56 results about "Disease area" patented technology

The invention discloses a tunnel lining disease automatic identification method and system based on multi-source data fusion, and relates to the technical field of facility detection, and the method comprises the steps: collecting multi-modal time sequence data, carrying out the time-space alignment, and obtaining a time sequence multi-source data set; reconstructing a tunnel center line based on a vehicle pose and constructing a lining structure consistency coordinate framework, and performing structured projection and distortion correction on alignment data to obtain a multi-modal fusion data set; dividing a two-dimensional structure grid under the coordinate framework, extracting and fusing geometric, texture, depth and energy features, calculating a structure consistency damage index, and extracting a suspected disease area; and calculating a disease credibility index and judging a disease type in combination with multi-modal physical evidence, mapping a suspected disease region back to a three-dimensional space, completing disease boundary extraction and geometric quantization, and outputting structured disease information. According to the method, the structure expression and the structured alignment of the cross-modal data under the unified geometric reference are realized by constructing the consistent coordinate framework of the lining structure.

The invention relates to the technical field of tunnel crack detection and artificial intelligence edge calculation, and provides a tunnel apparent disease detection method based on deep learning and knowledge distillation, which comprises the following steps: step 1, introducing spectral domain information enhancement to an original tunnel image, the edge texture features of the disease area in the image are enhanced through methods such as multi-scale wavelet transform and small-scale enhancement. Step 2, constructing a high-performance teacher model, introducing a flexible up-sampling structure to adapt to feature recovery requirements of different levels of semantic information, introducing an efficient visual coding module to enhance feature fusion capability of different scale channels, and designing a scale adaptive weighted loss function at the same time; by introducing a frequency spectrum enhancement mechanism, structural features of disease areas with low contrast, fuzzy edges and the like are remarkably enhanced in an image preprocessing stage, clearer information input is provided for a model, and the stable recognition capability of a system in environments of uneven illumination, complex background and the like is enhanced.

The invention relates to the technical field of road detection, in particular to a multi-dimensional road disease detection method and system based on a ground penetrating radar. The method comprises the following steps: acquiring original ground penetrating radar data, performing DC component removal, gain adjustment and background denoising on the original ground penetrating radar data, positioning a suspected disease area and defining the suspected disease area as a disease entity; extracting a time domain feature, a frequency domain feature and a spatial context feature of each disease entity in parallel to form a multi-dimensional feature vector; constructing a road disease knowledge graph according to the multi-dimensional feature vectors, and distributing an initial weight for each graph relation; and performing node matching operation according to the multi-dimensional feature vector and a knowledge graph, performing logical reasoning according to a graph relation path, fusing similarity and reasoning confidence, and outputting a diagnosis tag signal and a confidence signal. According to the method, the positioning accuracy of the suspected disease area is improved, comprehensive utilization of multi-dimensional information is realized, and a visual causal link is provided for diagnosis.

The invention relates to the technical field of material analysis, in particular to an intelligent inspection device and method for bridge structure diseases, and the method comprises the steps: determining a plurality of disease suspected regions through obtaining a plurality of frames of unmanned aerial vehicle images of a bridge structure, carrying out the feature analysis of each disease suspected region, and determining the feature value of each disease suspected region; according to different candidate time interval lengths and characteristic values, determining interval change fluctuation degrees representing the possibility of rain and sewage flow marks corresponding to different candidate time intervals in each disease suspected area, and carrying out feature distinguishing on the rain and sewage flow marks and crack diseases; according to the interval change fluctuation degree, determining interval division fitness, comprehensive identification capability and timeliness of different candidate time intervals; according to the interval division fitness, the target interval change fluctuation degree corresponding to each disease suspected area is determined, so that the crack disease area is determined for intelligent inspection, the recognition accuracy is improved, and the intelligent inspection effect is ensured.

