32 results about "Sensor observation" patented technology

The present application relates to a kind of infrared scene quantitative radiance calculation methods based on light ray tracking module, comprising: obtaining target mask information image, the radiance image of infrared scene, depth information image and position information image, sensor position information, sensor field of view and sensor observation direction;Infrared scene is divided into several view cones according to the resolution of target radiance area image, wherein several view cones and the object surface in infrared scene intersect to form several face elements;The radiance of each face element at the sensor is calculated by the theorem of solid angle projection;The radiance of several face elements at the sensor is accumulated, and the radiance of infrared scene to the sensor is obtained.The method supports full scene, single target, multiple targets as radiation energy source, and can be applied to high complex infrared scene simulation work;Without additional data support, the radiance at the sensor can be calculated without performing redundant work.

The present application relates to the technical field of navigation positioning, and in particular to a multi-source sensor adaptive weight fusion positioning method and related equipment, which comprises the following steps: collecting multi-source positioning sensor observation data, calculating corresponding health degree factors according to the data characteristics of each sensor, which are used to represent the data quality at the current time; inputting the health degree factors into a pre-trained reinforcement learning model, the model taking the maximization of the reward function constructed by the positioning error and the sensor health degree as the goal, and outputting the fusion weight of each sensor. According to the output weight, the multi-source observation data is fused and solved through factor graph optimization, and the final positioning result is output. This method can dynamically adapt to the differences in sensor working conditions and environmental disturbances, suppress the influence of abnormal data, realize the collaborative improvement of positioning accuracy and system reliability, and is suitable for multi-source fusion positioning scenes such as automatic driving, robots, intelligent navigation, etc.

A processor-implemented method for multimodal beam management, implemented by a network device, includes: receiving an input stream from one or more sensors by the network device; generating a digital twin modeling the environment of an area observed by the one or more sensors; the digital twin including one or more objects detected based on the input stream; and managing wireless communication signal beams, at least in part, based on the digital twin for communication with at least one user equipment (UE) in the area observed by the one or more sensors.

The application discloses a kind of based on digital twinning unmanned mine car reliability rapid early warning method, system, it is related to unmanned mine car technical field, including the following steps: the digital twin simulation model of unmanned mine car is constructed;Based on the digital twin simulation model, the digital twin reliability model that the reliability state change of each module of the unmanned mine car is characterized is constructed;Based on the measured data of the unmanned mine car, the consistency of the digital twin simulation model and the digital twin reliability model is judged, and after judging consistent, reliability state database is constructed;Based on the reliability state database, digital twin reliability rapid early warning model is obtained by training, and the early warning model is used to identify and output the current reliability state of the unmanned mine car according to real-time acquisition vehicle-mounted sensor observation data, to realize early warning.The reliability state of each subsystem and module of unmanned mine car is rapidly and accurately warned.

The application belongs to the technical field of navigation, and proposes an adaptive robust filtering navigation method based on multivariate t distribution and Bayesian shrinkage. First, multi-source heterogeneous sensor observation data is obtained. Second, the multi-source heterogeneous sensor data is modeled based on multivariate t distribution, and the innovation of the multi-source heterogeneous sensor observation data is extracted. Then, a continuous confidence factor is constructed, the fault detection is converted into a Bayesian inference problem, and the confidence diagnosis of the observation innovation is performed based on the confidence factor. Then, the innovation discount factor is constructed based on the confidence factor, and the weighted fusion target function is constructed based on the observation fitting term and the virtual robust term, so as to obtain the equivalent innovation observation, the equivalent observation noise covariance matrix, the equivalent innovation covariance and the robust Kalman gain. Finally, the observation information weight is dynamically adjusted, the equivalent parameters are used to complete the robust filtering iteration, and the optimal navigation solution is obtained. The application can improve the navigation positioning precision and robustness in the multi-source fusion navigation process.

This invention discloses a method for generating a safety constraint trajectory for an autonomous vehicle, belonging to the field of autonomous driving technology. The method includes the following steps: S1, acquiring environmental state information, sensor observation information, and the vehicle's current state information; S2, constructing a safety constraint topology based on the risk uncertainty state vector, wherein the safety constraint topology includes a set of safe state nodes and a set of safe reachable state transition edges; S3, dynamically evolving the safety constraint topology based on the risk uncertainty state vector to update the set of safe state nodes and the set of safe reachable state transition edges; S4, generating the trajectory of the autonomous vehicle within the dynamically evolved safety constraint topology. This invention can effectively address uncertainties in the traffic environment, such as changes in the behavior of surrounding traffic participants and changes in the reliability of sensor information, thereby improving the robustness of the system.

