130 results about "Active sensing" patented technology

A depth map for a scene may be generated by projecting, by a light projector, an illumination pattern onto a scene; capturing, by a camera, a camera image of the scene; generating, by a computing device, a plurality of ground truth depth values for sample pixels of the camera image based at least in part on the illumination pattern; and estimating a depth map for the scene based at least in part on the camera image and the ground truth depth values for sample pixels.

The invention discloses a road guardrail real-time monitoring device and system based on wireless networking, and relates to the technical field of road facility monitoring, the road guardrail real-time monitoring device comprises a cloud data management platform, the cloud data management platform is in communication connection with a guardrail monitoring node module, an edge computing gateway module, an abnormal state alarm module and an operation and maintenance management module, the modules are in electric signal connection; the guardrail monitoring node module is used for planning monitoring nodes in an area to be monitored and deploying guardrail monitors at the monitoring nodes so as to acquire guardrail state data of the monitoring nodes in real time. Through the wireless networking technology, the road guardrail state is monitored in real time, and tiny deformation, abnormal vibration and inclination angle change of the guardrail can be captured in time, so that the real-time performance and accuracy of traffic safety monitoring are improved, and compared with traditional passive inspection, the active sensing mode has the advantages that the traffic safety is improved, and the traffic safety is improved. The labor cost and the leak detection risk are greatly reduced, and a powerful guarantee is provided for road traffic safety.

The invention discloses a multi-modal information fusion and active sensing pipeline defect absolute positioning method and device, which are suitable for a complex pipeline environment. The method comprises a cable deformation error compensation model, a cable speedometer and wheel type speedometer fusion algorithm based on visual auxiliary dynamic slip rate adjustment, and a pipeline defect positioning and measuring algorithm based on an improved monocular distance measurement algorithm and an active sensing strategy. And a pipeline defect geographic coordinate solving algorithm based on mileage information, GNSS and IMU information fusion. The cable deformation error compensation model corrects a measurement error caused by self-weight deformation of the cable; a cable odometer and wheel type odometer fusion algorithm is used for inhibiting positioning drift caused by tire slipping; an improved monocular distance measurement algorithm is used for calculating depth information and measuring the defect size by using the actual radius of the pipeline and the defect pixel radius; the active sensing strategy dynamically adjusts the observation distance to improve the defect positioning precision; and fusing the mileage information, the GNSS information and the IMU information to solve the position of the defect in an earth coordinate system.

The invention relates to the technical field of mobile communication, and discloses a prediction-based network congestion avoidance system, which comprises a data sensing end, a space-time prediction end, a strategy generation end and an execution feedback end, and is characterized in that the data sensing end, the space-time prediction end, the strategy generation end and the execution feedback end are jointly integrated with a voice alarm module; a data sensing end is arranged, when network state monitoring is carried out, a network topological graph with weights is constructed in real time, a timestamp index feature matrix is generated, the time delay defect of a traditional passive response mechanism is eliminated, and an active sensing mechanism constructed at the end captures link dynamic features before service damage; the real-time performance and the first-onset performance of congestion risk identification are ensured, the problem of service interruption caused by post-detection is overcome, and the core defect of insufficient prediction model precision is solved by setting a space-time prediction terminal and based on a collaborative modeling architecture of a graph convolutional neural network and an attention mechanism during congestion risk analysis.

The invention relates to the technical field of information retrieval, in particular to an academic supply and demand dynamic sensing method and system based on space-time big data, and the method comprises the following steps: obtaining the path length of a source and a target college, screening migration direction stable labels, recognizing a trend consistent region, evaluating the local transfer capacity, and fusing a high-frequency path region. And extracting behavior track data, performing sequence comparison on the associated nodes, and generating a prediction chain space offset mark set. According to the method, space label units with stable migration characteristics are effectively distinguished by processing enrollment information and population migration trends and constructing a path length filtering and direction section repeating mechanism, and supply and demand migration origin areas are accurately locked in combination with change trends reflected by continuous direction consistency; spatial aggregation judgment is enhanced through a statistical means of a neighborhood capacity proportion and path intersection frequency, the sensitivity and dynamic response capability of a spatial prediction structure are improved, and active sensing and intervention prompting of a supply and demand change trend under multiple space-time dimensions are realized.

