1198 results about "Spatial structure" patented technology

The invention discloses a BIM model feature extraction-based unmanned aerial vehicle intelligent inspection path generation method for the interior of a building. The method comprises the steps of extracting a spatial geometric feature set, a spatial topological feature set and a semantic feature set from original BIM model data; constructing a basic space graph representing a space structure and a semantic enhancement graph representing a function relationship based on the feature set, and generating a multi-level semantic graph; task targets and dependency relationships are extracted from the inspection task description and the multi-level semantic graph, and a task weight matrix is generated; generating an optimized path set based on the multi-level semantic graph and the task weight matrix; performing multi-dimensional scoring and real-time optimization on the optimized path set to generate an emergency adjustment strategy; and finally verifying the inspection path. According to the method, through multi-level feature extraction and multi-level semantic graph construction, accurate understanding of the building space is realized, and the intelligent level and reliability of routing inspection path planning are improved.

The invention provides a real-time face blind restoration method and device based on identity constraint and frequency domain enhancement, and relates to the technical field of image processing, and the method comprises the steps: S1, generating an identity code through the fusion of CLIP and ArcFace, extracting spatial structure features in combination with ControlNet, and obtaining a high-frequency component through the decomposition of learnable wavelets; s2, an input image is mapped to a potential space, and identity, space and high-frequency features are fused to construct a condition vector; s3, performing iterative denoising based on the consistency model, and superposing lightweight wavelet residual correction to enhance high-frequency details; s4, according to the high-frequency energy dynamic distribution weight, reconstructing a multi-scale fusion image through inverse wavelet transform; according to the method, the problems of identity distortion, detail loss and low calculation efficiency of a low-quality face image in restoration are solved, and semantic consistency, detail fidelity and real-time performance of a restoration result are improved through identity-space-frequency domain ternary constraint, lightweight residual correction and degradation perception enhancement.

The invention provides an intelligent real-time detection method and system for PCCP welding quality, and relates to the technical field of online detection and intelligent evaluation of pipeline welding quality through machine learning. Light energy data and multi-light-source images of a spiral weld pool are collected, exposure parameters are dynamically adjusted through the energy difference of visible light near-infrared bands, and the real-time detection of the PCCP welding quality is achieved. Inhibiting strong light interference and generating a weld surface image; a stress concentration area is positioned by scanning a welding seam thermal deformation area and combining speckle pattern change, sound frequency change and the elastic characteristic of the thin-wall steel cylinder; inputting the surface image and the deformation data into a space-time convolutional neural network, fusing light energy change, image details and spatial features to construct a weld joint space structure diagram, and adaptively correcting the position of a sensor; and comparing the sinking depth of the three-dimensional point cloud reconstruction, analyzing the correlation between the sinking degree and the stress, and generating a probability thermodynamic diagram to output the pressure-bearing failure risk level, so that the probabilistic early warning of the pressure-bearing failure risk can be realized.

The invention provides a fire early warning method and system based on three-dimensional modeling, and the method comprises the steps: determining the transaction indexes of fire danger at different space units through the spatial structure characteristics of a three-dimensional digital twin model in combination with the state evolution mode of a physical field, and determining a risk cloud picture through all transaction indexes; extracting a risk sub-domain of the fire according to the risk cloud picture, and further generating a heat flux density field matrix among different space units; determining risk fitting degrees of different space units by combining the heat flow diffusion information with the monitoring information of the fire behavior in the target building, and performing time sequence aggregation on the fire risk in the target building according to all the risk fitting degrees and the local temperature field of each space unit to obtain fire danger propagation potential energy; and performing fire diffusion situation monitoring on the target building according to the fire danger propagation potential energy, and outputting a fire diffusion early warning signal. By adopting the scheme of the invention, the diffusion track of the fire heat flow can be accurately identified in the three-dimensional model.

