378 results about "Image boundary" patented technology

The invention relates to the technical field of intelligent control, in particular to a self-adaptive camera pose intelligent adjusting system which comprises a dynamic recognition module, a pose adjusting module, a mechanism control module, an information filtering module and a feedback association module. According to the method, the foreground pixel brightness gradient and the boundary continuity in the image frame are extracted, the target displacement path can be recognized, the tracking information is constructed, the target coherent perception under rapid scene change is guaranteed, the attitude parameters and the target motion direction and speed are combined, the offset correction instruction is generated, the response stability of the dynamic target is improved, and the target tracking accuracy is improved. The execution structure feedback is used for correcting control output, reducing the driving error accumulation risk, eliminating non-target disturbance through image boundary definition and motion consistency, improving data purity and combining a view angle execution state and path information to realize synchronous control of tracking and view angle adjustment; and the response efficiency and the following robustness of the system in a dynamic environment are enhanced.

The invention relates to the technical field of video coding, in particular to a video coding method and system based on multi-channel concurrent software and hardware mixing, and the method comprises the following steps: analyzing brightness distribution and edge structures, screening effective frames, calculating frame priorities, dividing image blocks and combining processing units, counting the number of frame streams, and analyzing frequency concentration. And evaluating image coherence and a load state, and outputting a processing channel adjustment record. According to the invention, through screening of image content features, occupation of redundant frames on coding resources is reduced, through dynamic configuration of frame priorities, timeliness and accuracy of target frame scheduling are improved, an aggregation strategy of a block structure is combined, picture consistency after image processing is enhanced, and task frequency trend identification is utilized, so that image processing efficiency is improved. According to the method, accurate resource matching of a high-load flow section is achieved, joint judgment of image boundary continuity and structure hopping frequency is adopted, an allocation strategy of a processing channel is optimized, an image structure and channel scheduling form linkage, and stability and adaptive capacity are improved.

The invention relates to the technical field of medical image processing, in particular to a medical equipment optical system calibration method and system based on image processing, and the method comprises the following steps: capturing a calibration image in medical equipment, analyzing the boundary structure of an optical calibration grid, screening the pixel distribution characteristics of a segmentation boundary, and extracting the geometric description characteristics of the calibration image; and generating a geometric distortion distribution diagram. According to the invention, by capturing the calibration image and analyzing the boundary of the optical calibration grid, the geometric distortion area is accurately identified, the accuracy of the distortion compensation image is improved, the non-linear distortion is compensated in a partition manner, the image quality of each area is optimized, the continuity of the image boundary is improved, and the structural symmetry and curvature change area are optimized. The distortion of the detail area is restored, the edge details are smoothed, the image quality is improved, the amplitude distortion of the optical calibration grid is effectively controlled, the edge detail distortion is reduced, the image integrity and consistency are ensured, and the image precision and the reliability of an optical system are remarkably improved.

The invention relates to the technical field of medical image processing and tumor treatment, and provides a tumor image boundary identification method and system fused with a fluorescence boundary, and the method comprises the steps: collecting a tumor dynamic fluorescence image sequence and breathing waveform data through a fluorescence imaging device; performing multi-scale noise suppression processing on the image sequence to generate a preprocessed image without artifacts; extracting fluorescence intensity distribution characteristics through a multi-layer characteristic weighted fusion network and generating an intensity distribution matrix; constructing a motion compensation model according to the breathing waveform data, and correcting the boundary displacement of the intensity distribution matrix; fusing the corrected fluorescence features and the tumor tissue texture features to generate an initial tumor boundary contour; iterative topological optimization is carried out on the initial boundary, and boundary discontinuity is eliminated; and mapping the optimized boundary to a space coordinate system of the laser treatment equipment, generating a boundary mapping model and updating the boundary mapping model in real time. The precision and safety of laser treatment can be improved, and damage to normal tissue is reduced.

