10 results about "Laplacian pyramid" patented technology

This invention discloses a method and system for transferring the style of traditional Chinese painting based on the Laplacian pyramid, belonging to the field of computer vision technology. The method constructs a multi-scale style transfer model based on the Laplacian pyramid. The multi-scale style transfer model includes a Laplacian pyramid decomposition module, a basic style transfer network, a detail enhancement network, an edge information selection module, and a Laplacian pyramid reconstruction module. Preprocessed content image datasets and preprocessed style image datasets are input into the multi-scale style transfer model for training. Style loss functions and content loss functions are used to optimize the multi-scale style transfer model, resulting in a multi-scale style transfer generation model. The target content image is then input into the multi-scale style transfer generation model to generate a stylized image in the style of traditional Chinese painting. This invention can generate high-quality stylized images with the style of traditional Chinese painting.

The application discloses a multi-focus fusion image enhancement method and device, a storage medium and a program product. Depth information is extracted from a multi-focus image stack and a depth map Gaussian pyramid is constructed, and at the same time, multi-layer Laplacian pyramid decomposition is performed on each multi-focus color image to realize separation of multi-scale information of the image. Then, based on the hierarchical depth index of the depth map Gaussian pyramid, clear pixels of each hierarchical level of the Laplacian pyramid are precisely fused into a full-zero fusion pyramid to ensure that the fused image retains clear details of each focal plane. Subsequently, differentiated filtering processing and nonlinear mapping are adopted for different hierarchical levels of the fusion pyramid to realize layered noise suppression and detail enhancement. Finally, through pyramid reconstruction, the multi-scale enhanced information is integrated to obtain a final enhanced image. The application is suitable for various scientific research, medical treatment, industrial detection and other scenes relying on microscopic imaging.

The application discloses a kind of fog wide field of view video image change detection method and device, method includes: based on color attenuation priori to single image is defogged, obtains clear image after defogging;By arctangent ratio operator and extreme pixel ratio operator, clear image after defogging is handled, respectively obtain two difference maps;Combining image energy features and Laplacian pyramid, the two difference images obtained are adaptively fused to obtain fused difference map and further denoising is combined with median filtering;To denoised fusion difference image, difference between change and unchanged pixel caused by sensor noise is compressed to obtain final difference map;Based on the nearest neighbor relationship of pixel, the EN-K-Means clustering algorithm of clustering prototype is initialized to carry out clustering analysis on final difference map to obtain final binary image.The device includes: processor and memory.The present application can effectively reduce the occurrence of false alarm.

The application discloses a low-light target detection method and device based on multi-scale dynamic fusion, and constructs a low-light target detection network based on multi-scale dynamic fusion comprising a detection network and an improved low-light enhancer; the improved low-light enhancer effectively solves the problems that the target boundary becomes blurred and the feature is difficult to extract due to the existence of abnormal light source interference in a low-light environment and the large target scale difference through Laplacian pyramid decomposition, a multi-perception detail enhancement module MDEM and a multi-scale dynamic fusion module MDFM; a low-light target detection model is obtained by training the constructed low-light target detection network based on multi-scale dynamic fusion, and the optimal performance is evaluated and selected to perform target detection on a low-light image, so that a result image of target detection is obtained. The application solves the problems of abnormal light source interference and large target scale difference in a low-light image, and improves the accuracy of low-light target detection.

Real-time image processing uses multi-planar images in a multiple camera system. Images are downscaled and gray scaled to reduce computational load. A target-centered depth map is estimated by sweeping multiple layers of depth across the downscaled and gray scaled input images to form a plane sweep volume (PSV) and corresponding layers of the PSV are compared to generate a similarity volume, by using Laplacian pyramids, including decomposing the downscaled and gray scaled input images into Laplacian pyramids to extract fine and large edges. Structural features are compared using the Structural Similarity Index, SSIM, at multiple depth layers. Depth values are selected for each pixel based on the similarity volume. The downscaled and gray scaled source images are warped to a target viewpoint based on the estimated depth map and the warped images are blended to generate a synthesized target image.

