56 results about "Spatial interaction" patented technology

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 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.

The invention belongs to the technical field of image segmentation, and discloses an edge prior Mama-based image segmentation detection method, electronic equipment and a storage medium, and the method comprises the steps: preprocessing an input feature through a space interaction enhancement (SIE) module; sS3D is utilized to capture spatial dependence and depth dimension context in the slice, and long-range dependence is calculated through a state space model; meanwhile, an EP component is used for explicitly enhancing local edge and texture features through convolution and background suppression operation; and finally fusing the outputs of the SS3D and the EP. According to the method, the advantage of Mamba efficient modeling long-range dependence is reserved, meanwhile, the detail perception capability of boundaries is remarkably improved, reliable separation of abnormal areas and precise description of local details under complex background interference are achieved, and segmentation robustness and precision in tasks such as industrial defect detection and medical image analysis are effectively improved.

The application discloses a dispatching collaborative optimization method and system based on a segmented agent and a feasible domain evaluation. The method comprises the following steps: obtaining engineering structure and equipment dispatching parameter space and operation conditions, and constructing physical conservation constraints; predicting first safety constraint responses and second safety constraint responses by using a segmented agent model for joint parameter combinations meeting the constraints; dividing a feasible dispatching domain based on flow rate responses, extracting volume indicators of quantitative dispatching scheme proportions, and extracting spatial interaction indicators of quantitative equipment area influence distribution; solving optimal structure parameters by taking minimum outer layer structure engineering quantity as an objective and taking the above two indicators meeting performance thresholds as constraints; and outputting recommended equipment operation strategies by taking minimum inner layer flow rate as an objective in the feasible dispatching domain corresponding to the optimal structure parameters. The application can realize double-layer nested collaboration of physical structure design and equipment operation dispatching, and can improve the cross-condition dispatching adaptability and cross-region response field decoupling capability of an engineering system.

The present application relates to the technical field of data processing, more specifically, the present application relates to a power project demand reserve overall balance method based on intelligent algorithm, comprising: obtaining the declaration text data and electrical scene image data of the power project to be checked; detecting the equipment entity node by using the Grounding DINO model; constructing a spatial interaction matrix based on the spatial distribution characteristics of the equipment entity node; fusing the text semantic features, visual feature vectors and spatial interaction intensity, deducing the electrical topology connection probability and generating the project topology graph; and calculating the topology structure similarity by using the subgraph isomorphism algorithm to determine the duplicate declaration project. The present application realizes the identification of electrical connection relationship by evaluating the spatial relationship and fusing multi-modal information, solves the problem that the traditional method cannot distinguish the same equipment in different topology positions, and improves the accuracy of the power project demand reserve overall balance.

The invention provides a myopathy progress prediction method and device based on a spatio-temporal topology network, and the method comprises the steps: carrying out the image segmentation and quantification of muscle biopsy sections of a patient at a plurality of time points, constructing a static pathological topology network with a single muscle fiber as a node and a spatial adjacency relation as an edge, and enabling the node to comprise the multi-dimensional features of subtypes, forms, textures, cell nucleuses and the like; and forming time-space diagram data according to a time sequence. The data are input into a pre-trained space-time diagram neural network, a space coding layer aggregates neighborhood information through a diagram convolutional network to capture space interaction, a time coding layer learns a time sequence evolution rule through a recurrent neural network, and a decoding layer predicts a network state of a next time point. Pathological network sequences of multiple time points in the future are generated through iterative prediction, then key indexes are extracted to draw a quantitative prediction curve, a visual pathology heat map is generated, crossing from static pathology to dynamic progress is achieved, and an objective and accurate myopathy prognosis evaluation tool is provided for clinic.

The present application relates to the technical field of dangerous rock monitoring, and particularly relates to a dangerous rock monitoring system and a risk assessment method thereof.The present application introduces a graph convolutional neural network to accurately model environmental factors such as wind speed and vegetation, overcomes the limitations of traditional wind force calculation models, corrects the influence of wind force tension, and thus more accurately assesses the stability of the rock mass;By introducing a dynamic adjustment mechanism of the environmental change coefficient and the vibration propagation coefficient, the model can adapt to changes in environmental factors such as temperature, humidity and precipitation in real time, and improve the adaptability and accuracy of the model;In addition, considering the spatial interaction and dynamic effect between rock mass units, an instability propagation equation is established to capture the propagation process of rock mass instability, so as to comprehensively consider the physical properties, spatial interaction and environmental changes of the rock mass, thereby providing more accurate and real-time instability prediction, and providing effective risk warning and emergency decision assistance for mining, slope construction and other engineering.

