130 results about "Image noise reduction" patented technology

The invention discloses a bearing defect detection method and system based on machine vision and ultrasonic detection, and particularly relates to the technical field of industrial automatic detection, and the method comprises the steps: S1, a synchronous collection module: carrying out pulse triggering synchronous collection, and generating a time-space reference table; s2, a feature extraction module: performing image noise reduction segmentation and ultrasonic frequency domain decomposition, and outputting a defect feature vector; s3, a fusion identification module: performing cross-modal feature alignment fusion to generate a defect classification conclusion; s4, a size measurement module: performing contour fitting to calculate inner and outer diameters, and outputting a size deviation value; and S5, a comprehensive judgment module: carrying out threshold comparison logic judgment, and generating a multi-modal detection report. According to the method, a space-time reference is established through an encoder, images are segmented in a self-adaptive mode, features are extracted through wavelet decomposition ultrasound, feature weights are re-calibrated through a parallel network and an attention mechanism, composite defects are recognized through cross-modal fusion, comprehensive judgment is conducted in combination with dimensional deviation, and a multi-dimensional quality evaluation system is achieved.

The invention discloses a photovoltaic module infrared image fault detection method based on unmanned aerial vehicle inspection, which relates to the field of fault detection, and comprises the following steps: configuring an unmanned aerial vehicle platform, planning a flight path, setting aerial photography parameters, setting an infrared thermal image acquisition and infrared image data return and storage mechanism, and performing gray normalization processing, image noise reduction, histogram equalization, edge enhancement processing and size standardization processing on the infrared image data, and performing data enhancement operation. An unmanned aerial vehicle infrared inspection technology is combined with a deep learning target detection model, a set of complete photovoltaic module infrared image fault detection process is established, and full-process automatic processing from image acquisition, image preprocessing, model detection to result evaluation and visualization can be realized. The method has the comprehensive advantages of being high in fault recognition precision, high in detection speed, standardized in processing flow and the like, and the efficiency and the intelligent level of photovoltaic power station component-level fault inspection are remarkably improved.

The invention discloses a yarn weak twist and hairiness intelligent detection system based on visual stroboscopic synchronization, particularly relates to the field of quality control in the textile industry, is used for solving the problem of accurate detection of weak twist and hairiness defects in the yarn production process, and dynamically adjusts the flash frequency of a stroboscope according to the real-time speed and acceleration data of yarn, so that the detection accuracy is improved. The light source and the yarn are ensured to move synchronously, and a high-resolution image is obtained. In combination with yarn motion spectrum analysis and image quality evaluation, a complexity score and a matching degree score are generated and are used for dynamically regulating and controlling image noise reduction and edge detection parameters, and characteristic extraction requirements under different yarn motion conditions are met. The weak twist characteristic and the hairiness texture of the yarn are accurately extracted through a multi-scale edge detection and wavelet transform algorithm, a twist distribution model is constructed, the boundary range is corrected in combination with hairiness distribution data, characteristic interference is reduced, and the detection precision and reliability are improved.

The invention relates to the technical field of artificial intelligence, is suitable for financial and medical scenes, and particularly relates to a low-illumination physical examination image noise reduction enhancement method, device and equipment and a storage medium, the low-illumination physical examination image noise reduction enhancement method comprises the following steps: obtaining a to-be-processed low-illumination physical examination image; based on a Retinex decomposition model, acquiring a preliminarily estimated illumination component of the low-illumination physical examination image, acquiring an accurately estimated illumination image according to the preliminarily estimated illumination component, and enhancing the accurately estimated illumination image through gamma transformation to obtain an enhanced image; performing noise reduction on the enhanced image based on a BM3D algorithm to obtain a noise-reduced image; and combining the enhanced image and the noise reduction image to obtain a noise reduction enhanced image. The problem that in the prior art, when enhancement processing is carried out on the low-illumination physical examination image through an image enhancement algorithm, synchronous processing is not carried out on noise and amplified noise in the enhanced physical examination image is solved, and the accuracy and efficiency of physical examination image recognition are greatly improved.

