25results about How to "Keep details" patented technology

The invention discloses an X-ray and NeRF algorithm-based luneberg lens internal structure analysis method, and relates to the technical field of three-dimensional imaging of optical lenses, and the method comprises the following implementation steps: S1, configuring an RGB-X-ray combined imaging system, and carrying out data acquisition, and S2, carrying out the calibration of external parameters of a camera through a calibration plate: carrying out the imaging through a specially-made calibration plate, and carrying out the calibration of the external parameters of the camera through the calibration plate. The method comprises the following steps: acquiring a plurality of frames of RGB (Red, Green, Blue) images to obtain external parameters of an RGB camera under a calibration plate coordinate system, acquiring a plurality of frames of X-ray images to obtain an external parameter matrix of an X-ray camera about the calibration plate coordinate system, performing implicit representation on a continuous field in a lens by utilizing NeRF, mapping three-dimensional coordinates to differentiable density and radiation values, and calculating the calibration plate coordinate system. According to the method, high-fidelity reconstruction from multi-angle X-ray projection to a three-dimensional structure is achieved, detail information in the lens can be effectively reserved, meanwhile, the continuity and symmetry of the structure are guaranteed, and compared with a traditional voxelization or CT reconstruction method, the problems that noise artifacts, fractures and unstable numerical values are likely to be generated in the traditional voxelization method are solved.

The invention discloses a geometric constraint-driven complex roadway body point cloud dynamic extraction method. The method comprises the following steps of S1, collecting three-dimensional point cloud of a roadway by adopting three-dimensional laser scanning equipment; s2, constructing a coordinate system according to the longitudinal central axis of the roadway, and realizing coordinate transformation operation of the three-dimensional point cloud; s3, a virtual cloth grid is constructed on the periphery of the three-dimensional point cloud, and each cloth particle in the virtual cloth grid dynamically shrinks from outside to inside under the combined action of radial attraction pointing to the X axis of the coordinate system and internal elastic force maintaining the shape of the virtual cloth grid; through multiple iterations, the virtual material distribution grids can be attached to the surface of the inner wall of the roadway; calculating the shortest distance from each point in the three-dimensional point cloud to the surface of the virtual distribution grid, and performing classification operation on roadway body points and non-body points in the three-dimensional point cloud; and S4, carrying out refined processing on the roadway body points in the three-dimensional point cloud obtained after classification, and finally outputting a roadway body model.

This invention discloses a two-branch image dehazing method based on edge constraints, comprising the following steps: Step 1: Constructing an image dehazing dataset; Step 2: Obtaining edge maps of the images using the Canny edge detection operator, and constructing a training sample using the edge maps, corresponding fog maps, and clear maps; Step 3: Randomly segmenting the images in the training samples as input to the network, and using data augmentation methods to expand the sample size; Step 4: Constructing a two-branch dehazing network based on edge constraints, including a dehazing subnetwork and an edge subnetwork; Step 5: Initializing network parameters and constructing a target loss function to optimize the parameters of the two-branch dehazing network; Step 6: Using the trained model to dehaze the test fog map to obtain a clear, fog-free image. This invention can utilize edge constraints to recover clear, fog-free images, solving the problem of lost spatial details and semantic inconsistencies in the repaired images during image dehazing tasks.

A method and system for super-resolution reconstruction of infrared images based on convolutional neural networks, relating to the field of electronic digital data processing, is disclosed. The method includes: inputting a low-resolution infrared image into a preset convolutional neural network to obtain multi-layer feature maps of the low-resolution infrared image; scaling the feature maps of different layers in the multi-layer feature maps according to a preset ratio and then stitching and fusing them to obtain a fused feature map; generating feature vectors from the fused feature map using global average pooling, and transforming the feature vectors using a fully connected layer to obtain attention weights; weighting the attention weights with the fused feature map to obtain an enhanced feature map; and performing upsampling reconstruction processing on the enhanced feature map using an upsampling structure, introducing a residual connection structure during the upsampling reconstruction process to generate a high-resolution infrared image. Implementing this method generates high-resolution infrared images with more detail.

