10058 results about "Visual detection" patented technology

The invention discloses a welded pipe surface defect detection system, particularly relates to the technical field of metal pipe surface quality detection, and is used for solving the problem of defect misjudgment and missing detection caused by mixed reflection interference under single light source irradiation in the existing visual detection technology. An annular light source is adopted for time-sharing pulse triggering through a light source control module, reflected light images at different angles are synchronously collected, a feature extraction module constructs a diffuse reflection intensity ratio and mirror reflection angle distribution matrix to generate a three-dimensional reflection feature spectrum, and reflection anomaly characterization of a defect area is enhanced; the area positioning module screens candidate areas and inhibits interference by combining strength ratio circumferential deviation degree and reflection angle gradient change, and the distortion correction module compensates geometric distortion errors based on curvature radius and station movement parameters, filters pseudo defects of abnormal time sequence fluctuation, and improves the accuracy of the distortion correction. And the defect judgment module utilizes a gradient-gray scale space coupling classification model to distinguish the types of cracks, scratches and corrosion, and finally judges the defect authenticity in combination with reflection characteristic deviation vector superposition.

The invention relates to the field of semiconductor packaging material defect detection, in particular to a semiconductor packaging material defect detection method based on deep learning, which comprises the following steps: acquiring a surface image, and extracting a two-dimensional contour and a feature point set; preprocessing the image, and separating a packaging material main body area; constructing a two-dimensional defect identification model based on Transform, and outputting a two-dimensional detection result; scanning suspected and unknown defect areas to obtain three-dimensional point cloud data, and extracting geometric and texture features; fusing two-dimensional and three-dimensional data through a space-time alignment model; utilizing the multi-modal fusion model to output defect positions and types; and evaluating the defect importance based on the material node connectivity and the stress distribution, and generating a visual detection report. According to the invention, high-precision detection of semiconductor packaging material defects is realized, the defect identification rate, the positioning precision and the detection efficiency are improved through multi-modal data fusion and a deep learning model, and a visual report can be generated based on material structure quantification defect importance.

The invention discloses a portal crane grab bucket control system and method based on multi-sensor fusion, and particularly relates to the technical field of portal crane grab bucket control. Image acquisition equipment and multiple types of sensors are arranged in a portal crane operation area, a multi-dimensional input data set under a unified time sequence is constructed, an optimized visual detection model and an attention mechanism are combined, high-precision recognition and abnormity judgment of the grab bucket state are achieved, and the system not only can automatically plan a grabbing path and a posture adjusting instruction, but also can automatically adjust the grabbing posture of the grab bucket. And control parameters can be dynamically optimized according to the grabbing effect and pose feedback, the grab bucket recognition accuracy, the control stability and the system intelligence level are remarkably improved, and particularly higher robustness and reliability are shown in the small-size, complex-pose or multi-target operation environment.

The invention provides an intelligent high-performance collaborative welding robot system, which belongs to the technical field of welding robots and comprises a multi-degree-of-freedom welding robot body, an intelligent control system, a high-performance welding power supply and auxiliary equipment. A welding process control module firstly obtains three-dimensional information of a workpiece based on visual inspection to construct a welding path; then selecting matched process parameters according to material characteristics and welding seam shapes; establishing a welding error matrix to monitor the welding process in real time; constructing a parameter error adjustment matrix for dynamic adjustment; analyzing parameter fluctuation by adopting a neural network to identify molten pool characteristics; the pre-trained neural network is used for evaluating the welding seam quality; and finally, a multi-robot collaborative welding strategy is integrated to achieve efficient operation, and the technical problem that in the prior art, welding process parameters in a welding robot are difficult to adjust accurately in real time so as to adapt to complex working condition changes is solved.

