1874 results about "Optical image" patented technology

Systems and methods are disclosed for classifying objects using electro-optical and synthetic aperture radar images through multi-modal feature alignment and fusion. A computing system acquires and preprocesses image data, then aligns features across modalities using a multi-modal alignment engine. A cross-modal attention fusion network extracts and integrates complementary information using transformer-based attention mechanisms. A modality-specific feature extraction framework processes EO and SAR images through specialized branches, ensuring optimal feature representation. An adaptive fusion decision system dynamically determines the best fusion strategy based on image quality and confidence scores. A self-supervised consistency controller enforces alignment between EO and SAR features using contrastive learning. The fused representations are processed by a neural network to generate object classifications. This system improves accuracy and robustness in environments where one modality may be degraded or missing, enhancing applications such as remote sensing, surveillance, and autonomous navigation.

The invention relates to the technical field of machine tool casting detection, and discloses an automatic detection system for surface defects of machine tool precision castings. The system comprises a surface information acquisition core module, a first defect identification core module, a second defect identification core module and a defect type fusion core module. The surface information acquisition module is used for synchronously acquiring real-time optical images and process parameter data in production aiming at the surface of the casting part, and constructing a defect diagnosis characteristic spectrum and an auxiliary text according to the real-time optical images and the process parameter data; the first defect recognition module inputs the atlas and the auxiliary text into a pre-training double-flow convolutional neural network to generate a first classification result of defect types; a second defect identification module extracts defect mechanism characteristic values from the atlas and matches the defect mechanism characteristic values with a pre-stored defect mechanism knowledge base to obtain a second classification result; and the defect type fusion module fuses the two types of results to determine a target defect type. The system solves the problems of single detection information and identification deviation in the prior art, improves the detection accuracy and real-time performance, and meets the requirements of different production scenes.

The invention relates to the technical field of landslide information extraction, in particular to an SAR image landslide information extraction method based on a deep learning algorithm. The method comprises the following steps: acquiring an SAR image and an optical image of a seismic region; mapping the landslide boundary marked in the optical image to the SAR image so as to mark the SAR image to obtain a label image; constructing a data set based on the original image and the tag image of the SAR image; training a pre-constructed semantic segmentation model by using the data set; and generating a segmentation image based on the trained semantic segmentation model to extract a landslide region. On the basis of the SAR image with rich polarization characteristics, the deep learning semantic segmentation network is used for landslide region segmentation, and the better segmentation precision is realized.

The invention discloses a mobile phone silica gel shell appearance detection system based on an optical image sensor, and relates to the technical field of appearance defect detection and intelligent visual identification. An image acquisition module acquires a high-quality multi-channel image through multi-angle synchronous acquisition; the dynamic light field regulation and control module realizes self-adaptive regulation of a regional light source based on reflectivity perception and a gray gradient change rate; the image processing and defect identification module fuses edge features, texture changes and a deep learning model to realize pixel-level defect classification; the material identification and shielding module identifies a non-silica gel area through multi-dimensional spectral features and eliminates interference; a time sequence defect evolution analysis module models a defect evolution track; the trend prediction module is used for predicting the extension trend of potential cracks and fatigue areas; the control feedback module realizes intelligent judgment and response linked with the manufacturing system; the system can realize high-precision and high-robustness automatic defect detection and risk prediction, and is suitable for online quality monitoring of large-batch flexible products.

The invention discloses a multi-source remote sensing image zero sample change detection method, and relates to the technical field of remote sensing image processing, and the method comprises the following steps: obtaining remote sensing images collected by two or more remote sensing sensors at different time points in the same geographic area, the image types including optical images and radar images; preprocessing each source image, unifying the spatial resolution and the registration precision, and denoising and standardizing the image; according to the method, the cross-modal shared semantic embedding space is constructed and unsupervised comparative learning is introduced, so that the semantic consistency of the multi-source remote sensing image is effectively improved, and the change recognition capability of the model under the zero sample condition is enhanced; and meanwhile, a difference fusion calculation and structure consistency constraint module is adopted, so that the boundary judgment precision of a change region and the overall structure consistency are improved, and the accuracy and stability of a detection result are remarkably improved.