The invention discloses a point cloud registration method, system and device and a medium, and relates to the technical field of three-dimensional reconstruction of scenes, and the method comprises the steps: obtaining a source point cloud and a target point cloud; semantic segmentation is carried out according to spatial structure characteristics of the point clouds, and plane points and non-plane points of the source point clouds and the target point clouds are obtained respectively; two-way distance search constraints are applied to planar points and non-planar points in the source point cloud and the target point cloud respectively, and a corresponding relation of two-way matching constraints is established; point-to-surface registration and point-to-point registration based on the maximum correlation entropy criterion are carried out on the plane points and the non-plane points after bidirectional constraint, and rotation matrixes and translation vectors of the plane points and the non-plane points are respectively obtained through multiple iterations; weighting the rotation matrix and the translation vector according to an adaptive weight, and applying the weighted rotation matrix and translation vector to the source point cloud to obtain the source point cloud after pose transformation; according to the method, the nearest neighbor corresponding relation from the source point cloud to the target point cloud and from the target point cloud to the source point cloud is considered, and the matching accuracy of the corresponding points is improved.

The invention discloses a collaborative editing method and device for a rich text format document and a storage medium, and the collaborative editing method for the rich text format document comprises the steps: taking each document element of the rich text format document as a node, and taking the attribute of the document element as the semantic information of the node, constructing a semantic tree by taking the spatial structure relationship between the document elements as an edge; performing parameter updating on nodes in the semantic tree according to the editing operation; nodes which do not meet constraint rules in the semantic tree after parameter updating are detected, and semantic conflict nodes are obtained; and performing semantic conflict correction on the semantic conflict node according to a conflict resolution strategy to obtain a corrected rich text format document, and synchronizing the corrected rich text format document to all editing ends. According to the method, effective and accurate collaborative editing can be carried out on the rich text format document, conflict detection and solution are carried out on the semantic level, and the risk of semantic errors and rendering abnormity in the collaborative editing process is reduced.

The invention relates to the technical field of BIM building optimization, in particular to a BIM-based prefabricated building design construction optimization management system and method. The method comprises the following steps: acquiring a panoramic monitoring image of a building area and a construction design initial BIM model; carrying out regional space structure evolution and construction scene three-dimensional simulation on the panoramic monitoring image of the building region, and constructing a three-dimensional construction scene graph; identifying assembly type building component information according to the construction design initial BIM model so as to generate building component assembly demand characteristics; performing dynamic construction sequence simulation optimization on the three-dimensional construction scene graph and the construction design initial BIM model based on building component assembly demand characteristics, and constructing a dynamic optimization construction sequence; and carrying out available material transportation path analysis on the three-dimensional construction scene graph so as to generate an optimal operation path of each material. According to the invention, real-time collaborative management based on the BIM and the cloud is realized, the building construction quality is improved, and the construction design decision is optimized.

The invention discloses a space-time spectrum combined super-resolution reconstruction method based on a giant remote sensing satellite group. The method comprises the following steps: acquiring time series, multi-view and multi-spectral data of the same area from a plurality of heterogeneous satellites, and performing radiometric calibration and atmospheric correction; sub-pixel-level alignment of the multi-source data is realized by adopting a joint registration model; extracting time change features by using three-dimensional convolution, extracting space structure and texture features by using two-dimensional convolution, and extracting and reducing the dimension of spectral features by using one-dimensional convolution; performing adaptive weighted fusion on time, space and spectral features through an attention mechanism to generate a joint feature tensor; and carrying out super-resolution reconstruction to obtain a target image with high spatial resolution, high time resolution and high spectral fidelity. The method gives consideration to both resolution improvement and spectrum authenticity, and is suitable for high-precision remote sensing application scenes such as fine urban mapping, agricultural monitoring, ecological environment assessment, disaster emergency and battlefield situation awareness, remote reconnaissance, target change detection and damage assessment.

