128 results about "Spatial interaction" patented technology

The invention provides a space interaction accurate recognition method and system based on multi-modal fusion, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting human skeleton, visual image and voice information, generating a space-time attention map through employing a feature extraction network, enhancing visual features, and executing feature complementary correction. Fusing the three types of modal information to obtain unified feature representation; when the recognition confidence is low, the space-time convolution generative adversarial network guided based on the action causal relationship graph complements the missing image frame, and the accuracy and robustness of space interaction recognition are improved.

The invention discloses an intestinal cancer immune response graph neural network prediction method, a medium and equipment, and the method comprises the steps: collecting pathological image information, immunodetection information and basic clinical information, extracting a tissue space distribution characteristic spectrum through a deep convolutional network, and constructing a graph neural network model in combination with an immunomarker expression characteristic matrix; spatial interaction characteristics of a tumor microenvironment are modeled by adopting a graph attention mechanism, finally a treatment response probability, an optimal treatment opportunity and an adverse reaction risk are predicted through a multi-task learning framework, and a clinical decision report containing a prediction response curve, a risk early warning threshold and a treatment time window suggestion is output. According to the method, through multi-modal data fusion and spatial interaction modeling, accurate prediction of intestinal cancer immunotherapy response is realized, and a more comprehensive reference basis is provided for clinical decision making.

The invention provides a pedestrian trajectory prediction method based on window attention and a space diagram interaction network, and belongs to the technical field of computer vision. The technical problems of difficult long-time dependence modeling and complex space interaction are solved. According to the technical scheme, the method comprises the following steps: S1, acquiring data of a data set; s2, in the time dimension, designing a window mask mechanism, and adjusting the attention receptive field at each moment; s3, constructing a hierarchical heterogeneous graph convolutional network according to a spatial dimension, and combining a pedestrian dynamic interaction graph with a scene static semantic graph; and S4, inputting the time dimension features and the space dimension features into a multi-scale expansion convolutional network to generate a multi-modal trajectory. The method has the beneficial effects that the model is subjected to experimental verification on a public data set ETH / UCY, the experimental result proves the effectiveness of the model, the superior performance of the model is shown on key indexes, and the generalization ability in processing different scenes is also excellent.

The invention relates to a vehicle trajectory prediction method and system fusing large kernel convolution and an attention mechanism. The system comprises an encoder module, a multi-head space attention module, a large kernel convolution pooling module, a convolution modulation module, an intention recognition module and a decoder module. Spatial interaction between a target vehicle and surrounding vehicles is modeled through a multi-head spatial attention mechanism. Meanwhile, an LKCP module, an intention recognition module and a CM module are creatively introduced. Wherein the LKCP module can additionally consider space interaction among surrounding vehicles, and the space interaction modeling capability among the vehicles is further enhanced; the intention recognition module deduces the maneuvering category of the vehicle based on the historical state information of the vehicle, and provides a basis for multi-modal trajectory prediction; and the CM module further captures the time dependence between moments in the historical trajectory of the target vehicle on the basis of the LSTM, so that the capture of the hidden state of the time dimension is enhanced. And multi-modal trajectory prediction of the target vehicle is realized.

The invention provides an anomaly detection method and device based on adaptive multi-scale feature modeling, and relates to the technical field of data anomaly detection. The method combines time component decomposition and a gating network, and allocates suitable expert networks for data on different time scales. In an expert layer, a deep convolutional network and a cross-time-slice attention mechanism are utilized to mine mutual relations in different time periods and among the different time periods in a time sequence. Then, combining a graph structure, and modeling spatial interaction characteristics among variables; and finally, learning the potential representation of the data to generate reconstruction data, and calculating a reconstruction error and the KL divergence of a potential space to carry out model training, thereby carrying out efficient anomaly detection under an unsupervised condition. According to the method, the precision of anomaly detection in the industrial control system is improved, a more flexible and accurate anomaly detection tool is provided for practical application, and the method adapts to complex dynamic changes of time sequence data in the industrial control system under the condition that no label data exists.