The invention discloses a visual detection system and method for tiny flaws of industrial products, and belongs to the technical field of product detection, multi-source image data of a target industrial product under multiple detection angles and illumination conditions are acquired, and an image information matrix is established; performing region segmentation and texture enhancement on the image, and extracting local texture direction inconsistency parameters; carrying out normalization analysis on the pixel ratio under different spectrum channels, and calculating a multispectral reflectance ratio abnormal index; constructing a deep convolution recognition model; reasoning the image by using the model, and outputting a defect judgment result and a confidence score; judging whether the area is a flaw area based on a dynamic threshold mechanism, and outputting a detection report containing flaw position information and a visual heat map; according to the method, multi-dimensional fusion identification of texture structure disturbance and spectral response abnormity is realized, the micro defect identification precision is effectively improved, and the method has high robustness, automation and engineering practicability and is suitable for high-precision quality control requirements of various industrial scenes.

The invention discloses an unmanned aerial vehicle small target aerial photography detection method and system based on RT-DETR, a medium and equipment, and belongs to the technical field of unmanned aerial vehicle visual detection, aerial photography images are collected based on an unmanned aerial vehicle, the images are input into a trained target detection model, and target position and category information is obtained. The method comprises the following steps: firstly, extracting low-layer features of an image, and simultaneously capturing information of a channel dimension and a space dimension based on an efficient multi-scale attention mechanism; and outputting features through the convolution residual block. Key features are processed based on a single-scale feature interaction module; for the coded feature map, fusing information of a shallow layer and information of a deep layer step by step in an up-sampling and transverse connection mode; in a down-sampling stage, context semantic information of a target is reserved, and global and local information interaction is enhanced. According to the method, the accuracy and robustness of small target detection are remarkably improved, and the practicability and deployment value in actual application scenes such as unmanned aerial vehicle aerial photography and remote sensing monitoring are expanded.

The invention relates to the technical field of image analysis, in particular to a heat exchanger welding quality visual inspection method and system, and the method comprises the following steps: collecting original image data from a welding image, carrying out the preprocessing of the original image data, including noise removal and brightness adjustment, and obtaining a preprocessed image; according to the method, in the whole process from welding image data collection to defect recognition result generation, preprocessing operation based on high-frequency noise pixel filtering and gray value frequency adjustment is carried out on original image data, interference information in an image is effectively reduced, and the reliability of the image data is improved; meanwhile, continuous iteration deconvolution operation and pixel detail optimization are carried out on the basis of preprocessing, the distinguishing precision and texture detail discernibility of the welding image are improved, the discernibility of the welding defect under different scales is enhanced through multi-scale-level image feature decomposition, and the precision of image feature data is comprehensively improved.

The invention discloses an automobile leather defect detection method and system based on visual inspection, and relates to the technical field of industrial visual inspection, and the method comprises the steps: reconstructing the three-dimensional shape of a leather surface and generating a three-dimensional point cloud picture by analyzing the parallax relation and illumination direction reflection characteristics among multi-view automobile leather images; automobile leather surface curvature change characteristics of the three-dimensional point cloud picture are extracted, multi-scale texture analysis is carried out, and potential defect areas are identified and marked; through a three-dimensional shape measurement method, defect three-dimensional shape characteristics of the potential defect area are extracted, and defect three-dimensional geometric parameters are calculated; by analyzing defect geometrical characteristics and spatial distribution rules of the defect three-dimensional geometrical parameters and utilizing a preset grading judgment rule to divide defect grades, an automobile leather quality evaluation report containing defect three-dimensional coordinates is generated; according to the method, through combination of curvature-texture multi-scale fusion detection, the recognition capability of complex surface defects is remarkably enhanced.

The invention relates to the technical field of computer vision detection, in particular to an unmanned aerial vehicle target detection method based on frequency-space joint attention and dynamic fusion, and the method comprises the steps: obtaining an unmanned aerial vehicle image data set, carrying out the preprocessing, and dividing a training set and a test set; constructing a target detection model, inputting the training set into the target detection model to extract image features, sequentially performing frequency domain detail enhancement, spatial domain salient region extraction and multi-scale feature adaptive fusion based on the image features, and establishing a feature sequence; screening the feature sequence to obtain an initial target query, and finishing target classification and positioning on the initial target query through a decoder; training a target detection model by using the training set, and inputting the test set into the trained target detection model to generate a detection result; on the premise that the real-time reasoning advantage of RT-DETR is kept as much as possible, the problems that in an unmanned aerial vehicle scene, a target is prone to missing detection, the scale change is large, the background is complex, and the target is fuzzy are effectively solved, and the detection precision is improved.

