16results about How to "Eliminate mismatch" patented technology

The application relates to the technical field of image detection, and discloses a scale-invariant contour matching method and device based on machine vision and a storage medium, the method comprising the following steps: extracting a target contour from a template and a query image and detecting key points; constructing a multi-scale contour context descriptor for each key point, the descriptor being composed of chord length ratios and chord angle features under multi-scale in a local neighborhood; performing feature matching, estimating scale and rotation transformation parameters according to chord length ratios and chord angles of a matched descriptor pair, and combining key point coordinates to calculate a translation parameter to generate a similarity transformation hypothesis; clustering all hypotheses as points in a high-dimensional parameter space to obtain candidate instances; for each candidate instance, fitting an accurate similarity transformation model and eliminating false matching by using a random sample consensus algorithm through matched point pairs associated with the candidate instance, and outputting final positioning parameters of a target object. The application realizes efficient, accurate and scale- and rotation-invariant contour matching.

The invention relates to a fuel cell self-learning control method for a vehicle-mounted multi-core controller, and the method comprises the steps: building a fuel cell system mechanism model based on fuel cell mechanism research, simplifying the model, and obtaining a fuel cell system control-oriented model; designing a controller to control the fuel cell system; calculating a model parameter at the next moment by adopting a model parameter self-learning algorithm; the controller parameters are updated in real time by adopting a controller self-learning algorithm; a multi-core processor is used, and fuel cell system self-learning control tasks are distributed to all cores of the processor and executed in a parallel mode. The fuel cell system parameter self-learning control method combining the model and controller real-time updating is provided, the working condition adaptation range of the fuel cell system is widened, and the model and control precision of the fuel cell system is improved; according to the method for realizing task parallelism by using the multi-core controller, the program running time is shortened, and the control real-time performance can be improved.

This invention relates to the field of industrial visual inspection technology and discloses a visual detection method for particulate contaminants in coolant. The method includes: acquiring parallel polarization image sequences and orthogonal polarization image sequences by performing dual-channel synchronous polarization image acquisition using a beam splitter; performing inter-frame cross-power spectrum subpixel displacement estimation on the parallel polarization image sequences to generate a frame-by-frame subpixel motion field vector sequence; performing subpixel-level translation correction on the dual-channel image sequences based on the subpixel motion field vector sequence to generate a background-stabilized dual-channel polarization sequence; performing pixel-by-pixel temporal fluctuation intensity statistics and short-time frequency analysis to generate a set of particulate contaminant events; extracting dual-channel grayscale time-series signals and calculating polarization degree time-series signals; performing phase-compensated coherent superposition to generate a cumulative polarization degree sequence; extracting multidimensional optical polarization feature vectors and inputting them into a pre-trained classifier to output material category labels and classification confidence scores; and generating a detection report.

This invention discloses a fine motor imagery decoding system based on PINN and multimodal fusion. The system employs a fine motor imagery decoding method based on PINN and multimodal fusion, and includes a multimodal physiological signal synchronous acquisition module, a data preprocessing and correlation analysis module, a dual-stream decoding network module, a physical manifold constraint layer module, an adaptive gradient balance optimization module, and a classification decision module. By deeply embedding biophysical mechanisms into a deep learning framework, this invention addresses the ill-posedness of the source localization inverse problem, overcomes overfitting in small-sample scenarios, and significantly improves the decoding accuracy, robustness, and physiological interpretability of fine hand movements.

The application relates to the technical field of intelligent detection, and discloses a system and a method for adjusting a recognition algorithm after intelligently detecting and recognizing a scene, wherein the method comprises the following steps: acquiring current frame detection data and extracting multi-dimensional scene feature descriptors, and maintaining a scene descriptor time sequence cache queue; performing time sequence difference analysis on the queue to generate a scene mutation prediction signal; based on the signal state, pre-fetching a target scene recognition algorithm parameter set to a pipeline preparation register; when a new frame arrives, promoting the parameter set in the preparation register to an effective parameter and performing feature separation operation; performing multi-dimensional target recognition on each feature response separation graph and calculating a weighted fusion confidence score; screening a candidate target region and outputting a detection and recognition result.

