116 results about "Difference-map algorithm" patented technology

The invention relates to a building prefabricated part quality detection method based on multi-modal vision. According to the method, multi-modal data including 2D image data and 3D point cloud data are obtained, an improved YOLOv8 model is used for performing defect coarse positioning on the 2D image data, defect parameters are calculated, defect areas such as cracks and exposed ribs can be quickly locked, and the parameters of the defect areas can be obtained. And by means of SIFT feature matching and ICP point cloud registration technologies, comparing with a two-dimensional template and three-dimensional geometric parameters of the BIM standard component model to obtain a two-dimensional registration difference chart and a three-dimensional deviation thermodynamic chart. And finally, according to the defect confidence coefficient, the two-dimensional registration difference chart and the three-dimensional deviation thermodynamic diagram, a preset dynamic weighting rule is adopted to carry out joint decision making, and a quality detection result is obtained. According to the method, through the multi-modal data, the improved YOLOv8 model, the point cloud registration technology and the preset dynamic weighting rule, the false detection problem can be effectively solved, the detection reliability and accuracy under the complex working condition are improved, and the quality management level of the building prefabricated part is improved.

A computer-implemented method can specify a source version and a target version of an application programming interface (API) and a target programming language; and retrieve a difference graph connecting from a source knowledge graph characterizing the source version of the API to a target knowledge graph characterizing the target version of the API. The difference graph includes one or more revision edges representing changes of the API between the source version and the target version. The method can install one or more function packages written in the target programming language and associated with the one or more revision edges; and run the one or more function packages to update the API from the source version to the target version.

The invention provides an urban green land invasion and occupation degradation identification system and method based on computer vision identification, and the method comprises the steps: collecting multi-temporal images of an urban green land, sorting the images according to timestamps, and generating a difference atlas to reflect the dynamic change of the green land; carrying out vectorization processing on the dynamic information, establishing a digital model as a reference standard of a greenbelt boundary, and carrying out superposition comparison with the latest remote sensing image to obtain a corrected greenbelt boundary; using the target detection network to identify a non-vegetation coverage area in the multi-temporal image, generating a preliminary green land invasion location map, then performing shape regularization and size filtering, and optimizing the green land invasion location map; and based on the optimization graph, time and space distribution characteristics of each factor are analyzed, prediction is carried out in combination with the change trend of the non-vegetation coverage area, and a trend prediction result is generated. And finally, carrying out quantitative evaluation on a prediction result, and generating a comprehensive degradation severity report. According to the invention, the identification efficiency and identification precision of urban green land invasion and degradation are improved.

The invention discloses a teaching course recommendation method and system based on English learning data, particularly relates to the field of semantic processing, is used for solving the problem of poor pertinence of a traditional English learning course, and comprises the following steps: aiming at systematic difference of native language and English expression on a syntactic structure, constructing a language structure difference map and extracting a structure offset label; the method comprises the following steps: performing dependency syntactic analysis on semantic consistent sentence pairs of multi-language aligned corpora to generate a structural difference feature set; on the basis, a semantic-grammar dimension mapping graph is constructed in a classified mode, and a general structure expression vector is established for graph nodes. A teaching course is divided into knowledge point units in combination with a context label, and a mapping relation between a structure label and the course is established. The system performs structure analysis and semantic matching on sentences input by the learner, identifies structure migration type expression errors, and recommends accurate teaching content according to context and structure labels.

The invention discloses a low-voltage distributed photovoltaic group dispatching and group control method and system based on multi-source information fusion, and relates to the technical field of photovoltaic group dispatching and group control, and the method comprises the following steps: obtaining the operation information of each photovoltaic node in a low-voltage power distribution network, and converting the operation information into a state vector; based on the state vector and a system optimization target, generating a photovoltaic group control instruction set, and establishing an expected physical behavior model; monitoring an actual behavior track of each node after the instruction is executed, comparing the actual behavior track with an expected physical behavior model to construct a response difference atlas, and quantifying response deviation; for nodes with response deviation, the difference type is judged according to a deviation map, a compensation instruction is generated by reconstructing a local optimization target based on a type matching correction strategy, and a correction path is output; and inputting the historical behavior deviation sample and the correction path into the graph structure time sequence learning model, and updating the node control weight and the regulation priority. According to the method, the response difference atlas is constructed based on the actual behavior track, and the control strategy execution deviation can be accurately recognized.