The invention discloses an intelligent construction site construction risk early warning system and method based on a BIM technology, and relates to the technical field of the Internet of Things. Multi-dimensional data of the field environment, structure, equipment and personnel are collected through a multi-source sensor network and are preprocessed; mapping the data to a BIM model, analyzing a spatial interaction relationship among personnel, machinery and environment by using a space-time diagram neural network, and identifying a periodic risk through an autocorrelation algorithm; calculating an index weight in combination with a dynamic weight distribution algorithm, and constructing a risk value calculation model; risk levels are analyzed and judged according to three conditions that personnel are at a mechanical operation position, under mechanical operation and no personnel are on site; a grading response strategy is adopted according to the risk grade; and optimizing an early warning threshold value through a threshold value judgment algorithm and an LSTM model by using a block chain evidence storage risk event, and iteratively updating a prediction algorithm.

The invention discloses a fine-grained zero-sample medical image classification method based on cross-modal feature alignment, and the method comprises the steps: 1, carrying out the partitioning of a full-section pathological image, and extracting the features of a local image block; 2, a cross-modal alignment module is used for designing a local window attention mechanism to enhance space interaction between image blocks; the semantic enhancement module is used for constructing a pathology prompt template based on a large language model to generate fine-grained category description, and expanding the distance between categories in a semantic space; and 4, performing weighted fusion on the image block features through coordinate sensing, and generating final slice-level classification prediction. According to the invention, through multi-scale space interaction of the cross-modal image block alignment module and semantic enhancement of the semantic refinement module based on the visual language model, the classification precision of the fine-grained medical image is significantly improved, and the limitation of the existing method on feature alignment and semantic differentiation is effectively solved; and an efficient solution is provided for zero-sample medical image classification.

The invention provides a self-supervised group behavior recognition method and system based on global and local comparative learning, and the method comprises the steps: extracting individual features through local branches, generating a soft mask by employing a multi-head self-attention mask module, separating significant / non-significant individual features through mask pooling, constructing a comparison sample, and carrying out the recognition of a group behavior through the comparison sample; feature alignment is optimized in combination with cosine similarity and local contrast loss; meanwhile, the spatial interaction relation of the behaviorists is captured by utilizing the spatial global Transform of global branches, short-term action and long-term behavior modes are fused through multi-scale time sequence coding, the consistency is optimized by adopting global comparison loss after spatial and temporal characteristics are aggregated, and finally, the two branch characteristics are integrated through global-local comparison loss for comparison, so that the accuracy of the behavior behavior is improved. And the loss weight is automatically adjusted to simplify parameter adjustment. After training is completed, a group behavior recognition result is output through the classifier according to the extracted spatial-temporal features, and the discrimination ability and robustness of the model to complex group behaviors are effectively improved.

The invention discloses a holographic projection system based on an AI large model. According to the invention, through the nano-scale optical coating and environment self-adaptive adjustment technology, harmful blue light is effectively filtered, environment light parameters are dynamically matched, the problem that eyes are injured by a common screen is solved, and the method is especially suitable for long-time learning scenes of children. The holographic projection core module adopts a naked eye 3D light field technology, presents complex models such as dinosaur, marine organisms and the like in a three-dimensional suspension manner through high-fidelity color restoration and dynamic depth-of-field adjustment capability, and is matched with gesture touch control and voice instructions of multi-mode interaction hardware, so that a user can directly touch a virtual object, and the real-time performance of the virtual object is improved. Experience upgrading from plane observation to space interaction is achieved, and knowledge such as English learning and animal and plant cognition is converted into interactive games and story narration through virtual teacher images and scene scripts. The autistic children can complete social dialogue training under the guidance of the virtual role, the system analyzes emotion fluctuation in real time and adjusts a guidance strategy, and social fear is gradually eliminated.

The invention discloses a cross-subject electroencephalogram emotion recognition model training method, a cross-subject electroencephalogram emotion recognition model training system and a cross-subject electroencephalogram emotion recognition method based on spatial interaction characteristics. The model training method comprises the step of providing an electroencephalogram signal emotion recognition method in combination with differential warm-up learning (DWL), a high and low frequency window (HFLFW) and a space interactive Colmogov-Arnod network (SIK). Firstly, electroencephalogram signals are converted into electroencephalogram feature maps through three-dimensional mapping, then a model is warmed up before training through differential warm-up learning, and the ability of distinguishing physiological differences of subjects is learned in advance. And processing local refinement and global structure features of the electroencephalogram feature map through high and low frequency windows respectively. And finally, capturing spatial interaction characteristics of electroencephalogram signals of different channels among different testees through a spatial interaction KAN so as to enhance the modeling ability of the model for different electroencephalogram modes.

