250results about How to "Accurate distinction" patented technology

The invention relates to the field of image processing, in particular to a welding quality comprehensive evaluation method and system, and the method comprises the steps: obtaining an ultrasonic image of a welding joint, carrying out the contour detection, and extracting a defect region of the welding joint; gradient features and gray features of pixel points in the defect area are calculated, feature vectors of target pixel points in the defect area are constructed, and the feature vectors serve as the expression degree of the defect area; edge information of the defect area is obtained so as to determine defect types, the defect types comprise cracks and bubbles, the shape and size of a window are set according to the defect types, bilateral filtering processing is carried out, defect information is extracted, and comprehensive evaluation is carried out on the welding quality. According to the method, the appropriate window shape and size are selected according to the defect type, the detail information of the defect is effectively reserved, the definition of the ultrasonic image is remarkably enhanced through the self-adaptive filtering strategy, and therefore the welding quality is better evaluated.

The invention relates to the technical field of carrier communication, in particular to a multimode power line carrier communication method and a carrier communication module, and the method comprises the steps: determining a frequency coincidence degree through analyzing the coincidence degree of a frequency corresponding to a positive number amplitude value on a spectrogram of each modal component in a carrier signal and a signal frequency range of the carrier signal, and determining a difference index by analyzing the difference between each characteristic modal component and all modal components of the noise reference signal in frequency, analyzing the centralized distribution condition of the carrier signal in energy, and determining a step length adjustment value in combination with the signal interference degree. And carrying out noise reduction processing on the carrier signal in the power line carrier communication process at the current moment. The invention aims to eliminate noise interference in carrier signals and improve the reliability of power line carrier communication.

The invention discloses an image recognition system based on machine vision, which comprises a deep learning model, and is characterized in that an image recognition module comprises an image data sensing module for receiving and processing original image data, capturing an image from a camera or an image file, and performing preliminary format conversion and preprocessing; the image feature extraction module is used for converting the image into a form which can be understood by a machine based on a convolutional neural network; the online learning framework is used for dynamically adjusting model parameters according to data input in real time; the environment adaptability adjusting module is used for dynamically adjusting image processing parameters, changing a feature extraction weight, adjusting a learning rate and adjusting an identification strategy according to environment changes; the recognition and classification module is used for executing object recognition and classification tasks based on the extracted features and the learned model; the parameter mapping unit is used for mapping the environment parameters to specific parameter adjustment of the model; and the environment adaptability development unit is used for extracting useful information from the environment data and converting the useful information into an instruction of an adaptability adjustment strategy.

The invention provides a primitive recognition method and device for a wiring diagram, electronic equipment and a storage medium, and relates to the technical field of image recognition, and the method comprises the steps: constructing a training data set according to the wiring diagram; training the residual network model and the semantic segmentation network model by adopting the training data set to obtain a primitive segmentation network model; detecting a to-be-identified wiring diagram according to the primitive segmentation network model to obtain a primitive mask area; and extracting edge point coordinates according to the primitive mask area to obtain a primitive segmentation result. According to the method, the advanced semantic segmentation network technology is combined, pixel-level fine segmentation is carried out on the primitive area of the line graph, the positioning detection and recognition capability of all types of primitives of the line graph is remarkably improved, and powerful support is provided for subsequent tasks such as primitive relation analysis and connection line optimization.

The invention relates to the technical field of image processing, in particular to an intelligent detection method and system for shaft forgings. The method comprises the following steps: acquiring gray values, positions and gradient directions of all pixel points in a surface image of the shaft forging; clustering all pixel points in the surface image by using a condensed hierarchical clustering algorithm to obtain a plurality of regions; calculating the suspicious degree of each region; determining a scratch burr area in the surface image of the shaft forging to realize intelligent detection of the shaft forging; in each round of iteration process of the condensed hierarchical clustering algorithm, for two to-be-combined clusters in each round of iteration process, calculating the separation degree of the two clusters; calculating the feature similarity of the two clustering clusters; determining the number of clustering clusters of the current iteration; a plurality of regions of the surface image of the shaft forging are determined. By dynamically adjusting the number of clusters, the problem of wrong merging or premature iteration stopping of a traditional condensed hierarchical clustering algorithm under the fixed number of clusters is avoided.

