1207 results about "Pixel based" patented technology

The invention provides a metal product surface flaw detection method and system based on machine vision, and belongs to the technical field of machine vision. The method comprises the following steps: constructing a multi-modal image data set through bright field image acquisition, dark field image acquisition and three-dimensional point cloud data acquisition of the surface of a detected metal product, and registering the multi-modal image data set; based on the registration multi-modal image data of pixel-level alignment, pixel-level defect segmentation is carried out by adopting a double-flow diffusion Transform model, and a defect segmentation map is output; and on the basis of the defect segmentation image and the registered multi-modal image data, through segmentation image binaryzation and region extraction, multi-dimensional defect feature extraction and quantification, defect classification and report generation, a final defect detection report is output, and the metal product surface defect detection method is completed. The invention effectively solves the core pain points of low precision, poor robustness and insufficient generalization ability for unknown defects in metal surface flaw detection, and provides an automatic detection method with high reliability and high precision.

The invention relates to the technical field of power equipment state monitoring, and particularly discloses a transformer fault diagnosis method and system based on image recognition, and the method comprises the steps: collecting a transformer multi-mode image sequence in real time, and carrying out the definition and part integrity evaluation and screening to form an initial image set; performing multi-scale space registration on the initial image set and a transformer normal state standard template to generate a reference image, and reversely deriving a displacement vector field based on pixel-level difference; carrying out smooth optimization and geometric reconstruction on the displacement vector field under the geometric constraint of the transformer structure, and generating a correction image with a real structure; fault feature enhancement is carried out in a gradient domain of the corrected image, a fault area is identified through matching of multichannel feature extraction and a transformer typical fault feature library, and a diagnosis report integrating fault types, confidence coefficients and geometric parameters is generated; according to the method, the problem of image geometric deformation caused by shooting condition differences is effectively solved, and the accuracy and reliability of fault identification are improved.

A system may detect a triggering condition by an imaging device. The system may capture, by the imaging device in response to the triggering condition, an image of a container. The system may perform, by a machine learning model, pixel quantification of the container. The system may determine, based on the pixel quantification, a status of the container.

The invention discloses a point cloud dyeing method, apparatus and device, and a readable storage medium. The method comprises the steps of obtaining a point cloud frame and a plurality of image frames; aiming at each space point of each camera device, generating an observation transformation matrix used for representing the projection movement condition of the space points on an image plane in the exposure process of the camera devices; generating a relative timestamp for indicating the imaging moment of the spatial point; based on the relative timestamp and the observation transformation matrix, generating a pixel coordinate of the spatial point projected to an image frame of the camera device, and based on the pixel coordinate, performing pixel color picking on the spatial point to obtain a pixel vector; establishing a corresponding relationship between each spatial point of different camera devices and each point cloud in the point cloud frame; and determining a color vector of the corresponding point cloud based on the pixel vector of each spatial point corresponding to the same point cloud. Visibly, according to the method, space-time alignment of the three-dimensional space points and the pixel coordinates on the image frame can be realized by constructing the observation transformation matrix and the relative timestamp, and the point cloud dyeing precision is improved.

The invention discloses a textile color difference detection method based on image data, and relates to the technical field of image processing and computer vision, and the method comprises the following steps: S1, collecting an image of a textile with a high reflection characteristic under a standard light source, constructing a light intensity prediction model, and carrying out the analysis based on pixel brightness distribution, identifying a brightness abrupt change region and a saturation critical region, and generating an image-level saturation risk probability graph; s2, performing multi-scale exposure area division on the image based on the image-level saturation risk probability graph, setting a target brightness range of each exposure control sub-area, and recording a global exposure parameter of the image acquisition equipment as an initial baseline of exposure scheduling; according to the method, pixel-level brightness convergence is realized through light intensity prediction and area exposure control, real color distribution is reconstructed in combination with color compensation, and a closed-loop process is constructed by introducing model self-correction, so that the detection precision and consistency of the micro chromatic aberration of the high-reflective fabric are improved, and the automation and industrial applicability are enhanced.