The invention relates to the technical field of land resource monitoring, in particular to a land resource dynamic monitoring and early warning method and system based on multi-source remote sensing data fusion, and the method comprises the steps: employing an unmanned plane to periodically collect optical images, SAR echoes and LiDAR point clouds, constructing a ground three-dimensional digital model, and carrying out the land parcel division; performing fusion to form a multi-dimensional feature vector, establishing an LSTM land parcel feature evolution model, and predicting a change rate interval of each feature in a current period based on a historical sequence; constructing a time sequence difference change detection algorithm, calculating a land parcel change rate, and screening potential abnormal land parcels by taking a prediction interval as an anomaly judgment threshold value; a double-branch convolutional neural network is adopted to identify crop states, growth stages and construction violation behaviors, abnormity is judged and determined, and confidence is given; spatial clustering is carried out on determined abnormal land parcels, accurate boundaries are obtained in combination with a three-dimensional model, multi-level early warning information is generated, and the decision-making efficiency and response speed of land resource monitoring are improved.

The invention provides an underwater target identification method and system based on multi-source sensor data fusion. The method comprises the following steps: firstly, synchronously acquiring an original sound wave reflection signal and original optical image data of a target underwater area, then carrying out acoustic compensation processing on the original sound wave reflection signal to generate a target sound wave reflection signal, and meanwhile, carrying out optical compensation processing on the original optical image data to generate target optical image data; performing dynamic weighted fusion on the reliability measurement of the target sound wave reflection signal and the reliability measurement of the target optical image data through an adaptive fusion module to generate an enhanced multi-modal data set; and finally identifying the specific category of the underwater target through a multi-modal feature matching and decision-making mechanism. According to the technical scheme provided by the invention, the limitation of a single sensing mode is overcome, the quality of collected information is improved, the direct confirmation efficiency of common target recognition is also improved, and high accuracy and data reliability of target category recognition in a complex scene are ensured.

The invention discloses a nondestructive testing device for a steel profile and a testing method of the nondestructive testing device. According to the method disclosed by the invention, the ultrasonic technology is combined with optical imaging, so that synchronous detection of surface and internal defects can be completed at one time. Ultrasonic waves penetrate through the interior of the steel profile, and hidden defects such as cracks and air holes are accurately recognized; the optical camera module captures visible problems such as surface scratches and corrosion in real time. The integrated detection mode avoids the tedious process of step-by-step operation required by a traditional method, for example, magnetic powder detection of surface defects and ultrasonic scanning of an internal structure are not needed, the detection period is greatly shortened, and the method is especially suitable for steel structure buildings, bridge engineering and other scenes with high requirements for detection efficiency and has good application prospects. The full-process automatic design effectively reduces the influence of human intervention, and ensures the scanning continuity of the detection area; the intelligent algorithm automatically analyzes the ultrasonic echo signal and the optical image data, and judges the defect level according to the preset standard, thereby avoiding subjective misjudgment of manual visual inspection.

The invention relates to the technical field of water purifier outer surface defect detection, and provides a water purifier outer surface defect detection method based on deep learning, and the method comprises the steps: constructing a water purifier outer surface multi-modal defect data set comprising a traditional image and an optical image; constructing a defect detection model based on the water purifier outer surface multi-modal defect data set; inputting a traditional image in the multi-modal defect data set of the outer surface of the water purifier into the high-precision defect classification model for training, and outputting traditional image features; inputting an optical image training set in the multi-modal defect data set of the outer surface of the water purifier into an anti-interference optical defect detection model for training, and outputting optical image features; inputting the traditional image features and the optical image features into a multi-modal sensing network to obtain a trained defect detection model; evaluating the trained defect detection model by using the verification set to obtain a verified defect detection model; and detecting the outer surface defects of the water purifier by using the verified defect detection model.