The application discloses a kind of low air space complex environment under unmanned aerial vehicle cluster target long-time robust tracking method, comprising: by the target detection model of pre-training to the unmanned aerial vehicle target is detected and is combined with environmental state information dynamic optimization;The detection result after optimization is parallelly input light graph convolution network and bidirectional LSTM module, respectively extract the spatial interaction feature and time sequence dynamic feature of target predicted position;Two kinds of features are fused using spatial-time sequence attention mechanism, to obtain more accurate predicted position information;Based on the confidence score of target detection frame, the predicted position of target and the actual detection result of target are two-stage data association.The method effectively improves the tracking accuracy and robustness of unmanned aerial vehicle cluster target in complex dynamic environment, especially in target occlusion, dense formation and background interference scene has strong adaptability.

The invention discloses a dam engineering leakage channel entrance-channel-escape full view identification method and system. The method comprises the following steps: acquiring multi-source monitoring data of a dam engineering area; constructing a background seepage flow field reflecting a macroscopic hydraulic gradient and an anisotropic diffusion tensor field reflecting local permeability characteristics based on multi-source monitoring data; performing bidirectional probability field evolution calculation by using an unsteady convection-diffusion equation set and respectively taking the inlet geometrical characteristics and the escape temperature anomaly as sources to obtain an inlet reachability field and an escape reachability field which are continuously distributed in the dam body space; and determining the three-dimensional full-view probability distribution of the leakage channel based on the space interaction overlapping characteristics of the two fields. According to the method, physical self-consistent reconstruction from discrete monitoring data to a continuous channel entity is realized by constructing a different-field coupling feedback and tensor guiding mechanism, and the topological fuzzy problem of leakage path identification in a complex medium is effectively solved.

This invention discloses an immersive light and shadow art space interaction method and system based on motion recognition. It collects user motion signals and analyzes them into posture features, then uses template comparison to filter valid action inputs. The system performs trajectory analysis on action sequences to extract rhythm distribution features and identifies emotional tendencies based on changes in action amplitude and speed, organizing the queue of actions to be processed according to the urgency of emotional response. For multi-limb synchronous movements, it partitions and decomposes the movements, identifying the temporal coordination relationship between dominant and subordinate limbs and establishing a cascading trigger mechanism. It maps action features to light and shadow control parameters and verifies rendering performance, generating optimized lighting effect execution commands. It monitors user interaction frequency and dwell time distribution to identify deviations from the immersive state, automatically triggering lighting adjustment strategies to restore user engagement. Through preloading and reuse scheduling of rendering tasks, it optimizes system resource utilization and outputs coordinated and unified spatial interaction control commands, achieving a natural fusion of action and light and shadow.

The invention discloses an interaction method, device and system of refrigeration equipment and the refrigeration equipment, and belongs to the technical field of refrigeration equipment. The interaction method of the refrigeration equipment comprises the steps of obtaining interaction data of a user and the refrigeration equipment and space structure information of the refrigeration equipment, wherein the interaction data at least comprises voice interaction data; based on the interaction data and the space structure information, obtaining space interaction features, the space interaction features being used for representing an association relationship between the interaction data and the space structure information; and determining and outputting a target interaction result of the user and the refrigeration equipment based on the space interaction characteristics. The specific article or area pointed by the user can be accurately recognized, and the situation that the interaction accuracy is reduced due to misunderstanding of the user intention is avoided.

The invention is suitable for the technical field of intelligent terminals, and provides a pose estimation method and device of a space interaction device, a terminal device and a storage medium, the method comprises the following steps: obtaining a current frame image of the space interaction device collected by a three-dimensional imaging device, the space interaction device being provided with at least two mark points; identifying visible states of all mark points in the current frame image; acquiring inertial measurement data output by an inertial sensor in the space interaction equipment; according to the visible states of all the mark points, the inertial measurement data and reference space coordinates, a pose estimation result of the space interaction equipment is generated, and the reference space coordinates are determined based on historical frame images. According to the method, the robustness of space interaction pose estimation can be improved, and the interaction continuity and precision of space interaction equipment in a complex scene can be guaranteed.

The invention discloses an interaction perception comparison coding and multi-mode pocket feature driven molecule generation method and system. The method comprises the following steps: firstly, constructing a pre-training and fine-tuning data set; the method comprises the following steps: acquiring spatial interaction, structure and sequence features of protein pocket-ligand compound data, optimizing the sequence features through cross-modal contrast learning, and fusing the optimized sequence features with the structure features to obtain first multi-modal fusion features; constructing a molecule generation model, pre-training the model by using a pre-training data set, and then finely adjusting the model by using a second multi-modal fusion feature fused with the first multi-modal fusion feature and a corresponding ligand molecule sequence feature; for a specific target protein, the model can generate a molecule adapted to the specific target protein according to the multi-modal fusion feature of the pocket. The invention also discloses a system for realizing the method. The method and the system provided by the invention can effectively generate the candidate molecule which is highly matched with the binding site of the target protein, has high affinity and is excellent in synthesis accessibility.