The invention discloses a foam concrete image processing method based on sub-pixel edge reconstruction, and particularly relates to the field of foam concrete image processing.The method comprises the steps that an image of foam concrete is obtained, and a boundary response feature set containing edge direction information, edge gradient change information and local intensity comparison information is extracted; performing edge structure classification on the image region based on boundary response feature set combined threshold judgment; and aiming at the image region which is judged to be the local direction convergence mutation region, identifying a cross mutation point set by fitting a direction tensor convergence trend, and executing directionally-guided corrosion and expansion image processing. By constructing a structure judgment variable based on image boundary response characteristics and guiding a corrosion expansion path and a vein backtracking path to execute sub-pixel-level aperture boundary separation, image structure processing and contour reconstruction of a porous adhesion area are realized.

The invention relates to the technical field of image recognition, in particular to a mechanical casting detection method and system based on image data analysis processing, and the method comprises the following steps: obtaining a casting image gray value, classifying according to a gray scale standard, generating a multi-layer image structure and a layering graph, setting a grid, counting pixels to form a density sequence, extracting a trend region, and building an index table; and extracting multi-angle image boundary point matching intersection points to form a coordinate matrix, screening a stable intersection point set, searching an original image comparison trend coordinate to extract an overlapping region, and generating a defect annotation image result. According to the method, an image is subjected to gray scale division to form a multi-layer structure, texture differential expression is enhanced, a pattern layer grid statistics density sequence is used for extracting a trend region, abnormal distribution positioning is achieved, boundary mutation points in a multi-view image are uniformly mapped, boundary recognition consistency and robustness are improved, and a stable boundary and the trend region are compared and marked; defect expression intuition and credibility are enhanced, and detection precision and stability are improved.

The invention relates to a multi-modal image registration method based on modal alignment distillation, and belongs to the technical field of image processing. The method comprises the steps of adopting a distillation learning guide type training process, performing guide type supervision on a multi-modal registration student model by using intermediate features of a same-modal registration teacher model with excellent performance and an output deformation field, migrating modals of the intermediate features of the student model, and effectively reducing modal differences, a high-quality deformation field close to teacher model estimation is output, and the multi-modal registration performance is improved; a deformable mask training strategy is adopted to deal with the problem that a registration result is inconsistent with a label image boundary caused by a black edge effect of spatial transformation in a registration process (namely, a black edge of the registration result and an original boundary of the label image), so that the negative influence on registration is effectively reduced, and the registration performance of the model is improved. According to the invention, a multi-modal image registration task can be realized, registration challenges caused by modal differences are effectively solved, and the effect of multi-modal image space alignment is achieved.

The invention relates to an X-ray image contraband detection method based on multi-scale feature fusion, and belongs to the technical field of image processing. The method comprises the following steps: acquiring an X-ray contraband data set, and dividing the data set into a training set and a test set; constructing an X-ray image contraband target detection model based on multi-scale feature fusion, wherein the model comprises an image branch, a self-adaptive high-low pass filter module, a text branch, a Neck layer and a Head head; images in the training set are input into the model to train the model; optimizing the model by adopting a loss function to obtain a trained model; and inputting the images in the test set into the trained model to obtain a contraband detection result. According to the method, through image and text joint training, the performance is improved in real-time task monitoring, the efficiency is higher, the calculation amount and memory occupation are reduced, and the problem that image boundary details are fuzzy in a complex scene is solved.

The invention relates to the technical field of topographic change analysis, in particular to an unmanned aerial vehicle-based topographic change detection system, which comprises a slope direction sensing track control module, a texture structure extraction module, a crack evolution track construction module, a direction trend comparison module and a patrol recheck positioning module. According to the method, a continuous elevation point column of an unmanned aerial vehicle scanning area is extracted, laser reflection point coordinates are fused, a space relation of transition point distribution is constructed, dynamic adjustment of a ground-imitated flight path is achieved, and a texture structure area with continuous directivity is recognized in combination with a high-angle image boundary communication relation; texture boundary evolution is compared at different time nodes to form a crack path, the stability of the path and the slope direction is judged through an included angle sequence, recognition and sorting of areas with the consistent direction are completed, a space comparison result is registered in a three-dimensional coordinate system, terrain change areas are accurately marked, and rapid positioning and continuous tracking of high-risk areas are achieved.