The invention discloses a government affair knowledge graph updating and version control method and system, and belongs to the technical field of artificial intelligence and knowledge graphs, Git-based file change drives incremental updating of knowledge graphs, and the method is implemented by the following steps: change monitoring: integrating Git version management; capturing file change through double modes of timing scanning and event triggering, establishing one-to-one mapping between a file Git version and a map version, and transmitting difference contents; difference preprocessing: standardizing difference contents into an analysis unit containing positions, types, original contents and updated contents, and filtering meaningless differences through a G-NF algorithm; constructing a difference subgraph; carrying out difference atlas fusion; and version control: storing version archives, and providing a multi-dimensional query tracing function. According to the method, version closed-loop management is achieved, change traceability is accurate and efficient, incremental atlas updating is achieved, total processing resource consumption is reduced, meanwhile, multi-scene version switching is supported, and repeated construction and maintenance cost is reduced.

The invention discloses a remote sensing image change detection method based on difference enhancement Swin Transform. The method comprises the following steps: firstly, constructing a backbone network based on a twin neural network architecture for extracting depth features of different levels of a dual-temporal remote sensing image; secondly, a difference enhancement module (DEM) is provided and used for enhancing difference feature learning between the dual-temporal remote sensing images on different levels; then, a Swin Transform module (STM) is introduced, global context information is modeled, and more change details are captured while a network acceptance domain is expanded; finally, a feature weight fusion module (FWFM) is designed to effectively aggregate the multi-level feature difference graph. An attention mechanism is integrated in the difference enhancement module provided by the invention, so that the difference feature expression of the dual-temporal remote sensing image can be effectively improved; meanwhile, the designed feature weight fusion module can effectively solve the problems of semantic loss, uneven contribution degrees of different levels of features and the like during remote sensing image change detection.

The invention relates to a heterogeneous remote sensing image change detection system and method based on a Mama model. The system comprises a feature extractor, a codec network and a change detector. The feature extractor is used for extracting first feature maps of an optical mode and an SAR mode respectively; the codec network is used for mapping and reconstructing the first feature map based on a Mama model to generate a second feature map of an optical mode and an SAR mode; the change detector subtracts the second feature maps of the same mode and calculates an L2 norm along the channel dimension, and weighted fusion is carried out on calculation results of the L2 norms of different modes, so that a difference map is obtained; the difference map processor optimizes the difference map based on a full-connection conditional random field method, and segments the optimized difference map into a varying region and a non-varying region based on an optimal threshold selected by an adaptive threshold segmentation algorithm. According to the method, a feature alignment process and difference chart generation are coupled into an end-to-end optimization task, and the problem of error accumulation caused by two-stage decoupling in a traditional unsupervised method is avoided.

The present application relates to a shield cutter health status assessment method based on Seq2Seq. After collecting data, the score of the time domain features is calculated for feature extraction, and the first 5% of the data is selected as a training set. All collected data is used as a test set, and the model is trained with the training set. The test set is then input into the GRU-based Seq2Seq model to output the difference, and a full life cycle degradation curve is drawn based on the difference graph. The wear state of the cutter disc is judged based on the full life cycle degradation curve. The present application can evaluate and predict the life cycle of the tool based on the tool wear mechanism to accurately control the timing of tool change.

The invention discloses a lightweight optical remote sensing image change detection method and system based on multi-scale perceptual learning, a storage medium and electronic equipment, and the method comprises the following steps: firstly, carrying out the preprocessing of a dual-time-phase optical image, marking a change region, and generating a label graph; then, the image and the label are cut into small samples, and the small samples serve as training data of an LCDNet model; according to the model, a lightweight encoder is adopted to extract a multi-scale feature map, a low-pass filtering down-sampling module reduces information loss, and a scale sensing block enhances the sensing ability of the model to different scale changes. And the multi-scale features are subjected to difference fusion through the spatio-temporal change perception module to generate a difference graph, efficient fusion decoding is realized through a learnable multi-scale decoder, and a final change graph is output. Model parameters are stored after training is completed, the preprocessed to-be-detected sample is input into the model, a detection change prediction map is output, accurate detection of a multi-scale change area is achieved while the parameters and the calculation amount are reduced, and the method is more suitable for actual deployment requirements.

The invention discloses a long function-oriented software supply chain vulnerability detection method, which comprises the following steps of: eliminating information irrelevant to vulnerabilities by applying a designed statement-level difference extraction algorithm on a pseudo-code level; secondly, utilizing a designed graph slicing algorithm to map pseudo code slices to a code attribute graph, identifying and positioning vulnerability-related statements and variable nodes thereof, tracing nodes which are semantically adjacent to variable nodes which are strongly correlated with vulnerabilities by tracking edges in an abstract syntax tree, and constructing a difference graph after slicing; afterwards, the difference graph is input into a graph matching neural network for training, so that the model can accurately judge the similarity of the difference sub-graph pairs between the vulnerabilities and the vulnerabilities after the vulnerabilities are repaired. Finally, whether the vulnerability exists or not is judged by comparing the distance between the to-be-detected function and the image obtained after the reference sample is sliced, the scale of the image is reduced, relevant information of the vulnerability is highlighted, and the time and hardware cost of model training are reduced while high detection accuracy is guaranteed.