The invention discloses a cell occlusion relation estimation method and system based on a pixel-level focus evaluation curve. The method comprises the following steps: acquiring a multi-focal plane cell image sequence of the same view at different focusing positions; performing cell instance segmentation on the image sequence to obtain a two-dimensional cell instance mask; calculating the definition value of each pixel in the mask on each focal plane, and constructing a pixel-level focus response curve; determining a focus depth interval of each pixel according to the peak position of the focus response curve and a preset relative threshold value; and comparing focus depth intervals of different cell pixels in the cell overlapping region, and judging the up-and-down shielding relationship between the cells. According to the method, automatic analysis from the original microscopic data to the cell upper and lower layer relation is realized through pixel-level depth modeling and interval comparison, the spatial resolution and credibility of occlusion relation judgment are improved, the compatibility with a conventional microscopic imaging process is high, and deployment and popularization are easy.

The invention discloses a semantic segmentation method based on phase contour constraint, and belongs to the technical field of computer vision. The method comprises the following steps of: acquiring a two-dimensional texture image and a deformed stripe image of a scene to be detected in the same view field by using a calibrated camera-projector system; resolving the deformed fringe image through a multi-step phase shift and Gray code technology to obtain absolute phase distribution, and calculating a gradient field; according to a preset sudden change condition, extracting a physical edge contour reflecting the depth change of the object from the gradient field; and mapping the physical edge contour into the two-dimensional texture image based on a pixel coordinate corresponding relation to accurately define a semantic object region, endowing a corresponding category label, and finally generating a semantic label mask image. According to the method, the uncertainty of the visual texture edge is corrected by utilizing the physical phase information, the problem of edge extraction in a complex illumination scene is effectively solved, automatic generation of semantic segmentation data is realized, and the training precision and robustness of a semantic segmentation model are improved.

Provided is a pattern inspection system, including a scanning electron microscope (SEM) including an electron gun configured to generate a first electron beam and emit the generated first electron beam toward a first wafer, a detector configured to detect electrons emitted from the first wafer based on the first electron beam emitted toward the first wafer, and at least one processor configured to generate a first SEM image including a plurality of pixels based on the detected electrons, and determine, based on a period of a pattern extracted from the first SEM image, a pixel size of a second SEM image to be generated by the SEM with respect to a second wafer.

A method and device for remote sensing image classification using quantum pixel matrix entanglement is provided. The method comprises: preprocessing an acquired raw remote sensing image to obtain image data containing multiband fusion; and calculating a pixel matrix entanglement coefficient μ and a Euclidean distance d between a cluster center and other pixel matrices based on a preprocessed remote sensing image, performing an iterative self-organizing classification on remote sensing image data based on the pixel matrix entanglement coefficient and a Euclidean distance threshold, and obtaining remote sensing image classification results.

The present disclosure provides systems, devices, apparatuses, and methods, including computer programs encoded on a storage medium, for panel aging condition recording strategies for OLED aging resistance. A display processor may detect that a value of a set of pixels displayed on a display panel remains static for a period of time and the value of the set of pixels exceeds a threshold for the period of time. The display processor may perform anti-aging pixel recording on the set of pixels based on the detection. The display processor may adjust a value of the set of pixels based on the anti-aging pixel record.

The invention relates to the technical field of image processing, in particular to a lens edge detection method and system based on image generation, and the method comprises the following steps: collecting a lens image through an industrial camera, carrying out the weighted graying, extracting an edge coordinate through a Laplace operator, constructing an edge pixel coordinate set, and carrying out the image processing; screening an edge validity marking result by combining a gray difference threshold, calculating a phase difference between a gradient direction and light source incidence based on a Sobel operator, extracting pixels in a consistent direction, carrying out spatial clustering, generating a lens edge pixel cluster, and fitting a continuous curve to construct a complete lens edge contour. Noise and reflection interference are restrained through pixel neighborhood gray difference, effective pixels are screened in combination with a gradient direction and light source incident phase relation, edge direction consistency is enhanced, pixels are clustered according to spatial continuity and gradient intensity, contours are continuously fitted based on pixel cluster distribution, and lens edge integrity and geometric consistency under complex illumination are improved.