The present application relates to a kind of time-domain electric source superconducting electromagnetic detection primary magnetic field compensation method and system, eliminate the influence of primary magnetic field on superconducting sensor observation, improve secondary magnetic field measurement accuracy.First, the primary magnetic field distribution of electric source emission current on ground is calculated, to design secondary field measuring line with primary magnetic field contour line;The compensation current of measuring line is calculated, and compensation transmitter and electric source transmitter are synchronized using GPS, and compensation current is emitted at measuring point to offset primary magnetic field, with the same characteristics of compensation current on the same contour line;By adjusting the load RL parameter of compensation system, the turn-off time of compensation current and electric source emission current is consistent, and the primary magnetic field generated by electric source emission current is completely offset.The present application can solve the problem that superconducting sensor loses lock and magnetic saturation due to the large change rate and range of primary magnetic field in the near-source area of electric source, realize effective observation of superconducting sensor in the near-source area, and expand the measurement area and detection area.

This application provides a method and system for reconstructing spatiotemporal physical fields based on fractional Fokker-Planck regularization and implicit sampling. The method includes: inputting sparse sensor observation data into a trained deep neural network embedded with physical evolution laws, outputting a predicted fractional field, and iterating backward from pure Gaussian noise to obtain a noise-free physical field. The backward iteration includes: using the Tweedie formula to map the noise state of the current step to the estimated noise-free physical field, performing multi-physics coupling gradient calculation; calculating a deterministic drift term and a controlled random Gaussian perturbation term, superimposing a physical correction gradient, updating the noise state for the next time step, and cyclically decreasing until the step count is 0 to obtain the noise-free physical field. The advantages of this application are: significantly improved sampling speed; enhanced physical consistency; and stronger robustness under sparse observations.

This invention relates to the field of coal mine safety monitoring and environmental sensing, and discloses a method and system for detecting and correcting harmful gases in underground mines based on vehicle emission monitoring. The method first acquires multi-source data on vehicle emission sources, spatial location, airflow field, and sensor observations, and performs time synchronization alignment. Next, it calculates the vehicle's flow field coupling factor to the sensor and calculates the exhaust gas transmission lag time based on the airflow field and location data. Based on emission source data, lag time, and diffusion parameters, it constructs an interference prediction model to quantitatively calculate the theoretical interference concentration generated by the vehicle. Furthermore, it calculates the dynamic confidence weight coefficient and combines the observed data with the theoretical value to calculate the corrected real environmental gas concentration. Finally, it compares the real concentration with a safety threshold and executes alarm triggering or suppression control based on the result. This invention can effectively isolate vehicle exhaust gas interference, restore the true background concentration in the roadway, reduce the false alarm rate, and improve the accuracy of coal mine monitoring and production efficiency.

This invention discloses a real-time probabilistic inversion method for TBM (Tunnel Boring Machine) extrusion load based on a surrogate model. First, the extrusion load vector and its prior value range are defined for the TBM shield tunneling environment. A surrogate model is constructed and iteratively updated based on a small number of high-fidelity numerical simulation samples to establish a rapid mapping relationship between the extrusion load and the shield structure response. Then, on-site measured shield monitoring data are acquired, and a likelihood function is constructed by combining sensor observation errors and surrogate model prediction errors. Finally, within a Bayesian probabilistic inversion framework, a Markov chain-Monte Carlo algorithm is used to call the surrogate model for sampling, obtaining the posterior probability density distribution, optimal estimate, and confidence interval of the extrusion load, and calculating the shield structure failure probability accordingly. This invention can meet the real-time requirements of inversion calculations and provide a quantitative assessment of the uncertainty of the inversion results, offering a scientific basis for safety decisions when TBMs traverse strata with large extrusion deformation.