The invention relates to the technical field of geographic information, in particular to an urban functional area identification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring multi-source data, and constructing graph structure data based on the multi-source data; and inputting the graph structure data into a preset neural network model, and outputting to obtain an urban functional area identification result, the preset neural network model being obtained by training a graph convolutional neural network model based on a spatial domain in combination with an attention mechanism fusing attribute representation and spatial connection. Therefore, city space interaction is simulated by constructing the graph structure data, and the attention mechanism jointly driven by the attributes and the space connection is utilized to identify the types of the city function areas, so that the problem of inaccurate identification of the city function areas in the prior art is solved, and accurate classification of the city function areas is realized.

The invention provides a method and equipment for determining track confidence and a sensing system. The method comprises the following steps: acquiring a first relationship between a target object and a first environment according to first track information of the target object and the first environment; and based on the first relationship, determining the airspace confidence of the first track information. In the embodiment of the invention, the spatial interaction relationship between the target object and the surrounding environment is introduced to determine the airspace confidence coefficient of the trajectory information of the target object. According to the scheme, on one hand, the possible influence of the surrounding environment on the motion behavior of the target object is considered, and the precision of the track confidence coefficient is improved; and on the other hand, the scheme can be suitable for various traffic driving scenes, such as scenes conforming to the inertia priori hypothesis and scenes not conforming to the inertia priori hypothesis, and the universality and robustness of the track confidence coefficient can be improved.

The invention relates to the technical field of computer graphics and virtual reality, and discloses an unstructured volume data hybrid rendering method based on WebXR and Gaussian splash technologies and a space interaction system. According to the method, a standardized visibility container protocol is constructed, a hysteresis space state machine is combined, and real-time logic cutting, efficient streaming rendering and smooth space interaction of unstructured volume data in any shape are achieved through general rendering entity abstraction, streaming zero-copy rendering pipelines and core algorithm innovation. According to the method, the problems of difficulty in geometric constraint of 3D Gaussian splashing data in the existing WebXR environment, bottleneck of rendering performance of a mobile Web end, single jitter of spatial state perception and the like are solved, and the method is suitable for various scenes such as AR transmission doors, photoscopes, holographic showcases and the like and has wide universality and practicability.

The invention relates to the technical field of data processing, in particular to an electric power project demand reserve overall balancing method based on an intelligent algorithm, which comprises the following steps: acquiring declaration text data and electrical scene image data of an electric power project to be subjected to duplicate checking, and detecting equipment entity nodes by utilizing a Grounding DINO model; constructing a spatial interaction matrix based on the spatial distribution characteristics of the equipment entity nodes; the text semantic features, the visual feature vectors and the space interaction strength are fused, the electrical topology connection probability is deduced, and a project topological graph is generated; and a sub-graph isomorphism algorithm is utilized to calculate topological structure similarity so as to judge the repeated declaration project. According to the method, the electrical connection relationship is identified by evaluating the spatial relationship and fusing the multi-modal information, the problem that the same equipment cannot be distinguished at different topological positions in a traditional method is solved, and the accuracy of overall balance of power project demand reserve is improved.

This invention discloses a multimodal spatial interaction head-mounted system and method for clinical nursing, comprising the following modules: A) a management platform; B) an indoor positioning and wireless communication base station, wherein the indoor positioning and wireless communication base station includes an ultra-wideband (UWB) positioning module and a positioning QR code; C) a nursing workstation, wherein the nursing workstation includes a data terminal, which includes an EHR / HIS integration module, a workflow configuration interface, and a device IoT gateway; and D) a head-mounted glasses terminal. This invention achieves high-precision spatial anchoring through hierarchical fusion positioning of UWB and visual SLAM, introduces multimodal aseptic interaction logic supporting emergency coverage commands to adapt to clinical practice, and innovatively adopts a dynamic privacy rendering and bystander detection mechanism based on the line-of-sight cone, effectively resolving the contradiction between information visualization, aseptic operation standards, and patient privacy protection in clinical nursing.

