1579 results about "Optical imaging" patented technology

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 discloses a bionic visual positioning system and method based on multispectral perception and a storage medium, and the system comprises a front-end multidimensional optical perception module, a mesopic vision preprocessing module and a rear-end fusion perception and target positioning module, the front-end multi-dimensional optical sensing module is used for performing optical imaging, spectral decomposition and polarization imaging; the mesopic vision preprocessing module is used for carrying out image preprocessing and optical flow estimation; and the rear-end fusion perception and target positioning module is used for feature fusion and target identification and positioning. According to the bionic visual positioning mechanism, through a bionic compound eye structure + multispectral + polarization + optical flow fusion perception strategy, the perception bottleneck of a traditional visual system in a high-dynamic and complex illumination environment is effectively solved, and the bionic visual positioning mechanism has the advantages of high robustness, low delay, wide field of view, multiple modes and the like; the method is especially suitable for application scenes such as automatic driving, unmanned aerial vehicles, robots and the like with extremely high requirements on real-time performance and reliability.

The utility model provides a large-aperture small-volume optical imaging system and a camera module applying the same, which are composed of eight lenses, the first lens has positive focal power, the object side surface is a convex surface, the image side surface is a convex surface, the second lens has negative focal power, the object side surface is a convex surface, the image side surface is a concave surface, the third lens has positive focal power, the image side surface is a convex surface, and the fourth lens has negative focal power. The fourth lens has positive focal power, the object side surface is a concave surface, and the image side surface is a convex surface; the fifth lens has negative focal power, the object side surface is a concave surface; the sixth lens has positive focal power, the object side surface is a convex surface; the seventh lens has positive focal power, the object side surface is a convex surface, and the image side surface is a concave surface; according to the optical lens, aberration can be effectively corrected, so that the optical lens has better imaging quality, larger aperture size, smaller volume and better thermal stability, and the overall imaging quality is improved.

The invention discloses an EPE co-extrusion adhesive film surface defect detection system based on image recognition, and relates to the technical field of industrial product quality detection, and the EPE co-extrusion adhesive film surface defect detection system comprises an image acquisition unit, an image processing unit and a result output unit, and the image acquisition unit comprises at least three light sources with different optical configurations and a camera which are used for synchronously or sequentially imaging the same detection area. According to the EPE co-extrusion adhesive film surface defect detection system based on image recognition, by adopting a multi-mode optical imaging and depth feature decoupling fusion technology, the problems of background texture interference and difficulty in low-contrast defect recognition in EPE co-extrusion adhesive film surface defect detection are effectively solved. The surface information is obtained from different physical dimensions through multi-light-source configuration, background textures and defect features are separated in combination with a feature decoupling algorithm, the recognition capacity of difficult-to-detect defects such as weak indentations, water waves and superficial impurities is improved, the occurrence probability of false detection and missing detection is reduced, and the reliability of a detection result is ensured.

The invention discloses a liquid crystal glass defect detection device and a control method.The detection device comprises a transmission mechanism, a portal frame and an optical imaging assembly, specifically, the angle of a camera is adjusted through an imaging adjusting assembly to meet the Gremer's law, the limitation of the depth of field of an inclined plane is solved, and single-time full-clear imaging is achieved; in the lighting system, a side-in type optical coupling assembly drives an optical coupling head comprising a hard air floating block and a silica gel pad by utilizing a linear driving and floating suspension mechanism, and a fixed-distance air film is flexibly attached to the silica gel pad through the air floating block, so that friction-free floating relative to a glass side straight surface is realized. The liquid crystal glass defect detection device effectively solves the problems of coupling difficulty and collision damage caused by glass edge position fluctuation in high-speed transmission, ensures efficient and stable light coupling so as to enhance internal defect contrast, and ensures high-precision and high-efficiency online detection.

