132 results about "Step detection" patented technology

The invention belongs to the technical field of video live broadcast monitoring management, and particularly relates to a live broadcast content real-time compliance detection method and system based on deep learning, and the method breaks through the limitation that traditional text detection only depends on dominant keywords by constructing a text semantic analysis chain matched with original words and mapping sensitive words through constructing metaphor words. The identification of deep semantic violation contents such as metaphor and private obscure expression is realized; the method comprises the following steps: performing linkage verification on text violation clues and image behavior characteristics through behavior characteristic analysis of image frames before and after time positioning association of text violation based on a time positioning cross-modal collaborative detection mechanism, and forming a multi-modal judgment logic for text triggering image confirmation; a progressive detection strategy of hierarchical thresholds is designed, a first threshold is set as violation confirmation and a second threshold is set as suspected violation early warning, and real-time preliminary detection and precise secondary verification are combined, so that stepped processing from suspected violation to violation confirmation is realized, and the real-time performance and accuracy of detection are balanced.

The invention relates to the technical field of equipment energy consumption monitoring and fault diagnosis, and discloses a large-scale equipment energy consumption anomaly detection method and a storage medium. The method comprises the following steps: synchronously acquiring equipment energy consumption, state and environment data, fusing to generate multi-dimensional initial features, and performing multi-scale transformation. And performing preliminary detection on each scale feature subset to generate abnormal confidence and mode description. And screening the feature subsets according to the confidence coefficient, and dynamically selecting a corresponding detection strategy according to the mode description. And performing deep feature extraction on the feature subset based on the selected strategy, inputting the obtained high-dimensional feature vector into a corresponding anomaly evaluation network, calculating a standard state matching degree, comparing with a dynamic threshold to generate a fine-grained judgment result, and finally finishing positioning and attribution analysis in combination with anomaly description to form a detection report. According to the method, efficient and accurate large-scale equipment energy consumption anomaly detection is realized.

The invention discloses a vacuum cavity pressure maintaining test and leak rate rapid estimation method and system, and the method comprises the steps: achieving the test preparation of multiple sections through a public metering manifold and a multi-way isolation valve, and building a section volume database; the pressure and temperature data are synchronously collected in a fixed sampling period by exhausting air to preset pressure and isolating a pump end; obtaining an equivalent pressure change rate through temperature normalization and deflation baseline deduction in combination with filtering and regression algorithms, and performing conversion to obtain a standardized leak rate; step-by-step detection is carried out on each functional section of the cavity through a segmented bipartite isolation strategy and volume correction, and rapid positioning of a suspicious leakage section is realized; through double-threshold determination of an early warning threshold and an unqualified threshold, a detection report is automatically generated and written into a historical database, and a detection-determination-maintenance closed loop is formed. The method can improve the precision of leak rate detection, and is suitable for vacuum coating equipment, semiconductor process equipment and industrial vacuum treatment devices.

The invention discloses a complex scene target detection method based on a model dynamic joint mechanism, and the method comprises the steps: carrying out the preliminary detection through an RT-DETR model, retaining more potential targets through dynamic threshold adjustment, and projecting a generated detection frame to a feature space of an improved YOLOv12 model through dual-mode feature mapping; the improved YOLOv12 model integrates an SEAM attention module and a rejection loss function so as to enhance feature representation and positioning compactness of an occluded target. Then, a model joint mechanism is adopted to process preliminary results of the two models; through difficult case mining and online learning, missing detection targets are supplemented, and the RT-DETR model is optimized; and intelligently fusing the detection results of the two models through dynamic weight distribution based on scene complexity and hierarchical fusion of a decision tree. And finally, post-processing is carried out by using an improved non-maximum suppression algorithm, and mistaken deletion is reduced. According to the method, the problems of missing detection, false detection and inaccurate positioning of the target in a complex scene are effectively solved, and the recall rate and the accuracy rate of detection are remarkably improved.