This invention relates to the field of dental 3D printing technology, specifically a sub-pixel edge refinement and adaptive slicing method for dental 3D printing. The method includes: calculating the curvature features of a dental 3D mesh model and generating a curvature image; achieving adaptive layer thickness allocation based on surface complexity through dual-threshold segmentation and dynamic programming smoothing; obtaining the initial slicing boundary using inverse ray tracing; performing sub-pixel-level boundary search using the Breaking Ball algorithm; and outputting a high-precision contour through multi-scale, coarse-to-fine refinement; establishing a light source radiation field model and implementing three layers of grayscale compensation: global compensation, extreme value compensation, and edge protection filtering; constructing a multi-objective optimization model; using a non-dominated sorting genetic algorithm to search for the Pareto optimal solution set; selecting the optimal layer thickness sequence based on user weights; and generating G-code printing instructions. This invention achieves synergistic optimization of accuracy, efficiency, and material conservation.

This invention proposes a method for simulating infrared turbulence degradation images based on Unreal Engine. The steps are as follows: constructing a 3D mountain simulation scene based on Unreal Engine; generating a blurred kernel texture image based on a calculated 2D point spread function; rendering the 3D mountain scene using Unreal Engine, convolving the rendered result with the blurred kernel texture image, and obtaining the simulated infrared turbulence degradation image through the convolution result. This invention achieves real-time turbulence blurring of the mountain scene by performing parallel convolution on each frame of the rendered 3D mountain scene with the blurred kernel texture image generated based on the 2D point spread function. The obtained real-time turbulence blurring effect preserves the details of the terrain well. It also considers the influence of the spatial frequency response information of the imaging system itself and the attenuation effect of atmospheric turbulence on image detail transmission, effectively improving simulation accuracy. Furthermore, parallel convolution reduces the complexity of generating the real-time turbulence blurring effect of the mountain scene, exhibiting good real-time performance.

The application discloses a multiphase flow interaction simulation method based on MPM and a phase field model, and comprises the following steps: step S1, storing mass parameters, phase field parameters and momentum parameters of Lagrange particles in an Euler grid; step S2, updating the phase field of the Euler grid according to the chemical potential to control the energy of the whole system; step S3, updating the momentum of the Euler grid according to gravity, elastic force and the surface tension of the updated equivalent phase field form; step S4, after the grid momentum is updated, processing the boundary on the Euler grid by using a slip boundary condition; step S5, after the phase field and the momentum are updated, converting the momentum parameters and the phase field parameters from the Euler grid variables to Lagrange variables; and step S6, updating the state of the Lagrange particles: updating the position and mass state of the Lagrange particles according to the information returned to the Lagrange particles.

This disclosure provides a virtual try-on method, apparatus, device, and storage medium. The method includes acquiring an original image; extracting an original clothing region image from the original image using a target segmentation model; performing outward cropping processing on the original clothing region image to obtain a cropped clothing image and adjusting its resolution to obtain a clothing image to be processed; determining a first latent space feature matrix corresponding to the clothing image to be tried on; merging the first latent space feature matrix with a second latent space feature matrix determined from the target clothing image to be processed; denoising and redrawing the merged latent space matrix to obtain a new merged latent space matrix; determining a target clothing region image from the target second latent space feature matrix; and replacing the original clothing region image in the original image with the target clothing region image to obtain a target try-on image. This disclosure only processes the image corresponding to the clothing region, preserving the clarity and detail information of the original image to the greatest extent.

The embodiment of the invention provides a self-adaptive confrontation image defense method based on intensity perception and related equipment, and belongs to the technical field of artificial intelligence security. The method comprises the following steps: firstly, constructing a multi-level confrontation intensity evaluation index, and comprehensively quantifying the disturbance intensity of a confrontation sample from three dimensions of a pixel level, a feature level and a prediction level; an intensity perception adversarial purification network is constructed, and the network is composed of an adversarial intensity predictor and an intensity-guided adversarial purifier in a cooperative mode. The predictor perceives the confrontation intensity of the input image through a sparse self-attention mechanism and generates a dynamic weight; and according to the sensed intensity information and the dynamic weight, the purifier adaptively executes purification operation through an intensity-guided multi-scale feature fusion and feature modulation module, and a clean image is reconstructed. According to the method, the defects of the existing static purification method are overcome, and the purification strategy can be dynamically adjusted according to the attack threat degree, so that the better balance between the anti-robustness and the model standard precision is realized under the wide anti-attack condition.

