105 results about "Spatial Projection" patented technology

The invention relates to a trajectory prediction model robustness enhancement method based on dynamic subspace projection decomposition. Comprising the following steps: firstly, extracting hidden layer semantic features containing historical tracks and map topology through a multi-modal feature encoder; secondly, constructing a dynamic routing mechanism based on scene self-adaption, and calculating projection weights of input features on a plurality of expert subspaces; then, executing truncation projection operation based on orthogonal decomposition, retaining core semantics located in a low-dimensional space, and filtering out adversarial disturbance located in an orthogonal complementary space; and finally, introducing a feature consistency constraint training mechanism, taking the reconstructed features of the clean sample as anchor points, and compulsively aligning the purified features of the confrontation sample with the anchor points. Compared with the prior art, the method has the advantages that the robustness of the model in white box gradient attack, black box query attack and physical semantic deception scenes is remarkably improved through feature purification of a physical level and structured consistency constraint, and the prediction reliability of the automatic driving system is ensured.

The invention relates to the technical field of perception fusion, and discloses a tug fusion enhanced perception method based on target tracking and obstacle recognition, which comprises the following steps: processing an AIS, an optical fiber compass, a Beidou RTK, a laser radar, a millimeter wave radar and a panoramic camera on a tug to establish a ship coordinate system; and collecting message data of the AIS and combining with the MMSI information to screen the target ship to obtain the initial position of the target ship. And predicting the state sequence of the target ship to obtain the position, speed and heading information of the target ship. And carrying out target identification on the image, outputting identification results of semantic levels of the ship, the buoy and the quay wall, and carrying out space projection alignment with radar data. And fusing the processed results to obtain a fusion result, and performing early warning according to the fusion result. According to the method, the target ship relative pose resolving precision and the obstacle recognition reliability are improved, the sensing link time delay is shortened, and the driver blind area risk is reduced.

The invention discloses a power distribution system harmonic source positioning method based on subsystem division, and aims to improve the accuracy and anti-interference capability of harmonic source identification in a power distribution system. According to the method, firstly, an obtained voltage signal is preprocessed, frequency domain feature information is extracted, a subspace projection operator is constructed through singular value decomposition, and effective extraction of each harmonic component in the signal is achieved. Then, carrying out subsystem division on the power distribution system according to the position of the tail end measurement point, for each subsystem, respectively injecting simulated harmonic current into each candidate node by adopting a virtual harmonic injection method, and calculating the response of the node to the tail end voltage; and comparing a simulation result with a measured value, constructing an error vector, screening out a node with the minimum error as a backup harmonic source node, and finally positioning the harmonic source node through zero setting of a connection node and a correction strategy of the most downstream node. The method is suitable for a multi-node and multi-source coexistence large-scale power distribution network harmonic suppression scene.

The invention discloses a real-time virtual environment view layout algorithm based on spherical space guidance. The algorithm comprises the following steps that an original view is acquired and preprocessed; abstracting into a circular structure and completely mapping to a constructed spherical view projection structure; weight analysis is carried out, a preset threshold value is compared, a high-weight standard view set and a low-weight standard view set are divided, and dynamic batch layout optimization processing is carried out on the high-weight standard view set; constructing a space pressure function field for the low-weight standard view set, and determining a target position by using a space pressure field guiding method; smooth movement from the current position to the target position is achieved through a Bezier curve interpolation method; and when the viewpoint or view angle change exceeds the threshold value, re-calculating the layout until the change amplitude is smaller than the threshold value, and generating a final layout. According to the method, the spherical space projection and the adaptive mechanical model are combined, the large-scale view layout is optimized, the method has the advantages of being efficient, stable and real-time, and the data visualization effect in the virtual environment is improved.