The invention discloses a crop disease intelligent identification method and system based on an unmanned aerial vehicle image, and belongs to the technical field of intelligent agriculture, and the method comprises the steps of data multi-dimensional collection, early disease identification, disease space-time deduction and crop management suggestion. According to the method, early disease recognition based on the spectrum sensitive vegetation index and the attention guidance double-branch network is adopted, the spectrum sensitive vegetation index capable of amplifying weak disease spot features is constructed, the weak disease features are highlighted through multispectral information enhancement and time sequence feature inhibition, meanwhile, the attention mechanism is utilized to focus on potential disease areas, and the disease recognition accuracy is improved. Therefore, the accuracy and stability of early disease recognition are remarkably improved. Disease space-time deduction combining propagation potential energy and a space-time diagram convolutional network is adopted, on the basis of considering factors such as environmental conditions, disease time sequence evolution and spatial neighborhood influence, a disease propagation path is dynamically simulated, future risks are quantified, and a visual risk prediction map and a propagation vector diagram are generated, so that agricultural management is assisted to be optimized.

The invention discloses a bridge intelligent inspection unmanned aerial vehicle integrated measurement and control system, and relates to the technical field of unmanned aerial vehicle measurement and control, and the system comprises a reference construction module, a pose acquisition module, a pose matching module, a coordinate generation module, and a disease locking module. According to the method, the reference three-dimensional model and the space reference control point are constructed, so that accurate registration of the real-time video stream and the historical model is realized; driving the unmanned aerial vehicle to actively adjust the pose and lock the disease area through visual servo control; the absolute three-dimensional space coordinates of the diseases are calculated through reverse ray tracing, integration of disease recognition, active observation and accurate positioning is achieved, the automation degree of bridge inspection is improved, and the problems that in the prior art, bridge disease recognition and space positioning links are disjointed, cross-cycle data cannot be aligned, and an active observation mechanism is lacked are solved.

The invention relates to the technical field of image analysis, in particular to a pinus massoniana disease model training method based on image analysis, and the method comprises the following steps: collecting a multi-time sequence image, constructing a boundary sample through gray scale and Sobel, obtaining a gradient deviation through CNN through outer normal gradient increment, and combining contour comparison, differential sequence and clustering recognition mutation points and marking to form a marking set; according to the marking and transition cluster, convolution kernel weight is adjusted to optimize boundary representation, the model is iteratively updated to improve the pinus massoniana disease identification precision, the time sequence stability is enhanced, the robustness in a complex scene is improved, the edge detail recovery capability is improved, and the detection consistency is enhanced. According to the method, contour gradient operation is carried out by extracting image gray and combining Sobel, subtle change is identified and time sequence information is fused to capture disease development, gradient response and error comparison are carried out to improve detection precision, mutation points are identified through differential clustering analysis and disease areas are marked, and the model is optimized to reduce boundary deviation.

The invention discloses a tomato leaf disease detection method, which is based on an improved lightweight target detection model MWD-YOLO11n to improve the accuracy and efficiency of disease identification. According to the method, three key improvements are carried out on the basis of an original YOLO11 model: firstly, a multi-scale dynamic attention mechanism (MSDA) is introduced, and the perception ability of the model to different-scale disease features is enhanced; secondly, wavelet convolution (WTConv) is adopted to replace part of a traditional convolution structure, and the capturing capacity of the model for disease edges and texture details is effectively improved; and finally, integrating a dynamic up-sampling operator (DySample), optimizing the resolution of the feature map, and further enhancing the characterization capability of the disease area. The method has high precision and low calculation amount, is suitable for deployment of edge equipment, shows excellent performance in tomato leaf disease detection tasks, and has good application prospects and popularization value.

The application discloses a three-dimensional detection and diagnosis simulation verification method and platform for tunnel apparent diseases and a storage medium. The method comprises the following steps: collecting point cloud data and image data of a tunnel model, performing difference analysis based on the two types of data to obtain an apparent detection result, and positioning a suspicious disease area of the tunnel model according to the apparent detection result. A machine learning model is used to analyze a disease diagnosis result corresponding to the suspicious disease area, and the disease diagnosis result is compared with preset real disease information of the tunnel model, and a comparison result obtained can be used to optimize the machine learning model. The scheme avoids the limitations of real vehicle verification and non-entity verification, and effectively improves the verification effect and verification efficiency of the machine learning model.

