141 results about "Bilateral filter" patented technology

The invention belongs to the technical field of image fusion, and particularly relates to an infrared and low-light-level image fusion improvement method based on rolling guide filtering, which comprises the following steps of S1, acquiring a low-light-level image and an infrared image, and preprocessing the infrared image for denoising; s2, converting to an IHS space to extract an intensity component; s3, decomposing the dual-source I component into a small-scale layer, a large-scale layer and a base layer by using rolling guide filtering; s4, performing small-scale layer fusion, and combining an absolute value maximization strategy with non-local similarity weighted denoising; s5, performing large-scale layer fusion, and performing joint sparse low-rank representation by adopting principal component analysis; s6, fusion of the base layer adopts a visual saliency mapping method; and S7, after IHS inverse transformation reconstruction, realizing multi-level fusion in combination with bilateral filtering detail enhancement and a guide filtering saliency map. According to the invention, based on IHS space and rolling guide filtering multi-scale decomposition, the effect of cooperative utilization of multi-modal information is improved, and the method effectively improves the problems of insufficient target detection precision and poor scene reconstruction robustness in a dark environment.

The invention discloses an unmanned aerial vehicle small target detection method based on Mama feature fusion, and relates to the technical field of computer vision, and the method comprises the steps: multi-modal data collection, synchronous collection of images and point cloud data through three types of sensors, and coverage of multi-scene and environment conditions; image preprocessing adopts improved bilateral filtering, adaptive histogram equalization and point cloud downsampling to unify a coordinate system; in the multi-scale feature extraction, five-level scale features are output through an improved CSPDarknet network, and the five-level scale features are enhanced through an SENet attention module; in the Mama feature fusion, multi-modal and multi-scale features are processed through a three-stage unit; generating a candidate frame by a dynamic anchor frame, screening according to IOU, and improving YOLOHead to realize classification and positioning; the dynamic optimization of the detection result finely adjusts parameters through on-line distillation. According to the method, the precision, the real-time performance and the anti-interference capability of small target detection of the unmanned aerial vehicle are improved, and reliable technical support is provided for low-altitude security, exploration and other scenes.

The invention provides a chromosome image enhancement method and system based on semantic guidance. The method comprises the following steps: S1, preprocessing; s2, outputting a deep-band probability graph, a grey-band probability graph and a shallow-band probability graph through a semantic segmentation network composed of a lightweight encoder and a multi-scale decoder; s3, implementing differential layered enhancement according to a band type: adopting local adaptive histogram equalization for a deep band, adopting central axis constraint bilateral filtering for a gray band, adopting dynamic threshold truncation and gamma correction for a shallow band, and performing weighted fusion for a transition region according to probability; s4, carrying out structure strengthening, wherein the structure strengthening comprises centromere local sharpening, stripe phase alignment, edge sensing super-resolution and overlapping region separation; and S5, performing quality evaluation based on the deep band integrity, the band stripe contrast uniformity, the SSIM and the noise density, and triggering adaptive re-enhancement if necessary. According to the scheme, the contrast ratio and details are remarkably improved while the stripe structure and the position relation are kept, and the method has the advantages of light weight, interpretability and cross-sample robustness and is suitable for being integrated into an automatic karyotype analysis process.

The invention discloses a long-distance binocular camera calibration optimization method based on multistage feature enhancement, and the method comprises the steps: carrying out the processing of a condition that a long-distance calibration plate has a highlight region and is fuzzy in angular points, employing a bilateral filter to suppress the reflection of a highlight mirror surface, reducing the reflection of light, and maintaining the definition of an image; the checkerboard texture is enhanced by adopting a CLAHE algorithm in combination with blocking processing and a contrast gain threshold value; a Sobel operator and a Harris corner response function are fused, gradient direction distribution characteristics of a pixel neighborhood are extracted through the Sobel operator, weighted fusion is carried out on the gradient direction distribution characteristics and the Harris corner response function, and the response intensity and specificity of a corner area are remarkably enhanced. A three-level image preprocessing framework including reflection suppression, contrast enhancement and corner enhancement is constructed, the problem of feature extraction of a traditional method under a complex illumination condition is solved, the corner area detection capability is enhanced, the problems of specular reflection noise, low contrast and corner blur are effectively solved, and the calibration precision is improved.