The invention provides a regional electromagnetic intelligent evaluation method and system based on spectral entropy weighting, and the method comprises the following steps: collecting electromagnetic spectrum data and the motion state of a patrol vehicle, and constructing a virtual aperture data matrix through the motion information; space covariance analysis and subspace projection are carried out on the matrix, multipath scattering interference is separated and eliminated, and a pure field intensity sequence is obtained through reconstruction. By calculating the normalized spectrum entropy of the Doppler power spectrum of the pure field intensity sequence, an inverse proportion weight coefficient representing the signal confidence is generated; and weighting the weight to a pure field intensity sequence, and mapping the pure field intensity sequence to a geographic space. And dynamically adjusting the density of the evaluation grid according to the field intensity gradient, and finally carrying out weighted centroid calculation based on inverse proportion weight to obtain a regional electromagnetic environment evaluation result. According to the method, the technical problem that a regional evaluation result is not accurate due to the fact that multipath components cannot be separated and single-point data quality cannot be evaluated in traditional mobile patrol is solved.

The invention relates to the technical field of unmanned aerial vehicles, and discloses a detection method and an electronic device based on a mooring platform unmanned aerial vehicle, and the method comprises the steps: obtaining visible light, infrared, laser radar, positioning and inertial measurement data; constructing a local geographic coordinate system and realizing space projection and time sequence synchronization of multi-modal data; performing dynamic weighted fusion on each modal feature through a multi-modal cross attention fusion network to generate a high-dimensional semantic feature map; and performing target detection and thermal anomaly discrimination based on the feature map. The electronic device comprises a multi-modal sensing unit, a space-time alignment module, a time synchronization module, a multi-modal fusion module and a target discrimination module. According to the invention, through a unified space-time alignment and adaptive fusion mechanism, high-precision and high-robustness comprehensive detection can still be realized under severe conditions such as dark light, haze or shielding, and long-time stable operation is guaranteed by relying on a mooring platform.

This application belongs to the field of coherent diffraction imaging technology, specifically disclosing an ultra-low dose coherent diffraction imaging method and apparatus. Based on a blind source separation strategy, this application uses principal component analysis to process the acquired diffraction signals, performing noise separation and updating in reciprocal space. This effectively separates mixed noise energy into noise components, thus avoiding crosstalk to the reconstruction process and significantly improving the convergence stability and robustness of coherent diffraction imaging when reconstructing diffraction signals with extremely low signal-to-noise ratios under ultra-low exposure doses. Simultaneously, this application constructs noise components separately for each scanning position and correlates noise components at different positions through low-dimensional spatial projection, achieving non-stationary noise separation. This enables more effective handling of random noise caused by the low quantum efficiency of ultra-short band detectors, thus maintaining extremely high noise robustness and reconstruction accuracy even under ultra-low exposure doses, achieving an effective improvement in resolution.

This invention discloses a hierarchical continuous attractor network based on intrinsic time constant gradients, belonging to the fields of artificial neural networks and cognitive computing. The network includes a spatial input extraction module, multiple continuous attractor layers, a spatial projection module corresponding to each layer, and a wave packet decoding module. Each layer has a preset and fixed time constant during initialization, and the time constants of each layer monotonically increase from the bottom layer to the top layer. The same external spatial input is projected to each layer in parallel. The bottom layer tracks instantaneous spatial changes with a shorter relaxation time, while the top layer accumulates slowly varying spatial statistics with a longer relaxation time. The cyclic connection weights of each layer are initialized with translation-invariant functions to form a continuous attractor manifold, and are fine-tuned online by superimposing Hebbian enhancement and weight decay. This invention can form multi-timescale spatial representations, improving the stability and precision of representations in high-frequency spatial regions.

The application discloses a kind of variable working condition diagnosis methods of rotary reducer based on multi-view transfer, belong to fault diagnosis technical field.The method is first to the multiple visual vibration data collected is preprocessed and constructs variable working condition data set;Through fourier transform, extract each visual spectrum feature;Typical correlation analysis is used to construct embedding class discriminant transferable feature objective function, combined with maximum mean difference technique reduces the distribution difference between training and testing field, and introduces multi-view consistency constraint;Through generalized feature decomposition, solve common subspace projection, extract multi-view features with discriminant and transferability;Finally, nearest distance classifier is used to realize the fault diagnosis under variable working condition.The application effectively solves the problem that rotary reducer has poor generalization ability due to data distribution difference under variable working condition, improves the accuracy and reliability of fault diagnosis.