The invention discloses an end-to-end polarization hyperspectral image classification method and system, belongs to the technical field of deep learning and optical imaging, and solves the technical problems of low reconstruction process speed, limited precision, low information utilization rate in a classification process and weak feature extraction capability in the prior art. The method comprises the following steps: carrying out target shooting based on a snapshot type space coding hyperspectral polarization imaging system, and carrying out system coding on a shot image to obtain two-dimensional aliasing data; reconstructing the two-dimensional aliasing data into a polarization hyperspectral data cube by using the trained reconstruction network; training the classification network based on the polarization hyperspectral data cube to obtain a trained classification network; and performing joint fine tuning on the trained reconstruction network and the trained classification network to obtain a polarization hyperspectral image classification model, and performing polarization hyperspectral image classification by using the polarization hyperspectral image classification model. The method is used for realizing high-quality reconstruction and accurate classification of the polarization hyperspectral image.

The invention relates to the technical field of optical imaging, and discloses an AR optical projection machine and an optical display system, the projection machine comprises a projection lens group, a color combination prism assembly and a three-color display array; the projection lens group comprises a diaphragm STO, a first lens, a second lens, a third lens and a fourth lens. The color combination prism assembly comprises a plurality of prisms which are glued with one another, and a film coating structure which is used for reflecting red light and blue light and transmitting green light is arranged on each prism; the three-color display array comprises three display chips; wherein the FOV (field of view) of the AR optical projection machine is greater than or equal to 30 degrees and less than or equal to 40 degrees; the ratio of the total optical length TTL of the AR optical projection machine to the effective focal length f of the system meets the condition that TTL / f is larger than or equal to 5.0 and smaller than or equal to 7. The field angle of the system is limited within the range of 30-40 degrees, the ratio of the total optical length TTL to the effective focal length f is kept within 5.0-7.7, an imaging field meeting the AR application requirement can be obtained within the limited optical path length, meanwhile, the overall compactness of the optical system is considered, and the optical system can be more easily integrated into small-size near-to-eye display equipment.

The invention discloses a bridge underwater safety detection method based on opto-acoustic dual modes, and relates to the technical field of underwater engineering detection, and the method comprises the following steps: obtaining water area particle size distribution and concentration data by using a multi-frequency acoustic suspended sediment concentration profiler, establishing an environmental parameter database, configuring a shipborne detection device according to the initial environmental parameter database, and detecting the underwater safety of a bridge according to the shipborne detection device. The method comprises the following steps: setting a three-axis stabilized platform carrying a polarization imaging camera and a multispectral LED array, deploying a multi-beam detection module and ADCP equipment, and establishing a unified coordinate system; multi-angle original intensity images are collected through a polarized optical imaging module, and multi-exposure fusion is carried out after processing is carried out through a mutual information minimization algorithm. An optical image and an acoustic point cloud are deeply fused by adopting a graph neural network, the detection precision is improved through dynamic weight optimization of an attention mechanism and a space-time registration algorithm, a multi-index fusion model is constructed based on fuzzy logic and a D-S evidence theory for adaptive early warning decision, upgrading from single-parameter alarm to multi-dimensional decision is realized, and the false alarm rate is reduced.

This invention presents a frequency-domain fluorescence lifetime imaging system, enhancing capabilities with a spatial beam attenuator and pinhole beam splitter. The spatial beam attenuator reshapes any beam into a circular Gaussian beam profile, being compact, cost-effective, with low loss and back reflection. Using digital printing technology, a thin optical film is deposited onto an optical substrate for precise local attenuation of the beam in either transmission or reflection mode. The pinhole beam splitter consists of an optical beam splitter with an active region the size of a pinhole, positioned near the beam's focus, which directs focused light into two paths based on acceptance or rejection by the pinhole. This configuration allows for two detectors to collect photons from both paths concurrently, facilitating dual-mode imaging. Consequently, the system can generate both confocal and conventional non-confocal laser scanning fluorescence lifetime images of the sample at the same time.

The invention discloses a multi-mode dam crack detection method based on acoustics-optics, and belongs to the technical field of underwater target recognition. According to the method, an underwater camera and an imaging sonar sensor are utilized to perform joint detection on cracks possibly existing on the surface of a dam: firstly, an optical image and a sonar image are respectively acquired, and crack feature extraction and preliminary recognition are performed in respective modes; and then, mapping detection results of the two modes to the same coordinate system through coordinate transformation, fusing optical detection information and acoustic detection information based on spatial consistency, and confirming the position and range of a crack target. According to the method, the complementary advantages that optical imaging definition is high and sonar penetrates through a turbid water body are brought into full play, the high crack detection rate and precision can still be kept in the underwater environment with extremely low visibility, compared with a single sensor, missing detection and false detection can be remarkably reduced, and reliable and automatic recognition of underwater dam structure cracks is achieved.