The invention relates to the field of image processing, in particular to an infrared image bilateral filtering method based on field programmable gate array (FPGA) optimization, which comprises the following steps: acquiring data through a hierarchical architecture of'on-chip BRAM cache + distributed register cache ', intercepting pixels in combination with a sliding window, calculating a spatial weight by using an LUT look-up table, and logically calculating a gray scale weight in real time. And carrying out weighted summation and normalization output. According to the method, the processing delay of the infrared image with the resolution of 1024 * 1024 is reduced to be less than 50ms, the frame rate is increased to be more than 60fps, and the method is suitable for a real-time target recognition scene. Through the combination of the optimized bilateral filtering algorithm and the efficient hardware architecture, the processing delay is remarkably reduced, the real-time processing of the high-resolution infrared image is realized, and the real-time performance is remarkably improved.

The invention relates to an underwater image enhancement method and device based on dark channel prior, and belongs to the technical field of image processing. A dark channel prior algorithm is called, and an original underwater image is restored to a preliminary defogged image; performing bilateral filtering processing on the transmissivity image calculated in the preliminary defogged image recovery process to obtain a defogged image; weighting different color channels in the defogged image according to the absorption intensity of a water body to different colors, fusing the channel information of all the weighted color channels, reconstructing a final image, and determining the final image as an enhanced original underwater image. And moreover, blurring caused by scattering is effectively removed, the real color of the image is recovered, the image definition and contrast are improved, and meanwhile, the operation simplicity and high processing efficiency are kept.

The invention discloses an art design intelligent color matching auxiliary system and method based on artificial intelligence, and relates to the field of art design. Comprising an image analysis module, and the image analysis module comprises a noise reduction preprocessing unit for carrying out noise suppression on an input image by adopting a bilateral filter and a semantic segmentation unit for analyzing an image semantic region and outputting a segmentation mask by using a DeepLabv3 + model; a color space conversion unit that inputs and converts the RGB image into a CIELAB space; a style feature extraction unit; a palette optimization module; and a rendering output module. According to the method, the four-dimensional statistical vector of the LAB color space is extracted, high-level features such as the quantized lightness centrality, the chroma discreteness and the distribution skewness are extracted, the problem of feature expression distortion of a traditional method is solved, the style loss function based on the Gram matrix is constructed, gradient descent optimization is combined, and it is ensured that the palette meets the aesthetic rule and style consistency at the same time.

The invention relates to the technical field of image data processing, in particular to a rubberizing quality detection method and device for automatic rubberizing equipment, and the method comprises the steps: obtaining an original image of a to-be-detected rubberizing region; performing filtering processing on the original image by using an improved adaptive bilateral filtering algorithm to obtain a filtered image, performing differential operation on the filtered image and the original image to obtain a residual image, and performing adaptive threshold segmentation on the residual image to extract a defect region, and carrying out rubberizing quality detection based on the geometrical characteristics of the defect area. The problem that the accuracy of rubberizing quality detection is not high is solved.

The invention relates to the technical field of information security, in particular to an AI video detection method based on multi-feature branch fusion, and the method comprises the following steps: extracting a frame extraction color image from a video, and obtaining a standardized frame sequence after preprocessing; calculating an inter-frame differential volume; obtaining a time sequence spectrum volume according to the standardized frame sequence; performing bilateral filtering decomposition on the standardized frame sequence to obtain an illumination consistency volume; respectively inputting the three types of volume features into a deep convolutional neural network, and after feature extraction and fusion, outputting an AI forgery probability through a classifier; and comparing the AI forgery probability with a decision threshold to generate a video category label, and calculating an index. According to the method, the multi-dimensional features of the time-space domain, the frequency domain and the physical illumination domain are fused, the potential traces of the deeply-forged video are effectively captured, the stable detection performance is kept under various video quality conditions, the accuracy is improved, and reliable technical guarantee is provided for media information security.

