Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

24results about How to "Optimize detection results" patented technology

Roof distributed photovoltaic identification method, system and device and storage medium

The invention discloses a roof distributed photovoltaic identification method, system and device and a storage medium, and belongs to the technical field of image identification. The method comprises the following steps: performing roof position marking and pixel feature extraction on a satellite image; performing clustering analysis on the extracted pixel features to obtain an initial pixel classification result; based on the initial pixel classification result, a Bayesian classifier is adopted to calculate the posterior probability of each pixel belonging to the roof category to obtain a probability graph; performing morphological operation on the probability graph to obtain an optimized roof area detection result; and carrying out weighted fusion on the optimized roof area detection result and an initial segmentation result obtained through semantic segmentation to obtain a final roof segmentation result. According to the method, technologies of pixel feature extraction, clustering analysis, a Bayesian classifier, morphological operation optimization, segmentation result fusion and the like are introduced, so that the precision and robustness of roof segmentation are improved, and accurate recognition of the building roof is realized.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO LTD RESEARCH INSTITUTE +1

APT attack discovery method based on feature enhanced community detection

ActiveCN119420491AImprove scalabilityOptimize detection resultsSecuring communicationGraph generationAttack
The invention belongs to the technical field of network security, and discloses a feature enhanced community detection-based APT attack discovery method, which comprises the following steps of: collecting log data and constructing an origin graph; the source graph is segmented into a plurality of sub-graphs, a feature association vector set and a weight set are generated for each sub-graph, the sub-graphs with feature association vectors and weights are reconstructed, each reconstructed sub-graph comprises a plurality of triads, and the feature association vectors and the weights exist among the triads; performing feature enhanced community detection on each reconstructed sub-graph; and performing rule matching on the communities in each reconstructed sub-graph to obtain attack communities, and according to the timestamp attribute of each reconstructed sub-graph, connecting the attack communities in each reconstructed sub-graph to complete APT attack discovery. According to the method, the origin graph is constructed by using the collected logs, and accurate division of attack communities is performed by performing feature enhanced community detection on the origin graph.
Owner:ZHEJIANG UNIV OF TECH

Target detection method, system and equipment based on virtual and real data and medium

The invention discloses a target detection method, system and device based on virtual and real data and a medium, and relates to the field of target detection, and the method comprises the steps: carrying out the target detection of a sea scene image through a target detection model, and obtaining the prediction types of a plurality of sea surface targets and a plurality of candidate boxes; the target detection model is obtained by supervising and training a student model through a feature map obtained by a teacher model, the teacher model is a trained neural network model, and the student model is obtained by performing knowledge distillation on the feature map of the teacher model through a multi-valued mask; and adopting a non-maximum suppression algorithm to screen the plurality of candidate frames according to the prediction categories to obtain a prediction frame of the sea surface target, and taking the prediction category of the sea surface target corresponding to the prediction frame as the category of the sea surface target. According to the invention, the speed and accuracy of target detection in a complex marine environment can be improved.
Owner:SHANGHAI UNIV

Track checking interval and back protection distance detection method

The invention provides a track checking interval and back protection distance detection method, which comprises a positioning extraction step, a contour combination step, a track piece identification step, a checking interval acquisition step and a back protection distance acquisition step, according to the method, a predetermined detection position is automatically positioned through profile data collected by a high-precision line laser sensor and corresponding mileage data, profile data of the position are extracted, then the profile data of the multiple line laser sensors are combined, profiles of the heads of the multiple rail pieces are automatically recognized and extracted from combined profile lines, and the accuracy of detection is improved. Due to the fact that the arrangement of the rail pieces at the preset detection position is fixed, the profiles of the guard rail head, the guard rail pair side wing rail head and the point rail can be conveniently and rapidly obtained, then the accurate checking interval value and the back protection distance value are rapidly obtained based on profile analysis and calculation, operation is convenient, detection precision is high, the calculation amount is small, and the detection accuracy is high. And a detection result can be quickly obtained on a track detection site.
Owner:ZHEJIANG TIANTAIXIANGHE INTELLIGENT EQUIPMENT CO LTD +1

Rapid blood oxygen detection equipment with micro-fluidic chip and detection method of rapid blood oxygen detection equipment