The invention provides a mechanical arm trajectory tracking control method fusing model prediction and sliding mode control. The mechanical arm trajectory tracking control method comprises the steps that a discrete sliding mode controller is constructed, and a discrete sliding mode surface based on trajectory tracking errors is designed; calculating a sliding mode control law; constructing a dynamics prediction model based on an echo state network, and performing online learning and updating by taking historical state data and a sliding mode control law of the mechanical arm as input so as to predict a state track of the mechanical arm in a future time domain; constructing a model prediction controller embedded with sliding mode control, and introducing a prediction state and a sliding mode control law into an optimization objective function of the model prediction controller; and under the model prediction controller, an optimization problem is converted into a quadratic programming problem to be solved, a smooth optimization control quantity meeting physical constraints is obtained, and the control quantity acts on the mechanical arm system. The high-frequency buffeting problem of sliding mode control is effectively solved, and meanwhile high-precision trajectory tracking of the mechanical arm under strong nonlinear interference is guaranteed.

The application relates to the technical field of semiconductor devices, in particular to a method for preparing a gallium oxide material for a power device based on phase conversion and application thereof. The method comprises the following steps: depositing a polycrystalline Ga2O3 film on a substrate and heavily doping the same as a substrate material for subsequent device preparation; bonding a light-doped beta-Ga2O3 film with a preset thickness on the polycrystalline Ga2O3 film through bonding, and using the lattice arrangement of the beta-Ga2O3 as a traction for the subsequent polycrystalline Ga2O3 phase conversion process; converting the polycrystalline Ga2O3 into beta-Ga2O3 under preset conditions, and repairing the damage of the film interface during bonding; and removing the substrate, thereby completing the material preparation of the device. The method utilizes the property that the metastable phase of gallium oxide isomers can be converted into beta-phase isomers under certain conditions, converts the polycrystalline Ga2O3 film into a high-quality beta-Ga2O3 substrate, eliminates the lattice mismatch between different phases, and finally obtains a low-cost high-quality beta-Ga2O3 film which can realize a large power device.

The present invention relates to a fuel cell self-learning control method for a vehicle-mounted multi-core controller, the method comprising: establishing a fuel cell system mechanism model based on fuel cell mechanism research, and then simplifying the model to obtain a control-oriented model of the fuel cell system; designing a controller to control the fuel cell system; using a model parameter self-learning algorithm to calculate the model parameters of the next moment; using a controller self-learning algorithm to update the controller parameters in real time; using a multi-core processor to distribute the fuel cell system self-learning control task to each core of the processor and execute it in parallel. The present invention proposes a fuel cell system parameter self-learning control method that combines real-time updates of the model and controller, improves the operating condition adaptability range of the fuel cell system, and improves the model and control accuracy of the fuel cell system; the present invention uses a multi-core controller to implement a task parallel method, which reduces the program running time and can improve the real-time performance of the control.

The invention discloses an electric vehicle aggregator intelligent bidding decision-making method and system for a virtual power plant, and relates to the technical field of power systems, and the method comprises the steps: employing an aggregation virtual energy storage model to evaluate the aggregation flexibility of an electric vehicle cluster at a first time level; converting the evaluated aggregation flexibility into an energy bidding interval of a second time level; constructing and initializing a bidding strategy model of the electric vehicle aggregator based on a reinforcement learning theory; determining a standardized energy bidding decision based on the bidding strategy model, performing affine transformation by using the energy bidding interval to obtain an energy market bidding decision, submitting the energy market bidding decision to the energy market and obtaining a decision reward; and training the bidding strategy model, and updating the bidding strategy. According to the method, time scale conversion is introduced, so that mismatching of minute-level aggregation modeling and hour-level bidding decision on the time scale is avoided; and the risk of price uncertainty faced by the electric vehicle aggregator during bidding decision making is overcome by optimizing the optimal bidding strategy.

The invention relates to the field of information management, in particular to an intelligent talent information management system in a technology transfer process, which comprises a talent information management module, a project information management module, a project analysis module and a skill matching module. A mean value clustering algorithm based on a flight path is used for carrying out clustering analysis on the comprehensive vector, the capability and adaptability of each talent are comprehensively reflected, and high-dimensional data integration is beneficial to considering more factors during matching, so that the matching precision is improved; the outlier detection technology is used in the skill matching module for confirmation and analysis, and the integrity and accuracy of a data set are ensured by identifying and eliminating abnormal values, so that an enterprise can more effectively allocate human resources and project budget, and more efficient resource allocation and cost control are realized.