The invention provides an expressway foreground image disease detection method and system, and relates to the technical field of expressway disease detection, and the method comprises the steps: obtaining an expressway foreground image, carrying out the recognition according to a preset neural network model to obtain a disease region and a disease type, and generating a Grad-CAM thermodynamic diagram for the disease region through a Grad-CAM technology; performing grid division on the Grad-CAM thermodynamic diagram containing the disease area to obtain standard detection frames, and counting the proportion of abnormal pixels in each standard detection frame; judging whether the abnormal pixel proportion exceeds an abnormal threshold value or not; if yes, the disease area in the standard detection frame is an effective disease area, the accurate boundary of the effective disease area is drawn to quantify the disease size, the disease position and the disease number of the expressway foreground image are obtained according to the accurate boundary, and disease detection is achieved in combination with the disease category. According to the invention, the detection convenience, the identification precision and the size standardization are improved.

The invention belongs to the technical field of road surface detection, and relates to a multi-dimensional radar map construction method based on electromagnetic signals, which comprises the following steps: S1, scanning a target area through high-frequency three-dimensional ground penetrating radar equipment, acquiring electromagnetic reflection signals, and preprocessing the acquired signals; s2, converting the time domain data of the preprocessed electromagnetic reflection signal into spatial domain data, and generating a three-dimensional data model; s3, blank data in the three-dimensional data model are complemented through an interpolation method, and high-resolution three-dimensional grid data are generated; s4, extracting a disease area based on a reflection intensity threshold value and performing type identification; and S5, constructing a three-dimensional disease visualization model, and mapping disease characteristic parameters by adopting color coding. According to the method provided by the invention, the depth resolution and the spatial positioning precision of disease detection are improved, and the real distribution and form of the diseases in the pavement can be reflected more comprehensively.

The application discloses a defect detection method for rail fasteners based on multi-scale feature enhancement, and is implemented according to the following steps: step 1, selection and preprocessing of an existing rail fastener defect dataset; step 2, construction of a feature extraction module of a rail fastener defect detection network; step 3, construction of a multi-scale feature enhancement and fusion module for rail fastener defect detection; and step 4, construction of a detection prediction and result output module. Through the function processing procedures of layered feature response highlighting, local texture sensitive enhancement, global context semantic aggregation, inter-layer heterogeneous feature collaborative fusion and dual-domain saliency modulation, the application differentiates and collaboratively enhances the shallow texture information, the middle structure information and the high-level semantic information, thereby effectively improving the representation ability, the category discrimination ability and the background suppression ability of the disease area, and improving the stability and reliability of the detection result.

The grape leaf disease area image segmentation method provided by the application cooperates the frequency domain and the spatial domain, adopts a global processing module in the image segmentation model, the global processing module performs frequency domain transformation and spatial selective aggregation in the window synchronously through the frequency domain and spatial domain cooperative attention mechanism, realizes the deep cooperation of the global perception in the frequency domain and the accurate positioning in the space, effectively suppresses the interference of the complex field background on the disease feature extraction while enhancing the feature discrimination ability, adopts a hierarchical feature constructor during feature extraction, captures the fast scale context information through hierarchical capture, effectively processes the significant scale change of the disease area, and the adaptive feature fusion module can dynamically integrate the multi-scale heterogeneous features adaptively, enhances the feature fusion capability of the network, and thus can effectively ensure the segmentation accuracy of the final grape leaf disease area.