The invention relates to the technical field of monitoring analysis, in particular to a park safety monitoring method and system based on dynamic visual identification. The method comprises the following steps: acquiring a plurality of park monitoring videos based on park monitoring equipment; performing three-dimensional illumination migration rendering on the plurality of park monitoring videos, and performing low-frame smooth completion so as to generate a time sequence monitoring image frame sequence; carrying out spatial position positioning calculation on the park monitoring equipment, carrying out topological association network reconstruction, and constructing an omnibearing monitoring perception topological map; performing dynamic object visual detection on the time sequence monitoring image frame sequence, and performing frame-by-frame optical flow tracking analysis to generate a dynamic target optical flow trajectory; and carrying out multi-time-point sampling on the dynamic target optical flow trajectory, and then carrying out mutation point identification so as to generate an optical flow trajectory mutation point. According to the invention, efficient park safety monitoring analysis and high-precision safety early warning are realized.

The invention relates to the technical field of visual inspection, and particularly discloses an optical communication filter appearance defect detection method and related device.The optical communication filter appearance defect detection method comprises the steps that polarization image sets of an optical communication filter to be detected at different polarization angles are obtained; preprocessing the polarization image set to obtain a defect enhancement image set; performing defect detection on the defect enhancement image set based on a pre-trained multispectral attention fusion network; according to the method, multi-polarization information, special preprocessing and a deep learning network combined with frequency domain-space feature fusion and a cross-modal attention mechanism are utilized, the detection capacity of the defects which are tiny, low in contrast and interfered by film layer textures on an optical communication filter is improved, and the omission ratio is reduced.

The invention provides a visual inspection system and an application method thereof. The system comprises an image acquisition module used for acquiring a multi-angle optical image and laser three-dimensional point cloud data; the data preprocessing module is responsible for denoising, geometric correction and multi-modal data alignment; the feature extraction module extracts texture, edge and defect features through a convolutional neural network; the defect detection module identifies cracks, scratches and foreign matters based on feature fusion; the adaptive optimization module dynamically adjusts a detection threshold value and classifier parameters; the result output module generates a detection report and marks defect positions; the feedback calibration module corrects the weight of the detection model according to an artificial rechecking result; the equipment control module triggers the sorting device to remove defective products; and the performance monitoring module counts the detection accuracy and the system response delay. According to the invention, the detection accuracy and the system stability can be improved.

The invention relates to the technical field of multi-image fusion recognition, in particular to a data fusion method and system for CCD visual detection, and the method comprises the following steps: obtaining a horizontal pixel row calculation gradient construction trend sequence, repairing an edge fracture to generate an integrity index, extracting a gray value to detect feature mutation, and distributing fusion weights to establish a mapping relation. And executing image fusion and balancing the contrast to generate a fusion matrix result. According to the method, the fracture edge region is identified, interpolation compensation is executed, the structural similarity index of the local gray sequence in the image overlapping region and feature direction mutation detection are combined, accurate identification of the edge matching result is guided, and fusion weight factor mapping corresponding to signal-to-noise ratio distribution is introduced; according to the method, the distribution relation between the pixels in the region and the credible weight is effectively established, the edge transition among the multi-source images is more natural through Poisson constraint and contrast balance adjustment of the fusion region, and the structural fidelity and the judgment stability of the fusion image are remarkably enhanced.