This application provides a message scheduling method, device, and program product for multi-view heterogeneous sensor data. It relates to the field of communication control technology. The method includes: receiving multi-view heterogeneous sensor data from an autonomous driving device and determining the source category of the sensor data; constructing a factor graph model of the sensor data based on the source category; representing each target state, each sensor observation, and the relationship between each target state and each sensor observation as nodes and edges in the factor graph based on the factor graph model, thereby constructing a Bayesian inference framework; and processing the received multi-view heterogeneous sensor data based on a sequential processing strategy. In this solution, a sequential / parallel switching scheduling strategy based on dependencies, combined with the factor graph model and the Bayesian inference framework, solves the non-convex optimization and convergence dilemmas of existing technologies.

This invention discloses a deep learning-driven AI data annotation quality verification method, relating to the field of annotation quality verification. It acquires building annotation vector data, multispectral image data, and sensor observation geometric parameters from remote sensing images. Topological envelope analysis is performed on the intersection contours of the projection cone and the ground, generating projection ambiguity envelope polygons for each building and cone intersection depth maps for each pixel. A sequence of equal-depth layered slices is constructed along the cone intersection depth direction. Topological disambiguation processing is performed on the overlapping areas of adjacent building projection cones. Annotation polygon attribution is determined, and pixel-by-pixel attribution confidence distribution is calculated and encoded as a geometric constraint tensor. This geometric constraint tensor is injected into a deep learning classification and verification network. A hierarchical verification based on projection ambiguity perception is performed on the annotation vector data, and the hierarchical verification results are output. Verification alarms are precisely focused on real annotation defect areas outside the projection ambiguity range.

This invention provides a method and system for measuring the lateral displacement of a bridge pier after a ship collision based on multi-source data fusion. The method includes: acquiring sensor observation data and calculating the bridge sensor displacement based on the sensor observation data; acquiring a set of bridge image frames, extracting the keypoint set corresponding to each bridge image frame set using the SuperPoint model, and then completing the keypoint set; calculating the bridge pixel displacement sequence based on the keypoint set, and then converting the bridge pixel displacement sequence to physical space to obtain the bridge visual displacement sequence; fusing the bridge visual displacement sequence and the bridge sensor displacement sequence using the EKF algorithm to obtain the observed bridge displacement; and fusing the bridge observed displacements corresponding to all cameras to obtain the actual bridge displacement. This invention solves the problem in existing technologies where measurement using visual methods is easily affected by environmental factors such as rain, fog, and dust, as well as object occlusion, leading to a decrease in measurement accuracy.

A method for a processor implementation of learning antenna offsets for sensing assisted wireless communication includes receiving an input stream from one or more sensors; generating a dynamic segmentation mask corresponding to an object observed by the one or more sensors based on the input stream; determining trajectories for the one or more sensors based on the dynamic segmentation mask; and predicting antenna localization for the object based on the trajectories.

This invention provides a method and apparatus for determining vehicle yaw rate, relating to the field of vehicle technology. The method, assuming the original measured value of the yaw rate is valid, first performs zero-bias compensation on it, then uses it as an observation variable. With the front wheel rotational speed as the control input and the yaw rate as the state variable, a discrete recursive filtering model is constructed. By running the discrete recursive filtering model, an estimated yaw rate is output. This method effectively eliminates the influence of sensor noise and zero-bias error by fusing dynamic model predictions and sensor observations through a discrete recursive filtering model, thereby improving the real-time performance and accuracy of vehicle yaw rate estimation.

The application discloses a multi-sensor data processing method suitable for high-altitude meteorological detection, which comprises the following steps: collecting meteorological data from multiple different types of sensors to obtain initial data; detecting and marking missing values and abnormal values in the initial data; using a lightweight missing data sensing type neural network to perform data interpolation to obtain a complete data sequence; performing point estimation and uncertainty joint inference on the complete data sequence to obtain corresponding point prediction values and uncertainties; solving data conflicts of different sensor data in an overlapping measurement interval to obtain fused single observation values and estimated uncertainties; and using a multi-expert hybrid model to dynamically select or weight fuse outputs of different expert models based on the fused single observation values and estimated uncertainties to obtain a fused meteorological parameter set. The application realizes real-time processing and smooth switching of multi-sensor observation data, and effectively improves continuity, stability and precision of detection data.

