjected to closed-loop calibration. According to the invention, data driving and a physical mechanism are fused, and accurate detection and root cause positioning of the abnormity of the optical fiber system are realized.

The invention belongs to the technical field of industrial detection, and discloses a defect detection method and system based on honeycomb catalyst stacking. Omnibearing image data of honeycomb catalyst stacking are obtained through a multi-angle polarization imaging technology, pixel-level polarization degree parameters are calculated to construct a global polarization feature map, and accurate distinguishing between an intrinsic porous structure and suspected defects is achieved. A blind area identification and virtual view angle reconstruction mechanism is introduced, so that the problem of a stacked edge detection blind area is solved; and a layered reflectivity compensation function is adopted, so that the optical interference of an interlayer overlapping region is eliminated. Texture features are extracted through multi-scale morphological filtering, multi-dimensional feature fusion is carried out in combination with polarization features, edge continuity indexes and correction reflection intensity, and a high-precision defect discrimination model is established. And for a low-confidence region, dynamically adjusting detection parameters and performing iterative optimization to form an adaptive detection closed loop. According to the invention, the detection precision and reliability are improved, and the defect position, type and severity can be accurately output.

The invention relates to the technical field of bullet quality detection, in particular to a cartridge case surface defect lightweight detection method and system. The method comprises the following steps: acquiring a visible light image, a near-infrared image and a polarization image corresponding to a cartridge case to be detected, and generating an enhanced image by adopting a dynamic weight fusion algorithm; performing dynamic feature extraction on the enhanced image by using a feature extraction network; and segmenting the extracted feature map by adopting multi-scale segmentation to obtain a defect region, identifying a defect type corresponding to the defect region by utilizing a capsule network-based lightweight hybrid classifier, and outputting an identification result. According to the scheme, the defect detection precision and efficiency are improved, and the problem of poor environmental adaptability is better solved.

The invention discloses a human body infrared image small target detection method based on an improved FGLCM feature, and relates to the technical field of image processing and target detection, and the method comprises the following steps: building a boundary singularity auditing baseline under a unified time baseline, carrying out the multi-scale energy mapping of a curved surface fitting residual error of a human body infrared image, and generating a traction residual error distribution diagram; and constructing a reflection pseudo peak discriminator based on the traction residual distribution diagram, and extracting a pseudo peak kernel position by combining polarization sensitivity estimation and view angle transformation consistency constraint. According to the method, a closed-loop self-adaptive regulation and control mechanism is constructed through residual distribution auditing, pseudo peak identification, gradient registration, differential entropy enhancement and time sequence threshold adjustment, fitting abnormity and false highlight spots in the infrared image are inhibited, the accuracy and stability of small target detection are improved, and the method is suitable for a complex photo-thermal environment.

The invention discloses an image recognition system for industrial part defect detection, and particularly relates to the field of part defect detection, which comprises a multi-axis controllable light source array module, a high-speed polarization camera module, an edge computing node module, a double-branch semantic segmentation network module and a physical constraint post-processing module, according to the invention, through combination of time-sharing stroboscopic illumination and polarization image sequence acquisition, multi-dimensional perception of surface topography and material differences is realized; generating an elevation map and a normal map by using photometric stereo solution, constructing a differential rendering layer reverse matching CAD model, and extracting flash sensitive features; a double-branch U-Net network is adopted to fuse geometric and polarization characteristics, the characterization capability is enhanced through a trans-attention mechanism, and a pixel-level mask is output; and finally, mapping a two-dimensional result to a three-dimensional coordinate system by means of calibration parameters, carrying out geometric verification in combination with a tolerance zone and a height threshold value, and automatically generating a structured defect report containing position, size, grade and visual information.

The invention discloses a transformer oil leakage detection method and device based on polarization-ultraviolet fusion imaging, and the device comprises a housing, a support, a camera, an environment induction device, an overall controller, a power supply, a polaroid rotating wheel assembly, a lens seat assembly, and an image processor. And the motor driver, the illumination intensity sensor, the ultraviolet irradiance sensor, the image processor and the power supply are electrically connected with the integral controller respectively. According to the invention, a multi-angle polarization image and a non-polarization image in the same field of view can be acquired, and then polarization characteristics contained in an oil stain fluorescence signal are extracted and effectively distinguished from non-polarization characteristics of background light; in the daytime mode, the transformer oil leakage detection device can identify a target area with relatively high polarization intensity, and through image fusion enhancement processing, non-target background signals are significantly suppressed, and the fluorescence significance of an oil leakage characteristic area is improved.