The invention discloses an abnormal data processing method and system for a virtual game, and relates to the technical field of big data processing. Receiving an interaction data frame sequence uploaded by the terminal equipment, and analyzing to obtain an input equipment sampling point set and a displacement coordinate vector; performing feature extraction on the sampling point set of the input equipment to obtain a high-dimensional feature vector; mapping the high-dimensional feature vector to a preset behavior feature space, calculating a multi-dimensional statistical distance of the high-dimensional feature vector in the behavior feature space, and generating a first abnormal confidence coefficient; calling space mapping data corresponding to the virtual scene; performing discretization ray stepping detection in the space mapping data based on the displacement coordinate vector to generate a second abnormal confidence coefficient; performing fusion calculation on the first abnormal confidence coefficient and the second abnormal confidence coefficient based on a dynamic weighting algorithm to obtain a comprehensive abnormal score; and judging abnormal data through the comprehensive abnormal score, and executing a state rollback operation for the virtual object.

The invention discloses a drainage pipe network data cleaning and intelligent repairing method fusing multiple models. The method comprises the following steps that S1, original monitoring data flow is collected; s2, carrying out the preliminary detection and elimination of the abnormity based on IQR; s3, performing upstream and downstream multi-source feature extraction and XGBoost weight analysis; step S4, multivariable depth autoregression prediction based on PatchTST is carried out; s5, generating and publishing continuous high-quality data; according to the method, the key technical problems of various abnormal types, incomplete abnormal detection, low cleaning and repairing precision, poor data continuity and trend consistency, high system integration and real-time processing difficulty and the like commonly existing in the actual collection and transmission process of the online monitoring data of the drainage pipe network are solved.

The invention discloses a synchronous detection system for surface density and wall thickness uniformity of a composite bulletproof helmet, which belongs to the technical field of bulletproof helmet detection and comprises a detector cooperative control module, a two-parameter synchronous acquisition module, a data preprocessing module, a two-parameter cooperative constraint module and an intelligent modeling output module. Through the integrated design that the detection unit integrates the 3D scanning detector, the microwave thickness measuring probe and the beta-ray density detector, and in cooperation with the synchronous triggering and double-channel signal acquisition mode of the double-parameter synchronous acquisition module, synchronous acquisition of the surface density and wall thickness data of the helmet is realized; the problems that traditional step-by-step detection is low in efficiency and poor in data relevance are solved, the detection efficiency and the accuracy of quality judgment are greatly improved, meanwhile, a detection report containing process optimization suggestions is output, the problems that traditional detection results are not visual, and connection with the production process is not smooth are effectively solved, and the product quality is improved. And accurate guidance can be provided for mass production quality control and process adjustment.

The invention discloses a CC attack gateway layer detection method and system based on an intelligent sliding time window, and belongs to the technical field of network security. The method comprises the following steps: analyzing the HTTP traffic of a gateway layer in real time, and extracting multi-dimensional features of the traffic and user behaviors; performing real-time aggregation and multi-dimensional analysis on the features by using a sliding time window mechanism; based on a risk score accumulation mechanism, matching the aggregation result with a pre-configured rule base to obtain a preliminary detection result and a risk score; when the initial detection is negative, further performing verification detection by using a pre-trained machine learning model; and finally, according to the risk score and a machine learning result, judging an attack and executing a progressive disposal measure. Through streaming processing, rule and model cooperation, intelligent degradation and other mechanisms, the problem that detection precision and processing performance cannot be achieved at the same time in a gateway scene in the prior art is effectively solved, and high-precision CC attack defense under the requirements of high concurrency and low delay is achieved.

The invention relates to the technical field of information, and provides a real-time target detection and automatic operation integrated system and method, and the method comprises the steps: capturing a target image in a dynamic environment through a visual sensor, processing the image through a YOLO algorithm to recognize the position and posture of an object, and obtaining a preliminary detection result; obtaining the corrected position information, generating an operation parameter adjustment instruction in combination with the current equipment state, judging whether the adjustment instruction meets the real-time requirement or not, and obtaining an optimized parameter set; matching the verification-passed adjustment permission with the optimization parameter set, if the verification-passed adjustment permission is consistent with the optimization parameter set, transmitting the parameter set to an automatic equipment controller, and determining a final execution instruction; a subsequent target image is re-processed through a refined filtering model, and the operation history is recorded in combination with an authority management log to determine a system security state; and extracting an abnormal index from the safety state of the system, and if the abnormal index is lower than a threshold value, maintaining the current parameter configuration to obtain stable operation configuration.