The application discloses a wavelet Mamba low-light image enhancement method based on illumination prior, and specific steps are as follows: step 1, an illumination estimation module is constructed, a low-light image is taken as input, and illumination quaternion prior is obtained; step 2, a wavelet Mamba encoding and decoding network is constructed, the low-light image and the illumination quaternion prior are input into the wavelet Mamba encoding and decoding network, and an enhanced image is obtained; step 3, a whole network composed of the illumination estimation module and the wavelet Mamba encoding and decoding network is trained, and a trained whole network is obtained; and step 4, a low-light image to be enhanced is input into the trained whole network, and a final enhanced image is obtained. The method can enhance the image while maintaining naturalness and details, and the enhanced image has high quality.

The application discloses an image feature extraction method and an image noise reduction method and related devices, and belongs to the technical field of image processing. The application can strengthen the connection between the local area and the global information of the features from the progressive angle of the large local receptive field and the global receptive field, so that the feature extraction method based on the self-attention mechanism can still capture the long-distance pixel dependence while reducing the calculation complexity, can well remove the image noise in the image noise reduction task based on the pixel level, and can maximize the retention of the detail information of the image.

The embodiment of the invention provides a cross-scene monocular depth estimation method and device, equipment and a storage medium. The method comprises the steps that cross-scene to-be-processed image data are acquired, then the to-be-processed image data are input into a preset estimation model, target absolute depth image data are obtained, the estimation model is determined based on multiple pieces of first image data and reference absolute depth image data corresponding to each piece of first image data, and the target absolute depth image data are obtained; and performing relative depth conversion processing on the to-be-processed image data to obtain relative depth image data, and finally determining a target depth map corresponding to the to-be-processed image data according to the absolute depth image data and the relative depth image data. According to the method provided by the invention, monocular depth estimation during cross-scene application is realized, and the accuracy of depth estimation is effectively improved.

This invention provides an efficient interpolation method for image upsampling. The method comprises the following steps: Step 1, upscaling the original low-resolution image LR by a factor of k using conventional bicubic interpolation to obtain a high-resolution image HR; Step 2, sharpening the images before and after upscaling to obtain the corresponding edge images LR. eg and HR eg Then, the high-resolution edge image HR eg Downsample k times and LR from low-resolution edge images eg Step 3 involves subtracting the lost sharpening information from the image edges during upsampling to obtain the portion of sharpening information lost during the upsampling process. This lost information is then added to the original image's LR (Light Rendering) matrix at a certain ratio. Simultaneously, the offset of the image center point during scaling is considered, and the interpolated pixels are fine-tuned. Finally, the optimized bicubic interpolation is used to enlarge the image's LR matrix by a factor of k to obtain the final high-resolution image. This invention offers a significant performance improvement compared to traditional upsampling methods and possesses a certain degree of versatility.

The application provides a satellite vegetation index fusion method based on optimal interpolation and fast Fourier transform, comprising: obtaining a meteorological vegetation index product and a high-resolution vegetation index product; performing multi-level interpolation processing on the meteorological vegetation index product based on optimal interpolation and plane equation interpolation, taking a specified vegetation index product as a background field, to obtain a vegetation index interpolation; performing fast Fourier transform processing on the high-resolution vegetation index product to eliminate a seam area contained in the high-resolution vegetation index product, to obtain a new high-resolution vegetation index product; and fusing the vegetation index interpolation and texture features corresponding to the new high-resolution vegetation index product, to obtain a vegetation index fusion result, wherein the texture features are used to describe a vegetation index change between two adjacent pixels in the new high-resolution vegetation index product. The application can significantly improve the precision of the vegetation index fusion result in a complex terrain or a region where multiple vegetation types coexist.

This invention discloses a low-light image enhancement method based on random region concealment and reconstruction. The network consists of two stages. In the first stage, the network is trained on a well-lit image dataset to reconstruct the noisy image after random regions are concealed, resulting in a denoising and reconstruction feature encoder for low-light noisy images. In the second stage, the network inherits the feature encoder model parameters from the first stage and inputs the extracted different features into a multi-scale feature fusion module guided by the reconstructed features. This allows the network to retain more image detail features while denoising. This invention utilizes a richer dataset of well-lit images, saving time and manpower by capturing a large number of real paired low-light images for network training. By fusing features extracted from different feature encoders, the network can quickly adapt to real low-light images under complex lighting conditions, achieving good low-light enhancement and denoising effects.