The invention discloses a quick video generation method and system based on structured space-time sparsity, and belongs to the field of computer vision and artificial intelligence. According to the method, an inherent structured and heterogeneous sparse mode of an attention matrix in a video diffusion model is systematically analyzed and revealed, and the core of the method is as follows: 1) a self-adaptive partitioning strategy is adopted, and various spatial interaction modes are approximated through dynamic image block grouping; 2) dynamically adjusting the sparse level of a window with time sequence change according to the inter-frame distance; and 3) automatically configuring a search algorithm, and optimizing a sparse mode while keeping a key attention path. The sparse attention mask optimized through offline pre-calculation is directly applied to attention calculation in a reasoning stage, so that 1.8-2.5 times of attention calculation acceleration is realized on a single GPU while the visual quality equivalent to a full attention baseline is kept, and a brand new solution path is provided for efficient long video generation.

The invention provides a collaborative decision-making method and device for multiple automatic driving vehicles, and the method comprises the steps: obtaining and analyzing a traffic scene, so as to obtain the scene features of the traffic scene; based on a first neural network and the scene feature, encoding the scene feature to obtain scene feature encoding information; generating a scene graph structure according to the motion information of the plurality of vehicles and the interaction relationship among the plurality of vehicles; based on a second neural network and the scene graph structure, determining spatial interaction information among the plurality of vehicles, the second neural network being a graph neural network GCN; and determining a cooperative driving strategy among the plurality of vehicles according to the scene feature coding information and the space interaction information. According to the scheme, the collaborative decision-making process of the multiple automatic driving automobiles is optimized.

The invention provides a multi-feature trajectory prediction and cross-defense early warning method for edge and coast defense control objects, relates to the technical field of trajectory prediction and intelligent control, and solves various limitation problems of poor trajectory continuity, lack of environmental constraints and the like of an existing trajectory prediction technology in edge and coast defense scenes. The method comprises the following steps: firstly, acquiring multi-channel monitoring video data, performing environment adaptation preprocessing, and detecting each target and category; based on a detection result, splicing the track fragments in the single-path monitoring range, and obtaining global track data of the target after preset constraint inspection; extracting features of the global trajectory data from a plurality of preset dimensions, and performing feature fusion to obtain high-dimensional vector representation of the target trajectory; and constructing a multi-dimensional feature constraint trajectory prediction model, respectively modeling through time dependence and space interaction, and outputting a subsequent trajectory of the target under a preset constraint. The method can effectively realize prediction and cross-defense risk identification of future trajectories of key control objects, and is applied to the field of public security.

The invention provides a historical and cultural block spatial evolution simulation method and system based on GIS space-time analysis, and the method comprises the steps: firstly obtaining a target space-time data set of a target block, which comprises geographic space distribution, building form change, humanistic activity tracks and the like, and then carrying out the preprocessing of a space-time topological structure; generating a target spatio-temporal topological data set containing a spatio-temporal association block space unit sequence and a dynamic attribute tag, and then extracting a static structure, a dynamic evolution mode and a space interaction dependency feature of each space unit based on a preset spatio-temporal evolution feature extraction model; and calling a space-time evolution prediction model to obtain evolution probability distribution and evolution association strength, and finally constructing a space-time evolution path map according to the evolution probability distribution and the evolution association strength, thereby generating a spatial form simulation result and planning intervention decision parameters of a target block, and realizing effective simulation and planning decision support for spatial evolution of historical and cultural blocks.