The invention provides a vehicle positioning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining first position coordinates of a target vehicle in a satellite coordinate system at a plurality of different moments in a preset time period through a satellite; through a preset transformation matrix, converting each first position coordinate into a second position coordinate in a pixel coordinate system; based on the projection relation between the target vehicle in the pixel coordinate system and the current driving road, whether the second position coordinate at the current moment is reserved or not is determined; if the second position coordinates are reserved, taking the second position coordinates at the current moment as the position of the target vehicle in the preset time period, so as to display a position identifier corresponding to the target vehicle in a map; and if not, deleting the current second position coordinate. Based on the space projection relation between the vehicle and the road, the vehicle positioning deviation is corrected, so that the vehicle position is accurate, and the vehicle positioning visual display is more accurate.

This application relates to the field of plasma physics technology and provides an asymmetric inversion method and apparatus based on a matching mechanism for plasma diagnostics. The method acquires plasma magnetic flux data, observation lines, and measurement integral values. The magnetic flux data is preprocessed to obtain preprocessed magnetic flux data. Based on the preprocessed magnetic flux data, a closed magnetic surface uniquely matched to each observation line is determined. A lower triangular matrix is ​​constructed based on each observation line and the closed magnetic surface. An inversion equation is constructed based on this lower triangular matrix and the measurement integral values. Finally, the inversion equation is solved to determine the parameter distribution values ​​of the plasma. This method achieves three-dimensional spatial projection of the observation lines and magnetic flux, rapidly determining the position of the closed magnetic surface using geometric relationships, thus improving computational efficiency. Simultaneously, it accurately establishes a one-to-one correspondence between the closed magnetic surface and the observation lines, making the ill-posed problem in solving the matrix equations a unique solution, improving the success rate of solving using the stacking method, and significantly reducing computational errors.

The invention relates to the technical field of mixed reality and immersive display, and discloses an immersive scene experience system and method based on mixed reality superposition projection, and the system comprises an experience module which is formed by a plurality of projection curtains in a surrounding manner, and an experience space is formed in the plurality of projection curtains; the projection module is used for constructing a holographic projection scene; the MR glasses device is used for displaying a virtual image and space interaction; the space positioning module is used for generating a space model and forming an NFC label identifier in the space model; the control module is used for receiving position information of the MR glasses in the projection space; and controlling a playing picture of the projection module and / or the MR glasses device according to the position information. Compared with a traditional mode, the integration degree between the virtual image and the holographic projection scene is higher; meanwhile, the user triggers a virtual event or operates a virtual object in a scene through a gesture, and dynamically adjusts the content of a virtual image according to real-time sensor data, so as to keep synchronization with the action of the user.

This invention relates to artificial intelligence, and particularly to a supply chain demand forecasting method based on condition-guided temporal diffusion and multimodal fusion. The method includes: acquiring multimodal business samples containing historical sales data with missing masks and graphic descriptions; obtaining cross-modal aligned feature vectors through feature extraction and spatial projection to construct a static multimodal conditional representation; under this guidance, performing inverse denoising sampling using a temporal diffusion network to obtain reconstructed temporal features; generating a measure signal to fill uncertainty through multiple sampling variance calculations, inputting it into a dynamic gating network to adaptively allocate fusion weights, and obtaining global cross-modal attribute features; finally, generating demand forecasting results and performing end-to-end training based on a joint loss function of prediction error and diffusion noise prediction loss. This invention effectively overcomes the problems of supply chain cold start and stockout gaps, significantly improving prediction accuracy and model robustness in extremely sparse scenarios.

The application discloses a PCBA foreign matter detection method based on a multi-resolution subspace projection, acquires a to-be-detected board and a standard reference board image, determines an adaptive down-sampling multiple based on a minimum foreign matter physical area, performs image registration with the aid of a mask to eliminate geometric deformation, extracts a multi-resolution feature map through a pre-trained deep convolutional neural network, calculates feature differences, and uses a dynamic threshold to screen a preliminary candidate point set, constructs a local principal component subspace of a local neighborhood of a reference image, performs first-stage screening by calculating the orthogonal projection error of a test feature vector in the space, maps remaining candidate points to a multi-scale feature space and splices them, constructs a global multi-scale principal component subspace, performs second-stage screening through a global projection error, and outputs a final result selection, and through the implementation of the application, the problems of a high-definition image computing power bottleneck and a high false alarm in comparison are solved, the application has zero-sample generalization capability, and sample-free training can accurately detect tiny foreign matters.