The invention relates to the technical field of rock mass fracture recognition, in particular to a rock mass fracture recognition method based on a boundary detection neural network model. According to the method, an innovative deep learning framework is provided for boundary recognition, the characteristics of a refinement strategy and sub-pixel convolution are combined, and a leading result is obtained on a data set. The research shows that the CED model can improve the performance of middle-level and high-level visual tasks including optical flow estimation, target suggestion generation, semantic segmentation and the like. According to the method, a novel architecture is provided to solve the precision problem of a CED algorithm, a reverse refining path is supplemented for an HED network to improve the recognition precision, and the path uses efficient sub-pixel convolution to merge features step by step; the CED provided by the invention can generate an edge image which is well aligned with an image boundary.

The invention discloses an image edge cutting method and device based on boundary detection, equipment and a storage medium, and relates to the technical field of image boundary detection, and the method comprises the steps: carrying out the preprocessing of an original image, and obtaining a target image; determining a scene type of the target image; based on an edge detection strategy corresponding to the scene type, performing edge detection on the target image to obtain an edge image; performing straight line detection on the edge image to obtain a plurality of candidate straight line segments; and based on a boundary positioning rule, determining a target boundary line segment from the plurality of candidate straight line segments, so as to carry out edge cutting on the original image according to the target boundary line segment. According to the invention, a more reliable image edge cutting effect can be generated.

The invention provides an image region-of-interest extraction method and system based on a Mama architecture, and relates to the technical field of image processing, and the method comprises the steps: obtaining a to-be-extracted image; performing multi-scale feature extraction on the to-be-extracted image through a local enhancement module; multi-scale semantic enhancement features are generated through a cross-scale self-attention module, and dimension reduction processing is performed through a feature conversion module; local detail features are generated through an adaptive detail enhancement module; performing global context enhancement processing on the local detail features through a pyramid pooling module to generate context enhancement features; performing up-sampling processing on the context enhancement features; the context enhancement features after up-sampling processing are fused through a self-adaptive global-local fusion gating module; and carrying out image extraction based on the decoded fusion features. The image segmentation precision is improved, the model is light in weight, reasoning is fast, and the problems of image boundary blurring and scale variability are effectively solved.

The invention provides an ore image segmentation optimization method and system based on edge detection, and relates to the technical field of image processing, and the method comprises the steps: obtaining an ore particle image with to-be-detected ore; preprocessing the ore particle image; extracting an edge image of the preprocessed ore particle image through a Canny edge detection algorithm with an adaptive threshold; in combination with the ore particle image, segmenting the edge image through a pre-trained SAM model to obtain a segmentation mask marking the boundary of the edge image; inputting the ore particle image and the segmentation mask into a CRF model, and optimizing the segmentation mask by taking minimization of an energy function value in the CRF model as a target to obtain an optimized segmentation mask; carrying out area filtering based on an area threshold value on the optimized segmentation mask, and reserving a target area representing the to-be-detected ore in the ore particle image; and outputting the target region as a segmentation result of the ore particle image.

The invention discloses a medical image segmentation method based on boundary constraint. The method comprises the following steps: S1, obtaining a medical image amplitude spectrum and a medical image phase spectrum; s2, forming a structure sensing frequency domain disturbance result; s3, obtaining a frequency domain enhanced medical image; s4, calculating structure perception medical image boundary enhanced attention output features; s5, performing global relation modeling and local texture modeling on the frequency domain enhanced medical image sequence; s6, generating an edge heat map; and S7, performing bidirectional gating interaction on the edge heat map and the output of the linear self-attention encoder by adopting a double-domain interaction fusion strategy to generate a double-domain interaction fusion feature map, performing up-sampling and convolution processing on the double-domain interaction fusion feature map in a decoder, and outputting a boundary enhancement segmentation feature map. According to the invention, the structure perception capability of the model in a medical image scene with fuzzy anatomical structure boundary and low texture contrast is effectively improved.

The invention provides an open vocabulary semantic segmentation method and device based on feature interaction and multi-modal data fusion. An SAM encoder of freezing parameters is adopted to extract RGB image and Mask image features in parallel, and boundary information enhancement is carried out through a feature fusion module. A CLIP image encoder of freezing parameters is used for carrying out multi-layer feature extraction on an RGB image, and multi-scale semantic information optimization is carried out through a feature enhancement module. And fusing image features extracted by the SAM branch and the CLIP branch through a feature interaction module to realize cross-network feature complementation. In a prediction stage, a category integration strategy combined with a temperature scaling operation is introduced to optimize prediction effects of known and unknown categories. According to the method, the advantages of SAM in the aspect of image boundary extraction and the image-text alignment capability of CLIP are combined, and the generalization capability and robustness of the model in an open vocabulary semantic segmentation task are effectively improved through multi-modal feature fusion and interaction.