The invention relates to a multi-view three-dimensional human body posture estimation method and system based on double-flow space-view-time sequence modeling. The method comprises the following steps: inputting a multi-view multi-frame image sequence, and performing human body detection and cutting; performing two-dimensional human body posture estimation on the input image at each view angle and each frame, and extracting image features; constructing an image-attitude bimodal alignment expression; sequentially executing sequential modeling of intra-visual space interaction, cross-visual-angle interaction and intra-visual time interaction on the image flow representation and the attitude flow representation in the same layer to obtain attitude flow fusion features; performing regression on the attitude flow fusion features by using a three-dimensional regression head to obtain three-dimensional skeleton coordinates; training the three-dimensional skeleton by adopting supervised learning; and inputting a to-be-estimated image sequence into the trained model and the regression head to obtain a three-dimensional human body posture estimation result. According to the method, the precision, robustness and deployability of three-dimensional attitude reconstruction can be remarkably improved under the condition of not depending on camera calibration parameters and human body priori.

The invention relates to the technical field of dangerous rock monitoring, in particular to a dangerous rock monitoring system and a risk assessment method thereof. According to the method, environmental factors such as wind speed and vegetation are accurately modeled by introducing the graph convolutional neural network, the limitation of a traditional wind power calculation model is overcome, and the influence of wind power tension is corrected, so that the stability of the rock mass is more accurately evaluated; by introducing a dynamic adjustment mechanism of an environment change coefficient and a vibration propagation coefficient, changes of environment factors such as temperature, humidity and rainfall can be adapted in real time, and the adaptability and precision of the model are improved; besides, spatial interaction and dynamic effect among rock mass units are considered, an instability propagation equation is established, and a rock mass instability propagation process is captured, so that physical attributes, spatial interaction and environmental change of the rock mass are comprehensively considered, and more accurate and real-time instability prediction is provided. And effective risk early warning and emergency decision-making assistance are provided for projects such as mining and slope construction.

Audio mixed reality devices and systems that may enhance, diminish, or modify real-world sounds, such as by overlaying audio streams onto real-world sounds or by combining audio streams with real-world sounds. The audio mixed reality devices and systems may enable presence in the real world, immersion in audio streams, or focus on real-world sounds. Immersive spatial audio scenes may be layered over or otherwise used to modify real-world sounds. An audio mixed reality device may capture and reproduce real-world sounds such that they appear spatially situated in the user's environment. The resulting auditory experience may ensure that real-world sounds maintain their natural origin points, thereby providing an acoustic foundation upon which audio streams can be overlaid or modulated without disorienting the user. By dynamically reconstructing a spatial representation of the external environment, the audio mixed reality device may facilitate the contextual and spatial interaction of audio streams with real-world sounds.

The invention relates to the technical field of laser scribing, and discloses a laser scribing planning method, device and equipment and a storage medium, and the method comprises the steps: carrying out the kinematics and laser-material interaction dynamics modeling of a dual-light-path laser system, and carrying out the preprocessing of historical scribing data, and obtaining a preprocessing time sequence data set; inputting the preprocessed time sequence data set into a time feature extractor to execute time dynamic feature extraction of the historical lineation trajectory to obtain a time feature vector; calculating spatial interaction features between the double optical paths to obtain spatial feature vectors; inputting the time feature vector and the space feature vector into a mixed density network, and establishing a material response probability model; and based on the material response probability model, performing layered optimization on a lineation path to obtain an optimal control parameter sequence of the dual-optical-path laser head. According to the invention, the global optimization of the double-light-path laser scribing path is realized, the scribing quality and efficiency are balanced, and the scribing positioning precision is improved.

The invention discloses a remote sensing image segmentation method based on semantic space interaction and edge guidance, which relates to the field of remote sensing image segmentation, and comprises the following steps: carrying out multi-level standard convolution block processing and semantic space interaction module processing on a preprocessed remote sensing image by utilizing a feature extraction network, extracting basic features, and carrying out semantic space information decoupling; and outputting multi-layer enhanced features, performing multi-level standard convolution block and up-sampling processing on the features through a feature fusion network, fusing the features through jump connection and combining a classification head to output a segmentation probability graph. According to the method, feature expression is enhanced through semantic space interaction decoupling, boundary recognition is enhanced through an edge supervision mechanism, and multi-scale fusion and joint loss optimization are carried out, so that the segmentation precision and boundary coherence of the remote sensing image in a complex scene are remarkably improved.