The invention belongs to the technical field of discrete element simulation, and particularly relates to a digital twinborn discrete element model construction method based on CT (Computed Tomography) scanning, which comprises the following three steps of: in a CT scanning stage, acquiring a high-resolution cross-sectional image by optimizing scanning parameters, and carrying out image noise reduction and feature enhancement processing; in the structural analysis stage, a segmentation model is constructed based on a deep convolutional neural network, and automatic annotation of a scanned image and intelligent prediction of a three-dimensional space topological relation are realized; in the discrete element modeling stage, the reconstructed three-dimensional grid model is converted into a discrete element model with real physical attributes through parameter calibration, and discrete element simulation is achieved. According to the method, the non-destructive detection advantage of industrial CT and the feature extraction capacity of deep learning are combined, microstructure characterization is converted into macroscopic performance prediction, and a reliable simulation analysis method is provided for performance optimization of the composite material.

The invention relates to the technical field of image analysis, in particular to a data visualization pathological diagram analysis system which comprises a pathological image noise reduction and enhancement module, a lesion area judgment module, a local texture and global structure fusion module, a self-adaptive multi-scale segmentation module and an error correction and optimization module. According to the method, by analyzing color channels, cell structure edge features and background noise distribution in the pathological image, accurately screening noise and optimizing image filtering, the image quality is effectively enhanced, the noise is reduced, the recognition accuracy of a lesion area is improved, and the recognition accuracy of the lesion area is improved in combination with cell nucleus gradient information and tissue edge distribution. The accuracy is further improved by using gray statistics and cell density, region division is weighted and optimized through the contrast and entropy of lesion tissues, the segmentation accuracy is ensured, the image segmentation scale is accurately adjusted in combination with the cell density and color gradient information, errors are reduced, accurate segmentation of lesion regions is ensured, and the accuracy of image segmentation is improved. And finally, the precision and reliability of overall image analysis are improved.

The invention discloses a cement homogeneity detection method based on image processing. The method comprises the following steps: S1, image preprocessing: converting an original image into a grayscale image; s2, image noise reduction: salt and pepper noise is eliminated through a filtering technology, and the influence of the salt and pepper noise can be effectively eliminated; s3, image enhancement: carrying out sharpening and detail enhancement on the grayscale image by adopting a Laplace enhancement algorithm; s4, carrying out threshold segmentation: carrying out threshold segmentation through gray difference, and identifying an interested part which is not uniformly stirred; s5, watershed segmentation of the adhesion part: identifying a plurality of local maximum gray value points by adopting a watershed segmentation method based on extended maximum transformation, and combining the local maximum gray value points into a unique maximum value point to realize accurate segmentation of the adhesion area; and S6, homogeneity judgment. According to the invention, through an image processing algorithm, the number, size, distribution and other characteristics of the granular cement blocks are accurately analyzed, so that whether the cement is uniformly stirred is judged.

The invention provides an unsupervised low-dose photon counting CT (Computed Tomography) reconstruction method and an unsupervised low-dose photon counting CT reconstruction device based on optimal transmission. According to the method, a low-dose photon counting CT reconstruction problem is modeled as a Cantrovitch problem under a distribution consistency constraint, and the method comprises the following steps: constructing and training an optimal transmission-based unsupervised projection recovery network and constructing and training an optimal transmission-based unsupervised image noise reduction network; performing detail recovery on the photon counting CT low-dose projection by using the trained unsupervised projection recovery network to generate a denoised projection; reconstructing the denoised projection by using an image reconstruction algorithm to generate an intermediate image; and performing noise reduction on the intermediate image by using the trained unsupervised image noise reduction network to obtain a final de-noised image. According to the method, the problem that a high-quality pairing data set is difficult to obtain and a photon counting CT low-dose image is difficult to reconstruct can be solved.