The invention relates to the technical field of machine vision and optical detection, in particular to a tea color automatic evaluation method and system based on machine vision. The method comprises the following steps: constructing a stable and repeatable optical measurement environment and calculating radiation baseline parameters; performing multi-band polarization sequence imaging on the tea sample to obtain original data with spectrum and structural characteristics; separating mirror surface and diffuse reflection components on the surfaces of the tea leaves, and performing spectrum consistency correction by combining a radiation baseline; performing multiband spectrum reconstruction and normalization processing on the basis of the corrected diffuse reflection image, mapping to a CIE Lab color space, extracting pixel-level brightness, chromaticity and color distribution statistical indexes, and generating a color feature vector in combination with spatial weighting matrix optimization; a final score is calculated by constructing a quantitative evaluation and grade judgment model and integrating perception color separation, drying calibration color separation and a penalty term, and a grade result is output. According to the method, objective, accurate and automatic evaluation of the color of the tea leaves is realized.

The invention discloses a polarization-state-based optical fiber vibration sensing system and application, and relates to the technical field of optical fiber sensing, and the polarization-state-based optical fiber vibration sensing system mainly comprises a transmitting end and a receiving end. The transmitting end comprises a laser diode, a first erbium-doped optical fiber amplifier, a first circulator, a polarization scrambler, a single-mode optical fiber link, a second circulator and a second erbium-doped optical fiber amplifier which are connected in sequence; and the receiving end comprises a polarization beam splitter, a first shunt module, a second shunt module, an optical mixer, a first balanced photoelectric detector, a second balanced photoelectric detector, a third balanced photoelectric detector and a polarization analysis module. According to the optical fiber vibration sensing system based on the polarization state and the application, the vibration monitoring performance and reliability in a long-distance and high-noise environment can be improved.

The invention relates to the technical field of workpiece detection, and discloses an intelligent visual detection method and system for the surface of a workpiece, and the method comprises the steps: projecting a polarization structure light pattern to the surface of the workpiece, and synchronously collecting an image of the polarization structure light pattern after deformation on the surface of the workpiece; separating a structured light component and a polarized light component from the image, reconstructing a surface three-dimensional shape according to the structured light component, and generating surface polarization degree distribution according to the polarized light component; performing multi-scale gradient scanning on the surface three-dimensional morphology, extracting edge change features, performing texture consistency analysis on the surface polarization degree distribution, and identifying an abnormal texture mode; identifying a mirror reflection area based on the surface polarization degree distribution, performing height compensation on a corresponding area in the surface three-dimensional morphology, generating a corrected surface three-dimensional morphology, and combining edge change features and an abnormal texture mode; according to the invention, the accuracy and robustness of defect identification can be improved, and the reliability and efficiency of the system in industrial field application are enhanced.

The invention relates to the technical field of laser ranging, in particular to a double-optical-comb hybrid ranging device which comprises a signal detection optical path system and a signal demodulation optical path system. Wherein the signal detection optical path system comprises a first optical frequency comb, a first optical isolator, a first optical collimator, a first beam splitter prism, a reference mirror, a Faraday rotator, a convergence mirror and a target reflector; the signal demodulation optical path system comprises a second optical frequency comb, a second optical isolator, a second optical collimator, a half-wave plate, a second beam splitter prism, a third beam splitter prism, a first polarization controller, a first photoelectric detector, a reflector, a polarization beam splitter prism, a second polarization controller and a second photoelectric detector. A third polarization controller; and a third photoelectric detector. According to the invention, three ranging technologies of asynchronous optical sampling ranging, multi-heterodyne interference ranging and synthetic wavelength ranging are fused, and the problem that a large ranging range and high ranging precision cannot be simultaneously considered in the ranging process is solved.