The present invention discloses a trajectory prediction method and device based on a dual attention mechanism. The method includes: obtaining trajectory data of multiple targets in an observation area in the previous time period; constructing graph structure data, in which nodes and targets correspond one to one; the graph attention network module is configured to extract spatial interaction information between targets and update node features of the graph structure data based on the spatial interaction information; the temporal attention network module extracts temporal interaction information from the updated target features and obtains the predicted trajectory of the target in the next time period based on the extracted temporal interaction information. The fusion of spatial interaction information and temporal interaction information is realized, that is, spatiotemporal interaction information is obtained, which can more effectively model and predict the motion pattern of targets in traffic scenarios to obtain better target trajectory prediction results, and can predict multiple target trajectories in parallel to speed up trajectory prediction.

The invention discloses a transform-based video behavior recognition algorithm. The algorithm comprises the following steps: S1, carrying out skeleton key point feature extraction, 3D convolution and down-sampling on video frames in an input video clip; s2, performing image pre-training vit block construction on a feature layer obtained by down-sampling, and performing local and global modeling through a corresponding space unification module and a time sequence unification module; s3, performing multi-level fusion on space and time sequence information features, and then sending the space and time sequence information features and skeleton key point feature information extracted by the pose formerV2 into a multi-feature fusion module for feature information fusion; and S4, the fused feature information passes through a non-training pruning module. According to the training-free pruning unified convolution and self-attention Transformer model framework, Vits space interaction capability is pre-trained, so that the Vits space interaction capability can be fully utilized and reserved in a space unified module, and the space modeling capability of PSUformer is enhanced; the hierarchical time sequence interaction in the efficient time sequence unification module can be flexibly used for enhancing the time sequence modeling capability.

The invention relates to the technical field of risk prevention and control, in particular to an electric power engineering construction site safety management method and system, and the method comprises the following steps: analyzing the spatial relation between constructors and high-voltage cable laying points based on the positioning and operation paths of the constructors, screening and adjusting path nodes, and judging the distribution of abnormal resident personnel; and dynamically evaluating the working condition risk level by combining the regional personnel density and the meteorological change, and adjusting the risk level of the operation region. According to the invention, through fusion of space positioning, path behaviors, risk monitoring and meteorological data, dynamic capture of operation behaviors and environment changes, combination of path space optimization and resident behavior screening, active perception of a space interaction relationship between personnel and a risk area, linkage of personnel distribution and extreme meteorology, continuous identification and linkage judgment of risk characteristics are realized, and the risk characteristics can be identified more accurately. And the partition risk levels are updated in real time according to operation behaviors and environmental conditions, and the field risk data linkage breadth and depth are enhanced.

The invention relates to the technical field of computer vision, in particular to an AI sorting garbage treatment method and system, and the method comprises the steps: obtaining a garbage bag; the garbage bag is subjected to bag breaking treatment, and to-be-detected garbage is obtained; collecting image information of to-be-detected garbage; inputting the image information into a perception recognition model for recognition, wherein the perception recognition model comprises an input end, a backbone network, an attention parallel fusion module, an up-sampling fusion layer and a detection head; acquiring an identification result of the to-be-detected garbage, performing image processing in the detection frame to obtain explainable distance feature information, and performing distance measurement according to the explainable distance feature information to obtain position information of the to-be-detected garbage; the to-be-detected garbage is grabbed according to the position information; and harmless treatment of the corresponding category is carried out on the to-be-detected garbage. According to the method, the effective boundary perception recognition model fusing attention refinement and a space interaction mechanism is applied, so that the detection and recognition precision of highly similar material garbage can be remarkably improved.

The present invention discloses a spatiotemporal multi-target behavior monitoring method, system and computing device, belonging to the field of video image processing and computer vision technology. The method of the present invention includes: acquiring video data including multiple pedestrian targets; analyzing the video data to obtain key frames; using dual-stream task branches to extract features from the key frames to obtain human skeleton posture information and group motion characteristics; obtaining a spatial interaction information attention map based on human skeleton posture information, group motion characteristics and a graph convolutional network, and obtaining a group behavior recognition result based on the spatial interaction information attention map. The method of the present invention can deeply explore the spatial relationship and interaction pattern between targets, more accurately identify group behavior, improve the accuracy and reliability of multi-target behavior monitoring, effectively identify park life behavior, and promptly warn of abnormal behavior.