The invention relates to the technical field of image recognition anti-counterfeiting, in particular to an authenticity identification method for analyzing micro-stereoscopic structure distribution on the surface of a product by using a mobile phone deep learning model. Comprising the following steps: image acquisition; image preprocessing: performing image noise reduction and region segmentation operation on the acquired image, extracting the edge of the micro-stereo structure through a Canny edge detection algorithm, performing fitting to generate a closed contour, and positioning an effective detection region of the micro-stereo structure in combination with contrast enhancement processing; extracting features; performing feature comparison; and outputting a result. According to the method, the limitation of the traditional one-dimensional or two-dimensional anti-counterfeiting feature is broken through by extracting the multi-dimensional features such as the height difference, the spatial arrangement and the geometrical shape of the micro three-dimensional structure on the surface of the product. The features are uniquely combined by depending on the three-dimensional distribution characteristic of the micro-stereo structure, and the complexity of the features enables high-precision equipment to be difficult to accurately imitate and copy, so that the anti-counterfeiting reliability is improved.

The invention relates to the technical field of metal detection, and discloses a polarization imaging metal surface scratch identification system. The system comprises a polarization imaging unit, an image preprocessing unit, a polarization feature extraction unit, a scratch recognition unit and a parameter self-adaption unit. The polarization imaging unit collects and transmits a metal surface polarization image; the image preprocessing unit performs noise reduction and enhancement on the image to generate an optimized image; a polarization feature extraction unit analyzes polarization state parameters of the optimized image to obtain polarization degree and azimuth angle distribution, and extracts polarization features of the scratch candidate area; the scratch identification unit compares the polarization characteristics with a preset template to generate an identification result; and the parameter adaptive unit dynamically adjusts the acquisition parameters of the polarization imaging unit according to the definition and contrast ratio of the scratch in the recognition result. According to the system, the polarization imaging technology is utilized, multi-unit cooperative work is combined, metal surface scratches can be accurately recognized in a complex environment, the system adapts to different detection conditions, and the recognition effect is improved.

The invention relates to the technical field of unmanned aerial vehicle image processing, and discloses an unmanned aerial vehicle image noise reduction and color enhancement optimization method and system. The method comprises the following steps: firstly, acquiring an original image sequence acquired in the flight process of the unmanned aerial vehicle, and identifying corresponding environment illumination intensity change data and motion fuzzy feature distribution; time dimension features of the original image sequence are divided based on environment illumination intensity change data, and a noise feature distribution map is constructed in combination with motion blur feature distribution; and finally, calling an equipment imaging parameter set of the original image sequence, analyzing a corresponding imaging mode constraint condition, and formulating a multi-stage noise reduction strategy framework for the original image sequence according to the constraint condition and the noise feature distribution map. The method realizes effective noise reduction and color enhancement of the unmanned aerial vehicle image by comprehensively considering the environment illumination change, the motion blur feature and the equipment imaging parameter, improves the image quality, and is suitable for the field of unmanned aerial vehicle image processing.

The invention provides a satellite-borne synthetic aperture radar signal processing method based on deep learning, and relates to the technical field of radar signal processing, and the method comprises the steps: collecting echo data of a satellite-borne synthetic aperture radar, carrying out the imaging processing of the echo data based on a constructed RATIR-Net network structure, obtaining a satellite-borne synthetic aperture radar image, and carrying out the processing of the satellite-borne synthetic aperture radar. And carrying out noise reduction processing on the obtained spaceborne synthetic aperture radar image by adopting a spaceborne synthetic aperture radar image noise reduction algorithm based on deep residual learning. According to the method, the imaging quality and the anti-interference performance are remarkably improved, and powerful technical support is provided for application of the satellite-borne SAR in the fields of disaster monitoring and the like.