The invention discloses a multi-modal model-based RPA element anchor point automatic searching method. The method comprises the following steps of S1, acquiring coordinates, text information and regional screenshots of target elements and candidate anchor point elements in a webpage; s2, according to the area screenshot, obtaining element categories of target elements and candidate anchor point elements through a target detection model; s3, inputting the coordinates, the text information, the regional screenshots and the element categories of the target elements and the candidate anchor point elements into a multi-modal model, performing vector conversion, vector alignment, element distinguishing, element attention and element judgment by utilizing the multi-modal model, and detecting and determining the target anchor point elements; s4, recording a relative relation between the target element and the anchor point element, wherein the relative relation is used for positioning the target element when the robot process automatically runs; the anchor point elements of the webpage are dynamically recognized through the webpage screenshot, the element coordinates and the element types, and the method has the advantages of being wide in application range and reliable in recognition.

The invention relates to a multi-modal target identification and tracking prediction method based on a laser radar and a binocular camera, and belongs to the field of robot / unmanned system perception identification. Comprising the following steps: preprocessing a target two-dimensional image acquired by a binocular camera and target point cloud data acquired by a laser radar to obtain a preprocessed two-dimensional image and point cloud data; s2, performing two-dimensional target detection and tracking detection based on the preprocessed two-dimensional image to obtain a two-dimensional target detection and tracking result; s3, performing three-dimensional target detection based on the preprocessed point cloud data and the two-dimensional target detection and tracking result to obtain a three-dimensional detection result; and S4, based on the pixel coordinates in the two-dimensional target detection and tracking result and the pixel coordinates of the vertexes of the target point cloud boundary in the three-dimensional detection result, target fusion tracking prediction is carried out, and the target ID, the position, the category and the target point cloud boundary are obtained. And accurate identification and tracking of the target are realized.

The invention discloses a spatial-spectral combined hyperspectral image classification method based on a multi-scale adaptive attention mechanism, and the method comprises the steps: firstly carrying out the extraction and fusion of features of different scales through a multi-scale feature fusion module, and comprehensively capturing the detailed spectral information of a hyperspectral image; secondly, dynamically adjusting a feature extraction process by using an efficient self-adaptive spectrum-space feature extraction module, and optimizing fusion and representation of spectrum-space features; and finally, enhancing the ability of the model to understand the context relationship in the image by using the context-aware fusion network. The three modules provided by the method are based on a deep learning framework, a convolutional neural network in deep learning can utilize multiband rich spectral information, and the method is suitable for hyperspectral remote sensing image data sets with different spatial resolutions, including a foreign hyperspectral data set and a domestic hyperspectral data set. The method has high adaptability and transportability, and can meet the requirement of image classification more easily.

The invention discloses a pinhole camera positioning detection method and a pinhole camera positioning detection system, and the pinhole camera positioning detection method provided by the invention realizes mobile detection and covers multiple scenes by integrating a laser emission module and a multispectral camera unit on a mechanical motion platform. High-reflection area features are extracted through inter-frame difference calculation, ultraviolet, thermal imaging and near-infrared image data are aligned and fused, a unified feature matrix is generated, and interference of environmental noise is effectively reduced. A convolutional neural network model is utilized to analyze high-reflectivity region features, and a pinhole camera and other reflecting objects are accurately distinguished. And finally, the position of the detection target is normalized into a unified coordinate system through a coordinate calculation module, accurate positioning of the pinhole camera is realized, a detection result is transmitted to a control terminal in real time to trigger an alarm system, and it is ensured that the system can provide efficient and intelligent safety protection in a complex environment.

The invention provides an adaptive CFAR detection method based on scene classification, and the method comprises the steps: carrying out the scene classification of an input SAR image through employing a K-means clustering algorithm, carrying out the target detection of a pure sea area obtained through classification through employing VI-CFAR, and carrying out the CFAR detection of a coastal area through employing a significance model. According to the method, the problems that a traditional CFAR algorithm is high in false alarm rate and unstable in detection performance in port and land complex backgrounds are effectively solved, detection parameters are optimized according to the complexity of different scene backgrounds, and therefore it is ensured that the CFAR algorithm can still maintain the constant false alarm rate in the sea clutter background, and the robustness of target detection is remarkably improved. The ocean area and the land area in the image are effectively distinguished, and the land area is shielded. According to the technical scheme, the problem that a traditional CFAR detection algorithm is interfered by a complex land background when detecting ships on the sea surface is solved.