The invention discloses a four-dimensional variation assimilation method and system based on hidden space projection and a super set. The method comprises the following steps: projecting a high-dimensional model state to a low-dimensional hidden space by using a pre-trained depth auto-encoder; secondly, generating super set members far exceeding the traditional scale through rapid reasoning of a depth generation model; constructing a flow-dependent background error covariance matrix in the hidden space based on the super set; combining a stream dependent background error with a static statistical background error, constructing a hybrid four-dimensional variational assimilation objective function in a hidden space, and performing optimization solution; and finally, reconstructing the optimal analysis hidden variable back to the original high-dimensional state space. According to the method, the calculation dimension is greatly reduced through the hidden space projection, the flow dependence information is greatly enriched through the super set, the static statistical stability and the flow dependence adaptability are combined through the mixed background error covariance, and therefore the assimilation precision and the forecasting skill are remarkably improved while the calculation efficiency is kept.

The present application belongs to the field of computer vision and artificial intelligence, and particularly relates to a four-dimensional dynamic scene representation and reconstruction method, system and device based on structural equivalence prior, aiming at solving the problems of poor spatio-temporal consistency, large calculation cost and low long sequence reconstruction accuracy in dynamic scene reconstruction. The present application comprises: decomposing the input four-dimensional voxel sequence into multiple two-dimensional feature planes containing spatial projection and spatio-temporal coupling; introducing structural equivalence prior to fuse the plane features, generating unified and continuous spatio-temporal latent space representation by establishing the internal correlation between spatial geometric gradient and time evolution; finally, using a decoding module containing residual connection to decode the latent space representation, and recovering the high-fidelity four-dimensional dynamic scene layer by layer. The present application effectively improves the consistency and accuracy of dynamic scene reconstruction by establishing an explicit spatio-temporal coupling relationship, while taking into account the calculation efficiency, and has broad application prospects in the fields of autonomous driving, augmented reality, etc.

The invention discloses a geographic road network topology consistency self-checking and repairing method based on a multi-mode large language model. The method comprises the following steps: obtaining geographic road network vector data, a high-resolution satellite remote sensing image, a vehicle GPS track sequence and a street view image of a key position of an area to be detected; extracting each modal feature by using a multi-modal encoder, and projecting the modal features to a unified language marking space through a space projection operator to realize semantic alignment; the aligned multi-modal features are input into a multi-modal large language model for self-check reasoning, and a diagnosis report containing road network topology errors is output; converting the diagnosis report into a solution diagram by using the model, and calling a code generation module to automatically write a repair code script; and executing the repair script to modify the road network data, feeding back the modified data to the model for closed-loop verification of anti-factual reasoning and virtual traversal semantic verification, and updating the production library after verification is passed. According to the invention, the accuracy of road network topology automatic repair is improved.

To provide a space projection device which achieves quality improvement in a space projection image.SOLUTION: A space projection device 100 includes: an optical medium 20 for diffusing projection light P1; and a light guide optical system 30 for guiding projection light (space projection light P2) diffused by the optical medium 20 so as to form an image at a space image formation part 40. The light guide optical system 30 includes a retroreflective member 32. The retroreflective member 32 includes a concave-convex structure 320 for suppressing a ghost image M.SELECTED DRAWING: Figure 1

The application discloses a four-dimensional variational assimilation method and system based on hidden space projection and super set, comprising the following steps: projecting a high-dimensional model state to a low-dimensional hidden space by using a pre-trained deep autoencoder; secondly, generating super set members far exceeding the traditional scale by fast reasoning of a deep generative model; constructing a flow-dependent background error covariance matrix in the hidden space based on the super set; combining the flow-dependent background error with a static statistical background error, constructing a mixed four-dimensional variational assimilation objective function in the hidden space and optimizing and solving the function; and finally, reconstructing the optimal analysis hidden variable back to the original high-dimensional state space. The application greatly reduces the calculation dimension through hidden space projection, greatly enriches the flow-dependent information through the super set, and combines the static statistical stability with the flow-dependent adaptability through the mixed background error covariance, so that the assimilation precision and the prediction skill are significantly improved while the calculation efficiency is maintained.