The invention discloses pavement crack detection equipment based on double spectrums, and the equipment comprises an equipment design module which comprises a camera module, a supporting structure, an inclination angle monitoring module, an image processing unit and a mobile device; the dual-spectrum fusion detection module comprises a thermal diffusion enhancement dual-spectrum multi-scale feature fusion image preprocessing module, noise reduction and multi-scale feature fusion are carried out on images collected by the infrared thermal imaging camera and the visible light camera, and a detection result and category and position information are output through an unsupervised enhancement BiSeNet hybrid wavelet transform network to complete detection; and the pavement quality evaluation module is used for realizing pavement crack detection through image splicing and BiSeNet network segmentation, realizing pavement quality evaluation through crack distribution diagram generation and area proportion calculation, and realizing detection result display through visual labeling. According to the invention, the detection efficiency can be greatly improved, the maintenance cost can be reduced, and powerful support can be provided for timely maintenance of the road.

The invention discloses a video analysis-based early warning and monitoring method for children hyperactivity behavior and a storage medium, and the method comprises the steps: firstly, guaranteeing the comprehensive monitoring of children behaviors through employing a multi-channel video collection device, and providing a sufficient continuous data source for subsequent analysis; furthermore, the quality of monitoring data is ensured through the use of image noise reduction and segmentation technologies, and accurate motion features are effectively extracted through the combination of an optical flow algorithm and a background subtraction algorithm; further, the movement behaviors of the children are comprehensively analyzed by calculating behavior parameters such as movement amplitude, movement direction change and continuous movement time, and potential behavior abnormity is revealed; the multi-dimensional behavior feature vector obtained through behavior parameter analysis is compared with the standard template, the behavior type of the child is automatically recognized, early-stage symptoms of abnormal behaviors such as hyperactivity and the like are found in time, and a basis for early diagnosis and intervention is provided for behavior problems such as hyperactivity and the like of the child.

The invention, which relates to the field of power transmission detection, discloses a visualization-based power transmission detection system comprising an image acquisition module, a preprocessing module, a feature extraction module, a defect identification module and an alarm module. A high-definition camera is used for collecting images, a path is planned according to an inspection task during preparation, equipment is debugged, shake is prevented in the process, and a continuous shooting mode is selected; noise reduction is carried out on the image, the image is enhanced after being processed through a wavelet transform algorithm, and the image is standardized into a specific resolution ratio and a specific pixel value through self-adaptive histogram equalization operation; extracting multi-scale features based on a deep learning model, extracting frequency domain features during defect identification, fusing the frequency domain features into vectors, inputting the vectors into a classifier, and optimizing through a feature pyramid network; and finally, sound-light alarm is generated when defects are detected, information is uploaded to a remote monitoring center, geographic information system linkage and local storage are supported, data distribution and decision support are ensured to be timely and accurate, and power transmission equipment is effectively maintained.

A deep learning segmentation method for asphalt mixture CT images relates to the technical field of aggregate image segmentation. CT images of asphalt mixtures are collected and voids are removed. Image equalization is performed using a gamma beam hardening correction algorithm. A filter window is selected, and an adaptive bilateral filtering denoising algorithm based on local image information is used to denoise the image. The U-Net model is improved, with the Inception convolution module replacing the standard convolution operation and residual connections replacing skip-layer connections. A spatial attention mechanism is introduced, and a joint loss function is used. Image samples are selected, aggregates are labeled, and data augmentation is used to increase the sample size to form a training set for model training. After training, this set is used to segment other images. By equalizing and denoising CT images and using the improved U-Net model, the method can achieve accurate segmentation of aggregate-mortar boundary information, avoiding aggregate adhesion issues.