The invention discloses an optical imaging and coding hole technology fused optical imaging system and method, and aims to integrate scattered polarization components in a reflected light signal into coding light field data with clear layers by constructing a polarization coding modulation system, so as to highlight a coupling relationship among optical elements. A refocusing sequence and a focal plane chromatography technology are adopted, spatial geometric information and light intensity distribution characteristics of different depth layers are fully excavated, and a three-dimensional distribution rule of surface topography is disclosed; wavefront correction and deformable mirror control technologies are introduced, imaging parameters of an optical system are adjusted in a self-adaptive mode, and the application range of measurement precision is expanded; light intensity modulation analysis and phase unwrapping window processing are combined, the change trend of the surface curvature is depicted, and key feature points of morphology measurement are grasped; finally, multi-dimensional and multi-level optical measurement information is fused, three-dimensional measurement output with rich content and reliable precision is formed, and comprehensive and high-quality measurement technology resources can be provided for application scenes such as precision optical detection and surface quality evaluation.

The invention discloses an electrostatic induction and optical imaging principle-fused online monitoring device and method for wear particles of a water-lubricated bearing, and belongs to the field of state monitoring of mechanical equipment. The device comprises a square insulation detection cavity, a detection electrode array, an electromagnetic shielding shell, a high-speed optical imaging module and a signal processing unit, the square insulation detection cavity is installed in a bearing lubrication water loop. The detection electrode array is fixed to the outer wall of the cavity and used for capturing electrostatic signals generated when the abrasion particles pass through. The electromagnetic shielding shell wraps the detection cavity and is grounded through a wire to eliminate environmental electromagnetic interference. The high-speed optical imaging module integrates a high-magnification microscope lens and a CMOS sensor, is coaxially mounted with the detection cavity, and obtains the morphology characteristics of the wear particles in real time; and the signal processing unit performs multi-modal data fusion analysis on the electrostatic signal and the optical image. Through cooperative detection of electrostatic induction and optical imaging, the monitoring precision and reliability of the wear particles of the water-lubricated bearing are remarkably improved.

The invention discloses a photovoltaic module surface defect online detection method based on multi-modal image fusion, and relates to the technical field of photovoltaic module detection.The method comprises the steps that a visible light line-scan digital camera, a short-wave infrared camera, an EL line-scan digital camera and a laser speckle imaging module are installed to collect real-time data, an optical image is subjected to dynamic window median filtering, and the surface defect of the photovoltaic module is obtained; the method comprises the following steps: carrying out time moving average combined dynamic threshold segmentation on an infrared image and an EL image, carrying out image-guided outlier filtering on 3D point cloud data, judging a pixel defect type based on gray-temperature correlation and calculating a fusion weight, respectively inputting the optical image, the infrared image, the EL image and 3D point cloud into GhostNet, lightweight ViT, CNN and PointNet-Lite to extract features, and carrying out image fusion on the 3D point cloud data. And after global average pooling and splicing, inputting into a channel attention module to generate a modal weight, and after weighted fusion, obtaining a defect type through a full connection layer. According to the invention, the accuracy of defect detection is effectively improved.

The invention relates to the technical field of oral implantation monitoring, and discloses a monitoring method for analyzing oral implantation health based on using images. The method comprises the following steps: acquiring an optical image data sequence of an oral implanting region by adopting optical scanning equipment, constructing a three-dimensional oral tissue model containing gingival contour features and an implant position, and identifying actual position distribution information of an implant in gingival tissue; and extracting an implant health index set comprising an implant marginal definition value, a surrounding gingival red and swollen area proportion and a gingival atrophy degree value. When any index exceeds a preset health threshold interval, abnormal early warning information is generated, scanning parameters are dynamically adjusted, and images are collected again for iterative monitoring. According to the method, dynamic and accurate monitoring of oral implant health can be realized, health abnormity of the implant can be found in time, and support is provided for long-term health maintenance of the implant.