The invention belongs to the technical field of image processing, and particularly relates to a geological three-dimensional exploration image reconstruction method, which comprises the steps of calculating credibility weights, adaptive adjustment parameters and geological complexity of data points, and determining contribution weights of the data points to grid nodes; screening adjacent points of the grid nodes, and constructing an initial three-dimensional grid based on the geological attribute values; calculating a gradient vector of each node of the initial three-dimensional grid, constructing a structure tensor matrix, decomposing the structure tensor matrix to obtain a feature value and a feature vector, dividing a structure region according to the feature value, calculating a relative weight and a normalized adjustment factor in each direction, and combining a preset region type factor to obtain a smooth adjustment coefficient of each grid node in each direction; and constructing a diffusion matrix through the smooth adjustment coefficients in all directions and the corresponding feature vectors, and iteratively optimizing the initial three-dimensional grid through an anisotropic diffusion technology to obtain a reconstructed geological three-dimensional exploration image. According to the invention, the accuracy of geological three-dimensional exploration image reconstruction is improved.

A radar image difference recognition method based on scattering center modeling and deep learning is proposed. This method utilizes a Gaussian scattering center model to parametrically model the target scattering source, extracting features such as position, amplitude, width, and direction. An automatic thresholding method based on mutual information is employed for image registration. Optimal rigid body transformation parameters are obtained through cross-threshold search and derivative-free optimization, effectively eliminating geometric errors caused by imaging offset. A difference map is generated using a logarithmic ratio operator, and high-confidence pseudo-label samples are obtained through hierarchical fuzzy C-means clustering. Simultaneously, virtual sample generation technology is combined to expand the training set. Finally, a wavelet-constrained convolutional neural network is constructed, incorporating dual-tree complex wavelet transform to enhance direction sensitivity, achieving accurate classification and diagnosis of scattering source changes. This invention significantly improves radar image registration accuracy, change detection robustness, and model generalization ability, making it suitable for applications such as stealth target performance evaluation, radar image detection, and target recognition.

The application discloses an enhancement method and device for a fatty liver image, and relates to the technical field of image processing. The gray value of a liver ultrasound image is mapped to a preset range, and logarithmic transformation is performed to obtain a first target image; the first target image is input into a pre-trained denoising model to obtain a second target image; and post-processing is performed on the second target image to obtain an enhanced liver image. Through gray mapping and logarithmic transformation on the ultrasound image, multiplicative speckle noise is converted into additive noise, which facilitates the pre-trained denoising model to effectively remove noise and significantly improve the image quality. Meanwhile, the pre-trained denoising model based on deep learning can maximize the retention of liver tissue details and boundary information while denoising, thereby avoiding the common problem of detail blurring in traditional filtering methods.

This invention discloses a method, apparatus, and imaging device for correcting metal artifacts using nonlinear projection decomposition. The method includes: Step 1, acquiring original CT scan data containing artifacts to obtain an original CT image with metal artifacts; Step 2, thresholding the CT image with metal artifacts to separate the metal from the reconstructed image, and then obtaining the metal projection region; Step 3, using an interpolation method to complete the metal projection region and outputting an interpolated corrected projection; Step 4, combining the interpolated corrected projection obtained in Step 3 to obtain the projection of the metal portion in the CT scan data, then obtaining fitted metal projection data using a rational fraction fitting method, and finally subtracting the contribution of the metal projection portion from the CT scan data to obtain the corrected projection; Step 5, reconstructing the projection data after subtracting the metal contribution, and fusing it with the metal region obtained in Step 2 to obtain a CT image corrected for metal artifacts. This invention can effectively preserve details and structural information near metal implants while removing metal artifacts.