The invention relates to the technical field of image recognition, in particular to an intelligent comparison recognition method and system for printed images, and the method comprises the steps: building a spatial position mapping relation according to a multi-dimensional feature set, and comparing various types of feature differences of corresponding positions to obtain a feature difference chart; according to a printing process parameter library, analyzing a characteristic offset rule of each difference area in the characteristic difference chart, and judging whether the difference is caused by printing pressure or ink supply fluctuation; and according to a historical defect case library, matching a difference mode of the feature difference chart, and identifying whether an abnormal difference caused by printing plate abrasion or paper deformation exists or not. According to the invention, through a mechanism of dynamically adjusting the feature matching weight, the feature similarity of the key area can be recalculated according to the cause labeling information detected in real time, so that the optimized feature difference graph is generated, the precision of the detection result is improved, timely feedback can be realized in the production process, and quality problem accumulation is prevented.

The invention provides a nameplate printing defect detection method and system based on image segmentation. The method comprises the following steps: acquiring a nameplate surface image and carrying out distortion correction and brightness homogenization preprocessing; generating a pixel-level segmentation mask by using the semantic segmentation network; template registration is carried out based on the segmentation result, and a deformation field vector and a registration difference chart are calculated; performing defect area extraction and type identification on the difference image; according to the method, deep learning semantic segmentation is adopted to realize pixel-level analysis of a nameplate printing area, deformation field registration is combined to accurately quantify overprinting offset, defect quantitative evaluation is realized through multi-dimensional scoring, the detection rate reaches 99% or above, and the detection time of a single piece is less than 0.5 second.

The invention discloses a cross-sensor remote sensing image unsupervised change detection method based on a structured graph auto-encoder, belongs to the field of computer vision and remote sensing image processing, and particularly relates to a cross-sensor remote sensing image unsupervised change detection method. The objective of the invention is to solve the problem of low cross-sensor remote sensing image change detection accuracy caused by difficulty in explicit modeling of semantic change and insufficient robustness to modal difference in an existing model. The method comprises the steps of 1, obtaining a source domain and a target domain; 2, obtaining a source domain graph structure and a target domain graph structure; 3, constructing a learnable structural difference tensor; 4, constructing a structured graph auto-encoder 1; 5, constructing a structured graph auto-encoder 2; 6, obtaining a trained structured graph auto-encoder 1 and a corresponding weight, offset and structural difference tensor; 7, obtaining a trained structured graph auto-encoder 2 and a corresponding weight, offset and structural difference tensor; and 8, obtaining a final difference chart.

A computer-implemented method can include generating a first knowledge graph from a first version of an application programming interface (API), generating a second knowledge graph from a second version of the API, identifying changes from the second knowledge graph to the first knowledge graph, and generating a difference graph based on the identified changes from the second knowledge graph to the first knowledge graph. The difference graph connects the second knowledge graph to the first knowledge graph via one or more revision edges, which represent the identified changes from the second knowledge graph to the first knowledge graph.

Although wedgelet-based partitioning seems to represent a better tradeoff between side information rate on the one hand and achievable variety in partitioning possibilities on the other hand, compared to contour partitioning, the ability to alleviate the constraints of the partitioning to the extent that the partitions have to be wedgelet partitions, enables applying relatively uncomplex statistical analysis onto overlaid spatially sampled texture information in order to derive a good predictor for the bi-segmentation in a depth / disparity map. Thus, in accordance with a first aspect it is exactly the increase of the freedom which alleviates the signaling overhead provided that co-located texture information in form of a picture is present. Another aspect pertains the possibility to save side information rate involved with signaling a respective coding mode supporting irregular partitioning.

The invention provides a food conveying detection method and device based on image recognition, and belongs to the technical field of food production detection, and the method comprises the steps: inputting target image data into a quality defect prediction model, and obtaining a quality defect probability value; if the quality defect probability value is greater than or equal to a preset threshold value, processing the target image data to obtain target data; the target data is matched with a plurality of reference images in a standard product template database, a plurality of similarities are obtained, and the reference images corresponding to different defect levels are stored in the standard product template database; and analyzing the target data based on the plurality of similarities and the difference atlas to obtain a detection result. According to the food conveying detection method and device based on image recognition, the reliability and efficiency of food quality detection can be improved.