The invention relates to the technical field of satellite remote sensing monitoring, in particular to a method for monitoring a resident-free island by adopting satellite remote sensing, which comprises the following steps of: acquiring optical images and cloud layer data of a target island through optical and meteorological satellites, predicting a cloud shielding probability, and scheduling a radar satellite when the cloud shielding probability exceeds a threshold value; comparing the effective area of the optical image with a reference demand, triggering radar imaging when a difference value reaches a preset proportion, extracting a coastline feature point set from a historical image, calculating a spatial distribution entropy screening subset, constructing an optimized affine transformation matrix to compensate a radar image, and obtaining a new optical image when the cloud cover is low. Coastline feature point errors of the calibration radar image and the new optical image are calculated, secondary compensation is carried out, global time sequence monitoring data are generated, monitoring continuity and data consistency in a cloud shielding scene are improved, and the method is suitable for resident-free island dynamic monitoring.

The invention relates to a metal surface defect identification method and device based on artificial intelligence, equipment and a medium. The identification method comprises the following steps: synchronously acquiring an electromagnetic impedance signal and an optical image of a metal surface based on an eddy current sensor and an industrial camera; generating a spatially positioned interference area mask by quantifying cross-physics field interference intensity of the electromagnetic gradient and the optical edge feature; performing skin effect compensation on an electromagnetic signal by using the mask, and simultaneously performing shadow suppression on an optical image to realize physical field decoupling; a double-branch neural network is called to fuse the decoupled electromagnetic impedance features and optical texture features, and cross-modal associated joint feature expression is established; and analyzing the defect probability heat map based on the fused features, and outputting defect types and coordinates in combination with geometric feature matching. According to the method, the problem of defect feature mixing caused by mutual interference of electromagnetic-optical signals is solved, and the recognition precision and the positioning reliability of the micro defects are remarkably improved.

The invention discloses an intelligent water quality monitoring and evaluating system based on image recognition, which relates to the technical field of environment monitoring, and comprises a fusion module for controlling a polarizer array to rotate based on an environment parameter set, capturing water surface optical images in different polarization directions, and performing image reconstruction through a polarization characteristic tensor decomposition method, generating a high-definition water surface image after reflection suppression; the three-dimensional diagram generation module is used for acquiring a morphology stripe image of the water surface through a DLP projection method, and generating a three-dimensional depth diagram in combination with the high-definition water surface image; the pollution identification module is used for correcting the three-dimensional depth map based on the real-time water temperature data, identifying spatial distribution of pollutants through a dynamic structure element opening and closing algorithm and generating a three-dimensional pollution distribution map; according to the method, mirror reflection noise is suppressed through multi-angle polarization image fusion, and the distinguishability of pollutant characteristics is remarkably enhanced while the image resolution is kept.

The invention particularly relates to a ship multi-modal image fusion recognition method based on graph neural structure alignment, and the method comprises the following steps: 1, obtaining a ship multi-modal image, and constructing a backbone neural network to extract the features of the multi-modal image; 2, constructing graph nodes of the graph neural network, and generating an adjacent edge relationship; 3, for graph structures constructed in different modes, adopting a two-level graph attention mechanism to complete structure alignment; step 4, utilizing an optimal transmission mechanism to realize structure alignment between the infrared and visible light modal diagrams; step 5, feature re-injection is carried out to fuse space coordinates and global information, and the positioning and expression ability of node features is improved; and step 6, training the constructed ship multi-modal image fusion recognition network by adopting local feature alignment loss, graph-level semantic consistency loss and classification supervision loss. According to the method, the problem of alignment errors caused by inconsistency of infrared and visible light modal images is solved, the structure and semantic information of the infrared and optical images are fully fused, the accuracy and robustness of cross-modal target recognition are effectively improved, and the method is suitable for complex scenes such as multi-modal ship recognition.

