568 results about "Transformation parameter" patented technology

The invention provides an interaction method and system based on deep learning, and relates to the technical field of computer vision, and the method comprises the steps: collecting a continuous image sequence, extracting feature points, calculating the position variation and gradient variation of the feature points, constructing a two-dimensional feature vector, and carrying out the clustering through a Gaussian mixture model, thereby obtaining a stable feature class. And weighting the feature points based on a feature weight distribution function, calculating feature similarity and constructing a matching relationship. And calculating a dynamic parallax threshold in combination with the vehicle movement speed, screening reliable matching feature pairs, and solving pose transformation parameters. A feature change sequence is extracted through a feature detection network, a motion feature mapping matrix is constructed, and a compensation depth map is generated in combination with depth information. And scene reconstruction is carried out based on the compensation depth map and the pose transformation parameters, the scene confidence score is calculated, the pose parameters are calibrated, a high-precision pose parameter sequence is obtained, and the robustness of feature matching and the accuracy of pose estimation can be improved.

The invention provides an industrial defect image generation system and method based on deep learning, and relates to the technical field of artificial intelligence. A defect form adaptive module, a physical attribute modulation module and a multi-mechanism fusion module are integrated in a defect image generation module; dynamically selecting a feature extraction unit according to the defect type label based on a pre-constructed generative network model, and generating a defect feature map; generating an affine transformation parameter based on the physical attribute vector, and performing channel-by-channel linear modulation on a defect feature map of a middle layer of the generative network model, so that a multi-scale defect feature map finally generated by the generative network model contains specified defect type features and physical attribute features; and fusing the multi-scale defect feature image and the defect-free background image to obtain a fused defect image. The problems that in the prior art, industrial defect image generation is insufficient in sense of reality, poor in controllability and poor in fusion effect are solved, the method can be used for data enhancement of industrial visual inspection, and downstream model performance is improved.

The invention discloses a multi-source ship target identification method based on two-stage collaborative fusion, and relates to the technical field of signal processing, and the method comprises the steps: firstly collecting target sea area data, including original optical image and radar image data, by means of an optical camera and a radar sensor on an aircraft, and then carrying out the preprocessing of the collected data through Gaussian filtering; performing sea-land segmentation by using a deep learning algorithm, constructing a loss function optimization network parameter to obtain a segmentation mask, and removing a land background area according to a mask result to obtain processed optical and radar images; an improved SURF feature and graph cut algorithm combined registration method is adopted, optimal transformation parameters are obtained by screening feature point pairs and solving the minimum value of an energy function, and image registration is achieved; for the registered images, fusing the images based on an adaptive fusion rule; and finally, extracting corresponding features through manual feature extraction and feature extraction based on deep learning, and fusing the features to obtain a final target recognition result.

The invention discloses a remote sensing image classification model compression method based on incremental information guidance, and mainly solves the problems of evaluation deviation caused by insufficient representation of dynamic characteristics of a filter and poor coordination of pruning and quantization technologies in the existing model compression technology. Comprising the following steps: 1) acquiring a remote sensing image data set and preprocessing the remote sensing image data set; 2) pre-training the model by using the preprocessed data; 3) obtaining rank information and gradient information of the feature map, and calculating an importance score of a filter in the model according to the information; 4) optimizing affine transformation parameters, obtaining scores and generating a sorting result; and 5) performing compression and fine adjustment on the model in stages to obtain a lightweight model. According to the method, model compression is guided by gradient information, collaborative optimization is realized through integrated design of pruning and quantification in combination with rank information, the model scale and the calculation complexity can be remarkably reduced under the condition that the precision is not affected, and the compression effect is effectively improved.

The invention belongs to the field of data processing, particularly relates to a standardized processing method, system and equipment for original engineering parameters of a flight simulator, and aims to solve the problems of serious field limitation, low processing efficiency and poor adaptive capacity in the prior art. The method comprises the following steps: analyzing a predefined configuration file, and dynamically generating a database temporary table matched with an original data file structure according to field structure information and a parameter mapping rule defined in the configuration file; directly loading original engineering parameter files into the temporary table by adopting a batch loading mechanism based on a file system path, and executing multi-file parallel import based on a task queue; and converting calculation logic in the parameter mapping rule into an executable query expression, and directly exporting a standardized parameter file after calculation is executed through the temporary table. According to the method, field limitation is broken through, efficient processing of mass data is achieved, instant updating of service logic is achieved through configuration rules, and the maintenance cost is greatly reduced.

Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

To provide a quenching simulation method for steel with high accuracy.SOLUTION: Provided is a quenching simulation method for steel, comprising: a calculation section 1 calculating a distribution of temperatures by a heat conduction analysis using a finite element method after inputting each of steel phases and physical properties at each of steel temperatures to separate a shape model; a calculation section 2 calculating distribution of strain or stress by an elastoplastic analysis; a calculation section 3 calculating distribution of phase fraction through calculation of a basic equation representing phase transformation; and a calculation section 4 calculating distribution of cooling speed from time change of temperature of each of elements, the method comprising a step of carrying out coupled analysis using phase transformation parameters of the steel calculated from the cooling speed calculated with the calculation section 4 on a procedure to calculate the phase fraction in the calculation section 3.SELECTED DRAWING: Figure 1

The invention relates to the technical field of data processing and mode recognition, in particular to a bearing fault diagnosis method based on multi-scale feature fusion, which comprises the following steps: fusing multi-source data such as vibration, acoustic emission and rotating speed, performing angle domain resampling by using rotating speed data, generating a two-dimensional order spectrogram, and stacking to construct a three-dimensional working condition information tensor; a master-slave modulation heterogeneous neural network is adopted, high-dimensional spatial-temporal features are extracted through a main branch three-dimensional convolutional network, time sequence details are extracted from an original sequence through an auxiliary branch one-dimensional convolutional network, affine transformation parameters are generated, and dynamic modulation is achieved on the high-dimensional features; and the output state vector is mapped to a fault evolution knowledge graph, probability prediction is carried out through a graph attention network and by introducing a Monte Carlo discarding mechanism, a probability mean value is calculated as a fault classification result, and the diagnosis confidence is quantified by a probability variance. According to the invention, through multi-scale feature fusion and dynamic modulation, the problem of insufficient feature discrimination caused by scale mismatch under variable working conditions is solved.

The invention discloses a global registration algorithm for low-overlapping-rate point clouds, and relates to the technical field of point cloud registration, and the algorithm comprises the steps: constructing a multi-scale descriptor under a multi-radius neighborhood for key points in a source point cloud and a target point cloud, screening a rough matching set through employing an evolutionary stabilization strategy, and obtaining a first-order matching set; based on a corresponding propagation mechanism, aggregating each matching element in the first-order matching set into a global candidate set through a corresponding propagation operation; and according to the aggregated global candidate set, generating transformation parameters with the same number, screening an optimal transformation parameter through a quality function, performing coarse alignment on the point clouds, and performing fine optimization through a truncation-ICP (Inductively Coupled Plasma) algorithm. Therefore, the global registration algorithm for the low-overlapping-rate point clouds can effectively cope with the situation of missing part of the point clouds, has relatively high robustness, and improves the registration precision under the conditions of low resolution and low overlapping rate.

The invention belongs to the technical field of laser scanning, and discloses a multi-station foundation laser scanning point cloud registration method and system suitable for a forest environment. Firstly, an original three-dimensional point cloud is converted into a two-dimensional distance image, a trunk is extracted based on continuity constraint, and the position of a trunk root point is searched; secondly, constructing a triangular descriptor, describing the spatial relationship among the trunks in scanning, and storing the spatial relationship in a hash table; and searching the corresponding triangular pairs by using the search operation of the hash table, calculating the similarity between scans, and extracting three-dimensional transformation parameters. And taking a to-be-solved scanning station pose as a node, taking relative transformation as a factor constraint, and obtaining a scanning station pose parameter with optimal overall consistency through factor graph optimization. And finally, by taking the conversion parameter after the factor graph optimization as an initial value, optimizing and adjusting the conversion parameter by using an ICP method, deriving the pose of each scanning station in the unified coordinate system through a depth-first strategy, converting the local point cloud into the unified coordinate system, and realizing global point cloud registration.