The invention relates to the technical field of industrial machine vision detection, in particular to a positioning detection method integrating deep learning and morphological operation. Comprising the following steps: S1, constructing a target positioning detection data set; s2, constructing an improved deep learning detection network; s3, training the improved deep learning detection network; s4, preliminary detection: inputting a to-be-detected image into the trained network, outputting a preliminary target detection frame and a corresponding confidence coefficient, and synchronously extracting a target candidate region image corresponding to the detection frame; s5, performing adaptive morphological optimization; and S6, fusion decision making: calculating the intersection-to-union ratio IOU of the preliminary detection frame and the edge after morphological optimization, and performing hierarchical fusion in combination with the confidence coefficient of the preliminary detection frame. According to the invention, through improving the collaborative design of the deep learning network, the adaptive morphological operation and the hierarchical fusion decision, the core problems of poor scene adaptability, small bubble missing detection of single deep learning and inaccurate edge positioning of traditional morphological detection are effectively solved.

The invention provides a micro-service anomaly detection method, system and equipment, and the method comprises the steps: obtaining the observable data of a micro-service, the observable data comprising real-time monitoring data and service call chain data: inputting the observable data of the micro-service to an anomaly preliminary detection module to obtain preliminary anomaly detection data; the preliminary anomaly detection module is an anomaly detection agent based on a neural network; calling latest log data based on the preliminary anomaly detection data, and inputting the log data into a clustering model to obtain a clustering result; determining micro-service abnormal data based on the clustering result; and outputting the micro-service abnormal data to a Kafka message queue. According to the micro-service anomaly detection method provided by the invention, the efficient neural network and the machine learning algorithm are introduced, and through two rounds of anomaly determination processes, the problems that an existing micro-service anomaly detection method is prone to false alarm and low in anomaly detection accuracy are solved.

The invention relates to the technical field of UWB range finding, and discloses a UWB range finding method, a base station, a UWB positioning method and a UWB system.The UWB range finding method comprises the steps that CIR information of a target label is acquired, first-path preliminary detection is carried out on the CIR information, and an initial first-path index is obtained; obtaining an energy characteristic, a slope characteristic and a peak value characteristic according to the CIR information and the initial first path index; according to the energy characteristic, the slope characteristic and the peak value characteristic, carrying out first diameter secondary detection to obtain a first diameter detection result; and performing correction or calculation according to the first diameter detection result to obtain a target distance measurement value. According to the invention, the ranging and positioning precision of the UWB technology in a complex indoor environment can be improved, the error is reduced, and the system stability is improved.

The invention discloses a design method of a three-order active filtering automatic test system, and the method comprises the steps: controlling a PXI platform through LabVIEW programming to achieve the generation of a sweep frequency signal and the collection of filtering response, and completing the signal processing, characteristic analysis and result visualization. The system integrates six core technologies, namely a modularized hardware architecture, automatic process control, frequency domain parameter precision measurement, multi-order characteristic synchronous detection, software and hardware collaborative linkage and simulation data comparison. On the basis of retaining traditional functions such as setting waveform type, amplitude, sweep frequency range, sampling rate, trigger mode, recording cut-off frequency, gain and other parameters, exponential sweep frequency accurate excitation and adaptive signal acquisition are innovatively realized, link interference is reduced through matrix switch multi-channel scheduling, a LabVIEW parallel thread and a feedback node mechanism are combined, and the adaptive signal acquisition is realized. And closed-loop analysis of amplitude-frequency / phase-frequency characteristics and real-time drawing of a Bode diagram are completed.