The invention discloses a multi-modal entity connection method based on data enhancement, which relates to the technical field of data processing, and comprises the following steps: enhancing entities by using a large language model, carrying out abstract processing on entity description through a design instruction, and extracting and optimizing key information; semantic information is enhanced by using a multi-modal large language model, enhanced information description is generated by fusing texts and visual features, and the enhanced information description comprises names, types, function and behavior features and physical or structural attributes of entities as well as spatial structures, appearances, color textures and other visual features extracted from the visual information; a candidate entity set is expanded and optimized through a retrieval technology, and retrieval enhancement is achieved; and performing decision selection by using a large language model, and selecting an optimal matching item from a candidate entity set obtained by retrieval enhancement. According to the method, through multi-level data enhancement and an accurate entity selection process, the accuracy and efficiency of multi-modal entity linking are remarkably improved.

The invention relates to the technical field of artificial intelligence, in particular to a spatio-temporal context extraction method and system for real world model training, and the method comprises the steps: extracting all image information and text semantic information through content feature vectors; structural information such as spatial layout of a scene and relative positions of people and objects in the collected image is extracted through the spatial structure feature vector, and feature information such as appearance, posture and action of a target object is extracted through the entity feature vector; obtaining a time sequence feature vector according to the content feature vectors, the spatial structure feature vectors and the entity feature vectors in a plurality of preset time periods, capturing multi-dimensional dynamic changes of the target physical place in a period of time, and analyzing the extracted vectors to obtain scene analysis feature data; all feature information is integrated to obtain the spatio-temporal context, the representation richness and comprehensiveness of the target physical place are improved, and the representation degree and adaptability of the real world model obtained through subsequent training to the target physical place are achieved.

The invention discloses a container number tallying identification method, and relates to the technical field of container intelligent tallying. According to the technical key points, the method comprises the following steps: deploying a multi-modal sensing device, carrying out initial calibration, and pre-training an improved YOLOv7-tiny target detection model, a transformer-based cGAN character segmentation model and a lightweight CNN-transformer-capsule network integrated hybrid recognition model; through cooperative collection of multi-modal data of the multi-modal sensing device, the system can effectively integrate texture information of RGB images, a space structure of depth images and three-dimensional coordinates of point cloud data, the problem that traditional single visual recognition is affected by illumination, shielding and the like is solved, a self-calibration mechanism corrects space-time deviation of a sensor in real time, and the accuracy of recognition is improved. The system can still accurately extract container number characteristics in complex scenes such as strong light reflection, low illumination at night, character abrasion and the like.

The invention discloses a warehouse-in and warehouse-out path planning system and method applied to stored goods, and relates to the technical field of intelligent storage. The method comprises the steps of establishing a three-dimensional space structure of a warehouse, generating a menu to be stored and matching various storage schemes, carrying out importance degree assignment and priority ranking on goods, calculating the residual space and the total weight of the warehouse, judging and optimizing the space and the weight, and planning and optimizing warehouse-in and warehouse-out paths. Through the mathematical planning method, the total cost is minimized, and the space utilization rate and the access efficiency are maximized. And meanwhile, the operation condition in the warehouse is monitored in real time, the in-out path and the in-out path are dynamically adjusted, and congestion and conflicts are avoided. In addition, a high-definition camera and a sensor are further installed, and safety management in the warehouse is ensured. According to the invention, intelligent warehouse-in and warehouse-out path planning of the stored goods is realized, the warehouse management efficiency and the space utilization rate are improved, and safe storage and efficient warehouse-in and warehouse-out of the goods are ensured.

The invention discloses an urban underground space structure health detection method and detection system, and the method comprises the steps: S1, collecting the multi-modal data of an underground space structure through the deployment of diversified sensors; s2, preprocessing the collected data, wherein the preprocessing comprises filtering denoising and feature extraction; s3, performing pattern recognition and health state evaluation on the processed data by using a deep learning model; s4, dynamically adjusting a threshold value of health assessment according to the environmental parameters, and predicting a future health trend; and S5, the evaluation result is displayed through a visual platform, a corresponding health examination report is generated, the health condition of the underground space structure can be monitored in real time by integrating multiple sensors and utilizing a data processing technology, potential problems can be found in time, an early warning threshold value can be dynamically adjusted according to real-time monitoring data through a dynamic threshold value adjusting mechanism, and the early warning efficiency is improved. The problems of false alarm and missing alarm caused by a fixed threshold value are avoided, and the accuracy and reliability of early warning are improved. The method is suitable for various underground space structures.