The invention relates to the technical field of optical localization, in particular to an optical localization feedback control system in a minimally invasive surgery of bile adipoma. The system comprises the following steps: an image optimization module is used for scanning a full-band optical image in an operation cavity, performing adaptive contrast optimization and constructing a spectrum optimization image; the focus positioning module is used for performing accurate focus positioning on the spectrum optimization image and extracting a focus optical contour; the three-dimensional reconstruction module is used for performing structural feature point identification and three-dimensional reconstruction on the spectrum optimization image to construct a three-dimensional structure model; and the visual error compensation module is used for performing multi-angle optical ranging and stereoscopic visual error compensation on the optical contour of the focus to obtain a three-dimensional compensation positioning coordinate. According to the invention, through real-time accurate position positioning, the instrument response speed and the tissue identification precision are improved.

The invention belongs to the technical field of fan damage detection, and particularly discloses an unmanned aerial vehicle-based offshore fan blade damage detection system, which comprises a detection partition determination module, an unmanned aerial vehicle acquisition control module, a damage image acquisition module, a fan damage analysis module and a fan damage feedback terminal. According to the method, the damage point and the blade area are positioned through preliminary cruising of the unmanned aerial vehicle, and the fan array is divided, so that the dilemma that a traditional detection mode is easily interfered in an offshore high-wind-speed environment is changed, and the complicated offshore environment can be flexibly coped with; meanwhile, the shooting distance and the shooting time point of the unmanned aerial vehicle are adjusted by combining the space coordinates of the damage point, the real-time blade rotating speed and the real-time offshore wind condition to generate a shooting parameter instruction, so that the limitation and the monitoring dead angle limitation of traditional fixed-view-angle monitoring are broken through; and finally, crack analysis of different depth layers is carried out on the optical image and the ray image, so that the damage degree can be evaluated more comprehensively and accurately.

The invention discloses a soil water content inversion method based on improved combination roughness, and relates to the field of remote sensing, and the method comprises the steps: synchronously obtaining a Sentinel-1 radar image and a Sentinel-2 optical image, and extracting different polarization backscattering coefficients, local incident angles and normalized water body indexes through preprocessing; the method comprises the following steps: generating a bare soil simulation backscattering coefficient data set, removing vegetation scattering contribution by using a water cloud model, obtaining a real bare soil backscattering coefficient, constructing a training set and a verification set containing actually measured soil water content, constructing a lookup table based on double models, and calculating the water content of the bare soil by minimizing a root-mean-square error between simulation and the real backscattering coefficient. Global search is carried out in a preset parameter space to determine an optimal earth surface root mean square height and a correlation length, a novel polynomial combination roughness is constructed, a physical correlation between the roughness and a backscattering coefficient is established, a dual-polarization empirical equation set is constructed, and simultaneous solution is carried out after parameters are optimized according to a criterion; according to the method, a more reasonable inversion result of the soil water content in a large range can be obtained.

The invention discloses a fault slip model smoothing method based on SAR observation data, and the method comprises the steps: firstly, obtaining multi-source observation data (including SAR, GNSS and optical images), and carrying out the joint calculation, and generating a high-resolution earth surface deformation field; the method comprises the following steps: combining a remote sensing image, visually interpreting and drawing a fracture trace, then carrying out data downsampling along an inclination angle direction, and finally constructing an irregular fault geometric model by using a TIN method so as to obtain an initial fault plane model. On this basis, a Laplacian operator suitable for triangular dislocation is defined, a slip inversion model is constructed in combination with an elastic dislocation theory, and a smoothing factor is introduced to balance slip details and calculation efficiency. And finally, optimizing a fault inclination angle and a smoothing factor through a grid search method, evaluating fitting errors and slippage roughness under different combinations, and determining optimal parameters. The final model not only comprises a triangular connection relation, but also provides slip amount distribution and fault dip angle information, and an important basis is provided for seismic activity evaluation and disaster response.