The invention discloses a micro-fluidic chip rapid blood oxygen detection device which is characterized in that the blood oxygen concentration is detected through a micro-fluidic chip blood oxygen detection method, then a correction factor is extracted through a detection method adopting an EEG signal algorithm, a detection result of micro-fluidic chip blood oxygen detection is corrected through the correction factor, and a correction result is output; the detection result of blood oxygen detection of the micro-fluidic chip is optimized; compared with the prior art, the blood oxygen detection precision of the micro-fluidic chip is further improved; a correction factor can be obtained through an EEG signal algorithm; the correction module is used for correcting a detection result of blood oxygen detection of the micro-fluidic chip; compared with the prior art, the blood oxygen detection precision is higher; sampling and sample adding equipment is arranged, and the sampling and sample adding equipment comprises a blood taking needle, processing equipment and a sample adding device; sampling a blood sample, processing the blood sample and adding the blood sample; compared with the prior art, the sampling operation is more convenient.
Owner:SUZHOU SUPUNA TECH CO LTD

A fire identification method for power equipment based on multi-parameter recursive graph

The invention provides a method for identifying fires in electric equipment based on a multi-parameter recursive graph, and relates to the technical field of electrical fire detection. The method comprises: using a smoothing filtering technology to pre-process monitoring video images, and creating a fire identification algorithm model based on artificial intelligence to detect and identify fire images in suspicious areas; the fire identification algorithm model identifies the hidden danger electrical monitoring data of the detection position, calculates the target feature vector corresponding to the trace features of the target video image, and builds a deep neural network sub-model and a power heterogeneous multi-parameter fusion model; then using a recursive algorithm module to arrange the power time series parameters into a recursive matrix, and constructing a graph convolutional neural network based on a multi-parameter recursive graph to extract features; using a fire warning judgment module to segment the suspicious unknown areas of the image sequence where the fire occurs, and timely predict and process them, and after identification and confirmation, automatically start a multi-parameter warning judgment program, and accelerate the issuance of warning signals by a background warning system.
Owner:ZHONGSHAN POWER SUPPLY BUREAU OF GUANGDONG POWER GRID

A method for remote sensing image target detection based on rotation region generation network

The present invention discloses a remote sensing image target detection method based on a rotation region generation network. The process of rotating target detection using this method includes the following steps: obtaining a remote sensing image data set, selecting a training set and a test set according to a certain ratio, and marking the training set with a five-tuple rotation bounding box; building a deep learning network framework, designing a network loss function for network training; using the training set images to train the network framework; using the trained model to test the test set to obtain a target detection result with rotation angle information. This method can effectively solve the problem of extracting features with rotation invariance to describe different orientations of the target, while ensuring efficiency, improving the robustness of the network in detecting the rotating target, and verifying the effectiveness of the detection network on a public data set. This method can be widely used in target detection tasks with multi-directional targets.
Owner:NANJING HONGTU ARTIFICIAL INTELLIGENCE TECH RES INST CO LTD

A video anomaly detection method and system

The present application belongs to the technical field of computer vision, video anomaly detection and video anomaly detection model design, and particularly relates to a video anomaly detection method, comprising: acquiring segment feature data of a video to be detected; inputting the segment feature data into a video anomaly detection model to acquire a detection result, wherein the video anomaly detection model comprises: an anomaly feature enhancement model, an anomaly score calculation model, an anomaly positioning model based on classification guidance and an anomaly score optimization model. The present application enhances the feature data of the video to be detected by the anomaly feature enhancement model in terms of time sequence information and motion information, so that it is more suitable for the anomaly detection task, and according to the anomaly positioning model based on classification guidance, parameters in the video anomaly process classification are mined and the anomaly score obtained by the anomaly score calculation model is optimized, so that a detection result with higher accuracy is obtained. Meanwhile, the anomaly positioning model based on classification guidance is convenient to use and can be installed in a memory for use as plug as needed.
Owner:INTELLIGENT MFG INST OF HFUT

Method for detecting the quality of a protein polymer

ActiveCN121347719Bachieve separationOptimize detection results
The application belongs to the field of biological drugs, and discloses a quality detection method of protein polymer, which comprises at least one of reverse phase HPLC detection, SDS-PAGE analysis, mass spectrometry detection, particle size detection, exosome surface marker detection, sterility detection and endotoxin detection. The quality detection method of some examples of the application can effectively realize the separation of components in the protein polymer sample by optimizing the HPLC condition, achieve better detection results, and establish the quality control standard of the protein polymer.
Owner:DARWIN BIOTECHNOLOGY (HUBEI) CO LTD