The invention discloses a coordinate system conversion calibration method for a 3D laser contourgraph. The method comprises the following steps: firstly, building a calibration device; the calibration device is provided with four calibration balls with adjustable spatial positions, the four calibration balls are enabled to intersect with a laser surface emitted by the contourgraph through adjustment, and the centers of the balls are not coplanar. Then, a world coordinate system is established through a laser tracker, and the center coordinates of all the calibration balls in the world coordinate system are obtained; and further, acquiring a circle center coordinate and a circular arc radius corresponding to the circular arc on the spherical surface of the calibration ball through a contourgraph to obtain a sphere center coordinate of each positioning ball under the contourgraph. And finally, according to the obtained coordinates of the sphere center under the two coordinate systems, carrying out transformation matrix parameter solving to obtain a transformation matrix, and selecting an optimal result. According to the method, the relative attitude of the 3D laser contourgraph can be accurately obtained, rigid body transformation parameters are completely solved, the parameter solving precision is high, and calibration of multiple coordinate systems can be achieved.

The invention discloses a multi-modal remote sensing image registration method based on domain self-adaption and an optimizer set algorithm, and relates to the field of image processing, and the method comprises the steps: respectively extracting the feature vectors of a reference image and an image to be registered, carrying out the feature matching of the feature vectors according to the class label containing conditions of the feature vectors, and obtaining a registration result; obtaining a feature matching vector based on a matching result; estimating transformation parameters corresponding to the affine transformation model by using a random sampling consistency algorithm, and optimizing the affine transformation model according to an estimation result and similarity measurement; and performing spatial transformation on a to-be-registered remote sensing image by using the optimized affine transformation model to realize spatial alignment between the reference image and the to-be-registered image. According to the method, firstly, the feature points of the multi-modal remote sensing image are extracted, the difference of feature vectors is reduced by using a domain adaptive method, the precision and robustness of feature matching are improved, transformation parameters are optimized through an optimizer set algorithm, and search is prevented from falling into local optimum.

The invention relates to the technical field of water quality prediction. The pollution risk prediction method and device based on multi-source water quality data fusion, the equipment and the medium are provided, and the method comprises the following steps: carrying out multi-source collaborative acquisition processing on hydrological data, meteorological data and real-time water quality monitoring data to generate a time-space association data set; carrying out pollution scene feature coupling analysis processing on the space-time correlation data set to generate a pollution type identification matrix and a dynamic driving parameter; collaborative activation processing of the process modules is carried out through a scheduling engine, and a target simulation module topology network is generated; performing adaptive parameter configuration processing on the topological network of the target simulation module to generate a migration and transformation parameter tensor; performing dynamic evolution processing on the migration and transformation parameter tensor to generate a risk early warning hologram spectrum; and carrying out multi-dimensional parallel rehearsal processing on prevention and control measures to generate a treatment efficiency quantitative report so as to improve the pollution characteristic analysis precision and optimize the accuracy of a prediction result.

The invention relates to the field of assembly automation and flexible manufacturing, and discloses an assembly method for a prefabricated firewall of a transformer substation, and the method comprises the following steps: setting a plurality of space positioning reference points at the edge of a wallboard; acquiring three-dimensional coordinate data to form a first point set and a second point set; calculating an initial rigid body transformation parameter between the wallboards according to the first point set and the second point set; establishing an energy functional for describing a total error; carrying out minimization solution on the energy functional by adopting a variational method to obtain an optimal disturbance vector field; according to the optimal disturbance vector field, a plurality of fine adjustment actuators of the wallboard are controlled, posture fine adjustment is conducted, and physical assembly connection of the wallboard and the target wallboard is completed. According to the invention, accurate attitude estimation and error correction in the wallboard assembly process are realized; the robustness and geometric fitting capability of the assembly process are improved; the assembly precision and efficiency are remarkably improved, and the problem that traditional redundancy control distribution is unstable is solved.

The invention discloses a self-adaptive environment image processing method for industrial gas detection, which relates to the field of industrial gas detection and comprises the following steps: extracting feature points of a current frame by utilizing a feature point detection algorithm according to image frames of an industrial monitoring video stream, and acquiring coordinates of feature points between frames by combining an optical stream tracking technology; generating affine transformation parameters, performing transformation decomposition on the coordinates of the feature points by using the affine transformation parameters, and extracting pose change parameters to obtain an image motion track; predicting an image motion track by using an image track processing algorithm, and comparing the predicted image motion track with a real-time image motion track generated by the current frame; and optimizing the affine transformation parameters, and carrying out frame-by-frame processing on the video stream by using the optimized affine transformation parameters. Through feature point detection and an optical flow tracking algorithm, image motion information in an industrial monitoring video can be extracted, and industrial application requirements of high real-time performance and high stability are met.