The invention discloses a deep foundation pit crack feature coding detection method based on image recognition, and aims to solve the problems that a two-dimensional image is difficult to accurately characterize a three-dimensional crack, and the opening width and the slab staggering height are inaccurately estimated, the deep foundation pit crack feature coding detection method comprises the following steps of: calibrating and collecting through short time sequence and multi-polarization imaging, segmenting the crack to extract a center line, and dividing a left side domain and a right side domain; carrying out local reconstruction in a mask neighborhood by adopting a nerve radiation field or three-dimensional Gaussian sputtering, establishing a left implicit surface and a right implicit surface, fusing a polarization solution line, applying occupancy priori and seam-crossing repulsive potential in a gap region, combining a reference object to obtain an absolute scale, measuring a millimeter-level opening and a dislocation along a central line section, and generating a feature code; and threshold value and time sequence comparison judgment is carried out, and the technical effects of high-precision three-dimensional measurement, reliable risk assessment and traceable management of the deep foundation pit crack are achieved.

The invention discloses an insulator pollution intelligent identification method and system based on a multispectral laser radar, and belongs to the technical field of external insulation state monitoring and intelligent operation and maintenance of a power system, and the method comprises the steps: S1, employing a multi-wavelength laser radar which comprises at least three emission wavebands and comprises 1550 nm to scan an insulator, and selecting at least three wavebands from {355 nm, 405 nm, 532 nm, 905 nm, 1064 nm and 1550 nm}; distance gating is set according to the measuring range, and the width of a time window is 5 ns to 50 ns so as to suppress corona and background interference; through double calibration of an airborne reference sheet and a ground polarization datum plate, fitting is carried out after registration and calibration, angle response correction is carried out on a DPR, and meanwhile, the angle sensitivity of a weight is constrained in complex index solution, so that the relative fluctuation of an SGT under different visual angles is controlled within 3%, and the relative fluctuation of a DPR is controlled within 3%. Therefore, the problem of inconsistent identification results caused by attitude change and incident angle difference is solved.

The invention provides an imaging method and system based on a polarization imaging lens and visual collaborative optimization, and a medium, and the method comprises the steps: integrating a four-way polarization filter array on the surface of an imaging sensor, and synchronously collecting a four-channel polarized light intensity image through single-frame exposure based on the imaging sensor; obtaining a three-channel RGB image, and inputting the four-channel polarized light intensity image and the three-channel RGB image into a polarization-RGB fusion neural network; polarization features and RGB features are extracted, heterogeneous information coupling optimization is carried out, and fusion features are obtained; constructing a polarization-color joint decoding network, carrying out polarization and RGB information collaborative decoding on the fusion features, training a polarization decoding process and a material classification task together based on an end-to-end joint optimization strategy, and outputting a material classification result; high-efficiency acquisition of original polarization information on a hardware level is guaranteed through the polarization filtering array; and an end-to-end joint training strategy is adopted to realize optimal decoupling and fusion of perception information.

The invention discloses a machine vision-based enzyme freeze-dried powder quality detection method, and belongs to the technical field of machine vision, and the method specifically comprises the following steps: in a closed optical cavity, synchronously collecting a multispectral polarization sequence of a sample through annular multispectral polarization illumination and microscopic imaging; performing short-time airflow pulse disturbance and continuous imaging on the sample, and constructing a polarization time sequence texture map by means of inter-frame polarization retention difference; according to Stokes parameters, calculating a deskewness graph and a specular reflection component graph, and carrying out joint normalization on the deskewness graph and the specular reflection component graph and the polarization time sequence texture graph to form a multi-channel feature stack; constructing a double-branch encoder, and performing comparative learning on the feature stack to generate an impurity prototype dictionary; using the dictionary to match the feature stack pixel by pixel, and tracking and inhibiting powder agglomeration false detection through a topological constraint connected domain; and recovering a height map by using an oblique incidence fringe phase shift method, performing pixel-level fusion with the candidate image, retaining targets with height abrupt change and consistent polarization characteristics, and outputting an impurity mask.