Tower crane worker fatigue detection method based on EEG and video signal fusion

The invention discloses a tower crane worker fatigue detection method based on EEG and video signal fusion, and relates to the technical field of fatigue detection, and the method comprises the steps: S1, data collection and marking: employing a motion camera to collect face video data of an operator, and employing an EEG sensor to collect EEG signals of the operator; carrying out subjective evaluation on the psychological fatigue of the operator by adopting NASA-TLX scores; s2, data preprocessing: preprocessing the collected face video data and EEG signals respectively, then segmenting the preprocessed video and EEG data by using a sliding window, and ensuring time axis alignment; and S3, multi-modal feature extraction, fusion and fatigue classification. According to the method, automatic extraction and fusion of data features are realized through the neural network, artificial subjective errors are reduced, the efficiency of processing large-scale data is greatly improved, and the complexity of manual feature selection is avoided.
Owner:SOUTHWEST PETROLEUM UNIV

A remote sensing image target detection method and system based on an optimized SSD algorithm

The application discloses a remote sensing image target detection method and system based on an optimized SSD algorithm, first, inputting a to-be-detected remote sensing image into an efficient remote sensing image target feature extraction network to extract key features, and obtaining a required feature map; then inputting the obtained feature map into a forward and reverse iterative fusion multi-scale feature network to perform feature fusion, and generating a new feature map; finally, utilizing an anchor box matching network based on a clustering algorithm to perform anchor box clustering matching on different categories of targets in the image according to the new feature generated by fusion, so that each to-be-detected target obtains the most suitable anchor box as a target detection result; the original feature extraction network VGG16 in the SSD algorithm is optimized, an improved RFB module and an efficient attention mechanism are added into the network, the feature extraction capability of the network is improved, the anchor box matching network based on the clustering algorithm is integrated into the algorithm, the accuracy of the anchor box matching target of the algorithm is improved, and therefore the detection capability is improved.
Owner:HUBEI UNIV OF TECH

Unsupervised fault detection method, system and equipment for hydraulic shock absorber and storage medium

The invention discloses an unsupervised fault detection method, system and equipment for a hydraulic shock absorber and a storage medium, which are in one-to-one correspondence schemes, in the scheme, a data unsupervised training detection model of the shock absorber in a healthy state is utilized, specifically, sample consistency is measured by comparing and utilizing a health center and a health sample, and a fault detection result is obtained. The multi-sensor mode consistency is measured by comparing the health center multi-sensor signal correlation with the health sample multi-sensor signal correlation, then the working state of the shock absorber is directly modeled through the two types of consistency, and a good detection result can still be achieved on the premise that no fault sample participates in training.
Owner:UNIV OF SCI & TECH OF CHINA

Cloud Detection Method in Remote Sensing Images Based on Multi-scale Convolutional Neural Network

The present invention relates to a remote sensing image cloud detection method based on a multi-scale convolutional neural network, comprising the following steps: step 1, establishing a multi-scale U-net neural network; the multi-scale U-net neural network comprises an encoder, a decoder and an SPP U-net network structure; step 2, collecting a number of remote sensing images containing clouds, performing cropping, channel selection, cloud annotation and data augmentation, and obtaining a training data set and a test data set required for training the multi-scale U-net neural network; step 3, using the training data set, using the BCELoss loss function and the SGD optimizer to train and update the parameters of the multi-scale U-net neural network; step 4, inputting the cloud-containing remote sensing image to be detected into the trained multi-scale U-net neural network for cloud detection, and the output result is a cloud detection binary image. The present invention performs feature multi-scale improvement on the ordinary U-Net network structure, adopts spatial pyramid pooling to improve the cloud detection accuracy, and can greatly improve the detection effect of small cloud areas and cloud segmentation edges.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY

Generator stator end shaping tool

The utility model discloses a generator stator end portion shaping tool which comprises a tool base, a shaping plate capable of rotating along the center of the tool base is arranged above the tool base, and an n-shaped shaping groove is formed in the downward direction of the shaping plate. The tool base comprises an upper base body and a lower base body which are formed by cylindrical splicing, the diameter of the upper base body is 1-2 mm larger than the inner diameter of a stator, and the diameter of the lower base body is 1-2 mm smaller than the inner diameter of the stator. According to the utility model, the tool base is clamped into the stator to be trimmed and is matched with the stator, so that the concentricity between the stator and the tool base is detected, the shaping grooves are formed in the shaping plate, the problems that the end part of the stator is too high and the diameter is too large can be effectively avoided, the replacement is convenient, and the detection of the end parts of stators with different sizes is facilitated; meanwhile, the detection result of the scheme can be directly obtained, unqualified products can be directly screened out, and the use effect is good.
Owner:FUJIAN KAIWEISI GENERATOR CO LTD