The invention provides a joint training and image processing method, device and system, and relates to the fields of artificial intelligence, optical imaging and the like. The method comprises the steps that a training sample is acquired, the training sample comprises a training image and a real label, and the real label is a foreground detection result corresponding to the training image; obtaining a modulation result after the training image is modulated by the first optical assembly, and determining an input image according to the modulation result; inputting the input image into the neural network model to obtain an output foreground detection result, and determining the foreground detection result as a prediction label; obtaining a foreground enhancement evaluation result corresponding to the input image, and determining comprehensive loss according to the prediction label, the real label and the foreground enhancement evaluation result; and updating structural parameters of the first optical component and / or model parameters of the neural network model according to the comprehensive loss. By applying the scheme, the task processing precision and the like can be improved.

The embodiment of the invention provides an optical imaging device and method based on a diffraction neural network. The optical imaging device based on the diffraction neural network comprises a diffraction neural network module used for receiving an input optical signal and correcting the input optical signal to output a corrected optical signal; the image sensor is used for obtaining a predetermined number of corrected images according to the plurality of corrected light signals received within a predetermined time range and outputting target electric signals corresponding to the predetermined number of corrected images; and the signal acquisition and processing module is used for receiving the target electric signal and processing the predetermined number of corrected images according to the target electric signal to obtain a target image. According to the optical imaging device based on the diffraction neural network, the influence of the correction image on the final imaging quality along with the time change can be reduced, so that the dynamic correction capability of the optical imaging device for the influence of atmospheric turbulence on imaging and the image quality of the target image are improved.

The invention relates to a 1.2-inch intelligent traffic monitoring system lens and a working method thereof. An optical imaging system of the lens is sequentially provided with a first lens to a fourteenth lens from an object space to an image space. Wherein the focal power of each lens adopts a positive and negative combined form, so that optical aberrations such as spherical aberration and the like are greatly reduced. Wherein the fourth lens and the fifth lens form an achromatic doublet lens group, the seventh lens and the eighth lens form an achromatic doublet lens group, the ninth lens and the tenth lens form an achromatic doublet lens group, and the eleventh lens, the twelfth lens and the thirteenth lens form an achromatic triplet lens group. Through reasonable lens matching, an optical system realizes large aperture, large target surface and no defocus in day and night, and through good correction of on-axis and off-axis aberrations, the lens has good imaging quality.

The invention provides a high-precision phase unwrapping method fused with a Transform self-attention mechanism. The high-precision phase unwrapping method is suitable for digital speckle interferometry, optical imaging and medical image processing. According to the method, on the basis of a U-Net structure, position coding and multi-head self-attention (MHSA) modules are introduced into a bottleneck layer, so that global feature dependence is established, and a long-range context is captured; a multi-head cross attention (MHCA) module is added in a decoding stage, attention weighting and noise suppression are performed on jump connection features, and selective fusion of key features is realized. A composite loss function is adopted in training, error variance loss and total variation loss are included, and phase periodic characteristics and smooth constraints are considered. Through simulation data training containing noise and complex phase jump, the unwrapping precision and robustness are significantly improved.

The invention belongs to the technical field of optical system aberration analysis, and discloses an experimental device for measuring and correcting image distortion of an optical imaging system, which comprises an optical axis testing device and an optical distortion testing platform, and the optical distortion test platform is used for testing optical distortion of the optical imaging system to be tested and integrating optical distortion data with optical axis deviation to obtain an image distortion fitting coefficient and a distortion correction model of the optical imaging system. According to the invention, the image distortion of the optical imaging device can be measured, the image distortion can be corrected, the imaging device can correct the deviation between the optical axis and the center of the target surface when the system is installed and adjusted, the optical distortion of the whole optical system can be corrected, and the method has guiding significance for the application of detecting and identifying the accurate position of a target by using the optical system.

