2300 results about "Performed Imaging" patented technology

Disclosed in the present invention are an edge-deployed semi-supervised anomaly detection method and system for a railway track foreign object. The method comprises the following steps: an edge device encoding and decoding a video stream captured by a camera to obtain an image frame sequence, and performing frame extraction; and using a semantic segmentation model to perform image segmentation on a certain image frame obtained by means of frame extraction, to obtain a railway track region segmentation image. The use of a single image as input may generate an expert model result having a high weight value; however, the determination based on a single image is not stable, multiple consecutive images of the task scene need to be inputted, the frequency of each expert model obtaining the highest weight is computed, and the expert model corresponding to the highest frequency is the final solution. The present invention supports scene-adaptive foreign object detection algorithm automatic selection, and a user can perform selection on the basis of prior knowledge, or selection may be performed by a scene-adaptive automatic algorithm selection method; the user only needs to provide a batch of image data of the current scene, and the optimal algorithm selection can be evaluated.

The present invention relates to the technical field of medical images. Disclosed are a deep learning-based CT artifact removal method and system. The method comprises: acquiring a CT image, and separately performing sine transform and wavelet transform processing on the CT image; constructing an image enhancement model, and performing image optimization on the processed image separately by means of the image enhancement model and a random inversion layer which are connected in sequence; coupling the optimized image and the original image and then inputting the coupled image into the image enhancement model for reprocessing; and performing element-wise addition on the reprocessed image and the optimized image to obtain an artifact-removed CT image. In the present invention, wavelet transform is introduced to process the CT image to extract the context and spatial information of the CT image, effectively extracting feature information in an artifact removal process and improving the performance of image enhancement; and a CT image resolution enhancement model based on a VMamba model is established, enhancing the long-term dependencies in network training, effectively recognizing and removing radioactive artifacts, and improving the network training efficiency.

The invention discloses an autoclaved aerated concrete member surface defect intelligent identification system based on image processing, and particularly relates to the field of defect identification, comprising an image acquisition module, an image preprocessing module, a defect candidate region extraction module, a defect identification and classification module, and a result output and alarm module; according to the method, a high-definition industrial camera is used for collecting a component surface image, and adaptive median filtering and a Retinex algorithm are adopted for image denoising and enhancement, so that the influence of noise and uneven illumination is eliminated; utilizing an improved multi-threshold segmentation and Canny edge detection algorithm to accurately extract a defect candidate region; the method comprises the following steps: extracting three types of feature parameters of shape, texture and gray scale, and inputting the three types of feature parameters into a deep learning model taking ResNet50 as a basic network to realize automatic identification and classification of four types of typical defects of cracks, holes, unfilled corners and surface peeling; and finally, the system divides severity levels according to the defect size, and triggers differentiated visual alarm and linkage control.

The invention provides a satellite weak and small target on-orbit observation system and method based on intelligent closed-loop feedback, and the system comprises a detection module which carries out the image enhancement and time sequence consistency enhancement of an infrared image, obtains an enhancement feature, and obtains a candidate target set based on the enhancement feature; the tracking module is used for carrying out target matching in the search area; when the matching succeeds, the candidate position is used as an observation value, and the observation value is input into a Kalman filter to obtain a target state vector; when the matching fails, taking a prediction state of the Kalman filter as a target state vector, expanding a search window by taking a prediction position as a center, and executing re-identification; the control module is used for mapping the target state vector into an attitude error and generating a control instruction by adopting a single-neuron self-adaptive PID (Proportion Integration Differentiation) controller; and the closed-loop scheduling module is used for dynamically adjusting operation parameters of at least one module according to the execution error and the detection confidence coefficient. According to the invention, the continuous tracking precision and attitude control stability of the weak and small target are improved.