The invention discloses a multi-focus image fusion and depth recovery method based on a Laplacian pyramid, and the method comprises a Laplacian pyramid construction module which is used for constructing a multilayer Laplacian pyramid expression for an input multi-focus image sequence {Ik} k = 1N (N is the number of images); the multi-focus image fusion module is used for fusing the images at different focus positions based on a fusion strategy of the Laplacian pyramid, and reconstructing a fused image through inverse transformation of the Laplacian pyramid; the focusing degree evaluation module is used for calculating the focusing degree of each image in the image sequence at each pixel position for depth estimation; and the depth recovery module is used for recovering the three-dimensional depth information of the scene based on the focusing degree evaluation result and the servo altimeter data.

The present application relates to the field of image processing, in particular to a kind of image detail enhancement method and system for dark light scene, its method includes: the dark light image is carried out denoising and obtains denoising image, detail enhancement is carried out to the denoising image, and detail enhancement image is obtained;Denoising image is generated by image degradation, frequency decomposition, cross attention mechanism and bidirectional convolution;In HSV color space, based on Laplacian pyramid, the brightness of denoising image and detail enhancement image is frequency division fusion, and target output image is obtained;Laplacian pyramid is based on the luminance information and texture information of image and pyramid level distribution fusion weight, and based on the way of non-local fusion, the pixel points of denoising image and detail enhancement image are fused, the present application is based on the Laplacian multiscale fusion method of HSV space, can accurately restore and enhance texture details, and can perfectly retain the hue and saturation of original image, ensure the high consistency and fidelity of color.

This invention relates to the field of seismic exploration and discloses a method, apparatus, electronic device, and storage medium for multi-seismic attribute fusion. The multi-seismic attribute fusion method includes: acquiring multiple seismic attribute images of a target stratigraphic level in a target work area; constructing a Gaussian pyramid based on each seismic attribute image; constructing a Laplace pyramid for each seismic attribute image based on the Gaussian pyramid; fusing the Laplace pyramids of multiple seismic attribute images to obtain a fused Laplace pyramid; and reconstructing the fused Laplace pyramid to obtain the fusion result of the multiple seismic attribute images. This solves the problem of improving the prediction accuracy of reservoirs.

This invention relates to the field of image processing technology and discloses an image enhancement method for handheld X-ray machines, comprising: Step 1, acquiring the image to be processed and performing grayscale statistics to construct a smooth grayscale histogram, and extracting the global information entropy and effective grayscale range from the smooth grayscale histogram; Step 2, using the effective grayscale range to perform linear mapping on the image to be processed to complete dynamic range pre-compression and generate a preprocessed image; Step 3, performing multi-scale decomposition on the preprocessed image to construct a Laplacian pyramid composed of several different frequency layers. By employing an adaptive preprocessing scheme based on the global information entropy and effective grayscale range of the image, the method achieves the technical effect of automatically adapting to different shooting locations and exposure doses, realizing precise compression of the image's dynamic range, and overcoming the shortcomings of traditional fixed-parameter algorithms in contrast adjustment failure under handheld low-dose radiography.

This invention discloses a camouflage target detection method and system based on boundary interaction learning, belonging to the field of camouflage target detection technology. The method includes: S1: Preprocessing the image to be detected and inputting it into an encoder, extracting multi-level encoded features through convolution operations; S2: Based on the multi-level encoded features, extracting high-frequency information through a Laplacian pyramid and fusing it with deep encoded features to generate multi-scale boundary features; S3: Generating boundary interaction features through bidirectional interaction operations, and performing attention weighting and calibration operations on the boundary interaction features to generate global contour enhancement features; S4: Based on the multi-level encoded features and decoded features, generating local optimization features through semantic guidance and spatial detail extraction operations; S5: Performing fusion operations based on global contour enhancement features and local optimization features, and upsampling and feature concatenation through a decoder to generate a camouflage target semantic segmentation result. This enhances the robustness and accuracy of the detection model.