The invention discloses a visual precise positioning method based on pixel fusion alignment, and relates to the technical field of visual positioning, and the method comprises the steps: obtaining a target image shot by a to-be-positioned terminal and rough pose data, screening a candidate grid set in a pixel fusion grid template dictionary based on the rough pose, and obtaining a candidate grid set; performing multi-channel pixel fusion alignment on the target image in the candidate grid set, performing step-by-step detailed search from top to bottom according to grid levels, and calculating a target three-dimensional coordinate in a minimum grid according to a pixel fusion alignment result; multi-source three-dimensional scene modeling, multi-layer grid organization, multi-channel pixel-level alignment and an online self-learning updating mechanism are comprehensively utilized, and the problem that in the prior art, in the indoor and outdoor integrated complex environment where satellite signals are weak and illumination and scenes change frequently, the multi-source three-dimensional scene modeling, multi-layer grid organization, multi-channel pixel-level alignment and online self-learning updating are difficult to achieve is solved. The method solves the problem that high-precision and high-robustness three-dimensional visual positioning is realized only by means of a single image of the terminal, and is particularly suitable for navigation guidance and intelligent equipment positioning application of large comprehensive transportation hubs, airports and urban complexes.

The invention discloses a load balancing Gaussian sputtering method for large-scale scene geometric reconstruction. The method comprises the following steps: step 1, acquiring a multi-view RGB image sequence of a large-scale scene, and processing the multi-view RGB image sequence by using a COLMAP tool to obtain camera parameters and an initial sparse point cloud; 2, based on a pixel-level load balancing strategy, effective Gaussian primitives are screened, spatial distribution of the effective Gaussian primitives is regulated and controlled through a loss function, and redundant primitives are reduced; 3, introducing global consistent geometric prior, fusing monocular depth and sparse point cloud depth to generate a reference depth map, and constructing depth consistency and smooth loss; 4, dividing illumination areas through a multi-area exposure compensation model, adaptively correcting brightness, and constructing image luminosity loss; and 5, performing global optimization in combination with multi-dimensional loss. And 6, rendering a depth map for the trained model, generating a TSDF field by using a TSDF fusion algorithm, and extracting a scene grid to obtain a final three-dimensional geometric model. According to the method, large-scale scene high-precision reconstruction can be realized on a single GPU, memory consumption is remarkably reduced, and geometric reconstruction quality and illumination robustness are improved.

The invention discloses an element stripping method and device based on multispectral data, equipment and a medium, and relates to the field of remote sensing image processing, and the method comprises the steps: collecting a multispectral image of a target region; a self-adaptive window filtering algorithm is adopted to pre-process the multispectral image to obtain a multispectral enhanced image, and the self-adaptive window filtering algorithm calculates a window adjustment coefficient based on noise density, gray variance and gradient magnitude; spectral features and texture features are extracted from the multispectral enhanced image; fusing the spectral features and the texture features, and constructing fusion features of each pixel in the multispectral enhanced image; determining a ground feature category of each pixel based on the fusion features to strip a plurality of vectorized layers containing different elements; according to the method, the three indexes of the noise density, the gray variance and the gradient magnitude can be fused, the window adjustment coefficient is obtained, dynamic self-adaptive change of the filtering window size is achieved, and higher-precision data support is provided for subsequent element extraction.

The invention relates to a display device. The display device comprises a display screen and a processor. The display screen is used for displaying images and comprises a plurality of pixels, and one pixel comprises a plurality of sub-pixels used for transmitting light of different colors. The processor is connected with the display screen and the backlight module, and the processor is configured to perform image analysis on the to-be-displayed image, obtain a gray scale average value of the to-be-displayed image, and obtain a corresponding multi-level classification label and a corresponding confidence coefficient; the confidence coefficient is used for representing the accuracy of the multi-level classification labels; determining a corresponding lookup table according to the multi-level classification label and the corresponding confidence coefficient; the lookup table comprises a corresponding relation between the multi-level classification labels and the pixel compensation gains; determining a pixel compensation gain according to the lookup table; calculating the pixel value of each pixel in the display screen according to the gray-scale value of each sub-pixel and the pixel compensation gain; and adjusting the transmittance of each pixel in the display screen based on the pixel value. The pixel compensation effect can be improved, and then the display effect is improved.