The invention belongs to the technical field of disease monitoring, and discloses a remote-sensing-based urban edge road disease monitoring and evaluation method and a remote-sensing-based urban edge road disease monitoring and evaluation system. Comprising the steps of collecting remote sensing image data and geographic information in real time, and executing data cleaning to obtain an original road assessment data set; performing deformation evaluation, performing semantic analysis on a deformation evaluation result, and outputting a disease tendency label; performing weight adjustment in combination with a disease tendency label, and outputting a score fusion proportion; extracting disease features based on the original road assessment data set, and calculating a disease score in combination with a score fusion proportion; performing trend identification based on the disease score, and outputting a trend field; combining the trend field and the disease score to carry out space aggregation on the corresponding road section to obtain an effective disease area; performing visualization processing on the effective disease area to obtain disease assessment visual data, and sending the disease assessment visual data to a preset monitoring terminal; the semantic intelligibility and the score adaptability of urban edge road disease monitoring evaluation are improved.

The application discloses a railway track disease detection method based on coordinate attention, comprising the following steps: acquiring a railway track image, performing adaptive pyramid scaling and normalization processing, and expanding a data set based on a Mosaic data enhancement method; adopting a lightweight backbone network based on FasterNet to extract multi-scale features of the railway track image; strengthening disease area related channel features based on an MSCAM multi-scale convolution attention module; connecting a coordinate attention CoordAtt module after the output of the MSCAM multi-scale convolution attention module to form a fused feature enhancement module, and obtaining disease area related channel features after association; fusing a perception loss on the basis of an original loss function of YOLOv8 to form a joint loss function, optimizing disease texture alignment in a deep disease area feature space, and forming enhanced features; inputting the features into a detection head to output disease categories, a bounding box and a confidence, and completing railway track disease detection. The application also discloses a system, an electronic device and a computer readable storage medium.

The application provides a crop disease identification method, device, equipment and medium, the method comprises: acquiring the RGB image and the NIR image of the target part on the crop under different shooting angles; determining the corresponding RGB weight and NIR weight according to the RGB image and the NIR image under each shooting angle; determining the disease area belonging to the target disease on the image under each shooting angle according to the RGB image and the NIR image under each shooting angle and the corresponding RGB weight and NIR weight, realizing the rapid identification of diseases at different angles of crops, and further monitoring the disease conditions of different growth parts of crops, and providing support for crop disease information acquisition and disease control.

The invention discloses a track sleeper chipping disease detection system based on a PCA technology, and relates to the technical field of chipping disease detection, and the system comprises the steps: collecting an original sleeper image through an image collection module as a to-be-detected image; the sleeper chipping image analysis module extracts a data dictionary by collecting a normal sleeper image set, generates a data model through PCA algorithm dimensionality reduction, constructs a reference image in combination with projection transformation of a to-be-detected image, preprocesses the to-be-detected image, and makes a difference between the to-be-detected image and the reference image to obtain a comparison image. And judging a falling block disease region through threshold segmentation and connected region area calculation, and marking an output result. According to the method, high-efficiency and high-precision recognition of sleeper falling block disease detection is realized, and the method is effectively adaptive to scenes with complex sleeper surface textures and redundant high-dimensional data.

The application discloses a highway pavement disease detection method, system and equipment, and relates to the technical field of highway pavement image processing. The technical scheme points are: obtaining a to-be-detected pavement image of a highway; inputting the to-be-detected pavement image into a pre-trained disease area segmentation model for segmentation and extraction to obtain a disease area image of the highway pavement; wherein, a first discriminator and a first generator are used to form a first generative adversarial network, the first generative adversarial network is trained, and when the number of training reaches a maximum number, a disease detection model is obtained; the disease area image is input into the pre-trained disease detection model for detection to obtain a disease detection result of the highway pavement; wherein, a YOLOv8 neural network is trained, and when a first loss function converges, the disease detection model is obtained. The problems that the prior art cannot capture detailed information and has false and missed detection of diseases when detecting pavement diseases are solved.