The invention discloses a distribution line unmanned aerial vehicle edge end real-time visual identification and target detection method and system based on lightweight AI. The method is based on a YOLOv8 architecture, and constructs a complete lightweight detection framework comprising a feature extractor, an enhancement module and a simplified detection head by introducing a space structure maintaining assembly, a separated large kernel convolution and a weighted reconstruction feature pyramid. A cross-dimension semantic relation model is constructed by utilizing a combined attention structure, multi-level feature fusion is realized by reconstructing a feature pyramid network, model training is performed by adopting a hybrid optimization function and a dynamic sample adjustment mechanism, and the model is deployed on a mobile computing platform after being optimized by a hierarchical knowledge transfer method. According to the method, the detection speed is remarkably increased while high precision is kept, and real-time identification and anomaly analysis of the power line element are effectively realized.

The invention provides a hyperspectral snapshot compression imaging method and system based on a space-spectrum prior decoupling model, high-quality reconstruction is realized through decoupling optimization and a deep expansion network, and the method comprises the following steps: constructing a training data set containing a compression measurement image and a corresponding reconstruction spectrum; establishing an objective function fusing space and spectrum prior, converting the objective function into constrained optimization, and converting the constrained optimization into three sub-problems of linear reconstruction, space prior and spectrum prior by adopting a semi-quadratic splitting method; a deep expansion network is designed to alternately solve sub-problems: a linear sub-problem is solved through analysis, and a space / spectrum sub-problem is subjected to implicit prior modeling through a private network, so that end-to-end reconstruction is realized; a mixed loss function is adopted to optimize model parameters, and images can be reconstructed in real time after training is completed. Space and spectrum prior decoupling is carried out, space structure details and spectrum features are respectively captured through an independent network architecture, the problem of mutual interference of joint modeling in a traditional method is solved, and high-quality spectrum image reconstruction is realized.

The invention relates to an underground assembly structure optimization method, equipment and a medium, and relates to underground space structure optimization. The method comprises the following steps: acquiring urban stratigraphic property related data; according to the urban stratum property related data and the use requirements of underground assemblies, on the basis of meeting preset design conditions and constraint conditions, traversing structural systems, component types and layouts in a pre-storage range, and constructing various underground assembly type structure design schemes; determining comprehensive anti-seismic capacity values of different underground assembly type structure design schemes; and determining an optimal underground assembly structure design scheme by adopting a preset multi-objective optimization algorithm according to the various underground assembly structure design schemes and the multi-objective optimization model. According to the method, the influences of stratum properties, use requirements and dynamic loads can be comprehensively considered, the reliability performance of the design scheme is accurately evaluated through systematic reliability analysis, and the safety risk is reduced; and the disaster resistance of the underground assembly in natural disasters such as earthquakes and the like is improved.

The present invention is an auxiliary hospital space design method and device based on a building energy consumption model, including: obtaining a natural language description of the initial hospital space layout diagram and functional requirements; extracting features from the space layout diagram and performing semantic analysis on the functional requirements description; inputting the spatial structure feature matrix into the energy consumption analysis model, combining the demand semantic vector, predicting the energy consumption performance of each functional area, and generating an energy consumption assessment diagram; obtaining an energy-optimized space design scheme based on the energy consumption assessment diagram and functional requirements; and simulating and verifying the energy-optimized space design scheme. The present invention realizes the intelligentization, optimization, and dynamic adjustment of hospital space design by integrating advanced technologies such as multimodal deep learning, generative adversarial networks, building energy consumption simulation, adaptive optimization algorithms, and multi-objective decision support systems.