A mechanism for processing video data is disclosed. The mechanism determines to apply a bilateral filter and a cross component sample adaptive offset (CCSAO) filter to samples in a current block of a current picture. The bilateral filter includes filter weights that vary based on a distance between surrounding samples and a central sample and differences in intensities of the surrounding samples and the central sample. A conversion is performed between a visual media data and a bitstream based on the bilateral filter and the CCSAO filter.

The invention belongs to the technical field of three-dimensional modeling, and particularly relates to a three-dimensional visual detection method for motorcycle tires. According to the method, a tire is fixed, multi-view point cloud scanning is carried out, and an improved SAC-IA algorithm is adopted for registration and fusion to construct a three-dimensional point cloud model; the method comprises the following steps: designing adaptive voxel grid filtering and denoising based on tire geometric prior, and after improved bilateral filtering smoothing, fitting and unifying a coordinate system through principal component analysis and least square to obtain a standardized point cloud model; and extracting four core parameters of thickness uniformity and sidewall contour curvature, inputting the four core parameters into the hybrid dynamic weight scoring network to output quality scores, and meeting the requirements of high-precision and high-efficiency quality inspection of motorcycle tires in an industrial environment.

The application discloses a UAV autonomous obstacle avoidance method and system based on vision-laser radar fusion, belongs to the technical field of UAV autonomous flight, and comprises the following steps: S1, collecting vision image data and laser point cloud data of the environment around a UAV through a vision sensor and a laser radar synchronously; adopting a hardware trigger and a timestamp double synchronization mechanism to control the time synchronization error of the vision image data and the laser point cloud data within + / -1 mu s; respectively carrying out denoising, enhancement and distortion correction processing on the vision image data; and adopting a bilateral filtering algorithm to remove image noise. The hardware trigger and the timestamp double synchronization mechanism are adopted to control the time synchronization error of the vision and the laser radar data within + / -1 mu s, the problems of fusion feature space dislocation and obstacle calibration distortion caused by a traditional synchronization mode are solved, a high-precision data foundation is laid for multi-sensor feature fusion, and the real-time sensing demand of high-speed flight of the UAV is met.

The application discloses a kind of based on deep learning and joint bilateral filtering's image dynamic range compression method, including steps: collecting original high bit image data, constructs data set, and preliminary processing is carried out to data set, obtains linear RGB graph and Y channel graph;Combined with the skip connection structure of UNet and the efficient light unit of ShuffleNet constructs deep learning network, utilizes deep learning network to linear RGB graph and Y channel graph processing, obtains luminance gain graph;With the help of joint bilateral filtering upsampling operation, luminance gain graph and original high bit image are processed, and original resolution luminance gain graph is obtained;Original high bit image is carried out inverse gamma operation, and then divided by original resolution luminance gain graph is carried out gamma operation to obtain compressed 8bit image.The application realizes a dynamic range adjustment algorithm, from high bit to low bit mapping process, beneficial to restore highlight details, brighten dark details, and maintain good image contrast.

The present application belongs to the technical field of image data processing, and particularly relates to a defoaming sand washing monitoring method and system based on image analysis, which comprises the following steps: constructing a structure tensor matrix of a pixel point, determining the flow direction coherence degree of the pixel point, determining the oil phase anisotropy confidence factor of the pixel point, determining the optimized anisotropy space kernel parameter of the pixel point, obtaining an enhanced sand washing outlet liquid discharge image, determining the area proportion of the oil phase region in the enhanced sand washing outlet liquid discharge image, and judging whether there is oil entrainment abnormality at the discharge port. By analyzing the gray scale characteristics of the pixel point and the pixel points in its neighborhood, and by adapting the anisotropy space kernel parameter, the present application overcomes the limitations of the traditional bilateral filtering algorithm using a fixed shape filtering kernel under a high-speed mixed flow field, realizes oil phase feature enhancement, and improves the accuracy and robustness of oil entrainment abnormality monitoring in the defoaming sand washing process.