The invention provides an active train sensing system and method based on thunder and vision fusion. Comprising an acquisition module used for acquiring multi-path image data containing different focal length images and three-dimensional point cloud data corresponding to the front of a train; the time synchronization module is used for generating synchronous image data and synchronous three-dimensional point cloud data; the coordinate transformation module is used for establishing a spatial transformation relation between the three-dimensional point cloud coordinate system and the image coordinate system; the image sensing module is used for inputting the synchronous image data and the three-dimensional point cloud data into the target segmentation network to obtain track coordinates; the point cloud sensing module is used for obtaining three-dimensional point cloud data in front of the train; and the thunder-vision fusion module is used for distributing an accurate center representative coordinate for each obstacle, generating structured obstacle information and outputting the structured obstacle information to a vehicle-mounted train control system. The multi-source sensing information utilization rate can be improved, the track obstacle recognition and three-dimensional positioning precision is improved, and the system sensing stability in a complex scene is enhanced.

The invention discloses a train control system, method, equipment and medium based on active sensing and autonomous localization, and the system comprises a multi-source autonomous sensing system which collects and outputs the information of the environment in front of a train by fusing the sensing data of a plurality of sensors; the vehicle-mounted standby system is in communication connection with the multi-source autonomous sensing system, accesses a pre-stored digital track map and is used for dynamically generating route topology and movement authorization and generating a train control instruction according to the train front environment information, the train real-time position and the line data of the digital track map; a dual-mode communication switching unit is arranged in the vehicle-mounted standby system and used for monitoring the communication state of the main train control system, and when the main train control system breaks down, the train control right is automatically switched to the standby system. Compared with the prior art, after the main train control system loses efficacy, the train can be made to be independent of a central control system and a fixed electronic map, the real-time state of a line is automatically adapted, and the safe driving instruction is generated.

The invention belongs to the technical field of robot autonomous operation and reinforcement learning, and discloses an intelligent active perception and behavior interaction method in an unknown shielding scene. According to the method, a viewpoint planning strategy of an active sensing agent and a pushing strategy of a behavior interaction agent are closely fused, a 2.5 D occupancy height map is combined, and a pushing point screening mechanism of geometric features and task heuristic weights and a dense reward function are fused; the problems of insufficient perception information, low action efficiency and unstable strategy training in an unknown shielding environment are solved. According to the method, the pushing success rate, the environment entropy reduction efficiency and the strategy generalization ability are remarkably superior to those of a traditional method, efficient environment exploration can be achieved only through minimum invasive pushing of the scene, a good foundation is laid for tasks such as downstream grabbing and cleaning, and the method is suitable for robot autonomous operation of disordered shielding scenes such as bookshelves and storage cabinets.

The invention discloses a laser deicing method and device based on ice layer thickness and surface state recognition, belongs to the technical field of fan blade deicing, and aims to solve the problems of low efficiency, large energy loss and high blade damage risk caused by incapability of accurately sensing the ice layer state in the conventional fan blade laser deicing technology. The system comprises an active sensing module and a laser clearing module. The active sensing module measures the thickness and the surface state of an ice layer through infrared laser, and performs multi-dimensional monitoring in combination with a laser radar, a camera and a thermal infrared imager. And the laser clearing module dynamically adjusts laser parameters for deicing according to the sensing result. According to the invention, a non-contact ice thickness measurement method based on infrared laser and a surface state identification method based on relative illumination intensity are created for the first time, and accurate sensing of the ice layer state is realized. A laser and a power supply are fully integrated in the unmanned aerial vehicle, the constraint of a ground platform and optical fibers is eliminated, and the deicing task of the fan blade is accurately completed.