The invention discloses an image measurement method for precise size measurement. The method comprises the following steps: step 1, selecting a laser scanner and an optical image measurement instrument to form a measurement array according to geometrical characteristics of a workpiece; 2, calibrating and verifying the measurement array, obtaining a basic error curve of the equipment through a standard gauge block, and collecting real-time environmental parameters after verification is passed; 3, calculating an environment interference coefficient Kenv, and starting measurement at the moment; 4, monitoring equipment acceleration sensor data in real time, and generating an equipment stability index Si; 5, when Si is larger than S < safety >, measurement is executed, and a result is output; and step 6, carrying out consistency analysis on multi-device results, if the results are consistent, outputting a final value, otherwise, triggering dynamic re-calibration. According to the invention, multi-dimensional cooperative control can be realized, the precision bottleneck of traditional image measurement in a dynamic environment is broken through, and the method is suitable for precision manufacturing scenes with high requirements on measurement stability and reliability.

The invention discloses an underwater robot target identification and tracking evaluation method based on deep learning, and the method comprises the steps: obtaining a target optical image, a sonar echo signal and a flow field parameter, constructing multi-modal data, and carrying out the preprocessing and space-time alignment; target apparent features and flow field features are extracted, dynamic weight fusion is carried out, and a target identification result is obtained through classifier processing; constructing a trajectory prediction model based on the target identification result and the flow field dynamic characteristics, and obtaining an initial trajectory prediction result by combining historical trajectory data optimization; constructing an implicit flow field model, and performing joint training with the trajectory prediction model to obtain an optimized trajectory prediction model; and a trajectory prediction result output by the optimized model is obtained, deviation is calculated in combination with actual trajectory data, the physical constraint weight and the target identification parameters in the trajectory prediction model are dynamically adjusted according to the deviation, and high precision and strong robustness of underwater target identification tracking of the underwater robot can be effectively improved.

The invention discloses a semiconductor processing defect detection method based on artificial intelligence, and relates to the technical field of semiconductor processing defect detection. The method comprises the following steps: acquiring wafer position coordinates, an optical image and process equipment dynamic parameter data; generating a microdefect feature matrix by using a multi-scale Gaussian filtering model and an asymmetric convolution algorithm; converting the process parameters into a position-associated process parameter matrix through space-time mapping and a correlation matrix algorithm; performing radial pooling and multi-expansion-rate cavity convolution algorithms on the fused feature tensor, and extracting global and local feature vectors; generating a defect probability distribution diagram by adopting a polar coordinate dynamic weighted fusion algorithm; and outputting the defect coordinates and the type identifier through an adaptive threshold algorithm, and generating a process equipment control signal according to predefined logic. Through an innovative multi-source data fusion calculation model, accurate defect identification and process closed-loop control are realized, and the detection precision and efficiency are improved.

The invention discloses a light field surface defect identification system and method based on multi-angle scattering, and relates to the field of optical image analysis. The system comprises a multi-angle scattered light field acquisition module and a defect intelligent identification module. The acquisition module obtains a hemispherical space scattered light field image of an optical element to be detected through one-time exposure of a collimation laser light source, a hemispherical dome and the like. The recognition module integrates a data preprocessing unit and an SFD-YOLO network, and on the basis of YOLOv11, the network replaces CBS in a shallow layer with a PSiam attention module to strengthen local significant feature perception, and replaces C3K2 in a deep layer with an OfficitMambaCSP module to strengthen global semantic modeling. The method comprises the steps of image acquisition, data set generation preprocessing, network training and defect identification. The problems that in the prior art, single-view-angle information is limited, and scattering data is insufficient in utilization are solved, Top1ACC reaches 95.6%, the parameter quantity is only 1.25 M, and the method is suitable for high-precision real-time detection of optical element defects.