The invention relates to the technical field of communication, in particular to a communication method for inhibiting an overhigh peak-to-average ratio in an orthogonal time-frequency-space system, which comprises the following steps of: 1, converting a signal from a delay-Doppler domain convenient for channel characterization to a time-frequency domain convenient for modulation implementation; step 2, performing preliminary suppression on the peak-to-average ratio by adopting a T-SLM method, generating a plurality of groups of candidate signals, and selecting one group with the peak-to-average ratio lower than a preset threshold or with the minimum peak-to-average ratio; step 3, carrying out Hisenberg transformation on the selected signal to obtain a time domain signal; carrying out iterative amplitude limiting filtering processing, adding a cyclic prefix, and then sending; step 4, removing the cyclic prefix by a receiving end, and recovering to a time delay-Doppler domain through Wigner transform and Sextile Fourier transform; performing preliminary detection by adopting a message passing algorithm to obtain a hard decision value and a log-likelihood ratio; and selecting a high-reliability observation value based on a log-likelihood ratio, and constructing a reliability selection matrix.

The invention provides intelligent detection equipment and method based on spectral data, and the method comprises the steps: converting a spectral signal of a to-be-detected sample into corrected spectral data, extracting a plurality of spectral feature wavebands, and screening out a spectral feature subset with a significant discrimination degree according to the feature contribution degree of each spectral feature waveband; generating a spectral feature space when the to-be-detected sample is detected according to the spectral feature subset, determining a feature similarity matrix among the samples in the spectral feature space, further performing sample grouping in the spectral feature space by a spectral clustering model, and generating a preliminary detection result of the to-be-detected sample; and if the detection confidence does not exceed the confidence threshold, performing spectral clustering parameter adjustment on the spectral clustering model until a detection result meets a set requirement, and outputting a final detection result of the to-be-detected sample. According to the technical scheme provided by the invention, the problem of insufficient generalization ability of a spectral clustering model caused by spatial change of spectral features in traditional spectral detection can be solved.

The invention provides a remote sensing change detection method and system based on deep reinforcement learning, and the method comprises the steps: carrying out the feature extraction and difference modeling of an input multi-temporal remote sensing image through a deep learning network, so as to generate a preliminary change prediction map; and introducing a reinforcement learning module, taking the preliminary change prediction map as an initial state, and performing multi-round iterative optimization on the preliminary change prediction map through a decision process comprising a state space, an action space and a reward function so as to generate a final change detection result. And the reward function comprehensively considers an intersection-to-union ratio improvement value, an F1 score improvement value and cross entropy loss, and introduces a misclassification penalty enhancement mechanism to preferentially repair missing report and false alarm areas. According to the method, through iterative optimization of reinforcement learning, errors in a preliminary detection result can be effectively corrected, and the detection precision and robustness are remarkably improved.

The application relates to the technical field of target detection, in particular to a target detection method and device combining computer vision and big data mining and a computer device. Based on a preliminary detection result, relevant enhancement and inhibition templates are searched in a pre-constructed context enhancement template library and a context inhibition template library, a spatial attention graph is generated through similarity matching calculation, fusion enhancement feature maps and fusion inhibition feature maps are obtained through fusion operation, and a general scene enhancement graph generated in combination with scene features is used to finely bidirectionally modulate a target feature extraction graph extracted based on a to-be-detected image, features conforming to the context of the target can be adaptively strengthened, and interference signals violating logical relations can be weakened, so that the detection capability for occluded targets, small targets and rare targets can be effectively improved in a complex scene, false detection and missed detection are reduced, and the accuracy and efficiency of target detection are improved.

The application discloses a system and method for synchronously detecting epilepsy attack and type identification, and the system comprises an electroencephalogram signal processing module, a multi-scale time-space-frequency feature electroencephalogram fusion module, an epilepsy attack detection task branch, a cross-task attention interaction module, an epilepsy attack type classification branch and a multi-task learning optimization module; the cross-task attention interaction module realizes bidirectional feature sharing between the task branches by establishing an information interaction mechanism at a feature level, so that the epilepsy attack detection task can utilize fine-grained structural information related to attack types to improve detection precision, and meanwhile, the attack type classification task can utilize attack time positioning and context information provided by the detection task; the application realizes collaborative modeling of epilepsy attack detection and attack type classification, improves the accuracy, robustness and clinical application value of epilepsy attack identification by sharing feature representation and cross-task information interaction, while ensuring the calculation efficiency.