The invention discloses a self-adaptive subspace projection suppression method based on optical pump magnetometer external noise, and belongs to the technical field of neural magnetic imaging (MEG) signal processing.The method comprises the steps that brain magnetic signals are collected through a wearable optical pump magnetometer array and preprocessed, and a signal and noise subspace decomposition model is established; integrating a model-driven noise modeling method and a data-driven noise modeling method, and constructing a noise subspace base vector; constructing a signal subspace basis vector in combination with a guide field matrix and event correlation analysis; identifying residual noise components based on event correlation analysis, and perfecting noise subspace modeling; signal noise separation is realized by adopting a hierarchical projection strategy; and analyzing the time correlation of internal and external space signals, and constructing a time projection matrix to remove residual interference to obtain a clean MEG signal. According to the invention, various types of external noise interferences can be effectively suppressed, the signal-to-noise ratio and the reliability of brain magnetic signals are remarkably improved, and the method is particularly suitable for practical application of a wearable optical pump magnetometer system.

The invention belongs to the field of safety risk monitoring and cognitive assessment, and provides a risk subjective assessment result classification method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an electroencephalogram signal and a near-infrared signal; according to the electroencephalogram signal and the near-infrared signal, determining an electrode-frequency band combination and an activated brain region of a subjective evaluation result; according to the activated brain region of the subjective evaluation result, determining a space projection relationship between the activated brain region and a scalp electrode, and according to the space projection relationship, determining the correlation between the activated brain region and an electrode-frequency band combination; according to the correlation between the activated brain region and the electrode-frequency band combination, a risk classification model is adopted for prediction, and a prediction result of a risk subjective assessment result of the detection target is obtained; according to the prediction result of the risk subjective assessment result, the classification result of the risk subjective assessment result is determined, and the accuracy of the classification result of the risk subjective assessment result, the data acquisition convenience and the interpretability are improved.

This invention relates to the field of tunnel defect identification technology, and discloses a method for identifying tunnel structural defects by fusing laser point clouds and visible light. The method includes constructing a spatial projection model to obtain a fused dataset; extracting bidirectional coupled feature vectors and screening structural defect sensing factors; performing a quantitative assessment of defect levels and constructing a three-dimensional spatial distribution map; training a structural deterioration trend prediction model to obtain future expansion states and bearing capacity change trends; calculating the probability of defect level transitions and outputting an early warning report containing location and treatment suggestions. This application can utilize registration error compensation operators to achieve accurate alignment of multimodal data, deeply mine the correlation between deformation and damage, eliminate redundant information, and realize dynamic quantification of defect levels and early prediction of deterioration trends, thereby improving the intelligence level and safety of tunnel operation and maintenance.

The invention discloses a wind fire extinguisher detection method and system based on field operation scene reconstruction, and relates to the technical field of intelligent measurement and testing, and the method comprises the steps: collecting operation operation data through an intelligent sensor, constructing a three-dimensional operation scene model, building a space projection relation between airflow propagation and terrain, and calculating the blocking effect of the terrain on airflow; and determining an airflow action boundary. And superposing the airflow action boundary and the combustible distribution, and calculating the proportion of the uncovered area to obtain a coverage effectiveness index. The method comprises the following steps: extracting time sequence data of coverage effectiveness indexes and equipment operation parameters under different operation positions, identifying response delay characteristics of parameter changes to the indexes, constructing influence weight distribution after time delay compensation, and identifying a parameter sensitive interval; and analyzing the fluctuation amplitude of the equipment parameters under different terrains in the sensitive interval, diagnosing the performance degradation mode of the equipment, and outputting a performance evaluation result. The operation efficiency and the equipment management level of the pneumatic extinguisher can be improved.