The present application relates to the technical field of computer vision and road detection, and particularly relates to a pavement disease identification method, system, device and medium based on semi-supervised learning. The method comprises: processing a pavement image through an image recognition model to obtain an identification result containing disease category and spatial position information; based on the identification result, quantifying a disease area according to a grid of a preset size to obtain a quantification result; based on the identification result and the quantification result, generating a structured data file; in response to a review operation on disease data in the structured data file, correcting the disease data based on a user interaction instruction to obtain corrected disease data; and based on a data set containing the corrected disease data, iteratively training the image recognition model. Compared with the prior art, the present application effectively closes the loop between the manual review and correction link and the model training link, so that the model can be iteratively optimized using continuously generated correction data to realize self-evolution of performance.

The invention provides an ancient tree area monitoring method and system and electronic equipment. The method comprises the steps that a first image and a second image of a monitoring area are acquired through acquisition equipment, the first image is acquired by the acquisition equipment at a first focal length, the second image is acquired by the acquisition equipment at a second focal length, and the first focal length is larger than the second focal length; processing the first image by using an ancient tree disease disaster model, and if a disease disaster exists in the first image, acquiring a central pixel of a disease disaster area in the first image; and according to the central pixel of the disease disaster area in the first image, acquiring the central pixel of the disease disaster area in the second image. The method can help the user to quickly locate the disease disaster part of the ancient tree, thereby helping to confirm the overall trend of the disease disaster of the ancient tree.

The invention relates to the technical field of bridge engineering, and particularly discloses a box girder web disease detection method and device, and the method comprises the steps: S1, driving an unmanned plane to scan along a preset route; s2, the unmanned aerial vehicle collects a multispectral image, thermal imaging data and point cloud in the box girder; s3, judging whether supplementary shooting is needed or not; s4, performing geometric registration on the multispectral image and the point cloud, and mapping the point cloud to a world coordinate system where the magnetic chassis is located; step S5, constructing a four-dimensional voxel library; s6, determining a candidate disease area based on a gray field of the thermal imaging data; s7, inputting the four-dimensional voxel library and the candidate disease region into the neural network model, and outputting a disease tetrad; and step S8, mapping the coordinates of the disease tetrad in a visual platform. The method can provide a high-quality decision basis for bridge operation and maintenance, and is suitable for concrete and steel box girder bridges.

The invention discloses an infrastructure apparent disease detection method, system and terminal based on an AI large model, and the method comprises the steps: carrying out the image enhancement processing of a to-be-detected image, and obtaining optimized detection data; an improved SAM disease detection model is constructed, the improved SAM disease detection model is an AI large model, the trained improved SAM disease detection model is utilized to classify pixels in a to-be-detected image to obtain a pixel classification result, and the area of a disease is calculated according to a classified disease area. And positioning the specific position of the disease according to the GPS information of the capital construction picture. According to the method, feature enhancement preprocessing is performed on the capital construction image to obtain a clearer detection sample with prominent details, and the disease is accurately detected in combination with the improved SAM network structure, so that the detection personnel can perform disease detection without approaching the dangerous area of the capital construction, the potential safety hazard is eliminated, and the detection efficiency is improved. And high-precision, rapid and automatic detection of the surface diseases of the infrastructure is realized.

The application discloses a kind of lightweight deep learning highway pavement disease real-time dynamic detection method, it is related to the technical field of pavement detection, it includes arranging multimodal sensor on inspection car, suspected disease area is obtained by fast positioning;Multi-modal sensor is allocated computing resource;The video frame time period when each suspected disease area is found is obtained, a unique ID is allocated to each suspected disease;Disease identification model is constructed, suspected disease area is screened, and target disease area is obtained;The disease geometry parameter of target disease area is identified, severity assessment is carried out, and disease risk parameter is obtained;Road surface material is obtained, combined with road surface material and disease risk parameter, maintenance treatment decision is generated;Self-learning training package is generated, and disease identification model is self-trained, and disease identification model is continuously optimized.The application has the effect of improving the accuracy, intelligence and applicability of highway pavement disease identification.