The invention discloses a twin structure change detection method for SAM2-assisted multi-scale feature coding, and the method comprises the steps: constructing a twin network architecture based on a multi-level Hiera encoder, and extracting a multi-level feature map of a dual-time-phase remote sensing image through the architecture; a multi-branch convolution block is used for processing the multi-level feature map, and the weight is reduced and the dual-time-phase feature dimension is unified; generating a change region difference chart based on the multi-level features, enhancing the feature response intensity of a real change region in the change region difference chart of each scale, and obtaining a multi-scale feature difference chart; a target loss function of multi-scale feature difference graph joint prediction is proposed, a model training process is optimized by using a hierarchical constraint relationship among different scale features, and the detection capability of the model to a multi-scale change region is improved. The method can effectively improve the remote sensing image change detection precision, especially shows obvious advantages in the aspects of reducing small change leak detection and improving boundary positioning precision, and has a good practical application prospect.

The invention discloses an unsupervised change detection method for heterogeneous remote sensing images. Based on the domain conversion mode of Cycle GAN, the heterogeneous images are converted into the same feature space through a style transfer network, and a lightweight attention mechanism is added to the generator and the discriminator of Cycle GAN to accelerate the convergence of the model and effectively complete the conversion of the heterogeneous space. The lightweight attention mechanism realizes the effective conversion of the image space domain from low dimension to high dimension. Compared with other existing methods, under the condition of only adding a small amount of model parameters, a large amount of high-dimensional feature information is provided for generating a difference map. The Euclidean distance between dual-phase images in the same feature space is calculated channel by channel, which is called a feature difference matrix, and then the maximum value of the channel dimension is taken as the difference map. Finally, a change detection map is generated through a series of threshold calculations and denoising operations, thereby enhancing the accuracy and completeness of the generated change map and realizing the effective improvement of the change detection accuracy. In addition, the heterogeneous change detection framework proposed by the invention is unsupervised, thereby avoiding a large amount of time and energy spent on collecting labeled data in supervised learning.

The invention discloses an SAR (Synthetic Aperture Radar) image change detection method combining convolution and mixed attention. The SAR image change detection method comprises the following implementation steps of: firstly, generating a difference chart for two SAR images by using a composite neighborhood intensity difference method; then, a hierarchical FCM clustering algorithm is used for carrying out pre-classification processing on the difference image, a pseudo label matrix is generated, variable and invariable high-probability sample pixels in pseudo label pixels are selected, spatial positions of the pixels are extracted, and on the pixels of the corresponding spatial positions of the two original SAR images, a pseudo label matrix is generated; pixel blocks with the pixel points as the centers are taken as a training set, and pixel blocks with all the pixel points as the centers are extracted from the two original SAR images to serve as a test set; and then training a neural network combining convolution and mixed attention by using the training sample set, and then carrying out change detection analysis on a test set by using the trained network to generate a final change detection result graph. The method has clear advantages in the aspects of SAR speckle noise suppression and change detection precision.

A computer-implemented method can specify a source version and a target version of an application programming interface (API) and a target programming language; and retrieve a difference graph connecting from a source knowledge graph characterizing the source version of the API to a target knowledge graph characterizing the target version of the API. The difference graph includes one or more revision edges representing changes of the API between the source version and the target version. The method can install one or more function packages written in the target programming language and associated with the one or more revision edges; and run the one or more function packages to update the API from the source version to the target version.

Aspects of the invention include systems and methods configured to extract enriched target-oriented common sense from grounded graphs to support efficient next step decision making of an autonomous agent. A non-limiting example computer-implemented method includes extracting common sense from a source. The extracted common sense can include a first knowledge graph. An environment state can be extracted from an observation. The extracted environment state can include a second knowledge graph. The second knowledge graph can include an interactive object and a state of the interactive object. A difference graph including the extracted common sense and the extracted environment state can be generated. A next action is selected based on the difference graph and the next action is taken by an autonomous agent.

The present invention discloses a training method for a model for detecting image changes, including: obtaining a training sample image and preprocessing the training sample image; using a generator network to process the first training sample image to obtain a first category probability map; performing a heat map on the second training sample image to obtain a second category probability map; using the first training sample image and the second training sample image to obtain a difference map; respectively operating the difference map with the first category probability map and the second category probability map to obtain a first sample image and a second sample image; using a discriminant perception network to process the first sample image and the second sample image to obtain a discrimination result; using the discrimination result and the first category probability map, according to a loss function, optimizing the parameters of the generator network and the parameters of the discriminant perception network to obtain a trained generator network and a trained discriminant perception network. The present invention also discloses an image change detection method.