The invention relates to the technical field of bionic navigation orientation and positioning, in particular to a carrier course angle measuring method based on polarized light imaging in a non-Rayleigh atmosphere. Comprising the steps of real-time sky polarized light imaging, atmospheric polarization mode resolving based on Mueller matrix imaging, non-Rayleigh polarization information interference removal, polarization orientation resolving based on Rayleigh scattering, space projection conversion and sun position information resolving. Alignment information of the sun in a carrier coordinate system is obtained by utilizing a Rayleigh scattering model and actual sky polarization imaging, and then a carrier course angle is obtained according to the orientation of the sun in a local geographic coordinate system, so that an orientation function is realized; meanwhile, the error influence caused by image registration and time-sharing rotation measurement of the multi-view-field polarization detector and the interference of environmental factors on a single point are avoided, the method can adapt to sunny and cloudy weather, is also applicable to cloudy and other non-Rayleigh weather, and is wide in application range.

The invention discloses a broadband full-Stokes polarization imaging device based on non-orthogonal four-channel polarization beam splitting, which comprises a dielectric substrate, a non-orthogonal polarization beam splitting metasurface and a focal plane detection array, and is characterized in that the non-orthogonal polarization beam splitting metasurface is composed of a plurality of sub-wavelength unit structures; the sub-wavelength unit structure is a single-layer anisotropic medium nano-column array and is configured to perform intrinsic-loss-free non-orthogonal four-channel beam splitting on incident light and form four spatially separated focuses on the same focal plane, and polarization states corresponding to the four channels form a regular tetrahedron measurement base on a Poincare sphere; therefore, full Stokes parameter measurement is completed by four pixels; the sub-wavelength unit structure forms a super-pixel unit, and the super-pixel unit is aligned and integrated with a focal plane detection array in a two-dimensional array form to form a compact polarization camera facing focal plane segmentation. The device is simple in structure, easy to integrate with the CMOS front end, small in device size, low in power consumption and high in mass production feasibility.

The invention relates to the technical field of wafer detection, in particular to a wafer defect detection method and device, and aims to detect wafer defects by adopting a polarization modulation and decomposition scheme according to corresponding characteristics of wafer surface scattered light and defect scattered light in a wafer defect detection process. The wafer detection method for improving the wafer defect detection accuracy is formed, and the wafer detection system for improving the wafer defect detection accuracy is formed according to the wafer detection method.

The invention discloses a bifunctional chiral metamaterial surface capable of switching polarization conversion and wave absorption, and belongs to the technical field of electromagnetic metamaterials. The method is used for solving the problem that most existing chiral super-structure surfaces cannot realize dynamic adjustability and quantitative controllability and cannot have dual functions of polarization conversion and wave absorption at the same time. The super-structure surface unit structure is composed of a graphene film layer, a gold-vanadium dioxide resonance layer, a silicon dielectric layer and a bottom-layer continuous gold film. Switching of two functions of polarization conversion and wave absorption is realized by changing the conductivity of vanadium dioxide; polarization conversion and dynamic regulation and control of the wave absorbing efficiency are realized by changing the Fermi level of the graphene; quantitative controllability of polarization conversion and a wave absorbing function is realized by controlling a function weighting function. Besides, the chiral super-structure surface also has the advantages of incident angle robustness, small thickness and small size, has double functions of broadband, and has potential application value in the fields of optical devices, communication equipment, biomedical sensors and the like.

The invention discloses a preparation method of a polymer dispersed liquid crystal holographic grating with s polarization high diffraction characteristics, and belongs to the technical field of holographic optics. Raw materials comprise 60-90% of a thiol-ene monomer, 10-40% of liquid crystals, a photoinitiator accounting for 1.25% of the mass of the monomer, and a coinitiator accounting for 1.56% of the mass of the monomer. Light with the wavelength of 532 nm and the light intensity of 5-30 mW / cm < 2 > is used for carrying out double-interference photoetching to generate photochemical reaction so as to generate the polymer grating film, and the light is s polarized light. Under the optimal recording condition, delta n under s polarization can reach 1.93 * 10, and delta n under p polarization can reach 1.21 * 10. In combination with morphology analysis, it is found that refractive index modulation strongly depends on the proportion of a liquid crystal-rich phase to a polymer-rich phase in the grating. It is proved that the size of liquid crystal microdroplets formed by holographic recording is larger due to low recording intensity, and therefore the threshold driving voltage of the HPDLC grating is reduced.