The invention provides a left heart data analysis method and system based on image segmentation, and relates to the technical field of medical image processing. Comprising the following steps: acquiring cardiac ultrasound image data and preprocessing; performing image segmentation on the preprocessed image data to obtain a segmentation result including a left ventricle, a left ventricular wall and a left atrium; searching a boundary line of the left ventricle and the left atrium, selecting two boundary points corresponding to the minimum and maximum abscissas in the boundary line as left and right mitral valve ring points respectively, and establishing a long axis based on the mitral valve ring midpoint and the cardiac apex point; modeling the ventricle into a structure formed by superposing a plurality of discs along the long axis direction, and obtaining the diameter of the corresponding disc; based on the obtained diameters of the corresponding discs, the left ventricular volumes in the diastolic period and the systolic period are calculated respectively, and the left ventricular ejection fraction is calculated. According to the method, image segmentation and geometric modeling are fused to achieve accurate calculation of the cardiac ejection fraction, meanwhile, the accuracy of cardiac structure image segmentation is improved, and an interpretable ejection fraction estimation process is achieved.

The invention provides an image compression artifact removal method based on a frequency domain hybrid expert network, and relates to the field of image processing. The method comprises the following steps: acquiring image data with compression artifacts; extracting shallow image features of the image data through an independent convolutional layer; extracting long-distance dependent image features of the shallow image features through a spatial attention mechanism; based on long-distance dependent image features, inputting the long-distance dependent image features into a frequency domain transformation expert network, and determining an optimal frequency domain transformation expert through parallel processing of multiple frequency domain transformation experts and an expert selection mechanism; processing the long-distance dependent image features through an optimal frequency domain transformation expert to obtain enhanced image features; performing image reconstruction on the enhanced image features to obtain a reconstructed image; the reconstructed image is an image after the compression artifacts are removed. The method is used in an image compression artifact removal process, and solves the technical problem that multiple types of complex compression artifacts are difficult to effectively remove in the prior art.

The invention relates to the technical field of robot perception and data generation technologies, in particular to a first-view-angle drilling method and device based on memory enhancement and a storage medium, and the method comprises the steps: extracting a plurality of target frames from a historical video stream stored in a space intelligent machine, obtaining a plurality of memory elements based on the plurality of target frames, performing three-dimensional reconstruction on each target frame, constructing a target world model, planning a first visual angle track of the target robot in the target world model, performing imaging simulation on the target robot, performing real-time rendering on a first visual angle video of the target robot, and performing real-time rendering on a second visual angle video of the target robot based on the same time axis and action script as the first visual angle video. A third-person video corresponding to the space intelligent machine is generated, and a drilling result is output; according to the method, the long-term memory data of the space intelligent machine is ingeniously used, high-quality drilling data can be quickly generated, the reliability of the first-view video is improved, and a reliable basis is provided for training and testing of a robot algorithm.

The invention provides a defect identification method, system and equipment of an automatic coil detector, and relates to the technical field of image processing, the method comprises the following steps: executing image acquisition when a coil reaches a target detection area; performing distortion and illumination correction on the detection image set, performing multispectral feature fusion on the corrected image set, inputting an enhanced image into a window identification channel to perform image traversal scanning of the enhanced image, and calculating texture energy and a direction consistency index in each sliding window; performing multi-scale image anomaly comparison by using the calibration position image and the enhanced image corresponding to the coordinate index; and performing morphological aggregation and boundary continuity analysis on the pixel points with the abnormal value identifiers, extracting geometric morphological parameters, spectral characteristic parameters and texture abnormal parameters, and outputting defect masks. According to the invention, the technical problem of low defect identification precision of the coil detection machine in the prior art can be solved, and the technical effect of improving the defect identification precision is achieved.

The invention relates to the technical field of program control, and discloses a femtosecond laser process parameter self-optimization method and system, and the method comprises the steps: carrying out the image reconstruction of real-time three-dimensional shape data, and obtaining a real-time ablation contour image; performing morphological feature deconstruction on the real-time ablation contour image to obtain a contour feature parameter set; performing deviation quantitative analysis on parameters in the contour feature parameter set and a standard feature threshold range to obtain a deviation feature vector; performing compensation strategy addressing on a preset process parameter adjustment rule base to obtain a preliminary compensation parameter combination; virtual machining track planning is carried out on the machined area, ablation morphology deduction is carried out on the planned track, and a fitting verification result is obtained; when a fitting verification result meets a convergence condition, performing parameter solidification packaging on the initial compensation parameter combination to obtain a final compensation parameter; according to the method, the self-optimization efficiency of the femtosecond laser process parameters can be improved.