An efficient and scalable attention model is provided, which can be referred to as multi-axis attention. An exemplary implementation can include two aspects: blocked local attention and spread global attention. These design choices enable global-local spatial interaction for any input resolution with only linear complexity. This disclosure also presents a new architectural element by effectively fusing convolution with the proposed multi-axis attention model. In addition, this disclosure proposes a simple hierarchical vision backbone by simply repeating basic building blocks across multiple stages, an exemplary implementation of which can be referred to as MaxViT. In particular, MaxViT is able to "see" globally throughout the entire network, even in earlier, high-resolution stages.

The invention discloses a pedestrian trajectory prediction method based on deep learning. The pedestrian trajectory prediction method is characterized by comprising the following steps of S1, receiving input data and performing preprocessing; s2, extracting spatial features from the input data by using a graph convolutional network GCN, wherein the convolutional neural network GCN simulates spatial interaction between pedestrians through an adjacent matrix; s3, extracting time features from the input data by using an encoder layer of a Transform model, wherein the Transform model captures a dependency relationship of pedestrians in a time dimension through a self-attention mechanism; s4, fusing the spatial features and the time features to obtain spatial and temporal features, and extracting spatial and temporal fusion features by using a Transform encoder; and S5, noise is added to the extracted space-time fusion features, then the features are sent to a full connection layer for pedestrian trajectory prediction, and future position information of pedestrians is output. The method improves the prediction precision and robustness, and is suitable for the fields of intelligent transportation and the like.

The invention discloses an airport clearance dynamic management method and system based on an electronic sand table technology, relates to the technical field of airport clearance management, and aims at a target obstacle in an airport remote sensing image, adopts space registration and dynamic feature extraction to construct an obstacle simulation body, and loads the obstacle simulation body to an airport three-dimensional prevention and control model. Through dynamic space interaction of an obstacle and a clearance limiting surface, key dynamic characteristic parameters are extracted, a risk prediction model is input after parameter screening and enhancement are carried out by utilizing a dynamic evaluation weight, a dynamic risk level is output, and multi-layer clearance situation visual display and real-time risk early warning are realized in combination with authority control. And the airport clearance risk management accuracy and efficiency are improved.

The invention relates to a multivariate time sequence anomaly detection method. An anomaly detection model used in the method comprises a U-Net encoder, a U-Net decoder, a time sequence characteristic memory module and a space interaction perception module. Performing multi-scale time sequence feature extraction on the weight-standardized one-dimensional convolutional layer in the U-Net encoder to obtain multi-level encoding features; in a time sequence feature memory module, enhancing long-term dependence features for the multi-level coding features; inputting the memory features into a space interaction perception module, constructing a graph structure between variables through a graph attention network, and outputting space enhancement features; in a U-Net decoder, splicing the corresponding memory features with the up-sampling features of the upper layer, and obtaining reconstruction features through one-dimensional convolution fusion; and calculating a dimension-by-dimension square error sum between the original time sequence fragment and the reconstructed data to obtain an abnormal score. Compared with the prior art, the method has the advantages of high precision, strong robustness, high efficiency and the like.

The present application relates to the technical field of image processing, and more particularly to a lesion segmentation method of adaptive dynamic text prompt, comprising: acquiring a lesion image, and generating an adaptive dynamic text prompt based on the lesion image; constructing a multi-modal enhanced fusion text prompt adapter based on a FiLM global channel recalibration module, a spatial cross-attention interaction module and a zero initialization gate nonlinear integration module cascade; the global channel recalibration module of FiLM utilizes a feature linear modulation mechanism to perform channel-level weighting on a visual feature map; before the feature enters spatial interaction, according to the text semantic enhancement band response, the activation of the background noise channel is inhibited. The present application overcomes the problems of insufficient utilization of multi-modal prompts, dependence on artificial static labeling of text prompts, serious dependence on prior information in the reasoning stage and difficulty in multi-modal feature fusion in a low-contrast environment in the existing medical image segmentation technology.