The invention discloses an ink-jet printing defect identification method and system, and relates to the technical field of image processing, and the method comprises the steps: collecting a to-be-detected printing image, and carrying out the template matching with a standard image of a corresponding printing template; calculating a color difference value between each pair of matched pixel points, obtaining a color difference matrix, dividing a color difference range, and obtaining a high color difference region and a low color difference region; based on the high-color-difference area, identifying an obvious ink dot defect area; calculating the defect probability of each pixel point based on the low-color-difference region; obtaining a corrected Euclidean distance between the pixel points based on the defect probability, and clustering and identifying an unobvious ink dot defect area; the detection result and the distribution condition of the ink dot defects are counted, and feedback regulation and control of the ink jet system are achieved; through the pixel point template matching, clustering and color difference correction technologies, the problem of unobvious ink dot defects caused by missing detection is solved, and accurate identification of the ink dot defects is realized, so that the accuracy and reliability of product quality detection are enhanced, and the printing quality of products is improved.

The invention provides a video processing method and device, computing equipment, a medium and a program product, and belongs to the field of video processing. The video processing method comprises the following steps: for any to-be-processed frame in a to-be-processed video, determining a first pixel set and a second pixel set corresponding to the to-be-processed frame from a plurality of pixels based on respective motion state information of the plurality of pixels of the to-be-processed frame; according to the respective motion vectors of the plurality of first pixels, determining the pixel positions of the plurality of first pixels in the prediction frame to obtain a first prediction pixel set corresponding to the prediction frame; determining a second prediction pixel set corresponding to the prediction frame based on a second pixel set corresponding to at least one to-be-processed frame before the to-be-processed frame in the to-be-processed video; and generating a prediction frame based on the first prediction pixel set and the second prediction pixel set. The method can improve the video rendering effect.

The invention discloses an LED lamp strip video imaging control method and system based on pixel coordinate mapping, and relates to the technical field of visual image processing. The pixel coordinate mapping-based LED lamp strip video imaging control method comprises the following steps of S1, acquiring geometric structure data and operation performance data of an LED lamp strip, preprocessing the geometric structure data and the operation performance data, and constructing a bending management database; s2, according to geometric structure data of the lamp strip, analyzing a mapping deviation between a pixel coordinate and a physical coordinate in real time; s3, geometric structure data and operation performance data are obtained, and bending light attenuation analysis is carried out; s4, evaluating the thermal load state of the bending area according to the operation performance data and the thermal management data of the LED; and S5, displaying the operation performance data and the abnormal alarm information in real time through an interface, and realizing data closed-loop management and partition operation and maintenance tracing. The problems that the display precision of the bending area of the LED lamp strip is reduced, the brightness and the color are uneven, and the performance of the LED is degraded due to local heat accumulation are solved.

A method for coding a video implemented in an encoder or a decoder including the enhanced interpolation filter, EIF, for motion compensation, the method comprising: i) determining control point motion vectors, CPMVs, for a block according to affine inter-prediction, the block being an affine block or a sub-block of the affine block; ii) for a predefined sub-block size determining a reference area for a sub-block with the predefined sub-block size according to values of the CPMVs; iii) comparing the determined reference area with a predefined threshold; iv) applying EIF for motion compensation, comprising deriving the pixel-based motion vector field for the block; wherein if the determined reference area is larger than the threshold, deriving the pixel-based motion vector field for the block further comprises motion vector clipping, wherein motion vector clipping range is determined based on motion model of the block and the size of the block.

