14results about How to "Meet real-time processing needs" patented technology

The invention relates to the technical field of artificial intelligence image recognition and data mining, and discloses an image data mining processing system and method combining a visual large model and a visual small model. The method aims at solving the problems that in the prior art, the image recognition recall rate and accuracy are difficult to consider, the calculation cost and the processing speed are unbalanced, the data management efficiency is low, and the model generalization ability is insufficient. The system comprises a data input module, a frame extraction deduplication module, a picture library construction module, a visual large model judgment module, a visual small model judgment module, a label preprocessing module, a manual inspection module, a training data generation module, a model training module and a data security module. According to the method, the generalization ability is guaranteed through preliminary screening of an LPM (Deic) large model, missing detection is complemented through secondary verification in cooperation with a YOLO small model, false alarms are eliminated in combination with manual verification, meanwhile, double models are optimized through targeted sample training, the pain point of missing detection or misjudgment of a single model is effectively solved, and accurate and comprehensive consideration of target recognition is achieved.

The application relates to the technical field of medical image processing, in particular to a root canal system three-dimensional reconstruction and isthmus identification method and system based on a CBCT image, which comprises the following steps: acquiring CBCT original image data; pre-processing the CBCT image; performing root canal system three-dimensional reconstruction on the pre-processed CBCT image; performing clustering segmentation based on a differential geometry theory on root canal cross sections in the root canal system three-dimensional reconstruction result to extract isthmus features, wherein the clustering segmentation based on the differential geometry theory comprises the following steps: super voxel segmentation driven by curvature flow, elliptical fitting and long axis extraction on a Riemann manifold, isthmus feature extraction by combining a geodesic distance field and a Hough transformation; and marking the isthmus of the root canal system three-dimensional reconstruction result by using the isthmus features, wherein the application realizes accurate identification of a root canal isthmus by introducing the differential geometry theory, improves identification accuracy, and significantly improves the success rate of root canal treatment.

The application discloses a kind of IEC104 protocol fast analysis device and method based on P4 programmable switch, device includes P4 programmable switch main body, protocol analysis unit, rule configuration unit, matching execution unit and unpacking unit;Hardware processing pipeline is equipped in P4 programmable switch main body, protocol analysis unit, matching execution unit, unpacking unit are sequentially arranged in the corresponding position of flow line and are connected, and rule configuration unit is connected with main body control plane in communication.This device cooperates through each unit, solves the drawbacks that existing software analysis delay is high, throughput is low, operation and maintenance are complex and traditional switch cannot be deeply analyzed, without additional deployment host, reduce cost and operation and maintenance difficulty, programmable and adapt to multiple business scenarios, meet the real-time performance, reliability requirements of new power system to communication.

The application provides a kind of spaceborne super high speed image intelligent processing method and device, including: high speed data interface unit, intelligent image processing unit, main control unit;The high speed data interface unit is connected respectively external data input unit, intelligent image processing unit and main control unit.This application keeps original data on front end FPGA, GPU module is only used as the position calculation of slice, avoids the repeated transmission of internal mass data, so as to cause the pressure of transmission bandwidth.

This application relates to an image processing method, apparatus, and computer device. The method includes: downsampling an image to be processed to obtain a downsampled image; generating an initial illumination image based on pixel information of each pixel in the downsampled image; performing FGS filtering on the initial illumination image to obtain an intermediate illumination image; performing brightness transformation and upsampling processing on the intermediate illumination image to obtain a target illumination image of the same size as the image to be processed; and using the target illumination image to enhance the brightness of the image to be processed to obtain the target image. This method can reduce the computational load in the image enhancement process without affecting the image enhancement effect, making it suitable for computer devices with lower computing performance and expanding its applicability.

This invention discloses an interpretable low-light image enhancement method. It constructs an unpaired learning framework, EDC-Net, with enhancement and degradation branches forming a closed loop. The enhancement branch adaptively enhances the brightness and contrast of the low-light image through pixel-level affine mapping, while the degradation branch predicts physically meaningful degradation parameters such as color gain and exposure scaling. The enhanced image is then reconstructed into a low-light image through a chain of explicit degradation operators, forming a cyclic consistency constraint. Training employs a three-stage progressive optimization strategy: degradation warm-up, master adversarial training, and fine-tuning. During the inference phase, only the lightweight enhancement branch is run. This invention achieves physical interpretability and controllability of the enhancement process, avoids overexposure and artifacts, improves training convergence stability, and significantly increases inference efficiency. It is suitable for real-time image processing scenarios such as nighttime surveillance and autonomous driving.

This invention discloses a piecewise adaptive Kalman track tracking method and apparatus based on residual classification, relating to the field of radar track tracking technology. Addressing the problems of poor adaptability to non-stationary measurement noise environments, parameter dependence on human experience, and complex FPGA implementation in existing track tracking methods, this invention proposes introducing a residual classification decision and piecewise adaptive noise adjustment mechanism into the Kalman filter recursive framework. First, a residual vector is calculated based on the predicted state and measurement data. Then, a classification decision is made using the residual vector, the predicted covariance, and the measurement noise covariance of the previous cycle, outputting the measurement quality level. Next, the measurement noise covariance is updated piecewise adaptively based on the measurement quality level. Finally, the filter gain is calculated based on the updated measurement noise covariance and the predicted covariance to complete the correction and update of the state and covariance.