A system for monitoring a petrochemical installation is disclosed. The system can include an optical imaging system comprising an array of optical detectors. The system can comprise processing electronics configured to process image data detected by the optical imaging system. The processing electronics can be configured to detect a target species based at least in part on the processed image data. The processing electronics can further be configured to, based on a detected amount of the target species, transmit an alarm notification to an external computing device over a communications network indicating that the target species has been detected at the petrochemical installation.

The invention discloses an image reconstruction method and device, equipment and a storage medium, and relates to the field of computational optical imaging, and the method comprises the steps: obtaining a first resolution image of an imaging target, and determining a point spread function of the first resolution image based on the shape and rotation angle of a pupil; determining a convolution relational expression among the imaging target, the point spread function and the first resolution image in the spatial domain by using the Fourier optics theory; converting the convolution relational expression into a product relational expression in a frequency domain based on Fourier transform, and converting the product relational expression into a linear equation set; solving the linear equation set by using a least square method to obtain a corresponding solving result, and constructing a second resolution image corresponding to the imaging target by using inverse Fourier transform and the solving result; wherein the resolution of the second resolution image is higher than that of the first resolution image. According to the invention, multiple low-resolution images collected in the pupil rotation process can be quickly reconstructed into high-resolution images.

The invention belongs to the technical field of cell electrophysiological signal recognition, and discloses a cell electrophysiological signal recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an original electrophysiological signal of a myocardial cell, mechanical data of the action of a mechanical probe and the myocardial cell, and illumination parameters of an optical imaging system, the method comprises the following steps: acquiring an original electrophysiological signal, identifying from the original electrophysiological signal to obtain a mechanical artifact signal associated with mechanical data, determining instantaneous mechanical stiffness of myocardial cells based on the mechanical artifact signal so as to identify and obtain a pulsation stage in which the myocardial cells are currently located, and calculating to obtain a photo-thermal artifact signal in the original electrophysiological signal according to the pulsation stage and illumination parameters, separating a mechanical artifact signal and a photo-thermal artifact signal from the original electrophysiological signal to obtain a real electrophysiological signal of the myocardial cell; by means of the method, the electrophysiological signal recognition accuracy of the myocardial cells is improved.

The invention discloses a super-resolution micro lens and a preparation method thereof. The lens comprises a photoresist spherical micro lens and a mixed substrate plane lens which are sequentially arranged from top to bottom. The specific preparation method comprises the following steps: S1, preparing a photoresist cylinder on a quartz substrate; s2, reflowing the photoresist cylinder into a micron lens by using a photoresist reflowing process; s3, preparing a mixed substrate plane lens on the surface of the to-be-detected sample; and S4, transferring the micron lens to the surface of the mixed substrate plane lens. By changing the thickness of the mixed substrate plane lens, adjustment of the amplification coefficient and the numerical aperture can be realized, and compared with a micro lens without a mixed substrate, the micro lens has higher imaging resolution. The method has a wide prospect in the technical field of optical imaging.

The invention provides an endoscope channel inner surface damage assessment method, and relates to the technical field of information, and the method comprises the steps: scanning an endoscope channel inner surface through an optical imaging technology to obtain spectral data containing microscopic texture features, and carrying out Fourier transform to obtain channel surface feature distribution maps at different use stages; performing deep learning neural network processing on the surface feature distribution map, extracting texture parameters related to material fatigue evolution and a chemical corrosion mechanism, and determining distribution features of a surface stress whitening microcell and a nano-crack network according to the texture parameters; and performing predictive analysis on the long-term use durability of the inner surface of the endoscope channel in combination with the damage risk level and the periodic cumulative stress data, and generating a final damage degree evaluation report. The micro texture features of the inner surface of the channel are obtained through an optical imaging technology, texture parameters related to material fatigue and chemical corrosion are extracted, molecular chain breakage and orientation rearrangement risks are evaluated, and the damage degree of the inner surface is judged.