A method for analyzing the behavior of stored grain pests based on YOLOv5 and an improved SORT algorithm

This invention relates to a method for analyzing the behavior of stored grain pests based on YOLOv5 and an improved SORT algorithm, belonging to the technical field of stored grain pest behavior analysis methods. This method utilizes a camera to collect and filter videos of stored grain pests crawling, and processes the videos frame by frame. First, each frame is preprocessed using OpenCV to detect the outline of the stored grain pests and extract target coordinate data. When target overlap or loss occurs in a frame, resulting in detection failures for certain stored grain pests, the frame is segmented and fed into the YOLOv5 target detection network for re-detection, optimizing the detection results. This method solves the problems of low accuracy, susceptibility to environmental factors, and poor detection performance when overlap occurs in existing stored grain pest behavior analysis methods, making it particularly suitable for the needs of stored grain pest behavior analysis.
Owner:YANGTZE UNIVERSITY +1

Wire diameter detector for connecting conductor of low-voltage surge protection device

ActiveCN222528600UMeet the actual work needs of on-site inspectionSolve the problem of uncertainty in judgment resultsMeasurement devicesElectrical conductorLow voltage
The utility model discloses a low-voltage surge protector connecting conductor wire diameter detector, which relates to the technical field of low-voltage surge protectors and comprises a comparator, and a standard sample area, a technical standard requirement area and an instruction area are arranged on the front surface of the comparator. The standard sample area is provided with six connecting conductor samples with different wire diameters, and the connecting conductor samples are fixedly mounted on the front surface of the comparator through wire clamps; the technical standard requirement area is engraved with a technical standard requirement of a surge protection device connecting conductor; and instructions and processes of the device are engraved in the instruction area. The low-voltage surge protection device connecting conductor wire diameter detector provided by the utility model meets the actual work requirements of field detection of a surge protection device connecting conductor, and solves the problems that direct measurement cannot be performed and electric shock risks exist.
Owner:宁夏回族自治区气象灾害防御技术中心 +1

Model generation method, target detection method, device, electronic device and medium

The embodiment of the present invention discloses a model generation method, a target detection method, a device, an electronic device and a medium. The model generation method includes: training the original detection model based on multiple groups of teacher training samples including a first sample image and sample annotation results of known targets in the first sample image to obtain a teacher network; using the first sample image and the first detection result obtained after the first sample image is input into the teacher network as the first training sample, and using the second sample image and the second detection result obtained after the second sample image is input into the teacher network as the second training sample; training a student network with the same network type as the teacher network based on multiple groups of first training samples and multiple groups of second training samples to generate a target detection model. The technical solution of the embodiment of the present invention achieves the effect of improving the generalization performance of the target detection model without increasing the cost of manual annotation.
Owner:BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1

Fluorescence-magnetic resonance bimodal contrast agent, preparation method therefor and use thereof

A fluorescence-magnetic resonance dual-modality contrast agent, a preparation method thereof and the use thereof. The contrast agent has the following structure: X-L-Y, wherein: formula (I); R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, and R12 are each independently selected from H, halogen, OH, NH2, COOH, CONH2, NO2, CN, and low alkyl groups, the low alkyl groups can be substituted with halogen, OH, NH2, COOH, CONH2, SO3H, NO2, and CN, wherein R3 and R4, taken together with the carbon atoms to which they are attached, may form a phenyl group or a heterocyclic group; R7 and R8, taken together with the carbon atoms to which they are attached, may form a phenyl group or heterocyclic group; L is a linking group; and Y is a metal chelate.
Owner:HAINAN PULIN PHARMA +1

Methods for detecting fungi in turf grass with a lamp assay having novel primer sets

The present invention provides a method for detecting fungal DNA in a turf grass sample with a loop-mediated isothermal amplification (LAMP) assay which contains primers for fungal DNA of at least one turf pathogenic fungi selected from Sclerotinia homoeocarpa, Rhizoctonia solani spp., Pythium aphanidermatum, Gaeumannomyces graminis spp., Microdochium nivale spp., Magnaporthe poae, Colletotrichum graminicola, Colletotrichum cereale and Pythium ultimum var. ultimum, comprising: subjecting the turf sample to a LAMP reaction wherein the LAMP reaction uses a primer set of four or more nucleic acid sequences with each primer in the set having from 15 to 50 nucleic acids The primers useful in the present method are selected from specifically selected internal transcribed spacer regions or genes of the target fungi to provide improved assay results.
Owner:SYNGENTA CROP PROTECITON AG