The invention relates to the technical field of image processing, and discloses an H.265 coded video packet loss image recovery method based on machine learning, which comprises the following steps: acquiring packet loss characteristics of a receiving end at the current moment, inputting a packet loss prediction model pre-constructed based on characteristic dimension expansion, and outputting a packet loss characteristic prediction value at the next moment; determining whether the receiving end sends key frame request information to the sending end or not based on a comparison strategy of different thresholds and packet loss feature predicted values under different network data, so as to obtain the key frame at the current moment for continuing decoding; and if recovery cannot be realized through the key frame request, introducing a packet loss recovery mechanism of intra-frame and inter-frame prediction for different lost image frame types, and performing image recovery of the lost area by using different packet loss image recovery strategies. According to the method, a complete technical chain from prediction, decision making to repairing is constructed, and the modern video coding standard and an intelligent learning mechanism are deeply combined, so that active sensing and accurate repairing of the video packet loss are realized.

The embodiment of the invention provides a multi-modal large model agent collaborative water quality inversion method based on active perception, which belongs to the technical field of data processing, and specifically comprises the following steps: step 1, a decision agent issues a water quality monitoring task; 2, the data intelligent agent collects multi-source remote sensing and ground monitoring data, image preprocessing and multi-modal enhancement are carried out, and a standardized input sample is generated; step 3, analyzing intelligent agent fusion image, time sequence and text features, and performing water quality level prediction and natural language interpretation through a multi-modal large language model; 4, performing task scheduling and resource allocation by the decision-making agent based on a water quality grade prediction result, generating a standard operation process, and triggering sampling and early warning; and 5, applying the execution result and the reward feedback to strategy optimization and parameter updating of the decision-making agent, and continuing to publish a new task to form a self-adaptive closed-loop iteration mechanism. Through the scheme of the invention, the prediction accuracy and interpretability are improved.

The application provides a detection device and method for fasteners and a fastener, and belongs to the technical fields of precision manufacturing and industrial visual detection. The method comprises the following steps: performing multi-spectrum active illumination configuration on a fastener production line to generate multi-spectrum illumination parameter data; deploying a multi-spectrum light source array according to the multi-spectrum illumination parameter data to construct a multi-spectrum active sensing network; and through the fusion application of multi-spectrum active illumination and neural radiation field three-dimensional reconstruction technology, the recognition accuracy of the surface defects of the fastener is significantly improved, the geometric size measurement is realized to the level of ±0.003 mm, and the detection rate of the micro defects is improved to 99.5%.

The invention discloses a health state assessment method and system driven by energy equipment operation data, and belongs to the field of data processing.The health state assessment method driven by the energy equipment operation data comprises the following steps that original operation data of energy equipment is collected, data cleaning, feature engineering and data standardization are carried out, and a health state assessment result is obtained; obtaining available data of the model; selecting a regression algorithm to construct a health assessment model, and training model parameters by using health equipment data and fault equipment data; after the original operation data of the to-be-detected energy equipment is preprocessed, the method has the beneficial effects that the operation data of the energy equipment are collected in real time, the health assessment model is constructed, the quantized energy equipment health score is output, and the active sensing of the state of the energy equipment is realized; the detected slight faults, early faults of non-core components and the like are temporarily not maintained, fault evolution data are continuously collected and used for training a more accurate health assessment model, and short-term risk is changed into long-term precision improvement.

The embodiment of the invention provides a Cartesian genetic programming energy scheduling method and related equipment, and belongs to the field of energy scheduling and evolution calculation. The method comprises the following steps: acquiring an environment state and a discrete action set of an energy system; a CGP population is initialized; adopting an explicit action selection strategy to splice the state and each candidate action into an augmented input vector, inputting the augmented input vector into a CGP individual to obtain a scalar score and preferentially execute the scalar score, and calculating the fitness; in the evolutionary process, an active sensing sampling mutation operator is applied to generate a filial generation: active nodes in a genotype are identified through reverse traversal, and a mutation budget is dynamically allocated according to the active nodes, so that resources are inclined to the active nodes, and meanwhile, a small amount of inactive node variation is reserved. According to the method, the search efficiency and the solution quality are remarkably improved through the directional variation mechanism, and meanwhile, the generated scheduling strategy is a completely symbolized mathematical expression, has high interpretability and easy deployment, and is suitable for real-time optimization scheduling of a multi-energy microgrid and an active power distribution network.