The invention relates to the technical field of anomaly detection, in particular to a circuit board processing anomaly detection system which comprises an image anchoring module, a gray scale comparison module, a candidate area screening module, a gradient closing verification module and a behavior track evolution module. According to the method, by setting the gray scale anchor points in the image frames and collecting the standard gray scale values, deviation accumulation caused by the overall illumination change of the image can be effectively avoided, the response delay area is recognized through inter-frame gray scale comparison, and early intervention on the etching abnormal process is achieved; a gray scale fluctuation low-amplitude segment in an image boundary region is extracted to recognize a texture missing region, the recognition accuracy of structural blur is enhanced, fine extraction of an abnormal structural form is realized in combination with gray scale gradient chain construction and a closed error judgment mechanism, region response change trajectory tracking in a frame sequence is superposed, and the recognition accuracy of structural blur is improved. Therefore, the judgment is not limited to single-frame anomaly detection and has a time sequence evolution recognition capability, an abnormal symptom region is stably captured, and a reliable detection result is generated.

The invention discloses an electric arc three-dimensional reconstruction system and method based on binocular vision. The system comprises a double-camera image acquisition module, a correction module, a boundary contour point extraction module and a three-dimensional reconstruction module. The dual-camera image acquisition module completes dual-camera parameter calibration and dual-vision arc image shooting operation at different positions; the correction module corrects an optical distortion area and a breakpoint area of the double-vision arc image to obtain a corrected double-vision arc image; the boundary contour point extraction module adopts a third-order Bezier curve to perform segmentation fitting on the boundary contour of the corrected double-vision arc image to obtain continuous double-vision arc boundary points; and the three-dimensional reconstruction module reconstructs a three-dimensional contour line of the electric arc through a triangulation method according to the camera calibration parameters and the double-vision electric arc boundary points, and generates a corresponding three-dimensional point cloud data set. According to the method, the distortion and breakpoint phenomena of the arc image can be repaired, and high-precision reconstruction of three-dimensional data of the arc is realized.

The invention discloses a PCB semantic segmentation method fusing ResNet and an attention mechanism. The method comprises the following steps of performing defect segmentation area cutting and data enhancement on a PCB image; carrying out image smoothing filtering on the enhanced PCB defect image data set by adopting a generalization edge preserving and structure preserving image smoothing model, and inputting a UNet model encoder to extract defect area features; performing layer-by-layer down-sampling on the defect area features to obtain initial feature maps of different scales; inputting the initial feature maps of different scales into a CBAM module according to corresponding levels, and adding the feature maps processed by the CBAM attention mechanism with the initial feature maps of different scales by the CBAM module; and the UNet model decoder obtains the feature map of each layer of the CBAM module, recovers the image resolution layer by layer, obtains an image boundary, and outputs a defect segmentation result. According to the invention, the segmentation precision of PCB image detection can be improved.

The invention relates to the technical field of image recognition, in particular to an unmanned aerial vehicle tracking system and method based on image recognition, and the system comprises a spectrum optimization module, a trajectory analysis module, a form adjustment module, a flight anomaly detection module and a tracking optimization module. According to the method, the brightness information of the ambient light and the reflected light of the unmanned aerial vehicle is finely analyzed and the spectral response of the image is adjusted, so that the image definition is greatly improved, the unmanned aerial vehicle can be accurately identified under various illumination conditions, and the flight path of the unmanned aerial vehicle is calculated in real time by accurately analyzing the image bounding box and timestamp information of the unmanned aerial vehicle. According to the method and the system, the tracking process is ensured to be continuous and accurate, any form change is effectively captured by continuously monitoring the form of the unmanned aerial vehicle in continuous image frames, the behavior mode change of the unmanned aerial vehicle is responded in time, and in the aspect of flight abnormity monitoring, behaviors inconsistent with a conventional flight mode can be accurately analyzed, and potential security threats can be identified in time.