The invention provides an efficient image denoising method based on a hybrid filter technology, and belongs to the field of digital image processing. Traditional bilateral filtering and self-defined convolution filtering are fused to denoise an image; the method comprises the following steps: performing bilateral filtering on a noisy image for preprocessing, and performing self-defined convolution filtering on the preprocessed image to obtain a denoised image; the denoising precision can be improved while the real-time performance is ensured, and key pain points in the fields of industry, medical treatment, consumer electronics and the like are solved.

This invention presents an enhanced micro-operation target segmentation method utilizing improved Otsu and edge operators, addressing the limitations of conventional techniques in microscopic visual environments. The proposed approach effectively mitigates accuracy constraints caused by image noise and shadow effects from uneven illumination. The methodology comprises three key phases: Applying an optimized bilateral filtering algorithm to perform noise reduction on grayscale images, producing denoised images; Segmenting micro-operation targets using the refined Otsu algorithm on these denoised images to obtain initial segmentation results; Directly applying the final segmentation result when meeting predefined criteria, or conducting iterative segmentation through the enhanced edge operator and Otsu algorithm if necessary. This innovative method demonstrates exceptional performance in micro-operation target detection applications

A method for filtering an input sample. The method includes obtaining a first input sample (SIN1) (e.g., one sample included in a TU) belonging to a first transform unit (TU) having a first dimension (e.g., width) and a second dimension (e.g., height). The method further includes calculating a first BIF offset ([delta] BIF1) for the first input sample using a first TU scaling factor (CTU1) associated with the first TU and a bilateral filter (BIF) function. The method further includes calculating a first output sample (Sout1) using the [delta] BIF1 and the SIN1. The first TU scaling factor is a function of 1) a two-dimensional (2D) lookup table (LUT), and sizes of a first dimension and a second dimension of the first TU, and / or 2) an activity score (e.g., MAD, MSD) of the first TU, and / or the BIF function is a sampled segment-by-segment linear function.

A video coder may receive video data and apply a filter to a plurality of types of samples of the video data. The plurality of types of samples may include two or more of: an input of a fixed filter, an output of a fixed filter, an input of a signaled filter, an output of a signaled filter, an input of an adaptive loop filter, an output of an adaptive loop filter, an input of a sample adaptive offset (SAO) filter, the method comprises the following steps: receiving the input of an SAO filter, the output of an SAO filter, the input of a bilateral filter, the output of the bilateral filter, the input of a cross component SAO filter, the output of the cross component SAO filter, the input of a deblocking filter, the output of the deblocking filter, filtered reconstructed residual data, a dequantization coefficient, a filtered dequantization coefficient, a predictor or a filtered predictor.

The invention discloses an image illumination anomaly processing method and device, electronic equipment and a storage medium, which are used for solving the technical problem that the processing effect and the real-time performance cannot be considered at the same time in the prior art. Comprising the following steps: acquiring a brightness component of an RGB image to construct a single-channel brightness matrix; marking an overexposure area and a low-illumination area of the single-channel brightness matrix and calculating a global illumination intensity index; adjusting bilateral filtering parameters according to the global illumination intensity index to adjust a single-channel brightness matrix, and generating a filtered brightness matrix; carrying out enhancement through a Retinex algorithm to obtain an enhanced brightness matrix; determining a key area according to the enhanced brightness matrix and generating a local processing strategy; performing two-layer wavelet transform on the RGB image to obtain a plurality of frequency band components; adjusting each frequency band component according to the global illumination intensity index and the local processing strategy; reconstructing and adjusting the frequency band component through wavelet inverse transformation to obtain a reconstructed RGB image; and converting the reconstructed RGB image into a target image in a preset format.

The invention discloses a loop filtering method and device for reconstructing a video. The method receives input data of a current block, wherein the input data includes reconstructed samples of the current block. At least two loop filters are applied to a current block, where the at least two loop filters belong to a loop filter bank comprising a bilateral filter (BIF) and an adaptive loop filter (ALF), and the classification processes of the at least two loop filters share one input source, one or more classification rules, one or more processing units or a combination thereof. A filtered output generated by applying the at least two loop filters to the current block is provided.