The invention discloses an appearance visual detection method and device for an electric control part of a new energy automobile. Structural stress distribution data of the electric control component are obtained and subjected to partition processing, and the surface of the electric control component is divided into a stress sensitive area and a conventional area; carrying out multi-wavelength spectrum scanning and polarization state detection on the stress sensitive area by adopting self-adaptive path planning, synchronously acquiring a polarization characteristic matrix, dual-wavelength interference data and depth spectrum data of the determined key attention area, and carrying out time domain synchronization and space registration processing to generate multi-dimensional detection characteristic data; extracting an optical anisotropy coefficient, a microcosmic deformation tensor and an interface reflection feature vector, and determining layering defect feature parameters in combination with multiple threshold judgment; and calculating local curvature distribution, an interface shear stress field and thermal stress distribution, and performing quantitative matching with the material characteristic parameters to generate quantitative evaluation indexes of the layering defects. According to the invention, accurate identification and rapid positioning of microscopic layering defects in the multi-layer composite insulation structure of the electric control component are realized.

The invention relates to the technical field of cable insulation layer detection, in particular to a cable insulation layer detection device and method. Comprising a visual detection mechanism, a collision detection mechanism, a marking mechanism and a transmission mechanism, the visual detection mechanism comprises a first support frame, three detection cameras, an annular light source, three first mounting plates, a light shield and a light shielding cylinder, and the first mounting plates and the detection cameras are annularly distributed around the axis of a cable insulation layer; the abutting detection mechanism comprises a second supporting frame, a rotating disc, an abutting detection assembly and a position adjusting assembly. The marking mechanism comprises a coating pipeline, a brush and a switching assembly. The device is suitable for detection of cable insulation layers of different diameter models, through cooperation of visual detection with the shading device and the annular light source, images of the cable insulation layers are captured in multiple directions, and various appearance defects are efficiently detected; the collision detection can be accurately adjusted according to the diameter of the cable, the visual detection is assisted to improve the detection comprehensiveness and accuracy, and the defect position can be marked.

The invention provides a titanium alloy bar visual detection method based on image segmentation. The method comprises the following steps: carrying out pretreatment and feature enhancement operation on an acquired titanium alloy bar surface image; constructing an adaptive segmentation algorithm based on region growth to carry out defect region segmentation on the surface image of the titanium alloy bar; performing defect feature extraction on the segmented defect region; a defect classification model is constructed, and titanium alloy bar defect types are classified based on defect features; performing quantitative analysis on the defect severity through a defect severity quantitative model; establishing a defect causal chain model, and carrying out defect traceability analysis and causal derivation; after defect traceability analysis is completed, fusion analysis is carried out on the multi-scale features, and decision suggestions are given. According to the method, the surface defects of the titanium alloy bar can be efficiently and accurately recognized and classified, the accuracy and robustness of defect detection are improved, and the defects of a traditional detection method in the aspects of efficiency, recognition capability, quantitative analysis and the like are effectively overcome.

Provided in the present invention is a three-dimensional reconstruction method based on LiDAR and vision multi-information fusion. The method comprises: calibrating a coordinate system of a LiDAR detection result and a visual detection coordinate system to unify the coordinate systems; obtaining sparse point cloud data of a LiDAR, and projecting data points onto a visual image; performing feature point extraction and depth estimation on an image collected by a monocular camera, so as to perform feature point extraction and depth estimation on a planar image, and thereby densifying a point cloud; fusing feature points, which are extracted from the image, with LiDAR point cloud data to form a dense point cloud, and mapping the dense point cloud to a three-dimensional space; and performing fast triangulation processing on the processed point cloud data to obtain a three-dimensional plane, performing spatial matching on image pixels and the three-dimensional plane, and restoring colors. In the method of the present invention, the LiDAR and the monocular camera are combined to complement each other, so that device costs are reduced, advantages in both robustness and stability are achieved, and the quality of point cloud data can be effectively improved.

