194 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 provides a dark image preprocessing method and device based on machine vision, equipment and a medium, and relates to the technical field of agricultural automation, and the method comprises the steps: constructing a multi-scale Retinex enhanced fusion adaptive gamma correction illumination compensation model, carrying out the processing of an original garlic seed screening image through the illumination compensation model, eliminating illumination unevenness and light reflection interference, and obtaining an original garlic seed screening image; obtaining a first garlic seed screening image; according to a texture complexity detection method based on a gray-scale guide map, designing an adaptive joint bilateral filter, and processing the first garlic seed screening image through the adaptive joint bilateral filter to obtain a second garlic seed screening image; and performing multi-resolution contrast enhancement processing on the second garlic seed screening image through a pyramid decomposition and entropy-driven partitioning strategy to obtain a preprocessed garlic seed screening image. According to the method, the defect detection accuracy and the classification efficiency can be effectively improved under the conditions of high noise and complex backgrounds, and robust visual preprocessing support is provided for subsequent automatic sorting.

The invention discloses a sports runway pavement damage identification method. The method comprises the following steps: establishing a construction defect template and a use wear template; controlling the unmanned aerial vehicle to fly along the geometrical shape of the runway through a preset flight path, adopting automatic exposure adjustment and shutter speed optimization to adapt to cloudy or strong light conditions, and collecting high-resolution runway surface images with the pixel resolution reaching the micron level to obtain a first image set; for the first image set, smoothing light interference noise by adopting bilateral filtering processing and reserving edge details, and correcting the influence of strong light reflection or shadow through pixel value normalization processing to obtain a second image set; and extracting defect features from the second image set, performing multi-scale feature analysis by adopting a convolutional neural network, calculating a crack length, a recess area and a bump height, generating a high-dimensional feature vector containing defect shapes and textures, and obtaining a defect feature set.

The invention relates to the technical field of image processing, in particular to an injection molding panel production quality detection method and system based on image enhancement. The method comprises the following steps: calculating the throwing degree of each pixel point; taking the product of the throwing degree and the standard deviation preset in the bilateral filter as the optimal standard deviation of each pixel point; processing and detecting the image based on the optimal standard deviation; the step of calculating the throwing degree of each pixel point comprises the following steps of: calculating the neighborhood gray scale confusion degree of each pixel point; obtaining a point cluster containing edge information in the image, and calculating gradient consistency between pixel points in the point cluster and other pixel points in the point cluster; setting a weight coefficient of gradient consistency, and determining the regularity of the pixel point by taking the weighted sum of a plurality of gradient consistency as a total trend; and taking the ratio of the gradient law degree corresponding to the pixel point to the neighborhood gray scale confusion degree as the throwing degree of the pixel point. The method and the device have the effect of improving the accuracy of subsequent product anomaly detection.

The invention relates to the technical field of insulator measurement, in particular to an insulator appearance parameter detection method and system based on RGB point cloud data. According to the method, denoising is performed on an original RGB point cloud image set of the side surface of a target insulator through a bilateral filtering algorithm, feature extraction is performed through an FPFH algorithm, and point cloud registration processing is performed through an ICP algorithm, so that a high-quality side surface global point cloud image is obtained; then, carrying out classification processing on the side global point cloud image by adopting a PointNet algorithm, and only retaining point clouds belonging to the insulated blade part; performing curved surface reconstruction on the point cloud of the insulating blade part through a B-spline curve curved surface fitting algorithm, and further combining into a three-dimensional model of the insulating blade part; and finally, projecting the three-dimensional model into a two-dimensional point cloud, calculating an edge point cloud connection line based on the two-dimensional point cloud, and further calculating a creepage distance and an overall structure distance. Based on various algorithms, the appearance parameters of the insulator can be automatically calculated.

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 discloses a method for detecting surface defects of a metal-coated crystal oscillator, which comprises the following steps of: acquiring an initial image of the metal-coated crystal oscillator in real time, and carrying out primary cutting according to coordinates to obtain an image B; converting the image B into a grey-scale map and then carrying out Gaussian filtering to obtain an original image C; setting a fixed threshold, and performing threshold segmentation on the original image C to obtain an image D; performing Hough circle detection on the image D to obtain a circle center coordinate and a radius of the crystal oscillator, and cutting the image B again to obtain an image M; the image M is amplified in proportion and then subjected to bilateral filtering processing, an image E is obtained, electrode deviation detection and surface dirty spot detection are conducted on the image E, and electrode deviation comprises electrode shape deviation and electrode eccentric defects. According to the method, the quantity demanded for samples is small, the problem that dependency on a data set is high is solved, meanwhile, recognizable defect types are added, different detection requirements can be met by adjusting parameters, and result visualization is achieved.