This invention discloses a compliant connection platform, comprising a first cross spring group, a frame unit, and a second cross spring group sequentially connected along the axial direction. The frame unit includes a support component and a first connecting portion and a second connecting portion respectively disposed at both ends of the support component. The first cross spring group is fixedly connected to the first connecting portion, and the second cross spring group is fixedly connected to the second connecting portion. The support component can deform in a plane perpendicular to the axial direction. The first and second cross spring groups are orthogonally arranged in a plane perpendicular to the axial direction, enabling the compliant connection platform to achieve five degrees of freedom passive compliance compensation. This invention achieves automatic alignment of docking points without active sensing control, has a simplified and compact structure, significantly reduces the accuracy requirements for docking and assembly, and is suitable for the rapid docking and reconfiguration needs of modular vehicles under complex operating conditions.

The invention relates to an industrial personal computer hardware state intelligent monitoring and self-repairing method and system. The method comprises the following steps: collecting hardware state data of an industrial personal computer in a current time period according to an embedded sensor configured in the industrial personal computer; determining a fault prediction model constructed based on a long short-term memory network, and inputting the hardware state data into the fault prediction model for adaptive time sequence analysis processing to obtain a hardware fault prediction result corresponding to the industrial personal computer; and according to a preset hierarchical repair mechanism, performing hierarchical repair processing of combining a software layer and a hardware layer on the industrial personal computer based on the hardware fault prediction result to obtain a hardware repair result corresponding to the industrial personal computer. By adopting the method, intelligent monitoring of the hardware state in the operation process of the industrial personal computer and active sensing and self-repairing of faults can be realized.

The invention relates to the field of data storage, in particular to a data query method and device, electronic equipment and a storage medium, a logical block address range of each node is stored in a cache of the storage medium, and the logical block address range comprises a latest accessed logical block address. The information can reflect the distribution condition of the hot data. When a data access request arrives, the address of the target logic block can be matched with the address range of the node, so that active sensing of hot data is realized. If the target logical block address is in the address range of a node, it can be determined that the node stores target data. Finally, the target data can be directly inquired and obtained from the cache according to the matching result, and a long I / O path is not needed. The data reading efficiency and the response speed can be improved.

The application discloses an AI teaching feedback and self-evolution method and system based on active sensing and mixed thinking mechanism. The method comprises the following steps: generating student behavior characteristics, emotion characteristics and teacher-student voice characteristics; generating student state-teaching content structured information through a semantic analysis model; obtaining behavior emotion analysis information through a thinking scheduling module core model; generating visual perception module optimization parameters, semantic analysis module optimization parameters and thinking scheduling module optimization parameters according to all historical high-quality classroom video annotated efficient interaction segments and behavior emotion analysis information of each period; and updating the visual perception type model, the semantic analysis model and the thinking scheduling module core model. The application constructs a self-evolution system, which can continuously improve the sensing accuracy, analysis accuracy and scene adaptability without manual intervention, and completely solves the problems of static and no evolution ability of the traditional teaching analysis system.

The present application relates to the technical field of pipeline hydrostatic test, and especially relates to a pressure water supplementing and metering device for municipal pipeline hydrostatic test, which comprises a water tank, a booster pump, a flowmeter and a control cabinet, a program controller is arranged in the control cabinet, further comprising a pressure sensor and a vibration sensor arranged along the axial direction of the pipeline to be tested, and an active tunable damper arranged between the pump outlet and the pipeline; the program controller synchronously collects pressure and vibration data, carries out correlation analysis on the data, generates a pressure wave space-time propagation graph, calculates a water hammer risk index and divides a risk level through a nonlinear fusion model according to the dominant frequency, amplitude, propagation speed change rate and vibration energy of the pressure wave, selects an inhibition strategy according to the risk level, calculates a pressure peak value reduction rate and a wave fluctuation decay time according to the data after inhibition, and generates an effect evaluation value. The present application realizes active sensing, graded inhibition and effect evaluation of water hammer risk, and improves the safety and intelligent level of the hydrostatic test.