The invention discloses a Transform low-light image enhancement method based on dynamic four-priori, and the method comprises the steps: obtaining a low-light image data set, and dividing the low-light image data set into a training sample set, a verification sample set and a test sample set; a Transform low-light image enhancement model DQPGT based on the dynamic four priori is constructed; inputting the training sample set into a DQPGT model to train the model, and verifying the model through the verification sample set to complete training of the DQPGT model; inputting a test sample set into the trained model for image enhancement and then outputting the test sample set; according to the method, spatial and frequency domain feature representation is collaboratively optimized on the basis of dynamic four-priori estimation and a frequency domain channel attention mechanism, so that the problems of uneven exposure, noise amplification and color distortion of an existing method based on the Retinex theory under a complex real illumination condition are solved.

A method of imaging an internal surface of a conduit, the method including deploying an inspection assembly within an internal volume of a conduit, the inspection assembly having a camera and a lighting array including a plurality of light emitters; illuminating a region of interest on said internal surface using the lighting array; and capturing image data of the region of interest using the camera, the image data including spatial data and intensity data at a plurality of different narrowband wavelength ranges of light.

An image processing method and apparatus, and a computer readable storage medium. The image processing method comprises: performing N-level pyramid decomposition on a visible light original image to obtain N visible light detail layers and a visible light base layer (S1); and performing N-level pyramid decomposition on an infrared original image to obtain N infrared detail layers and an infrared base layer (S2); and on the basis of the a-th detail fusion weight, performing image fusion on the a-th visible light detail layer and the a-th infrared detail layer to obtain the a-th detail fusion image (S3). The visible light original image and the infrared original image are subjected to N-level image decomposition to obtain the visible light detail layers and the infrared detail layers, and the visible light detail layers and the infrared detail layers are subjected to image fusion on the basis of the detail fusion weight. Since the visible light detail layers and the infrared detail layers comprise noise information, performing image fusion on the basis of the fusion weight can reduce the noise in the visible light detail layers and the infrared detail layers, thereby ensuring the fusion effect of the visible light detail layers and the infrared detail layers.

A method and apparatus for calibrating an imaging system provides a program stored in the imaging system having a graphical user interface and providing a plurality of tools to align hardware components of the imaging system including cameras for imaging cell culture vessels received by the imaging system and having a tool for providing a video image output of a cell culture vessel received in the imaging system.

The invention discloses an iron tower screw state detection method and system based on multi-modal image fusion, and belongs to the technical field of power system inspection, and the method comprises the steps: obtaining a multi-modal component image of a target iron tower; performing image preprocessing and feature extraction on the multi-modal component image to obtain a multi-scale feature map; constructing and training an iron tower screw identification model based on the multi-scale feature map; performing multi-stage detection and state evaluation on the obtained component image based on an iron tower screw identification model; and performing physical coordinate positioning on the missing screws in combination with multi-source information and a detection result, and establishing a cloud-edge collaborative closed-loop feedback mechanism to update and optimize the model. According to the method, the screws can be accurately recognized in a complex environment, multi-dimensional state monitoring of existence-deficiency-looseness of the screws is achieved, the management refinement level and the preventive maintenance capability are remarkably improved, federal learning is adopted to guarantee data privacy and enhance model generalization, and meanwhile, closed-loop feedback is adopted to enable the model to be continuously optimized.

The invention relates to the technical field of computer vision, in particular to a fabric color fastness analysis method and system based on image processing. Comprising the following steps: acquiring a multispectral image of a to-be-detected fabric, and synchronously acquiring multi-factor data; processing the multispectral image to generate an enhanced image; performing image recognition on the gray sample card in the enhanced image to generate a calibration image; performing spectral data projection on the calibration image through a dimension reduction algorithm, and performing color analysis and quantification on color change to generate color difference features; extracting texture features by using a conditional generative adversarial network, carrying out image recognition and calculation on the calibration image through a decoupling algorithm, and generating a region credibility graph; and inputting the chromatic aberration features, the texture features, the multi-factor data and the regional credibility map into an image feature fusion model for mapping, performing analysis through gradient visualization, and outputting an abnormal feature saliency map. According to the method, a color fastness objective analysis closed loop is created, so that the accuracy and the universality of an analysis result are improved.