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 an electronic screen film surface dust detection method based on photometric stereo. The method comprises the following steps: image acquisition: acquiring 4-8 grayscale images in different incident directions; image preprocessing: carrying out edge-preserving noise reduction processing on the original image by adopting a bilateral filter, improving the smoothness by combining a Gaussian filter, and converting the filtered image into a floating point type; normal reconstruction: calculating a surface normal vector corresponding to each pixel point through a least square method or robust estimation according to a photometric stereo principle by utilizing a multi-light source matrix form, and generating a normal distribution diagram; curvature calculation: estimating a local curved surface of each pixel neighborhood based on the reconstructed normal graph; and dust identification: through setting a dynamic threshold and a region growing algorithm, extracting a continuous and significant normal disturbance region, and carrying out classification, marking and visual output in combination with characteristics such as area, length, boundary curvature and the like.

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 a bilateral filtering remote sensing image denoising method based on an EMD distance, and the method comprises the steps: firstly, carrying out the clustering analysis of an image polluted by noise, extracting a key spectrum cluster and a center thereof, and generating a fuzzy membership matrix; thirdly, calculating the distance between spectral clustering centers, and constructing a spectral clustering difference matrix; for each pixel of the target image and a neighborhood thereof, calculating an Euclidean distance between the pixels, and substituting the Euclidean distance into a Gaussian function to generate a distance weight; then, extracting fuzzy membership degree vectors corresponding to the pixels from the fuzzy membership degree matrix, and calculating an EMD distance by combining the spectral clustering difference matrix as a spectral difference weight between the pixels; and finally, synthesizing the spectral difference weight and the distance weight, calculating an EMD bilateral filtering coefficient of each pixel, and carrying out EMD bilateral filtering on the image according to the EMD bilateral filtering coefficient, so as to effectively remove Gaussian noise and obtain a clear high-resolution satellite image.

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 provides an aero-engine main bearing micro-defect nonlinear phased array ultrasonic nondestructive testing method and device, and relates to the technical field of ultrasonic nondestructive testing, the method comprises the following steps: according to the sound beam focal spot diameter of the emission aperture of a phased array excitation probe, carrying out grid division on a target detection area; according to a focusing rule of a phased array emission aperture, focusing scanning of each grid is completed in sequence, and ultrasonic signals of each grid are collected through a phased array receiving probe in the scanning process; carrying out noise reduction processing on the ultrasonic signal by utilizing a self-adaptive bilateral filtering algorithm; a signal blind source separation algorithm is adopted to decouple the processing signals, nonlinear harmonic signals generated by the microdefects are separated, and positioning and quantitative analysis are conducted on the microdefects; and the two phased array probes scan along the contour of the cross section of the bearing ring to complete the full-coverage detection of each cross section of the bearing ring. According to the invention, the microdefect of the aircraft engine bearing can be subjected to nondestructive detection.

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.

Systems, methods, and instrumentalities are disclosed herein for determining whether to apply a filter and / or the parameters of a filter to be applied to a video block based on depth and / or motion information associated with the video block. The determination may be made based on the existence or non-existence of a depth discontinuity in the video block. The filter may be a bilateral filter, a deblocking filter, a sample adaptive offset (SAO) filter, a cross-component sample adaptive offset (CC-SAO) filter, or an adaptive loop filter.

The invention provides a tubular belt conveyor tube expansion detecting and adjusting method and device. A camera fixed at the upper end of a pipe belt machine is used for obtaining a real-time video, after preprocessing of perspective transformation, gray level conversion, bilateral filtering noise reduction and the like is conducted, edge detection is conducted by combining a self-adaptive multi-scale wavelet edge detection algorithm with a one-way edge detection operator, and an edge straight line is fitted through an LSD algorithm to calculate the pipe diameter. When pipe expansion is detected, the pipe diameter adjusting device is driven to adjust the pipe diameter, and closed-loop operation is formed. According to the method, the edge detection precision is improved by improving the wavelet edge detection method, the edge position of the pipe belt can be detected in real time, contact abrasion is avoided, the pipe expansion problem is solved in real time, and the labor cost and economic loss are reduced.

The invention relates to the technical field of intelligent control in the converter steelmaking process, and particularly discloses a converter steelmaking furnace mouth pressure intelligent balancing method with self-adaptive image segmentation, which comprises the following steps: image acquisition: acquiring a furnace mouth flame image in real time through an industrial camera; image preprocessing: adopting a dynamic gamma correction algorithm to adaptively adjust a correction coefficient according to an R channel mean value of the image; in the flame feature extraction stage, the corrected image is subjected to bilateral filtering to remove noise, and then an improved OTSU segmentation algorithm is input to extract a flame main reaction area; in the pressure intelligent control stage, a flame characteristic-furnace pressure nonlinear model is constructed, and finally the rotating speed of an ID fan is dynamically adjusted through a fuzzy self-adaptive controller; the furnace mouth flame image is intelligently monitored, then the furnace mouth pressure is analyzed, the system pressure fluctuation standard deviation is controlled to be reduced, the gas recovery rate is improved, the false detection rate is reduced, the energy efficiency of converter steelmaking is improved, and the production safety is improved.