The invention discloses a phased array radar for unmanned aerial vehicle detection based on multi-target tracking, which comprises a radar antenna array, a signal processing unit, a control unit and a display unit, and is characterized in that the control unit comprises a motion state judgment module; a filtering switching module; a Kalman filtering module; a particle filtering module; and a data association module. The method can achieve the high-precision detection and positioning of an unmanned plane target, has a multi-target tracking capability, and improves the detection efficiency and accuracy of the unmanned plane.

The invention discloses a forest fire audio recognition method based on a BP neural network, a medium and a product in the technical field of forest fire recognition. The method comprises the following steps: acquiring forest fire audio data to be detected; extracting a Mel-frequency cepstrum coefficient (MFCC) based on the frequency domain features of the forest fire audio data to be detected; inputting the Mel-frequency cepstral coefficient MFCC into a pre-trained forest fire audio recognition model based on a BP neural network, and outputting a forest fire category; wherein the forest fire category comprises a forest fire and a non-forest fire. Compared with a traditional visual monitoring means, the method can cover a wider forest area, in the same monitoring range, in addition, model training based on the BP neural network can efficiently process a large amount of audio data and rapidly output an identification result, the efficiency and accuracy of forest fire identification are further improved, and the method is suitable for popularization and application. The problems of limited coverage range, high cost and low accuracy in the existing forest fire identification technology are solved.

The invention relates to the technical field of target detection, and particularly provides a semi-supervised learning-based target detection method, system and device and a storage medium, and the method comprises the steps: obtaining a data set which comprises a marked image and an unmarked image; generating a pseudo label for the unmarked image based on the marked image by using a dense detector; dividing the pseudo labels into reliable labels and soft labels according to the scores of the pseudo labels by using a pseudo label distributor; the pseudo label is updated to the data set, the updated data set is utilized to train a target detection model, and the target detection model identifies a target object in the sample image after training; the soft label is set to only participate in the preset partial loss calculation in the training process so as to reduce the training error caused by the soft label. According to the invention, an efficient semi-supervised learning target detection framework is constructed, and the accuracy of a target detection model is improved.

The invention relates to the technical field of artificial intelligence, and discloses a document information extraction method and device based on image-text modal fusion and a storage medium, and the method comprises the steps: obtaining a text block in a to-be-processed picture; extracting semantic vectors from the text blocks according to a pre-trained NLP model, extracting visual vectors by adopting a computer vision technology, and fusing the semantic vectors and the visual vectors through an attention mechanism to form feature representation of image-text fusion; according to the image-text fusion features, constructing a full-connection directed graph; on the constructed graph network, graph attention convolution of a'node-edge-node 'ternary feature group is executed; important'text-position-text 'ternary information is dynamically weighted through a self-attention mechanism; and outputting a feature vector fused with text, vision and position information. Through deep fusion of the text, vision and position information, the accuracy and robustness of text information matching are remarkably improved, and the method can adapt to a complex and changeable image text environment.

The invention belongs to the technical field of pavement load positioning, and provides a pavement load spatial distribution positioning method and system based on multi-source heterogeneous data fusion in order to solve the problem that the strain distribution of a pavement full-scale space cannot be comprehensively monitored at present. The method comprises the following steps: acquiring road surface laser radar data and road surface mechanical data of a set road section at each moment; fitting the ground from the road surface laser radar data and removing the ground, and based on the road surface laser radar data from which the fitting ground is removed, performing clustering identification on a vehicle type and a corresponding load so as to track a track of the vehicle; according to the method, the vehicle position and the pavement stress are decoupled from the pavement mechanical data by utilizing a finite element mechanical analysis method, and the pavement stress and load distribution diagram in the three-dimensional space is generated by combining the tracked vehicle track, so that the precise real-time identification of the pavement vehicle load space distribution is ensured.