The invention discloses an intelligent welding forming method and system for a green building steel heating radiator, and the method comprises the following steps: carrying out the surface defect recognition of a steel heating radiator base material based on an AI visual inspection system, recognizing a qualified base material, and automatically matching the type of a welding material from a material database according to the material and thickness parameters of the qualified base material. Welding parameters are intelligently matched through AI visual inspection and a neural network model, a laser and friction stir hybrid welding process is combined, traditional manual operation is replaced, the welding efficiency and precision are improved, and the problems of uneven welding seams and the like are solved; welding data are analyzed in real time through a multi-mode AI model, parameters are dynamically adjusted, intelligent defect recognition and repair welding are achieved in cooperation with 3D visual inspection, and the quality stability is improved through whole-process monitoring; smoke dust is treated through an environment-friendly process, acid pickling is replaced with mechanical rust removal, efficient recycling of materials is achieved through waste recycling, a green manufacturing system is constructed, and the sustainable development requirement of green buildings is met.

The invention discloses a glass bottle surface defect detection method based on visual detection, relates to the technical field of surface defect detection, and aims to solve the problem of inaccurate glass bottle surface detection. According to the method, information combination is carried out on the types, the number and the severity of the defects, weight distribution is carried out, then comprehensive scoring is carried out, various factors can be comprehensively considered in the mechanism, a more comprehensive and accurate scoring result is obtained, and defect boundaries are extracted through a contour detection method. According to the method, the defect position can be accurately positioned, the defect boundary can be accurately extracted, a reliable data basis is provided for subsequent analysis and processing, defect candidate areas are generated through a threshold segmentation method, screening is carried out through size filtering, shape matching, texture analysis and other methods, candidate areas without defects can be eliminated, and the defect detection accuracy is improved. And an image of the defective glass bottle can is accurately obtained.

The invention relates to the technical field of visual inspection, in particular to a multi-mode industrial product dynamic defect detection system based on edge calculation. According to the method, by introducing a multi-modal image construction and enhancement mode, three-dimensional acquisition and enhanced expression of detail information of the surface of the wind power blade are realized, and by means of inter-modal image synchronization and a space registration mechanism, the consistency extraction capability of defect information under different sensor view angles is improved; through combination of density change trend analysis and direction mutation identification means, surface micro cracks, edge damages and other structural changes can be accurately identified in continuous frames, and further through multi-source discrimination and mutual elimination comparison of abnormal indexes, environmental interference and misjudgment risks are effectively eliminated, and the accuracy of the detection result is improved. Therefore, a stable defect track area with direction consistency and distribution continuity is screened out, accurate detection and partition identification of the surface defects of the wind power blade under the dynamic condition are achieved, and the reliability and precision of defect positioning are remarkably improved.

The invention discloses a light guide plate defect detection method and system based on a neural network, and particularly relates to the technical field of machine vision detection, and the method comprises the following steps: aiming at the problem of image instability of a light guide plate in a dynamic transmission or rotation process, continuously collecting an image sequence and extracting time domain features; and performing interference judgment in combination with the inter-frame consistency prediction coefficient and a first threshold to realize accurate identification of the abnormal image frame. For an abnormal image frame, further correcting the recognition credibility of the abnormal image frame by adopting a confidence adjustment and fusion mode, and meanwhile, introducing a frequency domain transformation and image enhancement strategy to compensate detail loss caused by motion blur; according to the method, inter-frame consistency analysis, confidence fusion regulation and control and frequency domain fuzzy recognition and compensation mechanisms are introduced, abnormal judgment and image quality restoration of the light guide plate image in the dynamic scene are realized, the recognition accuracy and stability of the neural network model on the defect type, position and confidence are improved, and the false detection and omission ratio is effectively reduced.

The invention relates to the technical field of industrial visual inspection, and particularly discloses a waste metal classification and recognition method and system based on image recognition, and the method comprises the steps: obtaining metal surface visual information through an image collection system, extracting multi-level depth features after preprocessing, and generating a preliminary classification result and confidence evaluation; when the confidence coefficient is insufficient, starting a multi-mode verification mechanism, acquiring element composition data by adopting a laser-induced breakdown spectroscopy technology, and acquiring surface topological characteristics by adopting a structured light three-dimensional scanning technology; matching the element data with a component database to generate a component verification result, and comparing the morphology features with a morphology database to generate a morphology verification result; and finally, three types of results are integrated based on a weighted fusion algorithm to generate a final classification decision, and a sorting mechanism is controlled to complete accurate sorting.