The invention provides a true random number generator and a true random number generation method, and relates to the technical field of chip design, the method outputs a current difference value through a first transistor and a second transistor, and adjusts the threshold voltage of the first transistor and the second transistor, the current difference value is used for controlling the output of the first output end and the second output end; and outputting random data according to the first enable signal and the current difference value, and performing chained processing on the random data to output a true random number. According to the method, the mismatch problem of the true random number generator is solved through a programmable charge trapping transistor, mismatch in a comparator is eliminated in a nonvolatile mode, meanwhile, the randomness of data is further improved by using a post-processing circuit, and the area and power consumption overhead are reduced.

The invention relates to the technical field of thermal interface materials, in particular to a composite thermal interface material based on metal aerogel and a preparation method and application of the composite thermal interface material. The composite thermal interface material based on the metal aerogel prepared by the invention has excellent flexibility. Compared with a conventional polymer-based heat-conducting pad in the prior art, a three-dimensional heat-conducting network formed by the metal aerogel greatly improves the deformability of the composite thermal interface material, the composite thermal interface material can be adaptively attached to the surface of a complex structure, better processing conditions and process results are achieved, and the interface thermal resistance of the thermal interface composite material is reduced.

The present invention provides an image feature matching method and device based on local consistency, the method comprising: obtaining two images to be matched; detecting feature points in the two images by SIFT algorithm and establishing feature descriptors; constructing a set of initial matching sets according to the similarity of feature descriptors in the two images; deleting mismatches from the initial matching set by neighborhood consistency constraint to obtain a second matching set; calculating the deviation of the motion vector of each feature point by the second matching set; optimizing a preset image feature matching model by constraining the deviation of the motion vector by motion vector consistency, and determining hyperparameters; performing feature matching on any two images to be matched by the optimized image feature matching model to obtain an image feature matching result. The present invention has the beneficial effects of: combining the local consistency of neighborhood consistency and motion vector consistency to remove and optimize mismatches in image feature matching, thereby improving matching accuracy.

The application discloses a kind of compressed computing spectral imaging reconstruction method and system based on pulse weighted network, it is related to computing imaging technical field, it can be from compressed measurement value with low energy consumption and high quality Reconstruct HSI data, can greatly improve the energy efficiency ratio of reconstruction algorithm.The scheme is specifically as follows: using coded aperture snapshot spectral imager CASSI obtains the two-dimensional compressed measurement value of known target scene three-dimensional hyperspectral imaging technology HIS data cube.The two-dimensional compressed measurement value obtained is preprocessed, image features are extracted, and the initial value of the reconstruction result of the HSI cube of the known target scene is obtained.The initial value of the reconstruction result is spliced with the coded pattern of the compressed spectral imaging system, and is sent into the trained multi-time-step reconstruction network to obtain the output result of the network, i.e., the reconstruction result of the hyperspectral data of the target scene to be measured.

The application relates to a multi-step tool calling data processing method and system based on a large language model, and relates to the fields of artificial intelligence and data processing, which comprises the following steps: in response to a calling instruction of a first tool, the first tool is executed to obtain a first complete result; the first complete result is written into a runtime storage area independent of a context of the large language model, and a corresponding first reference identifier is generated; a result abstract of the first complete result and the first reference identifier are returned to the large language model, so that the large language model generates a calling parameter for a second tool based on the result abstract; and in response to the first reference identifier contained in the calling parameter, the second tool reads the first complete result from the runtime storage area through the first reference identifier. The application has the effects of realizing decoupling transmission of intermediate results and model contexts and deterministic conversion of data structures in multi-step tool calling, reducing resource consumption and improving execution stability.

The invention discloses an optical and SAR image registration method and system based on multi-scale phase antisymmetry. The method comprises the following steps: acquiring an optical and corresponding SAR image pair as an original image pair; calculating the phase antisymmetry of each scale by using a multi-scale single gene signal to obtain the multi-scale phase antisymmetry of the image, and performing feature point detection on the original image to obtain the feature point of each original image; constructing a multi-scale phase antisymmetry directional diagram by using the phase antisymmetry of each scale, and generating descriptors of the feature points; similarity measurement of descriptors between original images is utilized to carry out approximate matching on feature points of image pairs to obtain matched feature point pairs, and mismatched feature point pairs are eliminated through an FSC method to realize accurate registration of the images; and transforming the image by using a transformation matrix obtained by FSC screening to obtain a registered optical and SAR image pair. According to the method, the registration effect of low-quality optical and SAR images can be effectively improved, and rapid and robust registration is realized.