The invention discloses a thromboembolism occurrence risk assessment method and assessment system. The method comprises the following steps: acquiring a blood vessel image map of a to-be-assessed patient; inputting the blood vessel image map of the patient to be assessed into a pre-trained risk assessment model; wherein the pre-training of the risk assessment model is based on a ResNet-50 model, and self-supervised contrast learning iteration is carried out by inputting positive and negative samples so as to update model parameters; extracting a feature embedding vector in the blood vessel image; according to the feature embedding vector, calculating probability distribution of embolism occurrence risk levels through a model classification head; and according to the probability distribution, selecting a risk level label and outputting the risk level label as an evaluation result. According to the method based on the time axis symmetry, the image data of the patient is collected before and after the embolism occurrence time point, the positive and negative sample pairs are generated, the problem that the embolism sample is difficult to obtain is solved, and meanwhile the sample collection cost is reduced through self-supervised learning.

The invention discloses a data fusion method and system for a fire detection sensor, relates to the technical field of data fusion, remarkably improves the reliability and accuracy of the system, and solves the problems of false alarm, missing report, environmental interference, sensor fault and the like. By introducing a detailed anomaly detection module and a multi-level threshold evaluation mechanism, the system can accurately distinguish normal fluctuation and real fire signals, and reduces false alarm and missing alarm; in addition, the environment monitoring module calculates an environment interference coefficient in real time and compares the environment interference coefficient with a threshold value, so that the influence of environment factors on the detection accuracy is effectively dealt with, and the detection reliability is improved. The safety fault-tolerant module monitors the state of the sensor and the data transmission process in real time to ensure that a data compensation mechanism is started when the sensor fails or data is lost, so that the fault-tolerant capability of the system is enhanced; the comprehensive measure ensures the stability and accuracy of the system under various interference and fault conditions.

The invention provides a track fastener state recognition method based on a three-section type parallel network architecture. The method comprises the steps that a track inspection image is acquired; constructing a convolutional neural network (CNN) backbone network, and performing multi-scale feature extraction on the image of the track fastener; performing convolution processing and up-sampling processing on the fastener features by using the local feature branches to obtain local fastener features; performing global average pooling and convolution processing on the fastener features by using the global feature branches; the method comprises the following steps of: processing the characteristics of the fastener by using a mask generation branch of a framework based on Vision Transform, and generating a prototype mask of the track fastener; local, global and mask fastener features are fused; performing non-maximum suppression and mask generation on the fastener feature map; and analyzing the health state of the track fastener. According to the method, the CNN backbone network and the Vision Transform are combined, a new three-section parallel network architecture is provided, accurate identification and state analysis of the track fastener are realized through instance segmentation, and the identification accuracy in a complex environment is improved.

The invention discloses a lithium mineral component detection method based on improved YOLOv8, and belongs to the technical field of computer vision and mineral detection.The method comprises the steps that dry powder samples of various lithium mineral components are collected, the collected dry powder samples are shot under an optical microscope, and then the shot images are segmented and marked to obtain lithium mineral components; constructing a sample data set covering various lithium mineral components; the method comprises the following steps of: improving a YOLOv8 network to obtain an improved YOLOv8 network; training the improved YOLOv8 network on the basis of the sample data set; and the trained and improved YOLOv8 network is utilized to realize lithium mineral component detection. By adopting the scheme, the lithium mineral component detection effect and efficiency can be improved, and technical support is provided for intelligent detection of lithium ores.

The invention relates to an X-ray-based defect identification method, belongs to the technical field of X-ray nondestructive testing, and solves the problems of low accuracy and efficiency of casting defect identification in the prior art. The method comprises the following steps: acquiring an X-ray image of a sample casting, and preprocessing the X-ray image to acquire an edge image of the sample casting; marking whether the contour has defects and defect types according to the area and defect features of each contour in the edge image of the sample casting; training a defect identification model by adopting the marked edge image of the sample casting; obtaining an X-ray image of a target casting, and preprocessing the X-ray image to obtain an edge image of the target casting; and inputting the edge image of the target casting into the trained defect identification model so as to identify whether the target casting has a defect and identify the type of the defect. According to the method, through combination of an X-ray imaging technology, an image processing technology and a machine learning technology, rapid and accurate identification of the internal defects of the casting is realized.