The application provides a bilateral filtering-based image processing method, device and equipment and a storage medium, and belongs to the field of image processing. The method comprises the following steps: acquiring a bilateral filtering Gaussian value domain coefficient, and setting a bilateral filtering Gaussian space domain coefficient; acquiring a first space domain filtering value of a current pixel point of a current frame original image according to the bilateral filtering Gaussian value domain coefficient and the bilateral filtering Gaussian space domain coefficient, and determining a first value domain filtering value according to the first space domain filtering value; performing sampling processing on a previous frame original image; determining a current pixel point of a sampling image according to the current pixel point of the current frame original image; acquiring a second space domain filtering value of the current pixel point of the sampling image according to the bilateral filtering Gaussian value domain coefficient and the bilateral filtering Gaussian space domain coefficient, and determining a second value domain filtering value according to the second space domain filtering value; and determining a filtering output result according to the first value domain filtering value, the second value domain filtering value, the first space domain filtering value and the second space domain filtering value. In this way, the power consumption is reduced, and the filtering effect is improved.

A kind of blood vessel image enhancement method based on multiscale Gaussian filter, comprising the following steps: step one: input endoscopic blood vessel image;Step two: the input blood vessel image is separated into RGB three channel planes;Step three: using multiscale Gaussian filter and bilateral filter to filter G component to obtain detail layer and base layer;Step four: detail layer is multiplied by a gain coefficient, then merged with base layer to obtain two enhancement results;Step five: two enhancement results are converted to HIS space, I component is carried out 4-layer wavelet decomposition to obtain 1 low frequency and 12 high frequency components, and the rule of high frequency weighted average low frequency modulus value maximum is used to fuse to obtain enhanced I component, then merged with HS, converted to RGB space to obtain the final enhancement result.The present application can carry out different adaptive enhancement to different levels of blood vessels to obtain more abundant blood vessel images, which can assist doctors in early diagnosis of cancer.

The application discloses a kind of self-adapting shadow enhancement method and device of smoke-passed infrared digital holographic reconstructed image, belong to image processing technical field.The application proposes a new image processing algorithm to enhance the shadow area caused by smoke-passed infrared digital holographic reconstructed image smoke sheltering, the algorithm is first using bilateral filter to remove noise to image, in combination with binaryzation, edge extraction, morphological algorithm divides shadow area, and in combination with bright area to achieve the purpose of enhancing the brightness of shadow area.The method disclosed in the application solves the problems of severe speckle noise, obvious shadow area, uneven brightness, missing object detail information and other problems of smoke-passed infrared holographic reconstructed image, can effectively enhance the image quality of smoke-passed infrared holographic reconstructed image, has significant effect in the aspects of shadow area enhancement and speckle noise removal, and belongs to the field of image processing technology.

The application discloses an infrared image column stripe non-uniformity correction method based on an improved median histogram, and belongs to the field of infrared image non-uniformity correction. The method comprises the following steps: calculating a column histogram of a single infrared image and a column mean value curve after wavelet denoising according to an input infrared image; performing an inverse operation on the obtained column histogram to obtain a column inverse histogram; generating an adaptive window of a bilateral filter according to the column mean value curve; generating the bilateral filter according to the spatial domain distance of the column and the difference in the gray domain of the column mean value curve; filtering the column inverse histogram according to the obtained bilateral filter to obtain a median histogram; and mapping the input infrared image according to the median histogram to obtain an infrared image after stripe removal. The application realizes a better stripe removal effect, avoids the generation of blind points, and omits the step of repeatedly calculating and comparing results to obtain an optimal parameter value in the original algorithm.

The present invention discloses a rail infrastructure safety assurance method, system, device, and storage medium, relating to the field of intelligent safety monitoring and control technology for rail transit. The method comprises: collecting raw track data through a multi-source perception module; processing the raw track data using a bilateral filter and region growing method to obtain track data containing semantic tags; extracting features from the track data through a data fusion hub to construct a spatiotemporal correlation feature matrix; performing thermal-mechanical coupling simulation based on the track data through a digital twin decision platform to obtain simulation results; and generating optimized control instructions and alarm information through an adaptive control module based on the spatiotemporal correlation feature matrix and the simulation results. The present invention solves the problems of perception system fragmentation, insufficient intelligent diagnosis and decision-making, and passive risk management in related technologies.