The invention discloses a solar silicon wafer visual detection method, and particularly relates to the technical field of silicon wafer detection. The method comprises the following steps: acquiring optical images of different incident angles, synchronously acquiring infrared transmission images, performing normalization processing, edge enhancement filtering and self-adaptive threshold segmentation on the acquired multi-angle images, extracting suspected crack areas, and respectively calculating a gray gradient change rate and a stress abnormal degree, so as to obtain a suspected crack area; calculating a crack credibility score according to the gray gradient change rate and the stress abnormal degree through a weighted scoring method, and comparing the crack credibility score with a preset crack detection threshold value to distinguish real hidden cracks and stress pseudo defects; if the credibility score is lower than the threshold value, secondary sampling is carried out by adjusting the illumination angle, and the judgment result is further optimized; according to the method, the false rejection rate caused by lattice stress pseudo defect misjudgment is effectively reduced, meanwhile, missing detection of real subfissures is avoided, and the accuracy, stability and production yield of silicon wafer defect detection are improved, so that the long-term reliability of a photovoltaic module is enhanced.

The invention relates to the field of unmanned aerial vehicle cluster control, in particular to a distributed unmanned aerial vehicle protective net dynamic generation optimization method and system. The method comprises the following steps: acquiring real-time environment sensing parameters and unmanned aerial vehicle real-time monitoring images; performing dynamic environment situation evolution on the unmanned aerial vehicle based on the real-time environment perception parameters, performing distributed cluster simulation, and constructing a distributed unmanned aerial vehicle cluster model; performing multi-target visual detection on the real-time monitoring image of the unmanned aerial vehicle, predicting the moving trend of each target one by one, and constructing a dynamic prediction path of each target; identifying an unmanned aerial vehicle communication module, and obtaining real-time communication network state parameters of the unmanned aerial vehicle cluster; and carrying out dynamic communication parameter optimization on the real-time communication network state parameters, carrying out instant communication topology adjustment, and constructing an instant communication optimization strategy. Through dynamic cooperative control of the unmanned aerial vehicle cluster, the anti-interference and fault-tolerant capabilities of the unmanned aerial vehicle cluster are enhanced, and the protection efficiency of the unmanned aerial vehicle protection net is improved.

The invention discloses a large-scale unmanned aerial vehicle marshalling method for an emergency fire rescue task, and the method comprises the steps: carrying out the clustering analysis of task points of a rescue region through an FCM algorithm, determining the membership degree of a flight task, and generating a task region; on the basis of real-time environment change of a fire scene, a dynamic membership updating task allocation state is realized through a visual detection algorithm of fusing a convolutional neural network with an FCM; meanwhile, through 3DT route planning optimization based on the laser radar technology, a 3D model recombination map model is established, linear optimization is carried out by introducing time parameters, and optimal path planning is provided for the unmanned aerial vehicle in real time. In the rescue process, data are automatically transmitted in a segmented mode through the slicing technology of the 5G network, an autonomous Mesh centerless network topology structure is implemented when signals are intense, real-time signal optimization is conducted through a repeater of the high-altitude unmanned aerial vehicle, and high efficiency and flexibility of rescue are ensured.

The invention relates to the technical field of stacking equipment, in particular to a movable robot stacking system and method. The incoming material conveying line is provided with a visual detection device, and each pushing station is provided with a limiting mechanism and a pushing assembly. The feeding ends of the marshalling conveying lines are connected with the pushing stations in a one-to-one correspondence mode. Each marshalling conveying line is provided with a cache area and a grabbing area. The empty tray conveying line is provided with stacking positions, and each stacking position is provided with a steering conveying assembly. The feeding ends of the full-stack tray conveying lines are connected with the stacking positions in a one-to-one correspondence mode. The movable robot assembly comprises a transverse ground rail assembly, a robot body and a clamp, and the robot body is configured to be capable of moving to the grabbing areas of all the marshalling conveying lines to grab products and moving to all the stacking positions to stack the products to the empty trays. The full-process automation of feeding, classifying, grouping, stacking and transferring of products is achieved, and the efficiency and accuracy of stacking operation are improved.