The invention belongs to the technical field of geological disaster monitoring and early warning, and relates to a rainfall type landslide-debris flow chain disaster intelligent dynamic monitoring and early warning method, which comprises the following steps: data acquisition: generating multi-source data including an optical image, an SAR image, an unmanned aerial vehicle image and ground data; preprocessing the multi-source data; performing space-time registration, data format and organization on the multi-source data after data processing; key characteristic parameters are calculated, and data fusion is carried out; constructing a multi-dimensional feature vector, and generating a multi-dimensional feature image; constructing a risk assessment model by using a deep learning model, and performing real-time prediction; dynamically determining the total risk level of each area according to a preset comprehensive research and judgment rule by integrating the real-time prediction result; and when the total risk level reaches a'high risk 'or'extremely high risk' threshold value, generating early warning information, and performing early warning release. According to the invention, comprehensive, whole-process three-dimensional perception, dynamic and self-adaptive intelligent evaluation and disaster prediction are realized.

The invention discloses a registration method and system for an optical image and an SAR image of the moon, and relates to the technical field of image registration, and the method comprises the steps: firstly determining the same typical moon appearance object in an image to be registered, and enabling the corresponding optical and SAR region images to form a region image pair; performing feature extraction and matching on each regional image pair by using a feature-based registration algorithm to obtain a preliminary matching point pair, and screening out a high-confidence matching point pair; and calculating a region affine transformation matrix of each region image pair based on the high-confidence matching point pairs, constructing a global optimization objective function according to all region affine transformation matrixes, solving an optimal affine transformation matrix, and finally realizing accurate registration of the to-be-registered image.

The invention belongs to the technical field of remote sensing image analysis, and provides a multi-source remote sensing building extraction method based on hybrid experts, electronic equipment and a storage medium. The method comprises the steps of basic model construction, two-way structure model construction, optical feature extraction, earth surface feature extraction, two-way feature fusion, ViT coding, feature injection and extraction and semantic alignment step-by-step up-sampling. According to the invention, a dual-path structure is adopted to assist the multi-scale encoder and the bidirectional attention fusion module, and DSM data and optical images are used for feature fusion, so that the capability of distinguishing buildings from backgrounds is improved; the hybrid expert LoRA structure is introduced into the ViT encoder, parameters of the feedforward neural network are dynamically adjusted, the adaptability and flexibility of the model to input features are further enhanced, and the calculation complexity is reduced.

The invention relates to the technical field of industrial vision, in particular to an aviation part crack detection and repair method which comprises the following steps: acquiring an aviation part optical image at a reference time point and an aviation part optical image at a to-be-detected time point; according to the method, logarithmic polar coordinate transformation is carried out on different time point images, rotation, scaling and translation parameters are extracted, an image registration relation is established, the structural consistency of time sequence images in a local area is enhanced, a structural tensor is constructed for each pixel neighborhood, the change characteristics of the dual-time-phase tensor are compared, a structural change saliency map is generated, and the structural change saliency map is obtained. Sensitive capture of a tiny deformation area is achieved, the responsiveness to an initial crack is improved, then a crack propagation interval is further refined into a main crack path in a self-adaptive threshold segmentation and skeleton extraction mode, the tip acutance of the crack is calculated in combination with tip contour information of a geometric boundary of the crack, and the initial crack is obtained. And quantitative support is provided for the crack danger degree.

The invention provides an injection molding part surface flaw detection method and device based on double-model collaboration, and the method comprises the steps: carrying out the local abnormal reflection feature analysis of a multi-view optical image collected on the surface of an injection molding part based on a first detection model, and obtaining a candidate flaw region; performing spatial positioning in the multi-view optical image based on the candidate flaw area to obtain a multi-view candidate image segment; performing surface geometric continuity analysis on the multi-view candidate image segments based on a second detection model to obtain a three-dimensional surface geometric consistency result; carrying out authenticity discrimination on the candidate flaw area based on a three-dimensional surface geometric consistency result to obtain a real flaw area; wherein the first detection model is used for capturing an optical response model of local abnormal reflection characteristics; the second detection model is a stereoscopic vision model for analyzing the geometric continuity of the multi-view lower surface. According to the invention, the false alarm rate of surface defect detection of the injection molded part under a complex surface condition is reduced.