The invention discloses a furrow identification and navigation line extraction method of a self-propelled transportation platform for ridge planting vegetables. The furrow identification and navigation line extraction method comprises the steps of image acquisition, image boundary smoothing processing, color conversion, threshold segmentation, denoising processing, edge detection, midpoint extraction and navigation line fitting. Gaussian blur filtering is used to carry out boundary blur processing on the image, then a traditional BGR image is converted into an HSV image to reduce the influence of an illumination condition on furrow identification, and a low-influence component is separated to carry out next processing; the method comprises the following steps of: enhancing gray information by adopting a Masking algorithm, effectively realizing threshold segmentation and successfully identifying a furrow position in combination with an OTSU method, further removing most noise interference in an image by utilizing a morphological denoising method, realizing deep denoising of the image on the basis of a FindContours, extracting a furrow boundary, and finally, extracting the furrow boundary. Then, the horizontal coordinates of the two boundary points of the furrow are utilized to solve the midpoint coordinate point cloud of each row in the image pixels, and finally, the point cloud coordinates are utilized to improve the RANSAC algorithm to realize the navigation line fitting of the furrow.

A method for detecting an image boundary using a generative adversarial network (GAN) model is provided. The GAN model includes a generator network and a discriminator network. The method includes the following steps. The GAN model is trained using a plurality of image pictures to obtain a weight value, an average value of a generator network loss parameter, and an average value of a discriminator network loss parameter. A generator network is updated with a first loss parameter, wherein the first loss parameter is a weighted sum of the average value of the generator network loss parameter and the average value of the discriminator network loss parameter. The discriminator network is updated with a second loss parameter, wherein the second loss parameter is the average value of the discriminator network loss parameter.

The invention relates to the technical field of power equipment fault detection, in particular to a power equipment fault detection and diagnosis system, which comprises a preliminary detection and diagnosis module for collecting a panoramic image of power equipment in a region and completing preliminary detection and diagnosis of the power equipment according to an image data processing result; and the secondary detection and diagnosis module is used for carrying out secondary detection on the power equipment of which the fault cannot be judged through the temperature so as to finish accurate diagnosis of the fault. According to the method, heat source points and fault features are accurately identified by using gradient analysis of infrared image data and a support vector machine model; a histogram clipping and gray scale weighted fusion method is adopted, so that the influence of background noise on an image boundary is reduced, the contrast ratio between a heat source point and a background is enhanced, and the identification of a fault position is more accurate; on the basis of heat source point identification, multiple types of faults are classified, so that different types of faults such as short circuit, overload and grounding faults are efficiently and accurately classified.

Aspects of the disclosure provide methods and apparatuses for video encoding / decoding. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. The processing circuitry receives a bitstream carrying a plurality of pictures, and determines at least a motion compensation padding (MCP) block that is located in an MCP area outside of a picture and next to a picture boundary of the picture. The processing circuitry derives, according to a plurality of candidates with positions located at the picture boundary within the picture, a motion vector of the MCP block for motion compensated boundary padding, and reconstructs at least a sample in the MCP block according to the derived motion vector for the motion compensated boundary padding.

The invention discloses an agricultural land boundary extraction method and system fusing SAM and an improved Segform model, and relates to the technical field of image processing, and the method comprises the steps: carrying out the polygonal ground feature extraction of a preprocessed image tile data set through employing the SAM model; inputting the agricultural land sample data set into an improved Segform model for optimization, and then performing agricultural land boundary extraction; the improved Segform model takes the Segform model as a basic network structure, a feature fusion module fuses high-level semantic information, a DySample ultra-light dynamic up-sampling module is adopted to generate sampling points, and a DANet dual attention mechanism and an ECA channel attention mechanism are added for feature optimization. According to the method, on the basis of high-resolution image data, refined extraction is carried out on the boundary of the remote sensing image by fusing an SAM large network model and an improved Segform model.

Provided are a display method of a head-up display and a head-up display. The display method of the head-up display includes the following steps: an original image is received; an image boundary of the original image is corrected based on projection surface distortion data to generate a corrected image; multiple first sub-light-emitting regions corresponding to an image boundary of the corrected image are determined; light emitting data are adjusted based on display boundary data to increase brightness values corresponding to the multiple first sub-light-emitting regions in the light emitting data, and brightness values of multiple second sub-light-emitting regions corresponding to a non-display region in the light emitting data are set as 0; and a display module is driven based on the corrected image and an adjusted light emitting data. The display method of the head-up display and the head-up display of the disclosure may achieve good display effects.