The application discloses a shoulder vehicle exclusion method based on an inspection system, and relates to the technical field of intelligent transportation. The method comprises the following steps: acquiring a parking area image shot by an inspection vehicle, identifying a vehicle target in the image and extracting license plate position information; generating a spatial distribution heat map of the vehicle in an image coordinate system based on vehicle three-dimensional feature reconstruction and spatial projection analysis; constructing a dynamic segmentation line model, and adaptively generating a shoulder area judgment boundary according to a parking type and road geometric parameters; distinguishing parking vehicles from shoulder vehicles through a multi-target trajectory correlation algorithm, and outputting a parking occupancy state. The application scheme can significantly improve the spatial positioning accuracy and behavior judgment reliability in a complex scene, break through the limitations in environmental adaptability, vehicle compatibility and time sequence continuity, and provide a high-robustness, full-period-coverage shoulder violation management and control solution for urban traffic management.

This invention discloses a shrinking-connected rod-shaped hybrid lattice structure and its simply supported beam structure, comprising multiple lattice unit cells arranged in a periodic array in three-dimensional space and shrinking-connected structures connecting lattice unit cells of different types of structures. The shrinking-connected structure is a transitional structure adopted for compression projection when connecting two different types of lattice structures. This invention introduces spatial projection into the formation of the connection structure, thereby ensuring the invariance of boundary connections for lattice structures of arbitrary spatial shapes. This facilitates the design of shrinking-connected structures, allowing even inexperienced designers to complete the design of hybrid structures. The lattice hybrid structure exhibits good mechanical properties when applied to simply supported beams and is easy to process and manufacture.

The application provides a high-speed real-time line laser three-dimensional imaging method, and relates to the technical field of data processing.The method comprises the following steps: extracting continuous strip units in basic strip data, forming strip columns according to the column direction of the continuous strip units, identifying the scanning angles of each strip column during imaging, calculating the consistency difference of the same strip column under adjacent scanning angles, calculating the mapping stability of the strip column under different angles to obtain an angular divergence value, calculating the strain degree generated by the strip column in space projection to obtain a sequence relaxation value, taking the sequence relaxation value as a stable correction factor, generating an angle window model according to the angle adjustment factor and the stable correction factor, determining the readable pixel range in each angle window, extracting strip image segments for recombination, calculating three-dimensional coordinates and forming three-dimensional strip coordinates, and obtaining real-time three-dimensional imaging data.The application can avoid the three-dimensional point cloud breakage phenomenon caused by strip mutation and realize line laser three-dimensional imaging.

This invention discloses a time-delay-constrained multimodal cooperative perception method and system for vehicle-to-everything (V2X) networks, comprising: acquiring point cloud data and image data and performing feature extraction, fusion, and spatial projection; constructing a two-dimensional convolutional neural network to extract a position-level importance probability map and a mask for filtering key information; constructing a benefit estimation neural network and a constraint evaluation neural network to predict the expected values ​​of system benefits and constraint conditions; simultaneously establishing an overall strategy selection module; the vehicle fleet performing target recognition and calculating rewards based on information interaction to obtain perception experience samples; updating network parameters based on perception experience samples to obtain the final overall strategy selection module. This invention optimizes vehicle transmission power, transmission channels, and perception data areas based on reinforcement learning, and introduces a strategy correction mechanism to dynamically correct risky strategies with high latency or high packet loss, avoiding target recognition deviations and decision-making errors caused by perception information delays and erroneous transmission.

This invention discloses a physically constrained dual-tower interactive prediction system and method for carbon nanotube synthesis, comprising a physical feature engineering module, a yield prediction tower, a mass prediction tower, a deep bridging module, and a training control module. The physical feature engineering module transforms the original experimental parameters into physical feature parameters. The yield prediction tower, connected to this module, implements mass conservation constraints through null space projection and outputs predicted yield values. The deep bridging module unidirectionally transmits yield information to the mass prediction tower through an information bottleneck mechanism. The mass prediction tower integrates physical features and bridging information, and outputs predicted mass features using an environment modulation gating unit. The training control module is used for overall training optimization. This invention addresses the problems of lack of physical consistency, negative transfer across multiple tasks, and insufficient generalization ability under small sample conditions in prior art purely data-driven models.