The invention discloses a radiation hot spot noise removal method and device based on a dual-CMOS image sensor, and belongs to the technical field of CMOS image sensor noise reduction, and the method comprises the steps: carrying out the calibration of a dual-camera system, and eliminating a mechanical assembly error; the imaging focal planes of the double cameras are ensured to be consistent through definition evaluation; pixel-level geometric alignment is realized by using Fourier-Mellin transform, so that an imaging error is smaller than a specific threshold value; adaptive weighted fusion is performed based on local features, and rigid transition of simple binary selection is avoided. According to the method, image details can be effectively reserved while the hot spot noise is removed, particularly, when an image containing English letters is processed, the contour definition and the recognizability are remarkably superior to those of a traditional algorithm, and an efficient solution is provided for image noise reduction in the intense radiation environment.

The invention provides an image noise reduction method and device. The method comprises the following steps: acquiring pixels of an input image; traversing each pixel of the input image, and by taking the current pixel as a center, calculating a corresponding variance map and a corresponding mean value map through a filtering window constructed by the first radius and the second radius; calculating an image low-frequency coefficient based on the variance graph; and obtaining a low-frequency image according to the low-frequency coefficient and the mean value diagram, thereby realizing noise reduction of the flat region of the image. And filtering pixel points in different directions of the current position based on a filtering window constructed by a second radius, calculating a filtering difference value between the current pixel point and the pixel points in each direction, and optimizing a filtering result in each direction through the difference value, thereby realizing protection of detail features of the image. And based on the difference value, calculating the average value of the intercepted areas, judging the area where the current pixel point is located based on the average value, and fusing the low-frequency image and the noise reduction result in each direction so as to realize differential noise reduction processing on the flat area and the detail area and obtain a final noise reduction image.

The invention discloses a tunnel face integrity evaluation method based on deep learning, and the method comprises the steps: firstly scanning a tunnel face through a laser radar carried on an unmanned plane, obtaining a point cloud file of the tunnel face, and carrying out the data registration, data noise reduction, data simplification and three-dimensional modeling of the point cloud file through a data processing technology; the method comprises the following steps: performing tunnel face image extraction and image preprocessing on a three-dimensional model obtained after data processing, performing crack identification through a YOLOv5 convolutional neural network, and performing enhancement and structure optimization on crack image features through operations such as image segmentation, image noise reduction, crack skeleton extraction, edge detection, crack skeleton line splicing and the like. And information such as crack width and crack length is obtained through the processed image. The face fracture density and the ratio of open, micro-open and closed fractures are calculated through the information, the face fracture density is used for distinguishing the completeness and local stability of the tunnel face rock mass, and the completeness and local stability of the tunnel face are evaluated more comprehensively through the ratio of the three fractures.

The invention relates to the technical field of atmospheric pollution monitoring, in particular to an image pollution value monitoring method and device, and the method comprises the steps: obtaining image data collected by a camera, and carrying out the preprocessing of multi-frame image noise reduction and light and shadow correction on the image data; performing feature extraction on the preprocessed image data to obtain global semantic features and local sparse features; performing dynamic weighted fusion on the global semantic features and the local sparse features to obtain fusion features; stripping interference features in the fusion features to obtain final fusion features; and inputting the final fusion feature into a deep full-connection network for analysis, and outputting various types of pollution values. It can be understood that according to the technical scheme, the image is preprocessed in advance, so that the image becomes an effective data source, the scene adaptability is improved, a double-model parallel architecture and interference stripping are achieved, the feature extraction and fusion precision is remarkably improved, and the prediction precision is improved.

A filter unit decomposes image data from an image sensor adapted to capture images at a predetermined frame rate into a low-frequency component and a first high-frequency component. A motion vector estimation unit reads data from an event sensor, adapted to asynchronously output information on a pixel in which a brightness changes, at a frame rate higher than the predetermined frame rate and estimates a motion vector. A motion compensation unit performs motion compensation based on the motion vector. The filter unit generates a third high-frequency component by adding the first high-frequency component and a second high-frequency component extracted from an image obtained by motion compensation at a predetermined ratio, and reduces a noise in the image data by adding the low-frequency component and the third high-frequency component.