A method for automatically determining a canonical pose of a 3D object comprises: providing one or more blocks of voxels of a voxel representation of the 3D object to a first 3D deep neural network, the first 3D neural network being trained to generate canonical pose information; receiving canonical pose information from the first 3D deep neural network, the canonical pose information comprising for each voxel a prediction of a position of the voxel in the canonical coordinate system; using the canonical coordinates to determine an orientation and scale of the axes of the canonical coordinate system and a position of the origin of the canonical coordinate system relative to the axis and the origin of the first 3D coordinate system and using the orientation and the position to determine transformation parameters of the first coordinate system into canonical coordinates; and, determining a canonical representation of the 3D dental structure.

The invention discloses a multi-modal image registration method and system based on deformation adaptation and computer equipment, and the method comprises the steps: collecting a plurality of groups of multi-modal images, carrying out the gray standardization, and constructing a diversified registration data set; building a registration network model comprising a pyramid coding module, a deformation adaptive module, a cross-modal interaction module and a registration parameter estimation module; inputting an image pair into the modules in sequence, respectively extracting basic feature mapping, deformation feature mapping and interaction enhancement feature mapping, and finally outputting an estimation conversion parameter matrix; a training process is supervised through a preset loss function, optimal network parameters are selected, and a trained registration model is obtained; in practical application, an image pair to be registered is input into the trained model, a conversion parameter matrix is obtained, and image registration is completed. The multi-modal image registration performance can be effectively improved, and the method still has good robustness and adaptability especially under the condition that serious geometric distortion and significant modal difference exist.

The invention relates to the technical field of multi-view angle analysis, in particular to a monitoring analysis method based on multi-view angle image area synthesis, which comprises the following steps: constructing a centralized dynamic anchor point set and generating multi-view angle coordinate transformation parameters and a multi-view angle observation position sequence based on target original position data collected by a multi-view angle sensor; and space-time constraint conditions of the centralized dynamic anchor point set are extracted. According to the method, through dynamic anchor point centralization processing and self-adaptive generation of multi-view coordinate transformation parameters, the coordinate system reference of multi-source heterogeneous data is effectively unified, and the cross-view positioning deviation is reduced; in combination with a space-time constraint mechanism of an elastic synthesis region, a target trajectory is dynamically predicted by using Kalman filtering and an elastic boundary is delimited, so that the stability and fault tolerance of trajectory prediction in a complex motion scene are improved.

The invention relates to the technical field of image processing, in particular to an injection molding part defect detection method and system based on machine vision, and the method comprises the steps: obtaining a to-be-detected image, constructing three-dimensional space points, calculating the direction difference between normal vectors of each space point and adjacent points in the same region to quantify the bending degree, and calculating the bending degree of the to-be-detected image; performing grid division on the to-be-detected image and the standard image, calculating the matching degree based on the average difference of the bending degrees of all the spatial points in the two grid areas, selecting the spatial points with the maximum matching degree in the two grid areas, and obtaining transformation parameters from the to-be-detected image to the standard image through singular value decomposition; and performing transformation alignment on the to-be-detected image based on the transformation parameter by using an ICP algorithm so as to identify the deformation defect of the to-be-detected image based on the two aligned images. According to the invention, the accuracy of image matching by using the ICP algorithm can be improved, so that the accurate recognition of the deformation defect area in the to-be-detected image is realized.

The invention provides a block adjustment method and device for a multi-source remote sensing image, and solves the problem that the splicing precision and efficiency of the multi-source remote sensing image in a large area are low. All panchromatic images and a multispectral image corresponding to each panchromatic image are distinguished from the image data set, and connection points of the panchromatic images are extracted; carrying out connection point matching among all panchromatic images; performing connection point matching between the panchromatic image and the corresponding multispectral image; performing control point matching on all panchromatic images and a satellite remote sensing orthographic reference image; obtaining object space coordinates of each matching point; based on the object space coordinates of the connection points and the RPC parameters of the images corresponding to the connection points, resection is carried out, and error points and error images are removed; joint adjustment is carried out on the connection points and the control points, and transformation parameters and object space coordinates of the connection points of each image are calculated; and according to the object space plane coordinates after the connection points are corrected, obtaining the elevation based on the DEM, comparing the obtained elevation with the original elevation, and if the obtained elevation value does not change, correcting the original RPC parameter file.