The invention relates to the technical field of image processing, in particular to a draw-out type switch cabinet copper bar processing size detection method based on machine vision, which comprises the following steps: acquiring a copper bar image containing a processing area, and performing local window division; constructing a light ladder anti-phase index of the copper bar image, wherein the light ladder anti-phase index is used for representing a deviation degree of a product of normalized brightness and a normalized gradient of a local window in the copper bar image; and constructing a compensation spatial imbalance index of the copper bar image, wherein the compensation spatial imbalance index is used for quantifying the structural risk of edge penetration in illumination estimation. In order to reduce the problems of serious uneven illumination, smooth hole edge transition and positioning deviation caused by metal surface mirror reflection after the copper bar of the switch cabinet is processed, a light ladder anti-phase index, a compensation space unbalance index and an iteration compensation intensity index are constructed; and the structural risk caused by spatial heterogeneity illumination and Gaussian permeation is accurately quantified.

The invention discloses a mobile phone shell production defect detection method and system based on AI vision, and relates to the technical field of automatic detection.The method comprises the steps that a surface image of a mobile phone shell is collected through an industrial camera, posture angle information of the mobile phone shell in the surface image is extracted, image correction is conducted on the surface image, and a regular mobile phone image is obtained; constructing a local analysis neighborhood and calculating a directional texture response component to form a texture response graph; comprehensive texture response intensity Rz is calculated in the local neighborhood and energized, and local texture energy Et is obtained for texture disturbance evaluation; and if abnormal disturbance exists, an energy aggregation analysis area is constructed in the center of the disturbance area, the texture energy space aggregation degree Ce is calculated, and then the texture energy spatial aggregation degree Ce and local texture energy Et are combined to fit a texture energy response value Me for texture energy state evaluation. According to the method, spatial quantitative analysis and aggregation degree quantification of texture changes are realized, and the method is suitable for online visual defect screening of a mobile phone shell with a complex structure on a high-speed assembly line.

The present application relates to the technical field of point cloud data processing, and more particularly to a self-adaptive grid fitting point cloud filtering method and system based on gradient compensation. The method divides the grid by the local density of the point cloud and performs surface fitting, calculates the grid gradient variation to determine the gradient compensation, and then corrects the fitting surface parameters. Based on the corrected parameters, the deviation of each point from the fitting surface and the local curvature are calculated to determine the adaptive filtering threshold, thereby classifying and removing the noise points. The present application can effectively maintain the detailed features of the point cloud and improve the filtering robustness of complex surfaces and noise.

The application provides an image processing method and device, a computer readable storage medium and a terminal device, the image processing method comprising: obtaining an image to be processed; calculating a statistical value of low-frequency information of the image to be processed in a luminance domain; determining a corresponding mapping curve according to a scene to which the statistical value belongs, the mapping curve representing a mapping relationship between an original luminance value and an adjusted luminance value of each pixel in the luminance domain, different scenes corresponding to different mapping curves; determining an adjusted luminance value of each pixel in the image to be processed according to the mapping curve; and mapping a gain of the adjusted luminance value of each pixel to each color channel of the corresponding pixel to obtain an adjusted image. The application provides an image processing scheme capable of improving the luminance of a low-light area of an image and avoiding overexposure of a highlight area.

The application discloses a breast tumor puncture path planning method and system. First, a target image is collected, and region segmentation is performed on the target image to obtain a breast contour image; then, three-dimensional reconstruction is performed on the breast contour image to obtain a breast three-dimensional image; the breast three-dimensional image is input into a pre-constructed hybrid adaptive attention model to extract a breast tumor lesion area; then, the breast area is modeled as a weighted graph, a tumor lesion target node and a starting node are taken as two endpoints, and a puncture path is planned by comparing distance values between adjacent nodes, so that accurate positioning of the breast tumor and accurate planning of the puncture path are realized.

This disclosure provides an information enhancement method, apparatus, device, and medium based on artifact region masks, including: channel-by-channel splicing of a first artifact region mask and a second artifact region mask to generate a metal artifact region mask; applying the metal artifact region mask to operable vectors to obtain mask representation vectors corresponding to metal artifact regions and mask representation vectors corresponding to non-metal artifact regions; determining artifact region branch information based on the mask representation vectors corresponding to metal artifact regions and non-operable vectors; determining non-artifact region branch information based on the mask representation vectors corresponding to non-metal artifact regions and non-operable vectors; and fusing multi-branch information of the artifact region branch information, non-artifact region branch information, and feature extraction map to obtain a target artifact removal image. This results in better removal of metal artifacts.