The application relates to the technical field of unmanned aerial vehicle (UAV) state estimation and autonomous control, and provides an UAV wind vector estimation method based on an extended Kalman filter and related products.The method comprises the following steps: initializing an extended Kalman filter in a wind vector estimator after the UAV system is powered on; periodically performing a recursive estimation process during UAV flight: performing data preprocessing on sensor data at the current moment, and extracting a preprocessed sensor observation vector; obtaining a UAV system model, predicting the state of the extended Kalman filter at the next moment based on the UAV system model and system input, and obtaining a prior state; correcting the prior state based on the sensor observation vector, outputting a UAV posterior state, and obtaining a wind vector estimation result at the current moment based on the posterior state.The application can improve the generalization of the method while ensuring the accuracy of the wind vector estimation.

The application provides a Kalman filtering method, system, device and medium for multi-mode observation input, which comprises the following steps: receiving inertial measurement unit data, adding the inertial measurement unit data and a corresponding time stamp into a first data queue; receiving sensor observation data; obtaining inertial measurement unit data meeting a time requirement from the first data queue; and using a Kalman filter to predict and update vehicle state parameters based on the inertial measurement unit data meeting the time requirement and the sensor observation data. The application uniformly carries out the prediction and update process when the sensor observation data arrives, thereby improving the reliability of vehicle state parameter update.

The application provides a semantic map-based underground and overground mapping and positioning method for a robot dog, and belongs to the technical field of autonomous navigation of mobile robots; the method comprises the following steps: acquiring original observation data through sensors carried by the robot dog; unifying the original observation data to a consistent space-time reference to obtain preprocessed observation data; performing sensor data compound filtering; adopting a multi-stage series filtering strategy to smooth the preprocessed observation data after time synchronization to obtain smoothed sensor observation values; setting a repositioning condition and taking the repositioning condition as a loop constraint; adopting an error state Kalman filter to obtain a predicted position of the robot dog through calculation; and adaptively switching different sources of observation data of the surrounding environment according to the surrounding environment and the actual elevation of the predicted position of the robot dog to construct an environment map.

This invention belongs to the field of Earth science and remote sensing technology, and discloses a method and system for identifying lithium-bearing minerals in deeply incised terrain. The method utilizes UAVs to acquire hyperspectral imagery and LiDAR topographic data; calculates the true solar-sensor observation geometric parameters of the deeply incised surface; designs a terrain shadow reflectance recovery model (TSRR) to recover reflectance in shadowed areas, and constructs a multi-parameter atmospheric correction lookup table (LUT) based on model 6S; constructs a radiative transfer-bidirectional reflectance distribution function (DIT-BRDF) model to correct for surface angle variations in deeply incised areas, and obtains the corrected spectral and spatial information; and constructs a lithium-bearing mineral identification model (SST) to automatically identify spodumene, lepidolite, lithiometrazine, and phosphogypsum. This invention significantly improves the accuracy and efficiency of remote sensing detection of lithium deposits under complex terrain conditions, providing a new technical approach for the rapid identification and quantitative assessment of lithium deposits in deeply incised areas.

This invention discloses a method for power grid data missing completion using adversarial generative networks and graph embedding. The method includes: performing self-cleaning processing on power grid measurement data containing missing values, combining physical laws and topological smoothness; identifying spurious data injection attack points and generating a cleansing mask; extracting spatiotemporal embedding features based on a graph network dual-mask mechanism to block the cross-node propagation of errors; constructing an adversarial generative network containing a dual-task discriminator to perform fine-grained cleansing quantification while judging the overall data authenticity, guiding the generator to output physically consistent high-fidelity data; and filling data blind spots through a hard-addressing fusion mechanism to retain real sensor observations. This invention solves the problem of completion failure caused by the intertwining of missing data and malicious attacks, improving the robustness and fidelity of smart grid sensing.

This application provides a data anomaly detection method based on Mahalanobis distance and chi-square detection, relating to the field of autonomous navigation and positioning detection technology. The method includes the following steps: In the extended Kalman filter correction stage, the residual vector of the sensor observation data is calculated, then the Mahalanobis distance is calculated based on the residual vector, and chi-square detection is performed using the Mahalanobis distance to determine if abnormal data exists. When abnormal data is detected, a correction suppression mechanism is triggered, and an abnormal data processing mode is entered. In the extended Kalman filter correction stage, this application first accurately calculates the residual vector of the sensor observation data, then scientifically calculates the Mahalanobis distance based on it, and effectively identifies abnormal data through chi-square detection. Once an anomaly is detected, the correction suppression mechanism is immediately triggered, entering the abnormal data processing mode to avoid erroneous correction of the system state by abnormal data, thereby significantly improving the system's positioning accuracy and operational stability, and providing a more reliable guarantee for autonomous navigation and positioning systems.