The invention discloses a power grid inspection image automatic processing method based on image matching, and the method comprises the following steps: obtaining a to-be-detected image of a corresponding power grid line at the current moment, and carrying out the image noise reduction and image enhancement preprocessing of the image of the power grid line; performing feature extraction on the preprocessed image to obtain a feature map; comparing the processed power grid image feature map with a fault model, and judging and outputting a fault type; information after image matching detection generates an inspection report through an automatic analysis system. The power grid inspection image is subjected to noise reduction and de-noising processing and then is subjected to feature extraction, so that the influence of infection factors on the inspection image is effectively eliminated, then the inspection image is compared with a fault defect model so as to identify the inspection target defect type, the fault model is obtained through the processed image and historical faults, interference of interference factors can be eliminated, and the inspection accuracy is improved. The recognition result is more accurate, the recognition efficiency is higher, and a high-precision and efficient recognition method is provided for patrol image processing.

The invention discloses a TGV glass substrate double-axis synchronous stable scanning detection method, which comprises the following steps: firstly, importing hole site coordinate data of a TGV glass substrate, dividing a dense sub-region and a sparse sub-region according to hole site space distribution density, generating a variable density scanning path, and realizing dynamic adaptation of detection speed and resolution; then the double-shaft synchronous driving mechanism drives the substrate to move, and the multi-degree-of-freedom visual scanning mechanism automatically switches the light source state and the camera rotation angle according to the type of the detected target and synchronously collects images; the adsorption pressure is monitored in real time in the whole detection process, and when the pressure is lower than a safety threshold value, automatic speed reduction or alarm is performed to guarantee substrate safety; and finally, defect identification and classification are completed through multi-frame image noise reduction, feature extraction and a support vector machine algorithm. The problems that in traditional detection, efficiency and precision are difficult to consider at the same time, the substrates are prone to damage, and the automation degree is low are solved, efficient, high-precision and low-damage batch detection of the TGV glass substrates is achieved, and the method is suitable for online detection scenes of mass production lines.

Embodiments of the present invention relate to a method and apparatus for analyzing angiographic images. The method comprises: acquiring an angiographic image; detecting vascular stenosis sites and using a sub-image of the detected stenosis sites as a first image; performing binarization and image noise reduction to generate a first binary image; performing vessel identification to generate a vascular image; extracting a centerline from the vascular image in the first binary image without changing the topological properties of the vascular image to generate a first centerline; sorting pixels on the first centerline to generate a first pixel sequence; measuring the vascular diameter at each first pixel to generate a first diameter; identifying the vascular stenosis rate at each first pixel to generate a corresponding first stenosis rate; and returning the first pixel sequence, first diameter sequence, and first stenosis rate sequence as vascular stenosis analysis data for the angiographic image. The present invention can improve analysis accuracy.

The invention relates to the technical field of deep convolutional neural networks, in particular to a cryoelectron microscope noise particle image detail reservation noise reduction method based on edge enhancement, which comprises the following steps: inputting a cryoelectron microscope noise particle image into a trained image noise reduction model, and outputting a noise-reduced cryoelectron microscope particle image; in the image noise reduction model, an initial feature map of a noise particle image of the cryoelectron microscope is extracted; inputting the initial feature map into a multi-scale feature extraction module to capture multi-scale structure characterization; inputting the multi-scale feature map into an edge enhancement module to detect and enhance macromolecule boundary features to generate an edge enhanced feature map; inputting the edge enhancement feature map into a detail retention module for processing and retaining structure details to generate a detail enhancement feature map, and performing convolution processing to generate a prediction noise component; and subtracting the predicted noise component from the cryo-electron microscope noise particle image to obtain a noise-reduced cryo-electron microscope particle image. According to the invention, the noise reduction quality of the noise particle image of the cryoelectron microscope can be improved.