The invention belongs to the technical field of display design evaluation, and particularly relates to an exhibition display layout design effect analysis and evaluation method, which comprises the following steps of: constructing a dynamic spatial topology network by collecting audience moving tracks, exhibit information and spatial structure data in real time; the problem of insufficient attention on space utilization influenced by dynamic factors such as human traffic fluctuation is solved. And dynamic changes in the space are converted into quantifiable network nodes and connection relationships, so that the space utilization state is changed from static design to dynamic monitoring, accurate capture of the real-time use condition of the exhibition space is realized, a comprehensive and real-time data basis is provided for subsequent analysis, and the real-time monitoring of the exhibition space is realized. Meanwhile, the dynamic space topology network is analyzed by means of spatial-temporal feature fusion to determine the edge weight and the exhibition area correlation degree, the spatial efficiency index and the dynamic line rationality index are generated in combination with an analytic hierarchy process and multi-dimensional analysis, and the defect that a space utilization rate core evaluation index is not established in the prior art is overcome.

The invention relates to the technical field of artificial intelligence, in particular to a sheet part performance rapid prediction method based on deep learning, which comprises the following steps: collecting multi-working condition simulation data to generate a training sample, constructing and coding a grid topological structure to extract multi-dimensional features, and inputting a perceptron to predict stress and evaluate errors after feature fusion and self-attention mechanism processing. According to the method, a structured training sample set is constructed by introducing simulation information, a geometric structure feature set is formed by combining node space coordinates, boundary constraints and a connection relation, so that mutual positions and constraint conditions among nodes are completely expressed in a graph structure, and through node-level feature extraction and feature fusion processing, a graph structure is obtained. According to the method, deep embedding of node geometric layout and boundary interrelation is realized, learnable expression of a stress evolution path in a space structure is established through local subgraph and context analysis, a multi-layer feature aggregation and attention mechanism is introduced in a node graph embedding process, and feature response expression of a key area is enhanced.

The invention relates to the technical field of medical image analysis, computer vision and deep learning, in particular to a texture perception and multi-scale feature adaptive fusion hip joint osteophyte detection method. According to the method, firstly, a bone texture feature extraction module is used for carrying out feature extraction and enhancement on a hip joint X-ray image, a parallel double-branch structure is adopted, gradient and space structure features are extracted through a Sobel operator and pooling operation, and feature maps are fused; then, the fused features are input into a double-backbone network, the first backbone network extracts local fine textures and long-range dependence features by combining convolution, self-attention and a gating mechanism, and the second backbone network extracts multi-scale semantic features through hierarchical grouping and depth separable convolution; and double-trunk output is dynamically weighted and fused through an adaptive fusion module, features are optimized through a multi-scale semantic fusion module, and finally the position and confidence of osteophyte are output.

The invention provides a digital twin three-dimensional model construction method based on a generative large model, and the method comprises the steps: obtaining multi-source monitoring data of a power distribution network, and processing the multi-source monitoring data into a training data set; the method comprises the following steps: mapping multi-source monitoring data into a multi-scale tensor subspace through tensor wavelet structured transformation, adaptively extracting spatial features through a learnable wavelet kernel, and keeping the structural continuity of a physical field in combination with a geometric prior regular term; constructing and training a generative adversarial network through a training data set; inputting and analyzing the physical parameter vector of the target scene, and if the topological similarity score is lower than a preset threshold value, adjusting noise vector regeneration; and if yes, outputting a three-dimensional model tensor and importing the three-dimensional model tensor into a digital twin platform, and driving real-time physical field visualization. According to the method, characteristics of a multi-scale space structure and a nonlinear physical field can be reserved, the physical rationality and generalization ability of the generated model are remarkably improved, and depth identification of topological attributes (such as hole connectivity and surface defects) and local geometric defects of the three-dimensional model is realized.