The invention provides an industrial visual anomaly recognition method, system and device based on multi-modal feedback and a medium, and belongs to the technical field of industrial visual detection.The method comprises the steps that a production line video stream is collected in real time, an ROI is automatically segmented, a picture sequence is generated, features of a set dimension are extracted, and the features of the set dimension are extracted; comparing a preset dynamic distance threshold with a feature library, and preliminarily identifying an abnormal image; a cue word of a detection requirement is constructed, the cue word and abnormal related information are input into the multi-modal large model, and a determined abnormal image is output; using the determined abnormal image to construct a data set to train a target detection model, and adjusting the learning rate in the training process; and inputting pictures captured in an industrial scene into the deep learning model, the multi-modal large model and the target detection model in sequence to obtain a recognition result, feeding back the recognition result to a user for confirmation, adding the recognition result to the data set, and optimizing training of the target detection model. According to the invention, accurate identification of abnormal images in industrial production is realized, and the identification efficiency is high.

The invention provides a defect detection system, a defect detection method and a model training method. According to the method, the defect detection precision of a deep learning model algorithm can be greatly improved, particularly, more accurate detection results can be obtained for target defects of different scales and backgrounds in a complex scene, meanwhile, through a self-attention mechanism and frequency domain feature fusion, the network can adaptively focus on important features, and the detection accuracy is improved. The interference of irrelevant information is reduced, the performance of the model is further optimized, in addition, the model is more intelligent in the target defect identification process through multi-scale feature fusion and the guidance of context information, more complex environments can be processed, and meanwhile, the accuracy of target defect identification is improved. The defect detection precision, the robustness and the processing speed of the deep learning model algorithm are remarkably improved, and the method is particularly suitable for real-time detection tasks in multi-target defects and complex environments; the invention belongs to the technical field of visual detection systems.

The invention relates to the technical field of optical lens defect detection, and particularly discloses an optical lens laser-induced damage on-line detection method and system, a linear polarizer and a narrow-band filter are connected in series in a detection laser light path, non-target polarized light is filtered through polarization direction matching, meanwhile, interference of the environment and scattered light is inhibited through the narrow-band filter, and the laser-induced damage on-line detection system is obtained. According to the method, external source noise such as ambient light and non-target polarized light is reduced through polarization matching and narrow-band filtering, randomness of speckle noise is offset through multi-angle collection and signal fusion in a visual detection mode, exposure is dynamically adjusted, an image is fused to improve the signal-to-noise ratio, noise and real signals are decoupled through self-supervised learning, and the real-time performance of the system is improved. Dust interference is removed in combination with morphological operation; a deep learning reasoning model enhances the damage identification capability in a noise environment, defocusing blur caused by mechanical vibration is eliminated through phase conjugate correction, and the influence of photoelectric conversion noise, dust interference and the like on the detection efficiency and accuracy is remarkably reduced through multi-link linkage.

The invention discloses an industrial image anomaly detection method based on deep learning, and particularly relates to the technical field of industrial visual detection. The problems of high false alarm rate, fuzzy fine defect positioning, insufficient real-time response capability, difficulty in model increment updating and the like caused by data distribution drift in an industrial scene are solved. According to the method, robust features are extracted through a multi-scale feature fusion auto-encoder, and a dynamic memory bank is constructed to update a normal sample prototype online; a dual-path detection mechanism is adopted to cooperate with a pixel-level reconstruction error and attention weighted feature matching deviation; efficient edge reasoning is realized in combination with block parallel processing and model compiling optimization; and designing an elastic incremental learning framework to prevent disastrous forgetting. And finally, false alarms caused by environmental changes are reduced, accurate positioning of pixel-level defects is realized, millisecond-level detection requirements of high-resolution images are met, safe and efficient model online evolution is supported, and adaptability and reliability of an industrial quality inspection system are comprehensively improved.