The invention discloses a small-size and conventional target joint detection method and device based on YOLOv5, and relates to the field of data processing. In the method, a target detection network is constructed based on a preset reference target detection network; performing sliding window division on the to-be-detected image to generate a plurality of detection windows with overlapping areas; inputting each detection window into a target detection network to obtain a preliminary detection result corresponding to each detection window; performing non-maximum suppression processing on the initial detection result of each detection window to obtain a first detection result containing a micro-size target; inputting the complete image of the to-be-detected image into a preset reference target detection network to obtain a second detection result containing the conventional target; and fusing the first detection result and the second detection result to generate a joint detection result, and outputting the joint detection result. By implementing the technical scheme provided by the invention, the detection comprehensiveness is improved.

The application relates to the field of intelligent traffic technology and discloses a traffic event secondary identification method based on video cloud platform stream pulling detection, which comprises the following steps: S1, pulling low-bit-rate video data in the cloud, performing low-bit-rate round-patrol event detection through a traffic event identification system, and outputting a preliminary detection result; S2, if the preliminary detection result is a traffic event, pulling high-bit-rate video data corresponding to the low-bit-rate video data, performing high-bit-rate event rechecking detection through the traffic event identification system, and outputting a final identification result; wherein the operation of the traffic event identification system is realized through dynamic scheduling of cloud computing power and sharing of cloud resources. Through low-bit-rate round-patrol event detection and high-bit-rate event rechecking detection of traffic events, the application reduces bandwidth resource consumption, effectively saves network resource and computing resource investment, and ensures identification accuracy under the support of an event detection algorithm based on a video analysis technology.

The invention discloses a sparse data reconstruction method and a related device, and relates to the field of data processing, and the method comprises the steps: obtaining an intracranial pressure sparse data flow collected at a sampling rate in a preset low sampling rate range in a sliding time window, calculating an intracranial pressure mean value, taking the intracranial pressure mean value as an initial value, and calculating the initial value; the method comprises the following steps: carrying out dynamic characteristic analysis on an intermediate intracranial pressure data sequence obtained by preprocessing an intracranial pressure sparse data stream, adding a step mark corresponding to a pathological step to obtain a target intracranial pressure data sequence, carrying out segmented fitting on the target intracranial pressure data sequence to obtain a segmented fitting result, and carrying out signal reconstruction to obtain a multi-component mathematical model set; the sampling rate is set to be within a preset high sampling rate range, and a reconstructed intracranial pressure change waveform is generated. According to the method, the intracranial pressure sparse data flow is preprocessed, and then step detection and model reconstruction are carried out, so that an intracranial pressure signal equivalent to an intracranial pressure signal acquired at a high sampling rate and a change trend waveform of the intracranial pressure signal are reconstructed from the intracranial pressure sparse data flow at the low sampling rate.

The invention discloses a personnel positioning method based on motion state constraint. The method comprises the following steps: 1, signal acquisition; 2, data preprocessing; 3, motion state recognition and classification; 4, step number detection; 5, step length estimation; 6, estimating a course angle; and 7, outputting position information. According to the invention, personnel positioning based on motion state constraint is realized, the classification result of human body motion identification is used as a constraint condition, the personnel positioning precision is improved, and the actual application requirement of personnel positioning in a complex environment can be met.

This invention discloses a synchronous detection method for machine vision devices, relating to the field of synchronous detection technology, comprising the following steps: constructing a scene screen; setting the placement position of the machine vision device based on the scene screen; acquiring a real-time target image based on the scene screen and the machine vision device; acquiring a grayscale segmentation threshold based on the real-time target image; acquiring a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructing a real-time reference value based on the real-time target region; determining whether the machine vision devices are synchronized based on the real-time reference value; if the machine vision devices are not synchronized, acquiring the time deviation between the two machine vision devices based on the real-time reference value; this invention addresses the problem that existing synchronous detection technologies fail to analyze whether synchronization is achieved based on image results, leading to low accuracy of synchronous detection results.