The invention discloses a method for detecting residual stress of a birefringent crystal, which is characterized by comprising the following steps of: fixing a sample to be detected on a sample loading table; the imaging lens is used for acquiring light rays which sequentially penetrate through the polarizer module, a sample to be detected on the sample loading table, the analyzer module and the camera module in four states in three states that polarization axes of the polarizer module and the analyzer module are mutually orthogonal and a polarization angle is gradually increased by 30 degrees, and in a state that the polarizer module and the analyzer module are in parallel, and the imaging lens is used for acquiring the light rays which sequentially penetrate through the polarizer module, the sample to be detected on the sample loading table, the analyzer module and the camera module in the four states; collecting a light intensity matrix set through a camera module; acquiring a reference light intensity matrix through normalized linear superposition, and performing pixel-by-pixel operation with the reference light intensity matrix on the basis of the first light intensity matrix, the second light intensity matrix and the third light intensity matrix to acquire corresponding phase delay matrixes; eliminating natural birefringence and updating a phase delay matrix by deducting respective overall average phase delay amount pixel by pixel; through pixel-by-pixel weighted stacking, isogradient lines are eliminated, and distribution information of residual stress is obtained.

An optical frequency domain reflectometer with environmental disturbance resistance and large strain measurement capability belongs to the field of distributed optical fiber sensing and comprises an opposite sweep frequency light frequency modulation continuous wave signal generation module, a light splitting device, a modulation device, a circulator, a polarization controller, an optical coupling device, a photoelectric conversion module and a data acquisition and processing module. An optical signal generated by an opposite sweep frequency light frequency modulation continuous wave signal generation module is divided into probe light and local oscillation light through a light splitting device, the probe light is modulated through a modulation device and sent to an optical fiber through a circulator, and a Rayleigh back scattering light signal generated by the optical fiber and the local oscillation light interfere in an optical coupling device to obtain interference light; the photoelectric conversion module mixes beat frequency signals of interference light, and the data acquisition and processing module analyzes and processes the beat frequency signals. According to the invention, the position information of the Rayleigh backscattering point is marked by using the modulated probe light, the Rayleigh scattering signal at the corresponding position is restored, crosstalk between channels is inhibited, and high-precision measurement in a large dynamic range and resistant to environmental disturbance is realized.

The invention relates to the field of optical measurement, in particular to a reflective interference film thickness measurement method and system for eliminating back scattering of a transparent substrate, and the method comprises the following steps: transmitting a light beam through a low-coherence-length broadband light source, and forming linearly polarized light through polarization modulation; focusing the light beam to the surface of the film through a confocal optical system; collecting reflection interference signals of the upper surface and the lower surface of the film; spatial filtering, low-coherence gating and polarization control are used for cooperatively inhibiting back scattering of the substrate. And processing the acquired interference signal, and calculating to obtain film thickness information. According to the invention, triple inhibition mechanisms are adopted for synergistic effect, and the method comprises the following steps: spatial filtering: shielding out-of-focus back reflected light through a confocal small hole; low-coherence gating: using a short coherence length to naturally suppress a reflected signal beyond a coherence range; and polarization control: further weakening stray light interference through polarization state matching, and effectively suppressing back scattering of the substrate.

The invention belongs to the technical field of vision measurement, and discloses a high-reflection curved surface reconstruction method and system based on multi-view point cloud fusion and optical optimization. The method comprises the following steps: acquiring multi-source heterogeneous data such as a stripe image, a polarization image and anchor point depth, and mapping the multi-source heterogeneous data to a unified workpiece coordinate system to form a standardized data set; calculating the normal direction of a sampling point based on data, establishing a slope field, and recovering the height through integration to obtain a geometric initial description of a curved surface; the method comprises the following steps: constructing a candidate light path through reverse ray tracing, generating a credibility weight in combination with a polarization degree, a reflection frequency, uncertainty and an incident angle index, and normalizing the credibility weight in a local neighborhood; fusing multi-source point clouds under the constraints of weights and anchor points, establishing a parameterized curved surface model, and constructing a joint optimization objective function containing geometric errors and optical consistency errors; and further adaptively adjusting a weight rule based on residual distribution, carrying out closed-loop iterative optimization, and outputting the initial surface shape of the high-reflection curved surface with high precision and good stability.