The invention discloses a wheat organ three-dimensional point cloud segmentation method based on dynamic voxel and category perception. Three-dimensional reconstruction is carried out on a wheat sample based on a three-dimensional Gaussian splash method, and dense point cloud data are obtained; performing data amplification on the dense point cloud data by adopting a dynamic voxel rasterization random sampling method combining dynamic voxel division and a random farthest point sampling strategy, and performing standardized point cloud quantity processing to obtain a standard point cloud data set; and based on the standard point cloud data set, carrying out key organ segmentation by adopting a category perception segmentation network. According to the data enhancement method, key geometric features are maintained while data diversity is expanded, a feature extraction module of the category perception segmentation network solves the problem of ignoring important points during sampling by fusing DCA and a weighted farthest point sampling strategy, and an improved loss function combining a point cloud space structure and information is adopted to improve the accuracy of data enhancement. And the segmentation precision of the wheat complex point cloud data is effectively improved.

The invention provides a training method of a live pig key point detection model and a body size measurement method and device.The training method of the live pig key point detection model comprises the steps that key point labeling is conducted on live pig point cloud data, and multiple key points are obtained; calculating geodesic distances between each point in the live pig point cloud data and the manifold structures corresponding to the plurality of key points, and performing Gaussian smooth mapping on the plurality of geodesic distances to obtain a key point heat map; determining a target loss function based on the key point heat map and the mean square error loss function; and performing regression training on the PointNet + + network by taking the live pig point cloud data as a training sample and the target loss function as a training loss function to obtain a live pig key point detection model. According to the method, the surface morphology and space structure information of the point cloud are fully utilized, multiple features such as the position, the normal vector and the curvature are fused, accurate detection of the semantic key points is achieved, and the live pig key point detection efficiency and accuracy are improved.

The invention relates to a cultural relic pattern recognition method and device based on an attention mechanism and a graph convolutional network. According to the method, the semantic representation of the image is effectively enhanced by introducing an attention mechanism, so that the model can more accurately capture the key features of the pattern. Meanwhile, in combination with the graph convolutional network, the nonlinear semantic association relationship between the local features of the pattern is further deeply mined, so that finer feature extraction and characterization are realized. In the optimization process of the model, the introduction of an attention mechanism not only improves the accuracy of recognition, but also enhances the distinguishing ability of the model to complex backgrounds and similar patterns. Besides, the spatial structure information in the image can be effectively processed by using the image convolutional network, so that the recognition of the cultural relic pattern has higher robustness and stability.

The invention provides a cloud condition adaptive geostationary satellite sea surface temperature inversion method based on deep learning, and relates to the technical field of sea surface temperature inversion, and the method specifically comprises the steps: obtaining geostationary satellite observation data, geographic information data, polar orbit satellite sea surface temperature and cloud products, and analyzing the sea surface temperature and atmospheric background data; performing standardization preprocessing on the obtained stationary satellite observation data; constructing a cloud detection data set; a cloud detection model of deep learning is constructed and trained; constructing a clear sky data set; a clear sky inversion model of deep learning is constructed and trained; constructing a data set for under-cloud inversion model training; constructing an under-cloud inversion model of deep learning and training the under-cloud inversion model; and integrating the cloud detection model, the clear sky inversion model and the under-cloud inversion model, adaptively calling the corresponding model according to a real-time cloud detection result, and generating a final sea surface temperature product. According to the technical scheme, the problem that in the prior art, the accuracy of a reconstructed product on the spatial structure cannot be comprehensively reflected is solved.