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 present invention relates to the field of image enhancement technology, and specifically relates to a method for detecting food impurities based on spectral technology, including: collecting an image of a mixture of normal food and impurity food, and performing preprocessing to generate an initial image; performing background segmentation on the initial image to obtain a target image, performing edge detection based on the target image to screen out a single food area, and using a bilateral filtering algorithm to calculate the filtering weight of pixel points for the single food area; reconstructing the pixel points in the single food area based on the filtering weight to obtain the spectral value of the pixel points after reconstruction; determining the spectral values of all pixel points in the target image after reconstruction, performing filtering processing, and identifying the impurity food through differential analysis and marking it; by optimizing the bilateral filtering algorithm, eliminating the interference of normal food on the impurity food, avoiding errors in the recognition results, improving the difference between the impurity food and the normal food in the spectral image, and improving the accuracy of identifying the impurity food.

The invention discloses an infrared image enhancement method and system combining background equalization and detail stretching. The method comprises the steps that an original gray infrared image is decomposed into an image background layer and an image detail layer through an image decomposition method based on a comprehensive average gradient and guided filtering; performing image enhancement processing on the image background layer based on contrast-limited adaptive histogram equalization to obtain an enhanced image background layer; denoising and stretching the detail layer of the image based on adaptive bilateral filtering to obtain a denoised and stretched detail layer; fusing the enhanced image background layer and the denoised and stretched detail layer, and carrying out stretching processing to obtain an enhanced gray infrared image; and performing pseudo-color processing on the enhanced gray infrared image to generate a color infrared image. The method is mainly applied to the technical field of infrared image enhancement, and has wide application prospects in the fields of electrical state monitoring, industrial defect detection and the like. The method has the outstanding advantages of good effect, high practicability, low cost and the like.

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 provides an image interpolation method based on deep bilateral learning. Inspired by the basic thought of a classical bilateral filter, the invention provides a novel deep bilateral learning method DBL. For each missing pixel to be estimated, the DBL learns and utilizes the intensity difference between the missing pixel and each anchor pixel in a predefined support domain and the space weight based on the distance, the missing pixel is added to a corresponding anchor pixel value, and a group of candidate values is generated for the missing pixel to be estimated. And the latter is used for further weighting the obtained candidate values, and a final estimated value is generated by calculating the weighted sum. The invention further designs a DBL-based deep bilateral learning network to specifically execute image interpolation, better image features are obtained based on multi-scale feature extraction and space and channel attention mechanisms in the DBLN, and a module capable of executing DBL in parallel is designed to map the features to pixels to be estimated, so that a high-precision HR image is generated.

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.

The invention discloses an underwater image enhancement method for a complex environment, and the method specifically comprises the following steps: firstly, correcting color cast caused by optical characteristics through an improved white balance algorithm, and effectively recovering colors; secondly, brightness distribution is adjusted and dark part details are enhanced by adopting logarithmic domain gamma transformation, so that the brightness distribution of the image is more uniform, and meanwhile, a self-adaptive histogram for limiting the contrast ratio is equalized, so that the contrast ratio and detail definition of the image are improved; and finally, noise is removed by using bilateral filtering, edge information is reserved, and deblurring processing is performed in combination with a U-Net network. According to the method, the color cast problem caused by optical characteristics is improved by using the improved white balance algorithm, a correct color basis is provided for subsequent processing, pixel distribution is adjusted by using logarithm domain gamma transformation, the importance of details of a bright part is reduced, a dark part region is further enhanced, and the overall brightness distribution is more uniform.

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 invention discloses a condensation image recognition method and system, and the method comprises the following steps: obtaining a color condensation image, and carrying out the preprocessing: converting an RGB image into a gray image, carrying out the filtering of the gray image through a mean filter and a denoising filter, and carrying out the subtraction of the gray image and the filtered image, and completing the preprocessing of the condensation image; in order to better adapt to the characteristics of the condensation image, adding a region consistency constraint term on a loss function of an Otsu threshold segmentation algorithm, and converting the preprocessed image into a binary image by using an optimized algorithm; adaptive improvement is carried out on bilateral filtering, and condensation edge points are extracted by using an algorithm based on adaptive bilateral filtering; and carrying out coloring processing on the extracted edge points to obtain a visual condensation liquid drop image. The method provides a condensation identification system with high precision and strong anti-interference capability.

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.