To provide an inspection device that can more accurately inspect the appearance of an object. [Solution] An inspection apparatus according to one aspect of the present disclosure includes: an acquisition unit that acquires an image of an object; a difference calculation unit that generates a difference map based on a comparison image which is an image of the object stored in advance and the image; a learning unit that generates a learning model that outputs the degree of abnormality of the object shown in the image in response to the input of the image by performing machine learning using a plurality of the comparison images; an abnormality calculation unit that generates an abnormality map for the object using the learning model; a coupling unit that generates a combined abnormality map based on the difference map and the abnormality map; and a determination unit that determines the state of the object based on the feature portion included in the combined abnormality map.

The invention relates to the technical field of software testing, and discloses an AI-based test demand analysis and use case generation method and system.The method comprises the steps that a new and old version demand document set is obtained, a corresponding logic flow graph is constructed, a logic increment difference graph is generated through graph isomorphism matching, and an overall influence area is determined; obtaining a stock test case set and mapping the stock test case set into a stock case path set, and executing path geometric deformation and expansion after an affected path is identified to generate a final evolution path; and finally, calculating the comprehensive energy loss of the evolution path, judging the evolution state of the use case, obtaining a final test use case set and establishing a use case evolution pedigree table. According to the method, activation and evolution of stock test assets are realized, and the maintenance cost of government affair software regression test is reduced.

The application provides a large model-based automatic code generation and optimization method and system. Among them, the application generates an initial logical framework by a large model, forms a symbolic structure through symbolic processing, and generates a code intermediate representation that retains key semantics, and finally outputs source code. An index set is constructed using a vulnerability knowledge graph, a source code instruction sequence is scanned through parallel computing, and risk instruction positions and vulnerability details are marked by combining semantic similarity and path pattern matching. Based on vulnerability information, a historical case database is retrieved, a matching relationship is established, and an optimization strategy containing repair operations and constraints is generated. A semantic analysis model is loaded at the risk position, a difference graph of execution mode is constructed to generate features, a large model parameter is fine-tuned based on the constructed adversarial sample, and the newly generated code is rechecked for vulnerabilities. The application realizes intelligent generation from requirements to code, and completes the loop of vulnerability identification, repair strategy generation, large model dynamic optimization, and post-repair verification.

The present application belongs to the field of structural health monitoring, and particularly relates to a method for detecting cracks in aircraft structures based on convolutional neural networks. Step 1: Construct a crack image dataset; Step 2: Train a YOLOv5 network using the crack image dataset to obtain a YOLOv5 model; Step 3: Construct a difference map dataset; Step 4: Obtain an improved YOLOv5 network, and train the improved YOLOv5 network using the difference map dataset to obtain an improved YOLOv5 model; Step 5: Perform an overall test on the image to be detected based on the YOLOv5 model and the improved YOLOv5 model. The present application can achieve efficient and reliable crack damage detection in fatigue testing of full-scale aircraft structures.

The present application provides a system and method for identifying encroachment and degradation of urban green space based on computer vision recognition, wherein the method includes collecting multi-temporal images of urban green space and sorting them by timestamp to generate a difference map to reflect the dynamic changes of green space; vectorizing the dynamic information, establishing a digital model as a reference benchmark for the green space boundary, and overlaying and comparing it with the latest remote sensing image to obtain the corrected green space boundary; using a target detection network to identify non-vegetation covered areas in multi-temporal images, generating a preliminary green space encroachment location map, and then performing shape regularization and size filtering to optimize the green space encroachment location map; based on the optimized map, analyzing the temporal and spatial distribution characteristics of each factor, combining the changing trend of the non-vegetation covered area to make a prediction, and generating a trend prediction result. Finally, the prediction results are quantitatively evaluated to generate a comprehensive degradation severity report. The present application improves the efficiency and accuracy of identifying encroachment and degradation of urban green space.

The invention relates to a generated image detection method based on texture complexity and difference feature focusing, and aims to detect and distinguish a generated image and a real image. The method mainly comprises the following steps: (1) providing a generated image detection model based on texture complexity and difference feature focusing; (2) providing a mask constraint-based directional feature difference chart generation method; and (3) providing a classifier structure based on image difference feature graph comparison.

Systems and techniques are described herein for processing image data. For instance, a method for processing image data is provided. The method may include predicting, using a machine-learning model, a difference map indicative of differences between a first image and a second image to generate a predicted difference map; determining a confidence map based on the predicted difference map; determining an error based on the confidence map and a comparison of the predicted difference map and a ground-truth difference map; and adjusting one or more parameters of the machine-learning model based on the error.