The invention provides a luggage case size and pose calculation method and related equipment, which can accurately obtain the actual size and pose of a luggage case and improve the processing efficiency and accuracy. The method comprises the following steps: acquiring an image pair corresponding to a luggage sorting scene through an RGBD camera, wherein the image pair comprises an RGB image and a depth image; determining N pieces of luggage case detection frame information corresponding to the RGB image according to the target detection model, mapping a target detection frame position in the target luggage case detection frame information to a coordinate of the depth image so as to determine a detected luggage position of the target luggage case on the depth image, and performing image processing on an area where the detected luggage position is located, generating a luggage surface binary mask image of the target luggage case, and calculating a minimum bounding rectangle of the luggage surface binary mask image to obtain size attitude information of the target luggage case in a depth plane; and determining the actual size and the actual pose of the target luggage case based on the luggage surface binary mask map and the size and pose information.

The invention belongs to the field of molecular sieve material characterization, and particularly relates to a method for analyzing aluminum atom pairs in a ZSM-5 molecular sieve based on super-resolution fluorescence microscopic imaging, which comprises the following steps: activating a ZSM-5 molecular sieve sample; contacting the obtained sample with probe molecules; washing the ZSM-5 molecular sieve sample, and removing unbound or nonspecifically bound probe molecules; imaging the marked sample by using a super-resolution fluorescence microscope to obtain an image sequence containing a single fluorescent molecule emission event; processing the image sequence, determining a space coordinate of each fluorescence event, and reconstructing a super-resolution fluorescence image exceeding an optical diffraction limit; and based on the space coordinates of the fluorescent dots in the super-resolution fluorescence image, carrying out statistics to obtain the position, surface density or distribution information of the aluminum atom pairs in the ZSM-5 molecular sieve. According to the method disclosed by the invention, nanoscale spatial resolution, direct imaging and quantitative analysis of Al-pair in ZSM-5 (Zeolite Socony Mobil-5) can be realized.

To provide a machine tool capable of more efficiently cleaning chips. [Solution] The machine tool is equipped with an imaging means for imaging the inside of the machining chamber of the machine tool that processes the workpiece, a determination means for determining the accumulation state of workpiece chips inside the machining chamber based on the image obtained by imaging and first and second determination criteria that are different from each other, and a cleaning means for cleaning the inside of the machining chamber with coolant based on the determined accumulation state.

The invention relates to the technical field of image processing, and discloses an automobile part crack detection method, device and equipment and a readable storage medium. The method comprises the following steps: acquiring component images of an automobile component shot at each preset shooting angle, and performing image fusion processing on the component images to obtain a target image of the automobile component; inputting the target image into a preset crack identification model, and determining a crack segmentation mask image; and analyzing each crack in the crack segmentation mask image, determining the crack parameter of each crack, and determining the crack with the crack parameter meeting a preset condition as an effective crack. The automatic image detection mode is combined with the crack recognition model for crack recognition, and the effective cracks of the automobile part are screened out through the crack parameters, so that the detection speed and the result consistency are improved, the omission ratio can be reduced, and the crack detection efficiency and accuracy of the automobile part are improved.

The invention provides an endoscope image stabilization control method, which comprises the following steps of: acquiring an original dithering image sequence and inertial data of an endoscope, fusing the original dithering image sequence and the inertial data, acquiring an initial mixed motion field, performing operation semantic segmentation on the original dithering image sequence, and acquiring a collaborative attention map in combination with a physical motion mechanism. Obtaining a space-time adaptive filtering kernel through the collaborative attention map, filtering the initial mixed motion field according to the space-time adaptive filtering kernel, obtaining a stable motion field, carrying out image deformation and interpolation synthesis processing on the stable motion field, and obtaining a stable image sequence; through the integrated technical scheme of operation semantic segmentation, dynamic image stabilization optimization and accurate jitter suppression, the problem of interference of endoscope jitter on the neurosurgery operation visual field is solved.