The application discloses a monocular depth estimation method based on active sensing, comprising: acquiring a monocular RGB image of a surgical area; acquiring an initial sparse depth measurement set; inputting the RGB image and the sparse depth measurement set into a depth estimation integrated model to output an integrated dense depth prediction map and a prediction uncertainty map; calculating a gradient of the prediction uncertainty map to a measurement value in the current sparse depth measurement set; selecting a next group of points to be probed by using a Stein variational gradient descent algorithm based on the gradient map; controlling a tactile sensing end of a surgical robot to move to an anatomical position corresponding to the point to be probed to perform contact measurement; updating the newly acquired depth measurement value to the sparse depth measurement set; iteratively optimizing the depth estimation and uncertainty evaluation, and outputting a final integrated dense depth prediction map as a surgical navigation three-dimensional scene model. The application can enhance the accuracy of monocular depth estimation by sparse proprioceptive depth measurement.

The application provides an intelligent pollution cleaning method based on multi-modal deep learning, real-time monitoring of a pollution accumulation area is performed, and a real-time picture of a trash rack area is transmitted, a pollution detection data set is generated, and a pollution recognition algorithm based on deep learning is trained, the pollution recognition algorithm is used to recognize pollution in the real-time picture of the trash rack area and mark position information of the pollution, a multi-modal deep learning model is established to determine whether a pollution cleaning device is started, and factors such as an area of the pollution accumulation area, a water level difference of an inlet, weather conditions and rainfall are comprehensively considered, when an output result of the model reaches a preset value, it is determined that the pollution cleaning device starting requirement is met, through intelligent identification, automatic operation and informationized collaboration of the whole process of the hydropower station pollution cleaning system, the application improves the pollution cleaning efficiency of the trash rack of the hydropower station inlet and the reliability of the pollution cleaning device, and promotes the intelligent leap of the pollution cleaning system from passive response to active sensing.

The application belongs to the technical field of measurement, and relates to a kind of water-related infrastructure intelligent measurement method and device, the method comprises: based on historical drawing, BIM model and laser scanning point cloud data, prior modeling is carried out in multi-source heterogeneous environment, and measurement task dynamic adaptation is carried out;Based on the dynamic adaptation result of measurement task, a multi-modal adsorption propulsion robot is designed;Through the multi-modal adsorption propulsion robot, multi-spectrum fusion active sensing and defect enhancement identification are carried out in turbid water area;Based on the self-optimizing path planning algorithm of structural constraint, path planning and motion control are carried out;Design lightweight semantic communication protocol, and build interactive console in virtual reality mode;Intelligently fuse and analyze the collected multi-dimensional measurement data, and evaluate the state of water-related infrastructure.Not only the work efficiency is improved, but also the safety of the measurement process is ensured;It is helpful to realize accurate maintenance and prolong the service life of infrastructure.

This invention belongs to the field of road engineering technology, specifically relating to an integrated self-adhesive rubber asphalt asphalt crack repair and monitoring system. The system includes: a self-adhesive rubber asphalt composite material layer for filling cracks and absorbing stress; a flexible sensing network unit embedded within the layer to sense strain and temperature; a data acquisition and signal conditioning module; a self-powered energy capture system that utilizes ambient energy to power the system; an edge computing terminal for localized damage assessment; and a remote cloud management platform. This system improves bonding strength and low-temperature flexibility through material modification, and combines embedded sensing and self-powered technology to achieve a leap from passive filling to active sensing of the repair body. It solves the problems of difficult power supply in the field and lack of coordination in monitoring, enabling real-time feedback of the interface mechanical state, significantly improving the scientific nature and predictability of highway maintenance, and reducing overall operation and maintenance costs.

The embodiment of the invention provides a control method and device of self-moving equipment, equipment, a medium and a program product, and relates to the technical field of intelligent control. The method comprises the following steps: if a pulse signal is detected from sensing signals acquired by a pressure sensor, determining a characteristic value of the pulse signal; wherein the characteristic value is used for representing a rainfall state in an environment where the self-moving equipment is located; and controlling the movement of the self-moving device based on the characteristic value. According to the embodiment of the invention, the self-moving equipment can actively sense the rainfall environment, and the robustness and autonomy of the self-moving equipment in the outdoor environment are improved.