The invention discloses a bridge crack detection method based on image recognition, and belongs to the technical field of image recognition, and the method comprises the steps: firstly, dividing a bridge image into three single-color channels of red, green and blue, carrying out the clustering and scanning of each spectral image, and precisely positioning a suspected crack point; a red channel weight matrix, a green channel weight matrix and a blue channel weight matrix are constructed by calculating a channel contrast value and a region track distortion value, and then gray processing and brightness adjustment are performed on a bridge image to enhance a crack region. Then, texture enhancement is carried out on the adjusted images through the red channel weight matrix, the green channel weight matrix and the blue channel weight matrix, and three texture-enhanced images are generated; and finally, processing the enhanced image by using a three-channel crack identification neural network to obtain the bridge crack, thereby improving the accuracy of crack detection.

The invention relates to the technical field of remote sensing image anomaly detection, in particular to a sequential InSAR coherence graph building damage detection method based on a generative model, which comprises the following steps: generating a building area InSAR coherence image time sequence by using a building area SAR image time sequence; training a WGAN generation model by using the InSAR coherent images of the building area from the second moment to the (T-1) th moment to obtain a trained WGAN generation model; subtracting the InSAR coherent image, generated by the trained WGAN generation model, of the building area at the (T + 1) th moment when the disaster does not occur from the InSAR coherent image, generated by the trained WGAN generation model, of the building area at the (T + 1) th moment after the disaster occurs, so as to obtain an abnormal image; and acquiring abnormal information based on the abnormal image, and comparing and screening the building damage area by using a set threshold value. According to the invention, a more accurate detection method is provided for the post-disaster building damage condition, and the building damage detection performance is improved.

The invention belongs to the technical field of power transmission line modeling, and provides a power transmission line channel point cloud modeling method and system, and the technical scheme is that based on standardized point cloud data, global statistical features are extracted, channel scene categories are automatically judged, and adaptive feature weight vectors are generated according to the judged scene categories; performing weighted calculation on the similarity by using the feature weight vector, and performing superbody clustering segmentation on the standardized point cloud data to obtain an optimized superbody set formed by a plurality of superbodies with similar internal features; based on multi-dimensional feature statistics and context rules, screening the optimized superbody set, and rejecting small non-ground interference superbodies to obtain a ground candidate superbody set; and performing identification, merging and curved surface fitting on the ground candidate superbody set to generate a continuous power transmission line channel ground model. High-precision identification of ground points is realized, and a high-quality ground reference can be provided for safety analysis of a power transmission channel.

The invention belongs to the technical field of biomedical detection, and particularly discloses a surrounding type multi-neurotransmitter recognition biological mixed synapse system which is composed of a flexible biological synapse device and a microfluidic channel, the microfluidic channel simulates a biological synapse gap and controls transmission and diffusion of different neurotransmitters, and the flexible biological synapse device and the microfluidic channel are used for detecting the biological synapse gap. The releasing and receiving processes of neurotransmitters in a biological synaptic gap are simulated; according to the flexible biological synapse device, direct interaction between biological tissues and equipment is realized, and the change of long-term synapse weight is simulated by utilizing a redox reaction of a neurotransmitter at a grid electrode, so that the dynamic adaptability and the information processing capability of a system are improved; when neurons generate peak signals containing different neurotransmitters, the system can accurately distinguish and identify the signals and efficiently transmit the signals; therefore, the biological mixed synaptic system disclosed by the invention becomes an ideal multi-neurotransmitter monitoring tool and can be widely applied to neuroscience research and clinical diagnosis.

The invention relates to the technical field of wind lidar measurement, and discloses a wind lidar data quality control method comprising the following steps: collecting wind lidar echo signals in a period of time, the wind lidar echo signals comprising atmospheric reflection signals and noise signals; carrying out average power spectrum estimation processing on the original echo signal; gaussian filtering processing is carried out on the average power spectrum so as to suppress obvious and burst noise and interference signals, and a calculation result is used for replacing an original power spectrum numerical value; the filtered power spectrum is obtained, a least square method mathematical optimization method is adopted, model parameters of optimal fitting given power spectrum data points are searched, a prediction model adopts a low-order polynomial, and whole range gate sequence data are selected for prediction fitting. Through power spectrum estimation and noise frequency domain statistical characteristic analysis, the signal and the noise can be distinguished more accurately, so that the influence of the noise on a measurement result is effectively reduced.