The invention provides a credible permission mutual recognition method, device and system for cross-domain agents, and relates to the technical field of artificial intelligence security, and the method comprises the steps: receiving a call request from a source domain agent for executing a corresponding operation on a target domain agent; obtaining an affine transformation parameter set through a permission conversion model according to the space relation characteristics of a source domain permission space and a target domain permission space involved in the calling request, and finally screening out affine transformation parameters suitable for permission voucher mapping by utilizing cone volume measurement evaluation and security verification, and mapping an original permission voucher of the source domain agent from a source domain permission space to a target domain permission space by using the affine transformation parameter, and generating a mapped permission voucher which can be identified and verified by the target domain. According to the method, the permission space is geometrized, and affine transformation, space division and geometric calculation are utilized, so that the permission credible mutual recognition problem in cross-domain agent collaboration is effectively solved.

The invention relates to an equipment positioning method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring current actual position information of a feature hole, detecting current image position information of the feature hole from a current feature hole image, and determining a main shooting coordinate system, detecting a first pose transformation parameter between any two of all the observation coordinate systems, a second pose transformation parameter between each observation coordinate system and a feature hole coordinate system of the feature hole in the current time period, and a historical zero offset pose transformation parameter between the main shooting coordinate system and the feature hole coordinate system; generating a feature hole pose variation based on the historical zero offset pose transformation parameter and a second pose transformation parameter corresponding to the main shooting coordinate system; on the basis of the parameters, correcting the posture variation of the feature hole; and performing pose positioning on the target vehicle based on the corrected feature hole pose variation. By adopting the method, the target vehicle can be accurately positioned.

The invention discloses a small sample crack recognition method and system based on transfer learning, and the method comprises the steps: constructing an innovative and deep-coupled neural network architecture, and enabling a self-adaptive crack perception attention module integrated with a parallel asymmetric convolution kernel to recognize the linear geometric features of a crack, and generating an attention graph; then, the attention map is adopted to carry out pixel-by-pixel signal pre-modulation on an original input image, the enhanced image is sent to a pre-training MobileNetV4 backbone network integrated with a feature-level linear modulation layer, and channel-level dynamic adaptation of feature flow in the network is realized by learning affine transformation parameters; and finally, the extracted depth features are sent to a Gaussian naive Bayes classifier for classification, and depth geometric analysis is carried out on the attention map so as to realize interpretable fracture severity evaluation. According to the method, the accuracy, robustness and interpretability of crack identification are remarkably improved, and the technical bottleneck in a small sample scene is effectively solved.

The invention provides an image target intelligent tracking and positioning method and system under Beidou position constraint, and relates to the technical field of Beidou positioning, and the method comprises the steps: obtaining a multi-source heterogeneous data flow, constructing a multi-modal representation model, and building a coordinate system dynamic projection transformation relation; generating a search mask to limit a tracking range by using the Beidou position information; bayesian correction is carried out on a tracking result through double-domain consistency measurement; and dynamically updating projection transformation parameters and feature weights based on residual distribution. According to the invention, deep fusion of vision and Beidou information is realized, and the precision and robustness of target tracking in a complex scene are improved.

The invention provides a medical image registration method and system based on a multi-dimensional loss function. The method comprises the following steps: preprocessing 3D-CT medical image data, wherein the 3D-CT medical image data comprises a fixed image and a floating image; the method comprises the following steps: constructing an initial model of a registration model by adopting a transformer-based deep learning architecture, and firstly, carrying out coarse registration on preprocessed 3D-CT medical image data to obtain coarse registration rigid body transformation parameters; further performing fine registration through an initial model of the registration model based on the rough registration rigid body transformation parameters; and further optimizing the initial model of the registration model by adopting a multi-dimensional adaptive loss function to obtain a final registration model capable of obtaining an optimal result. According to the method, a deep learning network technology is comprehensively adopted, a registration structure based on a transformer deep learning network framework from a coarse stage to a fine stage is adopted, a multi-dimensional self-adaptive loss function is introduced, and meanwhile, the registration adaptation range and the registration precision are improved.