The invention discloses a rolling bearing vibration signal multi-mode fault classification method. The method comprises the following steps: collecting a vibration time sequence signal of a rolling bearing; the vibration time sequence signals are input into a time sequence branch network and a space branch network in parallel, and the time sequence branch network extracts time sequence dependence characteristics of the signals through a one-dimensional convolutional neural network and a bidirectional gating circulation unit; the spatial branch network converts the vibration time sequence signal into a Markov transform field image, and extracts spatial structure features of the image by using a two-dimensional convolutional neural network and a window Transform-based visual network; performing bidirectional interaction and weighted fusion on the time sequence features and the spatial features through a cross-modal attention mechanism to obtain fusion features; and inputting the fusion features into a classifier, and outputting a fault classification result of the rolling bearing. According to the method, the problems that a traditional single-mode fault diagnosis model is insufficient in adaptability to complex working conditions, multi-mode feature fusion is insufficient, and the generalization ability is weak due to model structure redundancy are solved.

The invention discloses a robust point cloud registration method and system based on global spatial perception and multistage filtering. The method comprises the following steps: respectively obtaining point cloud initial features and spatial structure features of global spatial perception based on point cloud information; inputting the point cloud initial features and the spatial structure features into a transform network for feature enhancement, and obtaining enhanced features; and performing up-sampling processing and multi-stage filtering on the enhanced features to obtain a transformation matrix, and completing point cloud registration. According to the method, global spatial perception and multi-stage filtering are introduced, so that abnormal values can be effectively eliminated while feature matching is completed finally, and the precision and efficiency of point cloud registration are improved.

The invention relates to the technical field of gesture recognition, in particular to an air gesture action intelligent capture and interactive data processing method and system.According to the air gesture action intelligent capture and interactive data processing method and system, significant jumps are marked through timestamps, time sequence deconstruction of action streams is achieved, nonlinear alignment processing of time structures between paragraphs is introduced, and the time sequence deconstruction efficiency is improved. The fragment consistency recognition capability under the conditions of unequal action durations and different rhythms is remarkably improved, spatial topology among three points is modeled by adopting a graph structure, a graph convolutional network is introduced to process dynamic changes of connection relations among different nodes, the continuity and stability of structure judgment can be kept under a shielding or structure deformation scene, and the recognition efficiency is improved. Through a triple constraint mechanism of direction vector included angle amplitude, length ratio and slope fluctuation, the action is subjected to modeling support in three aspects of time dimension, space structure and direction continuity at the same time, and the dynamic stability of gesture recognition and the resolution precision of paragraph judgment are enhanced.

The invention discloses a lodging winter wheat spatial distribution extraction method based on bimodal feature fusion, and relates to the technical field of agricultural remote sensing monitoring, and the method comprises the steps: building a double-flow semantic segmentation network DMFCFNet, and training the network through employing a constructed sample data set, inputting the preprocessed remote sensing image and the DSM elevation image into a network in parallel to obtain semantic texture feature information of the remote sensing images with different scales and spatial structure feature information of the DSM elevation image; and performing feature correction and fusion on the obtained semantic texture feature information of the remote sensing image and the spatial structure feature information of the DSM elevation image, and performing segmentation prediction on the fused feature information to realize extraction of the spatial distribution information of the winter wheat lodging region. By correcting and fusing remote sensing image semantic texture features and DSM elevation features and combining multi-scale information aggregation processing, the winter wheat lodging region extraction precision is effectively improved, and the problems of small target missing detection and boundary blur are solved.

The invention provides a room decoration style migration method based on semantic and style information guidance. The method comprises the following steps: firstly, extracting semantic analysis features of an original room picture, then taking the original room picture, a reference style picture and the semantic analysis features as training samples together, and taking a room picture with a changed style as a label to construct a training set; a room picture feature and a reference picture feature are extracted by using a generator network, a normalization process is adjusted by using the reference picture feature through a double-branch normalization module to obtain space structure information and texture detail information, and a room image with a reference style is finally output through AFF feature fusion. And a discriminator network is used to discriminate the generated image by taking the label as a reference, and network training is completed. And finally, inputting the original room picture, the semantic analysis characteristics of the original room picture and the reference style picture into the trained generator network, generating a room image with a reference style, and completing decoration style migration.