Device (10, 27) and method for sensor-based observation of a driver (11) of a vehicle (30), in particular a head-up display, comprising an image generation unit (12) for generating an image, an optical module (13) for reflecting the generated image onto a reflective surface (14) viewable by the driver (11) of the vehicle (30), an image sensor (15) onto which an image of at least one area of ​​the driver (11) reflectable at the reflective surface (14) can be reflected by means of the optical module (13), and an evaluation unit (16) which is configured to identify at least one predetermined property of the driver (11) in image data generated by the image sensor (15).

The present application relates to the technical field of gas detection, and discloses a dangerous chemical emergency detection multi-sensor dynamic calibration and error compensation system, which comprises a data acquisition module, a space modeling module, a data determination module, a weight changing module and a data output module.The data acquisition module uses multiple sensors to form an array, acquires the response signals of target dangerous chemicals and related interference gases, and performs time registration and filter pretreatment.The space modeling module constructs an extended state vector, and establishes a state transition equation and an observation equation.The data determination module determines the fused concentration and real-time drift parameters according to the state estimation value and the sensor observation value.The weight changing module calculates the observation residual and the statistical quantity of each sensor, reduces the fusion weight of the sensor when the residual of any sensor continuously exceeds the preset threshold, and marks the abnormal state.The data output module uses the drift parameters of each sensor to online correct the original measurement value, and finally outputs the dangerous chemical concentration and the confidence interval after dynamic calibration, so that the self-calibration and data output of the system in an emergency scene are realized.

This application relates to the field of water conservancy engineering technology. It provides a method for detecting and repairing anomalies in hydrological data through multi-sensor collaboration. The method includes: establishing a dynamic trust level model based on environmental parameter sets and historical sensor states; generating a real-time trust level vector by fusing sensor health status, environmental adaptability, and historical reliability; verifying the consistency of multi-sensor observations using the real-time trust level vector; generating an anomaly arbitration command when data conflicts are detected; responding to the anomaly arbitration command by processing conflicting data clusters through a context-aware arbitration mechanism to generate an arbitration weight vector; reconstructing the conflicting data clusters based on the arbitration weight vector to obtain a repaired data stream; and feeding the repaired data stream back to the dynamic trust level model for updating. This method aims to improve the dynamic adaptability of data fusion, enhance the hydrological scenario matching degree of conflict arbitration, and optimize the physical rationality of the repair results.

This application relates to the field of industrial digital control technology, and in particular to a method, device, terminal equipment, and storage medium for correcting the flow field of a coal-fired boiler. The method includes: real-time acquisition of operating condition parameters and sensor measurement data of the coal-fired boiler; inputting the operating condition parameters and sensor measurement data into a trained reconstruction model to obtain a reconstruction result of the global flow field inside the boiler; evaluating the operating state of the coal-fired boiler based on the reconstruction result to obtain an evaluation result, and performing control optimization operations on the coal-fired boiler based on the evaluation result; and comparing the difference between the reconstruction result and the sensor observation data in real time. When the difference exceeds a preset threshold, the reconstruction model is adjusted to achieve accurate control of the coal-fired boiler.

The application discloses a toluene gas leakage diffusion range prediction simulation method and system, and belongs to the technical field of gas leakage diffusion simulation. The method comprises the following steps: a toluene leakage physical model based on Reynolds average Navier-Stokes equation set and a standard kappa-e turbulent flow model is constructed to generate high-fidelity true value data; a physical information neural network model of an 8-layer full-connection residual network is constructed, time coordinates, three-dimensional space coordinates, wind speed and wind direction are taken as inputs, and an initial predicted concentration field is output; a data assimilation model based on ensemble Kalman filtering is constructed, sensor observation data is fused, optimal state estimation is obtained through ensemble initialization, prediction steps and analysis steps, and a corrected concentration field is generated; based on the corrected concentration field, concentration values are converted into real-time dynamic risk fields through a dynamic risk field mapping function and a Probit toxicology model. The application realizes high-precision prediction and dynamic risk assessment of the toluene leakage diffusion range.