An optical imaging system includes a first lens having a negative refractive power, a convex object-side surface, and a concave image-side surface; a second lens having a positive refractive power; a third lens having a negative refractive power; a fourth lens having a positive refractive power; a fifth lens having a negative refractive power; and a sixth lens having a positive refractive power and an image-side surface having an inflection point. The first to sixth lenses are sequentially disposed in ascending numerical order from an object side of the optical imaging system toward an imaging plane of the optical imaging system.

The invention relates to the field of optical imaging and computer vision, discloses a large-view-field binocular image combination dynamic parameter adjusting system, and aims to solve the problems that a traditional head-up display is limited in view field and monochromatic display and information response are lagged. The system comprises a left and right eye image acquisition and preprocessing unit, a target positioning and trajectory prediction unit, a binocular parallax compensation and registration unit, a dynamic fusion display control unit, a color enhancement and information superposition unit, an eye movement tracking feedback unit and a parameter adaptive adjustment unit. Through binocular wide-angle acquisition, three-dimensional target prediction, sub-pixel-level image registration, panoramic stitching fusion, semantic color coding and dynamic parameter adjustment of eye movement driving, 120-degree * 60-degree distortionless panoramic display, multi-source information intelligent layered superposition and visual focus area adaptive enhancement are realized. According to the method, the air combat situation sensing efficiency and the weapon response speed are improved, and the method has high real-time performance (delay of lt, 80ms), strong environmental adaptability and engineering integration.

The invention discloses a microfluidic image flow cytometry identification system and a microfluidic image flow cytometry identification method based on multi-modal phase imaging and deep learning, relates to a microfluidic image flow cytometry detection technology, and belongs to the crossing field of microfluidics, optical imaging and artificial intelligence. The cell deformation chip is used for inducing a cell sample to generate controllable deformation through the cell deformation chip and discharging deformed cells; the optical imaging unit is used for scanning the deformed cells and collecting multi-modal phase images of the deformed cells; the data processing and analysis unit is used for preprocessing the multi-modal phase image and performing cell intelligent identification analysis on the preprocessed multi-modal phase image by using a deep learning feature extraction network, so that accurate identification and classification of cells are realized, and a leukocyte subpopulation identification model is constructed; and generating a cell imaging result and a cell mechanical parameter thermodynamic diagram. According to the invention, label-free identification of leukocyte subgroups is realized, and the problems of tedious operation and cell damage of traditional fluorescence labeling are solved.

Provided herein are imaging systems for a patient including an imaging probe and an imaging assembly. The imaging probe includes: an elongate shaft with a proximal end, a distal portion, and a lumen extending between the proximal end and the distal portion; a rotatable optical core with a proximal end and a distal end, and at least a portion of the rotatable optical core is positioned within the lumen of the elongate shaft; and an optical assembly positioned proximate the distal end of the rotatable optical core, the optical assembly configured to direct light to tissue to be imaged and collect reflected light from the tissue to be imaged. The imaging assembly is constructed and arranged to optically couple to the imaging probe. The imaging assembly is configured to emit light into the imaging probe and receive the reflected light collected by the optical assembly.

The invention relates to the technical field of industrial automatic detection, and discloses an industrial product surface defect automatic detection system based on computer vision, which comprises a dynamically controllable multi-mode optical imaging sub-module, a hypothesis driven deep fusion and verification sub-module and a central control and scheduling sub-module, the hypothesis-driven deep fusion and verification sub-module is used for analyzing the image sequence and outputting a classification result and confidence data, and when the confidence data is lower than a preset confidence threshold value, the hypothesis-driven deep fusion and verification sub-module generates a new optical parameter vector and sends the new optical parameter vector to the image sequence; and the central control and scheduling sub-module controls the dynamically-adjustable multi-mode optical imaging sub-module to acquire supplementary image data according to the new optical parameter vector, updates the image sequence, and executes the process in a reciprocating manner until the confidence data is not lower than a preset confidence threshold. Through a closed-loop mechanism of active detection and iterative verification, on-demand asking of information is realized, and the detection accuracy is improved.