The invention discloses a method for selecting a weak environment information active sensitive device of a patrolling ammunition fuze, which comprises the following steps of: selecting a function, calculating scores, and selecting an active sensitive device with the highest score to detect weak environment information; the selection principle comprises the measurement precision, the installation performance, the frequency response range, the detection sensitivity and the linearity of the active sensitive device and the measurement precision under the change of natural environmental factors. According to the method, the patrolling ammunition fuze can select the active sensitive device with the optimal performance to sensitize the environment characteristics according to the weak environment information available in the outer trajectory flight, so that fuze researchers do not need to select the sensitive device depending on experience, trial and error are avoided, the fuze research and development period is shortened, and the process cost is reduced; and the fuze can be reliably sensitive to weak environment information.

The invention belongs to the technical field of bolt fatigue damage monitoring, and discloses a high-strength bolt fatigue damage monitoring system and method based on piezoelectric active sensing, and the method comprises the steps: achieving the rapid monitoring of the fatigue damage of a high-strength bolt through the cooperative work of piezoelectric ceramic pieces PZT-A and PZT-B in combination with the driving of a high-voltage amplifier and the signal conversion of a charge adapter, meanwhile, the complex stress state of the high-strength bolt in actual service is simulated, and the damage state is fed back in real time through stress wave propagation characteristic changes. The test period is shortened, a large number of test pieces do not need to be consumed for statistical test, and the research cost is remarkably reduced. A standardized monitoring scheme is provided for high-strength bolt fatigue performance evaluation, and integrated deployment of a structural health monitoring system is supported. And through real-time monitoring data feedback, the research efficiency and precision are improved, and an intelligent solution is provided for safe operation and maintenance of an engineering structure.

The application relates to the technical field of intelligent storage, and provides an automatic fault repairing method based on a storage unit architecture and related equipment. A dynamic defect entropy of an internal defect accumulation degree of a storage medium is calculated by collecting defect-sensitive electrical parameters of a storage unit; when the dynamic defect entropy exceeds a preset repairing threshold, a voltage amplitude and a pulse width of a repairing pulse are adaptively generated; a repairing excitation matched with a storage unit type is applied to the storage unit according to the voltage amplitude and the pulse width of the repairing pulse, so as to drive atoms, dipoles or magnetic moments in the storage medium to be rearranged; defect-sensitive electrical parameters of the same address unit in the storage unit after repairing are collected, the dynamic defect entropy after repairing is recalculated, and if the repairing is invalid, the repairing parameters are strengthened and the repairing is repeatedly executed. Active sensing of internal metastable defects of the storage medium and material-level lattice reconstruction repairing are realized, so that the effective service life of the storage unit is significantly prolonged under the condition of radiation accumulation.

The application relates to the field of artificial intelligence, and in particular discloses a digital human intelligent service system for human-computer interaction; the system comprises a sensing end, an inference end and an interaction end; the sensing end is arranged in a physical space of a service site, collects behavior data of a user in a service scene and environment-related information in real time through a multi-modal sensor array, and sends original sensing data collected to the inference end; the inference end is used for receiving the original sensing data, performing identity recognition and intention inference processing on the original sensing data, generating a service instruction sequence matched with a current service context of the user according to an inference result, and sending the service instruction sequence to the interaction end; and the interaction end is used for receiving the service instruction sequence, driving a digital human virtual image to perform corresponding service actions. The application replaces the dependence on explicit operation of a user in a traditional instruction driving mode through active sensing of a user identity and behavior context by the sensing end.

This invention discloses a method, device, and medium for dynamic sensing across the entire distribution network, belonging to the field of power system operation and control technology. The method includes constructing an active sensing layer to collect transient waveform data; fusing the transient waveform data with distribution network operation data to generate a global data correlation cloud map; performing reverse backtracking based on the global data correlation cloud map when a tripping event occurs to form an event chain; constructing an operational stress accumulation model based on the event chain for latent defect early warning; sensing the defect source based on the latent defect early warning results; and generating a dynamic sensing map of the distribution network by integrating the event chain, early warning results, and defect source. This invention achieves end-to-end connectivity and closed-loop optimization from bottom-level data sensing to top-level decision support.