Embodiments can relate to systems and methods for generating hyperspectro-polarimetric images. The system can include a metasurface having a plurality of super pixels configured to encode spectral and polarization image data into spatial intensity distributions. The system can include an image capture device having at least one image sensor and a plurality of subsets of pixels configured to capture the spatial intensity distributions encoded by the metasurface. The system can include a processor in communicative connection with the image capture device. The processor can be configured to receive pixel data from the image capture device, generate captured image input data based on the pixel data, and access at least one computational reconstruction model configured to decode the captured image input data, and generate image output data based on the decoded captured image input data.

The invention discloses an active and passive fusion water depth inversion method based on adaptive spectrum weighting, and the method comprises the steps: carrying out the atmospheric correction of a multispectral satellite image, extracting a target region, and removing a land region and a deepwater region; the method comprises the following steps: acquiring a seawater point cloud of a satellite-borne photon counting laser radar in a target area, extracting sea surface and seabed information, and performing refractive index correction and tide correction to obtain a reference water depth; matching each pixel in the multispectral satellite image with a reference water depth, and dividing the multispectral satellite image into a reference pixel and a to-be-measured pixel; according to the spectral value of the multispectral satellite image, the Euclidean distance between each to-be-measured pixel and all reference pixels is calculated, and the reciprocal of the distance is used as the weight of each reference pixel; and introducing a weight-to-weighted least square method, and fitting a relationship from the spectral value to the water depth for each pixel to be measured to realize water depth inversion of the pixels to be measured. The method can effectively improve the active and passive fusion water depth inversion precision when the water depth distribution is uneven and the shallow sea area environment is complex.

The invention discloses an optical lens coating film defect detection method and system, and relates to the technical field of image processing, and the method comprises the steps: obtaining an image of a coating film surface under the irradiation of a standard light source, and carrying out the preprocessing, and obtaining the coordinate and gray value of each pixel point on a gray-scale image; based on the coordinates and the gray values of all the pixel points, calculating a defect-free background gray estimated value and a local deviation degree of each pixel point on the gray-scale map; calculating a local abnormal fluctuation level of a neighborhood of each pixel point based on the local deviation degree of the pixel points, and generating an illumination invariance threshold value of each pixel point; improving and calculating an LBP feature value of each pixel point based on an illumination invariance threshold; and determining a self-adaptive abnormal threshold based on the LBP feature value of the pixel point, and identifying an abnormal region based on the self-adaptive abnormal threshold to obtain the position and area of the defect. According to the method, the problem that defect features are difficult to accurately extract on the surface of the high-reflection coating can be solved, and coating defects can be accurately recognized.

The invention relates to the technical field of display methods, in particular to an adaptive multi-scene dynamic picture compensation method, which comprises the following steps of: judging dynamic pixels according to pixel-level gray scale difference operation results of a previous frame and a current frame and edge detection results of the previous frame and the current frame; according to the dynamic characteristics of each region of the picture, carrying out distinguishable region segmentation on the display picture; performing dynamic classification according to the dynamic pixels in each block; and performing elastic LUT configuration and management according to different dynamic levels, and outputting a compensation frame. According to different dynamic scenes, in combination with regulation and control of hardware, adaptive dynamic compensation of different scenes is experimented. The hardware module is responsible for quickly completing basic dynamic scene judgment, and the CPU adjusts the division mode of compensation parameters according to different display scenes, so that the image quality is improved, the excessive compensation is improved, and the problem of insufficient self-adaptability in different scenes in the prior art is solved.

The invention relates to a PID (Proportion Integration Differentiation) drawing element intelligent identification and topology reconstruction method based on visual detection, which comprises the following steps of: cooperatively extracting multi-modal information, detecting components based on improved YOLOv11, identifying all text labels in a graph by adopting PaddleOCR, and carrying out pipeline identification algorithm and merging filtering method based on probability Hough transform of pixel points. Identifying and defining the T-shaped connection point as a special topological node to obtain positioning information of components and characters in a PID drawing, associating the components with the characters by using a regular expression and an Euclidean distance, and converting image elements into a topological graph model with a semantic relationship; according to the method, the end-to-end automation process of detection-association-reconstruction is achieved, finally, display is conducted in a graphical interface mode, a data basis is provided for subsequent application such as drawing analysis, system simulation and equipment management, end-to-end automatic conversion is achieved, and efficiency is greatly improved.