The application discloses a micro-vision threshold segmentation algorithm based on OTSU improvement for micro-nano object images, and comprises the following steps: S1, combining image gradient information, calculating a new gray weight factor based on an exponential function and a logarithmic function, and performing bilateral filtering processing on the image; S2, calculating a traditional gray threshold of the filtered image by using a traditional inter-class variance formula, and calculating an improved gray threshold by using an improved inter-class variance formula based on a natural constant function; and S3, performing adaptive iterative operation on pixels of the image by using the traditional gray threshold and the improved gray threshold, so that three-region threshold segmentation is completed. The micro-vision threshold segmentation algorithm based on OTSU improvement disclosed by the application overcomes the problem that the calculation result is inaccurate due to the imbalance of the pixel quantity ratio during threshold segmentation, and improves the limitation of poor local analysis capability of the global threshold segmentation algorithm.

The invention provides a railway track crack defect detection method and device based on machine vision, and relates to the technical field of crack detection, and the method comprises the steps: obtaining an original track image; preprocessing the original track image, and performing image enhancement in combination with a bilateral filtering strategy to obtain a track image with a high signal-to-noise ratio; based on a convolution attention mechanism, improving the target detection model in combination with multi-scale feature fusion and a residual connection strategy to obtain an improved target detection model; inputting the track image with the high signal-to-noise ratio into the improved target detection model for track crack detection to obtain a crack segmentation mask graph; performing morphological processing on the crack segmentation mask graph, and obtaining a crack image frame by extracting geometrical characteristics of the crack; and associating adjacent crack image frames according to a continuous frame matching algorithm, and constructing a space-time development track of the track crack by combining the space position information of the crack as a defect detection result. The problem that the rail operation safety cannot be effectively guaranteed is solved.

The present application relates to a kind of port tyre crane or bridge crane unmanned truck accurate secondary positioning method, the tyre crane or bridge crane is scanned by laser radar installed on the unmanned truck, obtains point cloud data, is then processed by RANSAC algorithm to the point cloud data by bilateral filtering algorithm to point cloud data is carried out noise reduction processing, obtain linear equation about tyre crane or bridge crane, to further obtain accurate position information, the unmanned truck is dispatched.The present application is not only low in cost, and will not be affected by weather, further improve the work efficiency of unmanned truck.

The application discloses a virtual object matching method and device in a complex environment, comprising: determining a sparse three-dimensional point cloud of a target based on a camera pose, and obtaining depth image (RGB-D) information of the target; combining the RGB-D information with the sparse three-dimensional point cloud to obtain a dense three-dimensional point cloud; removing outliers in the dense three-dimensional point cloud by using a specified bilateral filter, and weighting adjacent points by using an improved Gaussian weighting function; sampling based on the dense three-dimensional point cloud and a normal vector of each point calculated to obtain key points; calculating feature descriptors of a virtual model and a real scene based on the key points obtained by point cloud sampling to estimate the corresponding relationship between the two point clouds; and completing transformation estimation according to the corresponding relationship to realize matching of the virtual object and the real scene. The method can improve the stability, accuracy and real-time performance of matching of the virtual object and the real object in markerless augmented reality.

The application discloses a camera calibration method and system under uneven illumination conditions, and belongs to the technical field of image processing, and comprises the following steps: S1, processing an input image by using a multi-scale Retinex algorithm; S2, performing Gaussian homomorphic filtering processing on the image obtained in the step S1; S3, processing the image obtained in the step S2 by using an Otsu algorithm; and S4, performing camera calibration on the image processed in the steps S1-S3 by using Zhang Zhengyou plane calibration method. The application firstly enhances image details by using the multi-scale Retinex algorithm and the Gaussian homomorphic filtering, then obtains a final calibration board image by combining Otsu algorithm image segmentation and bilateral filtering processing, and further realizes high-precision calibration of the camera, and is worth popularization and use.