The application provides a millimeter wave radar high-voltage line intelligent detection and trend prediction method, including the following steps: step one, taking the radar echo map in an antenna scanning cycle as the input of a convolutional neural network; step two, setting a first threshold, and retaining the line point detection result greater than the first threshold; step three, using the line point detection result as the input, using a multi-curve fitting method, and obtaining the preliminary detection result of multiple power lines; step four, performing pre-order traversal on the preliminary detection result of each power line, sequentially connecting each node obtained through the traversal, and obtaining the power line detection result in the form of a line segment; step five, performing a smoothing operation on each power line detection result sequence in the form of a line segment; step six, setting a second threshold, removing the power line in the form of a line segment with a confidence degree or length less than the second threshold, and outputting the remaining power line in the form of a line segment as the detection result.

The RAKE receiver signal synchronization detection method provided in the application comprises the following steps: sorting each correlation value in an initial correlation value set by a RAKE receiver to obtain a final correlation peak position set, selecting a first group of correlation value positions from the final correlation peak position set as a first correlation value position set, and selecting a second group of correlation value positions from the final correlation peak position set as a second correlation value position set; determining the initial position of each correlation value in the second correlation value position set, and selecting the associated position of each correlation value position to be detected based on the initial position to obtain an associated position set of each correlation value position; comparing the associated positions in each associated position set with the final correlation peak positions in the first correlation value position set to determine the number of paths; determining a synchronization detection position based on the number of paths, and processing the received signal based on the synchronization detection position. The synchronization performance under a low signal-to-noise ratio is improved.

The invention discloses a big data-based electric energy quality detection method and system. The method comprises the following steps of 1, constructing an original data tensor; 2, constructing a disturbance memory tensor and storing the disturbance memory tensor in a disturbance memory pool; 3, inputting the original data tensor into an improved MLP-Mixer network, including a spatial path and a feature path which are respectively used for executing Patch mixing and Channel mixing operations, and generating a disturbance representation fusion tensor; 4, introducing a double-flow cross mixing mechanism, and generating a disturbance potential score; 5, judging whether a disturbance risk exists or not according to the disturbance potential score, and outputting a preliminary detection result; 6, performing traceability judgment on the preliminary detection result in combination with a disturbance memory tensor to obtain a disturbance propagation trend; and step 7, outputting an electric energy quality detection result. According to the invention, an improved MLP-Mixer network and a double-current cross mixing mechanism are fused, and high-precision detection of power quality disturbance is realized.

The invention belongs to the technical field of flexible detection equipment, and particularly relates to a flexible detection device for cotton-like super-soft fabric, which comprises a U-shaped base, a rectangular through hole is formed in the center of the top end of the U-shaped base, and a square detection cylinder is fixedly connected to the hole wall of the rectangular through hole. According to the flexible detection device, two-dimensional flexible detection can be completed through single-time clamping, repeated clamping damage and positioning deviation of traditional step-by-step detection are avoided, the detection efficiency and the result authenticity are improved, then the linkage detection logic of surface sliding friction and internal directional extrusion friction is constructed, and the detection accuracy is improved. The real stress process that a human body makes contact with the fabric is accurately simulated, directional extrusion deformation of the fabric is achieved through the gap design of the square detection cylinder and the square detection copper test block, the defect of irregular deformation of traditional extrusion detection is overcome, flexible related parameters are accurately quantified, and meanwhile the functions of monitoring the detection state in real time and early warning abnormity in time are achieved; and the accuracy and reliability of detection data are ensured.

The invention relates to the technical field of visual inspection, and discloses a PCB multi-parameter synchronous detection method, electronic equipment and a storage medium, and the method comprises the steps: generating a PCB elevation map through the fusion of a 2D image and 3D point cloud data, carrying out the synchronous comparison analysis of the height and contour of a component installation position through the combination of the standard height and contour information in a design file, and carrying out the detection of the 3D point cloud data. And integrated detection is realized. According to the method, by introducing the elevation map generated by the three-dimensional point cloud data, the defect that 2D detection lacks depth information is made up; meanwhile, due to space-time alignment fusion of 2D and 3D data, high-resolution details of a two-dimensional image are reserved, height dimension information is increased, and the coverage dimension and precision of detection are remarkably improved; meanwhile, according to the method, through multi-parameter synchronous analysis, matching judgment of the height and the contour is completed at the same time in one detection process, the detection efficiency is improved, and the missed detection risk caused by multiple times of independent detection is effectively reduced.