A system and method for estimating object distance and / or angle from an image capture device may obtain an image including a fiducial marker captured by an image capture device; extract a pixel width and / or a pixel height of the fiducial marker in the image space of the image; determine, based on the pixel width and / or the pixel height, a known width and / or a known height, and one or more calibration parameters, a distance of the fiducial marker from the image capture device; estimate, based on the pixel width, the pixel height, the known width, and the known height, a yaw angle of the fiducial marker with respect to the image capture device; determine, based on a slope of a positional vector of the fiducial marker, a roll angle of the fiducial marker with respect to the image capture device; and / or provide the distance, the yaw angle, and / or the roll angle.

This invention proposes a method, device, equipment, and medium for vehicle lane keeping and lane changing control. It detects lane lines in the road image directly in front of a target vehicle using an existing lane detection model; determines pixel reference points in the road image based on the target vehicle's speed; uses a greedy algorithm to iterate and filter the pixel groups corresponding to each lane line to find the pixels closest to the pixel reference points, obtaining the nearest pixel group; sorts the pixels in the nearest pixel group; calculates the average of adjacent nearest pixels based on the sorting result to determine the lane center pixel; and controls the target vehicle's lane keeping or lane changing based on the determined lane center pixel. This reduces the computational resource requirements of the lane keeping system and improves the system's real-time performance and stability.

The invention relates to the technical field of LED display screens, and discloses an LED display screen pixel uniformity compensation algorithm and an implementation method, and the method comprises the steps: collecting photoelectric response data of a target pixel and horizontal and vertical adjacent pixels in an LED display screen; performing chromatic aberration deviation analysis on the target pixel based on the photoelectric response data to obtain a pixel difference value; a pulse modulation mode is selected based on the pixel difference value, driving control is carried out through a pulse hybrid modulation circuit according to the pulse modulation mode, the pulse modulation mode is a PAM modulation mode or a PWM modulation mode, and according to the method, the PAM modulation mode or the PWM modulation mode is intelligently selected according to the pixel deviation degree through the pulse hybrid modulation driving technology. The technical problems under different compensation requirements are effectively solved, and the response speed and the control precision of pixel uniformity compensation of the LED display screen are ensured.

The invention discloses an implicit self-supervision hyperspectral characterization anomaly detection method and system based on background credibility enhancement, and belongs to the technical field of intelligent analysis of sensory images. According to the method, a cross-modal implicit mapping method based on self-supervised learning is adopted, potential hyperspectral representation is mined from visible light data, and the capability bottleneck of a traditional method when labels are lacked or hyperspectral collection is limited is effectively made up. Secondly, the proposed implicit neural representation reconstruction framework can combine modeling space and spectral features, the problem that the space receptive field of an existing modeling method based on pixels or local structures is limited is broken through, and the processing capacity for complex background interference is improved. In addition, a background credibility enhancement mechanism is introduced, the attention degree of the model to different areas is adaptively adjusted according to clustering characteristics, and the false alarm rate is remarkably reduced. The mechanism is different from an existing mode depending on artificial prior or rule setting, and has better generalization and data driving characteristics.

The invention relates to the field of image processing, in particular to a textile cloth surface defect intelligent detection method based on machine vision, and the method comprises the steps: obtaining an original gray level image of a textile cloth surface at the current moment; calculating a texture confidence index based on gray similarity distribution of pixel points and neighborhood pixels in a search radius area of the pixel points, and adaptively inhibiting normal textures by using a ratio relation between a maximum value and a mean value of similarity weights; calculating a form confidence index based on a local brightness contrast characteristic and an isolation characteristic of a pixel point, and filtering fluff interference by integrating brightness, isolation and abnormal characteristics; calculating a gradient sharpness index based on a high-order power operation result of the gray difference of the pixel points in the horizontal and vertical directions; and finally, generating a defect residual image through multi-dimensional feature fusion, and carrying out segmentation identification. According to the method, normal textures, villus, shadows and real defects can be effectively distinguished, and the detection accuracy under a complex background is remarkably improved.