An infrared dim small target detection method based on deep sparse low-rank neural network

The application discloses an infrared dim small target detection method based on a deep sparse low-rank neural network, and belongs to the field of infrared data processing in remote sensing digital image processing. Due to the small volume and low brightness of the infrared dim small target, the target is difficult to be detected from an image, and therefore, the application is proposed to improve the performance of an infrared dim small target detection algorithm in small target detection and solve the problem of inaccurate target detection result in a clutter background. Specifically, the original infrared image is segmented into a series of infrared image blocks by using a sliding window; a target detection model based on target sparse representation and background low-rank constraint is established; each variable of the target detection model is solved by using an alternating direction multiplier method after the infrared image block is input; the model is expanded into a convolutional neural network, and relevant parameters in the model are continuously updated; a target detection result in the obtained reconstructed infrared image block is obtained; and the target detection result of the infrared image is output. The application can obtain good detection results for infrared targets with different attributes in different background environments.
Owner:HARBIN INST OF TECH

Grounding tool and method for detecting outer anticorrosive coating of pipeline under complex earth surface condition

The invention discloses a grounding tool and method for detecting an outer anticorrosive coating of a pipeline under a complex earth surface condition. The grounding tool comprises a bottom end, a body, a funnel and a handheld end, the bottom end is installed at one end of the body, the handheld end is installed at the other end of the body, the funnel is installed on the body, the bottom end is arranged to be of a semicircular angled wedge-shaped structure, the interior of the body is of a hollow structure, and a plurality of kidney-shaped holes are formed in the body. The grounding device is simple in structure and convenient to operate, can adapt to a complex ground surface environment, can realize reliable grounding in a high-resistance ground surface environment, and ensures smooth detection.
Owner:CHINA NAT PETROLEUM CORP +2

A method and system for detecting abnormal users based on multi-layer features

ActiveCN118568330BOptimize detection results
The application belongs to the technical field of user detection, and particularly relates to an abnormal user detection method and system based on multiple feature layers, which effectively fuse user behavior patterns, user attributes and user tweet features in social data, summarize social network user data into four levels of user statistical attributes, user behavior attributes, user network attributes and high-dimensional attributes, and use a composite neural network model based on an attention mechanism to classify and predict normal users and abnormal users, so that better abnormal user detection results can be obtained.
Owner:UNIV OF SCI & TECH BEIJING +1

Noise testing device for automobile exhaust tail pipe

The utility model discloses a noise testing device for an automobile exhaust tail pipe, which relates to the technical field of automobile exhaust detection and comprises a detection handle, a fixing unit is arranged on the outer surface of the detection handle, and a protective cover is arranged at one end of the detection handle. According to the device, through cooperation of the detection handle, the detection head, the adjusting block, the protective cover, the sleeve and the clamping groove, the detection head can be protected in the detection process, the influence of dust on the detection result is prevented, the protective cover is also convenient to disassemble, assemble and clean, the protective effect is maintained, and the detection efficiency is improved. And through the cooperation of the adjusting screw rod, the connecting piece, the movable ring, the second connecting rod, the first connecting rod and the supporting block, the device can be conveniently connected and fixed with the automobile tail pipe during detection, and the device is small in size, convenient and flexible to move and rapid to disassemble and assemble, so that the detection flexibility is improved, the detection time is saved, and the detection efficiency is improved.
Owner:TS ENG(SUZHOU) CO LTD

Label propagation overlapping community detection method based on core community attraction mechanism

The invention provides a label propagation overlapping community detection method based on a core community attraction mechanism. The label propagation overlapping community detection method comprises the steps of constructing a network model and preprocessing; identifying core communities in the network model and distributing a unique label for each core community; spreading the label and adjusting the spreading weight; the nodes are allowed to belong to a plurality of core communities at the same time, label distribution of the nodes is adjusted according to the association degree of the nodes and different core communities, and an overlapped core community structure is formed; evaluating a label propagation result; and according to an evaluation result, adjusting a core community attraction mechanism and label propagation parameters, and optimizing a core community detection effect. According to the method, the core communities in the network are identified, and the label propagation process is guided by using the core communities, so that the label propagation precision is enhanced; according to the method, a self-adaptive mechanism is adopted, the label propagation path and the weight are adjusted in real time according to the interaction frequency and the correlation degree between the nodes, the unnecessary calculation overhead is reduced, and the propagation efficiency is improved.
Owner:GUANGDONG UNIV OF TECH