The invention discloses a printed pattern edge sharpening processing control and hardware imaging optimization system, and relates to the technical field of printed pattern imaging processing, and the system comprises a fragile feature pre-analysis module which recognizes the boundary of a fine line and a high saturation color block, and generates a feature map; the ambient light acquisition module obtains illumination parameters and positions a strong light reflection area; the structured light compensation imaging module projects adaptive structured light to optimize imaging; the texture layering module divides and marks image layers; and the layered sharpening module carries out differentiated sharpening on each image layer according to the ambient light parameters and outputs a high-quality image. According to the method, the fragile characteristics of the printing are accurately identified, and imaging optimization is carried out in combination with ambient light changes, so that edge sharpening and imaging quality collaborative improvement are realized; based on feature analysis and light parameter acquisition, an imaging strategy adaptive to a scene is constructed, layered differentiation sharpening is performed, accurate reduction of patterns is guaranteed, and high-precision printing detection and display requirements are met.

The invention relates to a wavelet guided Transform underwater image enhancement method based on prompt learning. The method comprises the following steps: S1, obtaining a degraded underwater image; s2, preprocessing the degraded underwater image serving as the training set to obtain training sample data; s3, inputting the sample into a wavelet guided Transform network based on prompt learning for training; and S4, after training is completed, performing image enhancement on the test sample to obtain a result. The performance of the method and the system is superior to that of other underwater image enhancement methods, the details of the image can be recovered more finely, and the method has advantages in the aspect of avoiding artifacts compared with other methods.

The invention provides a pipeline leakage positioning method, device and equipment and a storage medium, and belongs to the field of intelligent detection.The pipeline leakage positioning method comprises the steps that concentration data and a pipeline image are synchronously obtained when a detection probe conducts detection along a to-be-detected pipeline; performing image matching on the pipeline image and a reference image to determine spatial position data of the detection probe in a three-dimensional space, the reference image being an image obtained by photographing the pipeline by using known spatial position data in the three-dimensional space; determining a concentration distribution model of the tracer gas on the to-be-detected pipeline based on the concentration data and the spatial position data at different moments; and determining one or more leakage point positions on the pipeline based on the area with the concentration value reaching a preset condition in the concentration distribution model. In the process, by establishing a concentration distribution model, the problem that in the prior art, due to gas diffusion, a pain point is difficult to accurately position is greatly solved, and the repair efficiency and the detection reliability are remarkably improved.

The invention provides a three-dimensional image modeling method and device based on plane data, and the method comprises the steps: carrying out the full-color / multispectral band fusion, bit depth adjustment, thin cloud removal, image enhancement, stripe removal and light and color uniformity of a satellite surveying and mapping image, and achieving the real color recovery of the image; performing splicing preprocessing on the plurality of small orthographic satellite surveying and mapping images after real color recovery, performing image registration on the to-be-registered image and a reference image, performing image geometric correction on the registered image, and performing image mosaic processing on the plurality of images after image geometric correction to obtain a single large-scene image; and three-dimensional image matching, building mask extraction, three-dimensional building modeling and three-dimensional building post-processing are carried out on a single large scene image to obtain a three-dimensional digital surface model, and ground three-dimensional real image modeling is completed. By applying the technical scheme of the invention, the technical problem that the existing two-dimensional surveying and mapping data is difficult to meet the increasing application requirements of three-dimensional scenes is solved.

The invention relates to the technical field of tunnel hidden engineering detection, in particular to a digital detection method and system for the number of tunnel anchor rods, and the method comprises the following steps: carrying out the image collection of a tunnel arch part along the center line of a tunnel through image collection equipment, so as to obtain a panoramic image of the tunnel anchor rods; performing image preprocessing by using a block adaptive image enhancement algorithm to obtain an anchor rod region detail enhancement image; carrying out anchor rod labeling on the anchor rod area detail enhancement image to obtain an original data set so as to construct a model data set; constructing an improved target detection model for a tunnel environment, and training and optimizing the improved target detection model in combination with the model data set to obtain an anchor rod number detection model; and performing real-time identification and statistics on the tunnel anchor rods based on the anchor rod number detection model to realize digital detection of the number of the tunnel anchor rods. According to the method, the anchor rod detection efficiency and precision are remarkably improved, and a complete digital solution is provided for tunnel anchor rod number detection.