The feature extraction section extracts source domain structural features from input source domain image data and, extracting target domain structural features from input target domain image data. The rigid transformation section generates transformed structural features by rigid transforming the structural features with reference to conversion parameters. The relighting section generates new view features with reference to the transformed structural features and the conversion parameters in a way that new view features approximate the structural features which are extracted from input image data at the views indicated by the conversion parameters. The class prediction section predicts source domain class predictions from the source domain structural features and the source domain new view features, and predicting target domain class predictions from the target domain structural features and the target domain new view features. The updating section updates at least one of the feature extraction section, the relighting extraction section, and the class prediction extraction section.

The invention relates to the technical field of power supply, and provides a self-adaptive adjustment control method for a transformer. The method comprises the following steps: constructing a transformer module which comprises a first transformer and a second transformer; acquiring a plurality of transformation paths of the first transformer, performing operation monitoring, and outputting a monitoring data set; carrying out load abnormity identification on the data set, and determining an abnormal path greater than a preset load index; determining a transformation parameter corresponding to the abnormal path, and outputting a first transformation parameter and a second transformation parameter based on a load index self-adaptive separation parameter; after the first transformer performs voltage transformation on the abnormal path input signal by using the first parameter, the second transformer performs voltage transformation on the first signal by using the second parameter and outputs a second signal. According to the method and the device, the technical problems that the local overload loss is aggravated and the system operation stability is reduced due to the fact that the transformer cannot dynamically optimize energy efficiency distribution under the load fluctuation or abnormal working condition during power supply are solved, and the technical effect of improving the fault tolerance and energy efficiency balance of multi-path transformation is achieved.

The invention discloses a safety auditing method and device supporting data owner replacement, equipment, a medium and a product, and relates to the field of auditing, and the method comprises the steps that if the data ownership is changed, an original data owner calculates a trap door parameter value based on a random number j and a private key of the original data owner; the new data owner calculates a conversion parameter value according to the trap door parameter value and a private key of the new data owner; the cloud server calculates the label of each data block after the data ownership is changed according to the conversion parameter value, the reciprocal of the random number j and the label of each data block before the data owner changes; the cloud server generates auditing evidences according to the labels of the data blocks and the inquiry information; the third-party auditor carries out safety auditing according to the auditing evidence and the inquiry information, and after the data ownership is changed, it can be ensured that the changed data owner can still ensure the continuity of data integrity verification under the condition that all the data are not downloaded.

The embodiment of the invention provides a method and device for protecting model safety, equipment and a storage medium. The method comprises the steps of obtaining an input feature representation for a first model layer in a machine learning model; generating a first feature tensor for the first model layer at least by processing the input feature representation with the first weight tensor in the processing unit; transmitting the input feature representation and the first feature tensor to a trusted execution environment; in the trusted execution environment, processing the input feature representation with the direction transformation parameter to generate a direction correction tensor; and in the trusted execution environment, correcting the first feature tensor based on the direction correction tensor to determine an output feature representation corresponding to the first model layer.

The invention provides an image processing method and device, equipment, a medium and a program product, and relates to the technical field of image processing. The image processing method comprises the following steps: carrying out linear transformation on an original grayscale image to obtain an initial grayscale image; performing gamma transformation parameter calculation on the initial grayscale image to obtain a first gamma transformation parameter; performing equal region division on the initial grayscale image to obtain a plurality of image blocks; for each image block, under the condition that the contrast ratio of the image block is greater than or equal to a threshold value, determining that the first gamma transformation parameter is the gamma transformation parameter of the image block; under the condition that the contrast ratio of the image block is smaller than a threshold value, the gamma transformation parameter of the image block is adjusted based on the first gamma transformation parameter, and a second gamma transformation parameter is obtained; determining the second gamma transformation parameter as the gamma transformation parameter of the image block; and performing nonlinear transformation on the initial grayscale image based on the gamma transformation parameter of each image block to obtain a target grayscale image so as to adjust the brightness of the original grayscale image.