Aspects of the disclose provide methods and an apparatus for video and / or image coding. The apparatus includes processing circuitry that receives a bitstream including a plurality of pictures. The processing circuitry determines an initial motion vector (MV) associated with a motion compensation padding (MCP) block according to motion information of a boundary block located at a picture boundary of a picture in the plurality of pictures. The boundary block is located in the picture. The MCP block is located in an MCP area outside of the picture and adjacent to the picture boundary. The initial MV has a fractional precision. The processing circuitry generates a final MV associated with the MCP block based on the initial MV. The final MV has an integer precision. The processing circuitry reconstructs, according to the generated final MV having the integer precision, at least a sample in the MCP block.

Systems and methods for image processing (e.g., image extension or image uncropping) using neural networks are described. One or more aspects include obtaining an image (e.g., a source image, a user provided image, etc.) having an initial aspect ratio, and identifying a target aspect ratio (e.g., via user input) that is different from the initial aspect ratio. The image may be positioned in an image frame having the target aspect ratio, where the image frame includes an image region containing the image and one or more extended regions outside the boundaries of the image. An extended image may be generated (e.g., using a generative neural network), where the extended image includes the image in the image region as well as generated image portions in the extended regions and the one or more generated image portions comprise an extension of a scene element depicted in the image.

The invention relates to the technical field of wearable monitoring, in particular to farm intelligent wearable inspection equipment, which comprises a track thermal difference recognition module, an abnormal target labeling module, a high fever behavior screening module, an image information extraction module, a structure label generation module and an individual inventory recognition module. According to the invention, by extracting the infrared temperature measurement data and calculating the thermal fluctuation difference value, the positioning of a temperature abnormal section is realized, the identification capability of tiny thermal environment variation is enhanced, the high-heat target area is positioned, the image filing is completed, and the target screening accuracy and the image utilization efficiency are improved. Static high-heat individuals are identified based on the calorific value state and the spatial position stability, the discovery probability of potential abnormal objects is improved, through image boundary contour extraction and structural feature comparison, the individual identification efficiency is improved, and image information and dynamic path data are synchronously analyzed, so that the monitoring result is more continuous and complete, and the detection accuracy is improved. And the intelligent response capability and the information processing depth are improved.

The invention provides a model training method and a lesion image segmentation method and device, and belongs to the technical field of medical image analysis. The model training method comprises the following steps: constructing a U-shaped image segmentation network, the U-shaped image segmentation network comprising an encoder and a decoder; wherein the encoder is used for encoding the lesion image to obtain an encoding feature; the decoder is used for decoding the coding features to obtain a decoded lesion image; a boundary key point of a lesion area in the real lesion image is extracted through a differential evolution boundary enhancement module, and a boundary area of the real lesion image is obtained; and based on the loss of the boundary region of the decoded lesion image and the real lesion image and the loss between the decoded lesion image and the real lesion image, optimizing the parameters of the U-shaped image segmentation network, the parameter-optimized U-shaped image segmentation network being used for lesion image segmentation. The model obtained by training based on the method can realize image segmentation with low parameter quantity, low calculation load and high precision.

The invention relates to a method and a system for identifying particles in insulating oil driven by deep learning, which can realize automatic identification and classification of particles in insulating oil by combining a micro-flow digital imaging technology and a semantic segmentation method of deep learning, constructing a unified training data set and combining a multi-task segmentation model. Images of the particles in the transformer oil are obtained through the micro-flow digital imaging module, and pixel-level classification and particle recognition are carried out on the images through the multi-task segmentation model. The segmentation branches in the model are responsible for extraction of particle boundaries, and the classification branches are used for analyzing particle morphology and outputting particle categories. The model adopts multi-scale feature fusion, an attention mechanism and a deep residual network structure, and the problems of particle morphology diversity, size change, image boundary blur and the like are solved. Through the high-precision particle recognition algorithm and system, the accuracy and efficiency of detection of the particles in the insulating oil are effectively improved, manual intervention is reduced, and the safety and long-term stability of the transformer are improved.