The invention discloses an assembly clearance detection method based on visual fusion of MLSD and SAR (Synthetic Aperture Radar). The method comprises the steps of calibration of a handheld mobile camera, collection and sampling of images, setting of a threshold value around an assembly gap, linear feature detection based on MLSD, image slice processing, linear feature screening and slope calculation, and linear spacing calculation. According to the method, a Pycharm is adopted based on a pyhton language, and a straight line detection and spacing calculation algorithm is developed by depending on an Opencv image processing library; and developing an SAR display method by adopting Unity 3D based on a C # language. According to the method, accurate and robust detection of linear features is realized by adopting a deep learning-based MLSD algorithm, and a detection result is visually and clearly displayed on a real product assembly site in a virtual-real fusion form by adopting an SAR technology, so that a user can obtain and understand the detection result in natural space interaction. SAR display breaks through the limitation of information display of a traditional two-dimensional screen, a detection result is overlaid to an assembly site, a user interacts with information in a more natural and immersive mode, and perception and cognition of assembly gap detection are enhanced.

This invention belongs to the field of image processing technology and discloses a method and system for indexing the spatial interaction of crowds in a digital twin scene based on an octree. The method includes: determining a target three-dimensional space containing pedestrian data; constructing an octree corresponding to the target three-dimensional space based on an octree spatial partitioning algorithm; wherein the root node of the octree is the target three-dimensional space, and the leaf nodes are the smallest three-dimensional spaces partitioned in the octree; responding to a spatial query request, recursively traversing all nodes of the octree based on an intersection test algorithm to obtain leaf nodes that meet preset query conditions; merging the pedestrian data stored in the obtained leaf nodes, and outputting a set of potential interactive objects based on the merged result. This invention utilizes the recursive subdivision capability of the octree in three-dimensional space, and integrates intersection test algorithms for three basic geometric shapes: points, axis-aligned bounding boxes, and spheres, to achieve natural expression and efficient management of three-dimensional spatial crowd interaction data.

The invention relates to a combined transport network transport capacity speculation method and device. Comprising the following steps: acquiring feature vectors of nodes and links of the intermodal network in a preset time period and generated impact events to obtain an intermodal dynamic graph; according to the combined operation dynamic graph, calculating the residual availability degree of the nodes, and performing diffusion processing to obtain a node joint vector which represents the influence degree of the impact event on the nodes; calculating a node reference correction quantity according to the joint vector, calculating a node mixed representation result according to the reference correction quantity, screening the mixed representation result through the transport capacity demand quantity to obtain a space interaction result of the intermodal network, the mixed representation result representing a recovery trend of the node, the reference correction quantity represents available capacity deviation generated by the node through an impact event; and deducing based on a space interaction result to obtain a node available capacity change value and an overall available capacity change value of the intermodal network, and obtaining a transport capacity speculation result. According to the invention, the available transport capacity speculation accuracy of the intermodal network under the impact event influence can be improved.

This invention provides a crane collision avoidance early warning method based on a spatiotemporal graph attention network and a Transformer architecture, comprising the following steps: S1, real-time collection of raw monitoring data within the work area using sensing sensors to construct a set of historical trajectories of the target; S2, construction of a dynamic heterogeneous spatiotemporal topology graph and feature initialization of nodes; S3, modeling the spatial interaction relationships between different targets using a graph attention network, extracting spatial interaction features and assigning corresponding risk weights; S4, inputting the spatial enhanced feature vectors into a Transformer-based network in chronological order, performing temporal encoding, and outputting predicted trajectories for multiple future time steps; S5, combining the predicted trajectories with the crane's planned motion path to assess collision risk, and outputting corresponding early warning signals or control commands when the risk exceeds a preset threshold. This method achieves early perception and dynamic prevention of potential collision risks during crane operation, improving operational safety and intelligence in complex working environments.

The application provides a posture estimation method of a tag device, a space interaction system and an electronic device. The posture estimation method of the tag device comprises the following steps: determining a tag coordinate system according to the position of the tag device, and determining an accelerometer coordinate system according to the position of an accelerometer of the tag device. The gravitational acceleration of the tag system is determined. An anchor-tag rotation matrix set is determined. A target rotation matrix is determined according to the relative orientation angle between the tag device and an anchor device. The posture estimation information of the tag device in the anchor coordinate system is obtained according to the target rotation matrix. Therefore, the posture estimation method, the space interaction system and the electronic device provided by the application can reduce the design distance of the antenna on the tag device, reduce the antenna complexity of the tag device, and thus meet the light and thin, small and compact requirements of the tag device. Meanwhile, the posture estimation accuracy of the tag device on the anchor device side can also be improved.