The invention discloses an image super-resolution reconstruction method based on a double-domain chimeric attention mechanism, and belongs to the technical field of image super-resolution reconstruction. The method comprises the steps that an image is collected and preprocessed; constructing an image processing model; the image processing model is trained by adopting the preprocessed image, a self-adaptive attention distribution strategy is adopted in training, local attention weight is dynamically adjusted, an edge perception multi-constraint loss function is adopted, overall reconstruction and edge quality are dynamically coordinated, and detail definition and contour naturalness of a reconstructed image are improved; and carrying out image super-resolution reconstruction by adopting the trained image processing model. According to the method, the ViT module based on the double-domain chimeric attention mechanism is embedded into the bottleneck layer of the U-Net network, the edge perception multi-constraint loss function based on the gradient alignment course evolution strategy is adopted, and the obtained model has good image super-resolution reconstruction performance.

The invention discloses an anomaly detection method and system based on image alignment and feature difference analysis, and relates to the technical field of computer vision and industrial automation detection, and the method comprises the steps: obtaining a to-be-detected image and a reference image, and carrying out the image alignment processing of the to-be-detected image and the reference image; obtaining a region of interest corresponding to the reference image, wherein the region of interest is a preset region; cutting in the aligned to-be-detected image according to the region of interest to obtain a local image corresponding to the region of interest; obtaining a reference feature corresponding to the region of interest, wherein the reference feature comes from a pre-established reference feature library; extracting features of the local image as to-be-detected features; and comparing the to-be-detected feature with the reference feature to obtain a comparison result, and judging whether the target part existing in the local image is abnormal or not. The problem of dependence of offset interference and abnormal samples is solved, and the method is adaptive to multiple industrial scenes.

The invention discloses a light field reconstruction brain image brain region boundary extraction method based on convex hull fitting. The method comprises the steps that the p percentile of a brain image is calculated, and image cutting, contrast stretching and Gaussian filtering smooth denoising are carried out; carrying out Canny edge detection on the filtered image to obtain a binary edge image; boundary enhancement and connection are carried out through expansion and closed operation, all connected regions are extracted, and the contour with the maximum area is selected as the contour of the brain region boundary; a datum point is determined based on the contour of the brain region boundary, the polar angle and distance of each point except the datum point are calculated and sorted, and convex hull fitting is carried out through Graham Scan scanning based on the datum point and the sorted point set; converting the convex hull into a closed boundary region, and obtaining a mask image of the brain image after light field reconstruction through a mask function; according to the method, the special boundary form of the light field reconstruction image can be accurately adapted, deep learning and data training are not needed, and the generated mask has high geometric consistency.

The invention provides an imaging method, device and equipment of an interventional instrument. The imaging method comprises the following steps: acquiring a movement track and a current position of the interventional instrument in an interventional environment; according to the motion trail and the current position, a local scanning visual field area of the imaging equipment is determined, and the local scanning visual field area at least comprises an expected advancing path of the interventional instrument; and imaging the interventional instrument according to the local scanning view area to obtain a local image of the interventional instrument. The radiation quantity in the imaging process of the interventional instrument is reduced, and the imaging accuracy is improved.

The invention provides a BIM-based construction crack detection image real-time comparison and early warning system, and relates to the technical field of building construction, and the method comprises an extraction module which is used for carrying out the bimodal feature fusion processing of original image data, and generating a fusion feature image comprising texture and thermal radiation information; performing image preprocessing and crack contour extraction on the fused feature image, performing geometric fitting on the crack contour, calculating and determining a dominant extension direction of the crack contour, a long axis along the dominant extension direction and a short axis perpendicular to the dominant extension direction, and obtaining initial geometric parameters of the crack; and meanwhile, recording initial position information of the crack in the image. According to the invention, tracking and real-time intelligent early warning of the development state of the construction crack are realized.