The invention specifically relates to a multi-parameter state monitoring and fault diagnosis system for an intelligent circuit breaker, and relates to the technical field of state monitoring and fault diagnosis of power equipment. A surface / bulk charge and electroluminescent optical monitoring module; a mechanical-electrical performance correlation analysis module; and a diagnosis evaluation module. According to the invention, the dielectric property micro-change module adopts a low-frequency superposition excitation and partial discharge fingerprint spectrum fusion technology, and can sensitively capture dielectric micro-change of gradual deterioration such as damp and uniform aging; the surface / body charge and electroluminescent module performs mixed optical imaging through a non-contact electrostatic potential array and PMT / APD, and accurately recognizes surface charge accumulation and early electrical tree growth; the mechanical-electrical association module quantifies thermal mechanical stress accumulation and impact vibration influence based on FBG strain monitoring and multi-physics field coupling modeling.

Disclosed in the present invention are a conical optical illumination-based reflective scanning super-resolution optical microscopy system and method. The system comprises a sample displacement module, an optical microscopic imaging module, an annular focused beam generation module, a beam scanning module, a super-resolution focused illumination and collection module, a super-resolution optical imaging module and a computer. By means of using the advantages of annular focused beam illumination, high focusing efficiency of traditional lenses, and high beam scanning speed, high-efficiency super-resolution focused illumination with an extended depth of focus is achieved, and further traditional optical lenses can be used to achieve fast super-resolution optical microscopic imaging; fast label-free far-field super-resolution two-dimensional microscopic imaging is implemented by means of two-dimensional beam scanning; by means of performing label-free far-field super-resolution two-dimensional microscopic imaging on samples at different axial positions, super-resolution two-dimensional microscopic images of different cross sections of samples are obtained, thereby achieving three-dimensional tomography. The present invention can be applied to fast label-free super-resolution microscopic imaging of biological samples, and can also be applied to other fields such as industrial super-resolution microscopic inspection.

Disclosed is devices and techniques for 3D LiDAR sensing without beam scanning with moving parts or 2D optical imaging based on the combination of a lens' position-to-angle conversion and the wavelength division multiplexing / demultiplexing (WDM) in the output probe light for LiDAR sensing. This 3D LiDAR sensing can be implemented on stacked photonic integrated chips to provide.

The invention relates to the technical field of image visual angle analysis, and particularly discloses a quartz crucible bubble group multi-visual angle three-dimensional reconstruction and dynamic analysis system, which is characterized in that an optical imaging device and a sound wave transmission imaging device are arranged outside a quartz crucible, and boundary contour data and bubble internal structure data of bubbles in the crucible are sequentially acquired; further constructing a three-dimensional model of bubbles in the quartz crucible, separating and identifying the bubbles, and obtaining key feature information of each bubble; in a time sequence of continuous acquisition and modeling, the growth rate of each bubble is calculated in real time, and the aggregation behavior and the fracture sign of a bubble group are monitored; by setting the abnormal judgment threshold and predicting and early warning the potential risk in the bubble group, the effectiveness of the data is remarkably improved, and the monitoring means of the bubble behavior is innovated, so that the production process is optimized, the material quality is improved, and the potential safety hazard and economic loss caused by the bubble defect can be remarkably reduced.

The invention is suitable for the technical field of wafer detection, and provides a wafer detection system and a detection method thereof.The wafer detection system comprises a multi-axis motion platform, an optical imaging system and a control and processing unit, and the multi-axis motion platform is used for bearing a wafer and driving the wafer to rotate, translate and move in the focusing direction; the optical imaging system is used for imaging the surface of a wafer and supports switching of multiple illumination modes, the illumination modes comprise bright field illumination, dark field illumination and oblique illumination, and the control and processing unit is electrically connected with the multi-axis motion platform and the optical imaging system. According to the system, multi-angle and multi-dimensional image data of the same suspected defect point can be obtained through wafer attitude regulation and control of the multi-axis motion platform and cooperative switching of multiple illumination modes of the optical imaging system; and on the basis, four types of quantitative characteristics of motion adhesiveness, three-dimensional contour, multi-modal optical response and multi-view morphological stability for representing the physical essence of the defect are extracted, so that the real defect and the false defect are distinguished.