This invention discloses a pedestrian trajectory prediction method based on anisotropy and target guidance across dimensions, belonging to the technical field of trajectory prediction and intelligent transportation systems. The method takes the pedestrian's historical trajectory and the positions of surrounding pedestrians as input. After trajectory feature extraction and Transformer temporal modeling, spatial interactions are decoupled by dimension, and the effectiveness of the interaction is determined by a discriminator on a target-by-target, time-step-by-time, and spatial-dimensional basis. Multimodal target points are predicted based on a conditional variational autoencoder network and explicitly encoded and marked with their positions, which are then introduced as structural constraints into the decoding stage. Masking is removed, and non-autoregressive global decoding is employed, ensuring that the predicted positions are all globally constrained by the target points. This method improves the precision of spatial interaction modeling and the stability and rationality of trajectory prediction, while reducing computational overhead. It can be applied to autonomous driving and intelligent transportation systems, providing accurate prediction basis for path planning and risk warning.

A method and device for determining a trajectory confidence level, and a sensing system. The method for determining a trajectory confidence level comprises: on the basis of first trajectory information of a target object and a first environment, acquiring a first relationship between the target object and the first environment; and on the basis of the first relationship, determining a spatial domain confidence level of the first trajectory information. By means of introducing a spatial interaction relationship between a target object and a surrounding environment, a spatial domain confidence level of trajectory information of the target object is determined.

The invention discloses a brain magnetic signal deep learning classification method and system based on spatial-temporal feature fusion, and belongs to the technical field of biomedical signal processing. The method comprises the following steps: acquiring and preprocessing a multi-channel magnetoencephalogram (MEG) signal, particularly an MEG signal acquired by adopting an optical pump magnetometer (OPM); performing feature extraction and classification on the preprocessed MEG signals through a spatial-temporal feature fusion deep learning model, and extracting local time features and preliminary spatial interaction features from a time sequence of the MEG signals through a parallel multi-scale one-dimensional convolutional neural network (1D-CNN) module; flattening the extracted feature map, and inputting the flattened feature map into a Transform encoder module; and outputting a classification result through the full-connection classifier. According to the method, the problem of poor processing of high-dimensional and low-signal-to-noise-ratio characteristics of MEG signals in a traditional method is solved, and the accuracy and robustness of classification are remarkably improved through deep fusion of spatial-temporal characteristics.

The application discloses a kind of mobile robot collision prediction method and system based on deep learning.The method comprises: obtaining the real-time motion state of mobile robot, load state, planning path and surrounding dynamic obstacle perception information;Based on the motion state, dynamically calculate the available occupation profile data of each time in the future time window, and construct the space-time feature coding data representing the correlation between robot and obstacle;The space-time feature coding is input into the pre-trained deep space-time network model, which includes time series feature extraction layer and spatial interaction feature extraction layer, outputs collision probability, predicted collision time and collision point space-time heat map;According to the prediction result, generate multi-level warning signal.The application realizes the forward-looking prediction and hierarchical response of collision risk within several seconds in the future, effectively improves the running safety and efficiency of multiple mobile robots in complex scenes.

This invention belongs to the technical field of brain network analysis. To address the inaccuracies of existing brain network analyses, it proposes a dynamic brain network analysis method and system based on subnetwork alignment. This method involves reordering nodes within the same functional subnetwork for each time window, capturing spatial interaction patterns of nodes using spatial hybridization experts, modeling the independent temporal evolution of sequence tokens for each functional subnetwork across the entire timeframe using temporal hybridization experts, capturing collaborative or competitive dynamics across functional subnetworks using multi-head self-attention mechanisms, fusing global topological information from the original functional connectivity matrix with updated temporal tokens for each functional subnetwork, and introducing learnable brain state prototypes to obtain compact representations of subject states through aggregation, thereby yielding brain network analysis results. This invention improves the accuracy of brain disease classification and the interpretability of neuroscience.

The invention relates to the technical field of immersive man-machine interaction of virtual reality, augmented reality, mixed reality and the like, and discloses a virtual reality universal interaction method and system based on space interaction points. According to the method, position and rotation information of equipment such as a handle, gestures and eye movement is collected and packaged into a unified'space interaction point 'containing information such as three-dimensional position and rotation orientation, space movement and numerical value adjustment instructions are executed based on association between the unified'space interaction point' and an interaction hot area, and two interaction logics of single-point path sliding and rotation locking are supported. The system comprises an input acquisition module, a space interaction point generation module, a unified interaction processing module and an application logic response module, supports multi-device concurrent input and priority configuration, and can avoid device coupling and instruction conflicts. The scheme does not need to independently adapt to the equipment SDK, unifies interaction habits, adapts to multiple scenes such as consumption-level VR and industrial AR training, and improves interaction compatibility and fluency.