The invention discloses an intelligent ecological protection and management method for a natural reserve, and the method comprises a satellite remote sensing ecological environment monitoring method which achieves the remote sensing image segmentation based on a satellite remote sensing image and a neural network model, is used for accurately distinguishing ecological systems, and accurately calculates the area of each ecological system through two-dimensional integral operation. Visual display is realized in a thermodynamic diagram form, and real-time monitoring of ecological system changes is realized; according to the species quantity change prediction and decision-making method, a neural network model is used for extracting a nonlinear feature relationship between species quantity change and each environmental factor in a species quantity change prediction data set, and accurate prediction of the species quantity change trend on the premise of known environmental factor change trends is realized; according to the species identification method, accurate identification and distinguishing of similar species are realized through big data and a neural network model. The method has the advantages of being large in monitoring range, automatic in monitoring, high in species identification and quantity statistics accuracy and high in population quantity change trend prediction accuracy.

The invention discloses an infrared imaging insulator epoxy resin internal defect detection method and system, and relates to the technical field of defect detection, and the method comprises the following steps: constructing a to-be-detected epoxy resin model, and heating the epoxy resin model to obtain an imaging time sequence diagram; analyzing the imaging sequence diagram to obtain influence factors of internal defects of the epoxy resin model; and judging influence factors of the internal defects, and determining a detection method of the epoxy resin model according to a judgment result. According to the method, the internal defect information of the basin-type insulator is obtained by utilizing infrared imaging, the defects such as bubbles and cracks in the basin-type insulator are quickly and accurately distinguished by adopting a comprehensive brightness difference standard method, and efficient scanning can be realized in the detection process by adopting array type bubble defect arrangement and accurate model construction; particularly, by constructing a plurality of groups of models with different defect depths and diameters, the system can quickly judge influence factors of different defects, so that the overall scanning efficiency is improved.

The invention provides a drainage well lid blockage detection system and method based on machine vision, and the system comprises a data collection module, a preprocessing module, an edge detection module, a rectangular calibration module, a blockage detection module and an early warning judgment module. Whether the point is a blockage point or not is judged at the corresponding position in the grey-scale map according to the pixel value, the blockage point is summed, the ratio of the blockage point to the total pixel value serves as the standard for judging the blockage rate, and a corresponding early warning and solution scheme is provided according to the blockage degree grade, so that the blockage rate can be accurately judged even if the blockage object is cleaned. And water accumulation in rainy days is avoided to a certain extent.

The invention provides a loop-mediated amplification primer group, a kit and a detection method for detecting influenza A virus, influenza B virus and respiratory syncytial virus, and relates to the technical field of biotechnology. Specific loop-mediated amplification primers are respectively designed aiming at M1 protein genes of influenza A viruses, NEP genes of influenza B viruses, F gene conserved segments of respiratory syncytial viruses and human RnaseP genes, and each set of primers comprises two outer primers (OF / OB), two inner primers (FIP / BIP) and at least one loop primer (LF / LB). Compared with a traditional detection method, the detection time is greatly shortened, a basis can be provided for clinical diagnosis more quickly, treatment measures can be taken in time, complex nucleic acid extraction and purification steps are not needed, the swab sample can be detected after being simply treated, the operation difficulty and the requirement for professional skills of operators are reduced, and the detection efficiency is improved. And popularization and application in all levels of medical institutions are facilitated.

The invention relates to the technical field of image processing, in particular to a crack contour extraction method for a well logging diagram, which comprises the following steps of: acquiring the well logging diagram, and obtaining space parameters of pixel points according to gray values and position characteristics of the pixel points in the well logging diagram; the method comprises the following steps: acquiring a space parameter of a pixel point, acquiring an environment performance value of the pixel point according to the space parameter of the pixel point and surrounding pixel points, acquiring a crack characteristic value of the pixel point according to the environment performance value of the pixel point and the coordinate spacing of the pixel point, and classifying according to the size of the crack characteristic value so as to distinguish the crack position of the logging diagram. According to the scheme of the invention, the method achieves the positioning of the position of the crack, enables the edge of the crack to be clearer, achieves the accurate monitoring of the contour of the crack, and effectively improves the exploration technology.