The invention provides an SPECT bone imaging noise reduction method and device and a storage medium, and relates to the technical field of nuclear medicine image processing.The SPECT bone imaging noise reduction method comprises the following steps that S1, data collection and reconstruction are conducted, specifically, multi-stage downsampling is conducted on standard-dose SPECT table mode data to generate low-dose SPECT data; s2, data preprocessing: performing cutting and linear normalization processing on the reconstructed low-dose and standard-dose SPECT images; s3, model construction: constructing a deep learning model of a lightweight Restormer architecture; and S4, model training: carrying out end-to-end model training by utilizing the preprocessed multi-stage low-dose and standard-dose image pair. According to the method, the deep learning model of the lightweight Restormer architecture is constructed, and the FFT frequency domain self-adaptive decomposition module is integrated step by step, so that high-frequency noise and low-frequency anatomical features in the image can be effectively separated, and high-frequency details of a skeleton region are effectively reserved while the noise reduction quality is remarkably improved.

The invention discloses an image noise reduction method and device, equipment and a medium, which are used for realizing multi-channel wavelet high-frequency noise reduction. The method provided by the invention comprises the steps of performing wavelet decomposition on a to-be-denoised image to obtain a plurality of high-frequency components, and determining a plurality of high-frequency channel vectors; each high-frequency channel vector is obtained by combining high-frequency components of a plurality of channels of the to-be-denoised image at the same image coordinate position; for each high-frequency channel vector, determining a similar vector of the high-frequency channel vector, and generating a high-frequency similar vector matrix; on the basis of the high-frequency similar vector matrix, determining a parameter for performing noise reduction on the high-frequency channel vector; performing noise reduction processing on the high-frequency channel vector by using a parameter for performing noise reduction on the high-frequency channel vector to obtain a high-frequency channel vector after noise reduction; and on the basis of each denoised high-frequency channel vector, performing wavelet reconstruction by adopting a mode corresponding to wavelet decomposition to obtain a denoised image.

The embodiment of the invention provides an SEM image noise reduction method. The method comprises the following steps: acquiring an SEM image to be denoised as an original image; constructing a noise reduction evaluation function to enable the noise reduction evaluation function to comprise a first item and a second item, and performing noise reduction processing on the original image by using the noise reduction evaluation function to obtain a corresponding noise reduction image; wherein the first item is used for reducing the pixel value fluctuation of the noise reduction image, and the second item is used for reducing the difference between the original image and the noise reduction image. Compared with the prior art, the method has the advantages that more image details in the original image are reserved on the basis of realizing image noise reduction, and the image quality of the noise-reduced image is improved.

The embodiment of the invention provides an image noise reduction method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring an original image; wherein the original image comprises at least two channels; for each channel, determining image data of the channel under at least two preset resolutions according to the original image; according to the image data of the channel under the at least two preset resolutions, determining denoised data corresponding to the channel; and according to the denoised data corresponding to each channel, determining a denoised image corresponding to the original image. For different channels in the original image, image data under different resolutions are obtained, information of multiple scales in the image is reserved, for each channel, independent noise reduction is performed on the channel in combination with the image data under each preset resolution, mutual influence of the channels is avoided, and the image noise reduction precision is effectively improved.

The invention discloses an automatic meter reading identification method for a substation inspection robot vehicle. The method comprises the following steps: constructing a substation environment three-dimensional grid map; setting a multi-objective function for global path planning of the inspection robot vehicle; global and local path planning is carried out by adopting an improved DOA optimization algorithm and an improved DDPG reinforcement learning algorithm, and an optimal path of the inspection robot vehicle is found; according to the DDPG algorithm, an improved GOA algorithm is introduced into a reward and punishment function to optimize a safe time interval model optimization path; an NLM model is adopted to carry out image noise reduction, and a SegVG model is adopted to carry out image feature extraction; and an improved MHAFF model is adopted to accurately identify digits.