The invention discloses an underwater image enhancement method and system based on binocular vision and polarization imaging. The method comprises the following steps: firstly, synchronously acquiring an orthogonal polarization image pair through a binocular polarization imaging unit, recovering scene depth information from the polarization image pair by using a binocular stereoscopic vision technology, and calculating a transmissivity graph; analyzing the polarization characteristic difference between target reflected light and backscattered light, establishing a polarization difference model, and separating background scattered light; solving an underwater imaging equation in combination with the depth information and a polarization difference model to obtain a preliminary restoration result of the target reflected light; and finally, further improving the image quality through the steps of multi-scale spectrum analysis, adaptive filter construction and post-processing by adopting a spectrum adaptive image enhancement technology. The system comprises a binocular polarization imaging unit, a calculation processing unit and an active illumination unit. According to the method, the problems of color distortion, low contrast and fuzzy details of the underwater image are solved, and the visual quality and usability of the underwater image are improved.

The invention discloses a parameter measuring device and method of an optical switch and optical communication equipment, and relates to the technical field of optical switch measurement, and the parameter measuring device of the optical switch comprises an optical path module, a signal conditioning circuit, a driving module, a signal acquisition module and an upper computer. The optical path module converts the optical signal into a current signal; the signal conditioning circuit conditions the signal into a voltage signal and amplifies the voltage signal; the driving module provides a driving signal and a synchronous triggering signal; the signal acquisition module acquires a voltage signal based on the trigger signal; the upper computer calculates performance parameters of the optical switch according to the voltage signals acquired for multiple times, wherein the performance parameters at least comprise two items of insertion loss, extinction ratio, switching time and the like; according to the technical scheme, one-key measurement of performance parameters such as insertion loss, extinction ratio, switching time, polarization-dependent loss, insertion-dependent loss and repeatability of the optical switch can be realized, meanwhile, the measurement cost of the optical switch is reduced, and the test efficiency and accuracy are improved.

The invention discloses a large-view-field high-resolution imaging system based on polarization regulation and control, the large-view-field high-resolution imaging system comprises a metasurface system array and a camera along the direction of a light path, and the metasurface system array comprises a plurality of pairs of metasurface systems which are distributed in an array; each pair of metasurface systems comprises a first metasurface system and a second metasurface system; the first metasurface system is used for performing high-resolution imaging and large-view-field imaging on a first polarization light beam and a second polarization light beam of an incident light beam respectively; the second metasurface system is used for performing large-view-field imaging and high-resolution imaging on the first polarization-state light beam and the second polarization-state light beam respectively; the camera is used for acquiring and fusing images formed by different metasurface systems so as to capture a high-resolution central region of interest and surrounding environment information of a wide field of view. The system can efficiently realize higher imaging quality.

The invention relates to the technical field of machine vision detection, particularly discloses a mechanical part surface defect vision detection system, and aims to solve the problems of blind areas, environment light sensitivity, insufficient tiny defect detection capability and the like in the detection of complex curved surface high-reflection parts. Comprising an optical imaging module, a geometrical morphology sensing module, a dynamic polarization regulation and control module, an image fusion and enhancement module and a defect identification and decision module. The three-dimensional morphology of the surface of the part is sensed in real time, the imaging polarization state is dynamically regulated and controlled according to the three-dimensional morphology, multi-frame polarization image fusion and digital diffraction enhancement processing are combined, full-coverage and high-contrast detection of the complex curved surface part is achieved, motion blur is effectively restrained, and the detection capacity of sub-pixel-level tiny defects and the system environment adaptability are improved.

The invention relates to the technical field of computer vision, and discloses a vision-based steel structure positioning and grabbing method, which comprises the following steps of: acquiring a steel structure image through a polarization-adjustable multi-light source array and inhibiting reflective interference; performing multi-scale feature extraction on the image to generate a feature point cloud containing welding seam and contour information; if the point cloud has shielding missing, extracting a topological sub-graph of a corresponding region from a pre-stored BIM model; seamlessly splicing the topology sub-graph and the field point cloud by taking curvature continuity as a constraint to generate a compensation point cloud; and finally, the manipulator is controlled to execute avoidance grabbing in combination with the boundary coordinates of the reflective area. The method effectively solves the problems of incomplete point cloud data and low grabbing precision of the steel structure in light reflection and shielding environments, realizes high-precision pose reconstruction and safe grabbing control, and is suitable for automatic construction and assembly scenes of the steel structure.