This invention proposes a test-time optimized method for super-resolution reconstruction of UAV aerial infrared images, belonging to the fields of image processing and computer vision. A test-time optimization framework based on unfamiliar infrared degradation perception is constructed: a teacher-student model fusion mechanism is introduced to synthesize degraded reference images, and the optimization amplitude is dynamically controlled to prevent catastrophic forgetting; a frequency domain degradation estimation network calculates the blur kernel and noise parameters to generate pseudo-label images to guide model optimization; a multi-scale linear layer parameter optimization strategy is designed, updating only linear layer parameters to achieve rapid adaptation; and a joint constraint optimization process using reconstruction loss and feature consistency loss ensures pixel-level reconstruction accuracy and the preservation of pre-trained feature extraction capabilities. This method effectively solves the problem of super-resolution quality degradation caused by unknown degradation conditions in UAV aerial photography scenarios, significantly improves generalization ability under complex degradation migration conditions, and is suitable for applications such as nighttime search and rescue, security patrol, and agricultural assessment.

The invention discloses a two-stage compression denoising imaging method for a large-area array Geiger mode APD (avalanche photo diode). The method comprises the following steps: intercepting photon events in a pre-sampling time window at the front part of a data block to carry out global histogram statistics, fitting and estimating time domain characteristics of background noise based on Poisson distribution, screening and compressing full-frame data, and eliminating most noise; carrying out local joint histogram statistics and peak value extraction on the compressed data based on a pixel space neighborhood, and reconstructing a preliminary distance image and a preliminary intensity image; if the effective data in the neighborhood of the data meets the flat area condition, standard median filtering is executed; otherwise, starting a robust filtering algorithm based on absolute median difference MAD for processing. According to the method, the cooperation of front-end data efficient compression and rear-end accurate denoising and edge preserving is realized, and the method has the advantages of high compression ratio, high adaptability and excellent imaging quality, and is particularly suitable for real-time three-dimensional imaging of a large-area-array GM-APD laser radar system.

This invention discloses an air-ground collaborative stereoscopic electromagnetic spectrum mapping device and method. The device includes an airborne platform, a vehicle-mounted platform, and a ground station. First, it receives mapping parameters, plans a collaborative acquisition path between the airborne and ground platforms, and simultaneously collects, frames, and stores spectrum and spatiotemporal information. Second, after compensating the spectrum data from each platform, it performs three-dimensional fusion of air, time, and frequency. Based on the platform's real-time location and the fused data, it delineates dynamically complete areas and completes missing grids using an online optimization algorithm with a forgetting factor. Finally, it calculates the map coverage in real time; if the coverage exceeds a threshold, it replans the supplementary measurement path until a complete stereoscopic spectrum map is generated. This invention combines the advantages of airborne and ground platforms to achieve high-precision three-dimensional spectrum perception in large-area, complex scenes, improving completion accuracy and real-time performance.

The application discloses a kind of based on deep learning's pulse parameter intelligent detection method and system, the method is applied to the time-frequency data of transient astronomical signal is carried out automatic analysis, comprising: S1.image stage: the original FRB signal data observed by radio telescope is carried out physical correction, the original format of signal data is converted into the two-dimensional image of standardized time-frequency graph matrix;S2.detection stage: the time-frequency graph is input into deep learning model;Deep learning model utilizes its feature extraction capability, through a signal discrimination branch, automatically locates the time-frequency area where FRB pulse signal is located in background noise;S3.regression stage: after successfully locating signal area, network directly regresses each attribute of the target by two branches, so as to obtain the predicted value of each pulse parameter of FRB signal.The application integrates the extraction of multiple parameters into an end-to-end deep learning model, greatly improves the data processing speed, simplifies the processing procedure.

The application provides an accounting data management method, system, device and medium based on edge computing, which extracts a structured feature vector of newly added accounting voucher data; extracts a similar voucher set similar to the newly added accounting voucher data from a high-frequency subject area and a sparse subject area in historical accounting voucher data according to a data partition granularity; determines the distance between the structured feature vector of the newly added accounting voucher data and the feature vector of each accounting voucher in the similar voucher set, and then generates a risk confidence value of the newly added accounting voucher data based on the occurrence frequency of similar accounting vouchers and the feature vector distance; and when the risk confidence value exceeds a set threshold, updates the compliance verification result and the structured feature vector corresponding to the newly added accounting voucher data to an accounting voucher database. The technical scheme provided by the application can overcome the interference caused by the natural long-tail distribution characteristics of accounting subjects on similar voucher retrieval in accounting data management.

The present application relates to the technical field of computer, disclose a water quality instrument measurement data intelligent correction method in response to sudden water quality change, the method comprises: real-time monitoring the water quality data of target water area, obtain the original data sequence of the target water area;The original data sequence is carried out mutation feature identification, obtain the candidate abnormal section of the original data sequence;The candidate abnormal section is carried out suddenness verification, obtain the sudden abnormal data section in the candidate abnormal section;The data reconstruction is carried out to the sudden abnormal data section, obtain the corrected data sequence;The formatted processing is carried out to the corrected data sequence, obtain the final correction result of the target water area in response to water quality change, the present application can improve the automation efficiency and response speed of water quality abnormal monitoring and data processing.

The application discloses a space-based infrared dim small target detection method based on a vector signal, in order to overcome the low timeliness and large resource consumption bottleneck of the traditional "imaging-caching-preprocessing-detection" link, skips the image caching and preprocessing link, and directly takes the DN value vector signal read out by the detector as input. Wherein, the two-dimensional or higher-dimensional features of the target are recovered from the one-dimensional vector signal through the network based on the CNN and BERT mechanisms and with the help of the Markov random field model; the network based on the self-supervised U-Net structure is used to decouple the target and background clutter features, and the multi-scale detection mechanism is combined to selectively enhance the target features to complete the detection; the network is lightened through the multi-teacher knowledge distillation architecture, and pruning and quantization are combined to obtain a lightened detection model suitable for the resource limited environment on the satellite. The application realizes the "detection and calculation integration", and significantly improves the timeliness and resource efficiency of the space-based infrared dim small target detection.