The application belongs to the technical field of small molecule fluorescent probe, and provides a kind of nonamethylenecyclooctyne dye probe and its application in disease diagnosis.A kind of nonamethylenecyclooctyne dye is prepared, and the dye can be rapidly covalently combined with serum albumin in vivo or in vitro to form fluorescent protein, which is suitable for targeted imaging of various diseases.Nonamethylenecyclooctyne dye is injected through tail vein, rapidly combined with serum albumin in vivo, and can be used for targeted imaging and diagnosis of different degrees of brain damage in mouse stroke and targeted imaging of tumor.In addition, the pre-prepared nonamethylenecyclooctyne dye and human serum albumin complex can also be injected through tail vein to achieve rapid targeted imaging of tumor.Compared with ICG, NIR-940 can rapidly covalently combine with serum albumin at 37 DEG C or even room temperature, overcoming the defect of non-covalent combination of ICG, and being suitable for high-contrast targeted imaging of disease area.

The present application relates to the technical field of computer vision and road detection, and particularly relates to a pavement disease identification method, system, device and medium based on semi-supervised learning. The method comprises: processing a pavement image through an image recognition model to obtain an identification result containing disease category and spatial position information; quantifying a disease area according to a grid of a preset size based on the identification result to obtain a quantification result; generating a structured data file based on the identification result and the quantification result; in response to a review operation on disease data in the structured data file, correcting the disease data based on a user interaction instruction to obtain corrected disease data; and iteratively training the image recognition model based on a data set containing the corrected disease data. Compared with the prior art, the present application effectively closes the loop between the manual review and correction link and the model training link, so that the model can be iteratively optimized using continuously generated correction data to realize self-evolution of performance.

The application discloses a tomato leaf disease detection method based on an SSP-DETR model, which is realized through the SSP-DETR model and comprises the following steps: acquiring a tomato leaf disease image dataset and classifying; inputting the tomato leaf disease image into a StarNet network module for feature extraction and outputting feature maps P2, P3, P4 and P5 of different dimensions; inputting the P5 into an attention feature extraction module and outputting F5; inputting the P2, P3, P4 and F5 into a multi-scale fusion module for feature fusion; inputting the fused feature map into a Decoder decoder and outputting a tomato leaf disease area prediction frame; acquiring the tomato leaf disease area prediction frame and a disease area classification in the corresponding tomato leaf disease image, and optimizing the model by using a loss function for back propagation; and inputting the tomato leaf disease image into the optimized model to obtain a disease detection result. The application can realize comprehensive detection of tomato leaf diseases, has high detection precision and good robustness.

The present application relates to the technical field of image generation, and in particular to an image generation method based on a generative model, a medium and equipment, a multi-channel conditional input tensor graph is constructed through disease type and spatial attribute information, different disease types are mapped according to different channels, non-zero pixel marks disease areas, so that the target image generation model can learn and generate disease characteristics by channel, and mutual interference of multi-disease characteristics is avoided; through a spatial self-adaptive normalization module built in the generator, spatial difference modulation parameters are predicted by using the multi-channel conditional input tensor graph, so that the model can inject disease types and spatial attribute information into feature maps at each intermediate generation stage, and disease and non-disease areas are processed in a targeted manner, the relative characteristic relationship of the disease area is retained, high-frequency texture details are strengthened, and the local characteristics of the target disease image are enriched, so that high-quality image generation can be controlled according to user-specified attributes.

The invention relates to the technical field of medical care, and particularly discloses an infection risk assessment method and system for nursing of an infectious disease department, and the method comprises the following steps: 1, collecting patient information, an inpatient area environment, medical operation and meteorological data, and constructing a multi-dimensional data set; 2, processing the data set, and extracting key feature vectors containing seasonal feature vectors; 3, inputting the key feature vector into a pre-training hybrid model to generate an infection risk level; 4, loading a corresponding nursing scene on the VR platform according to the risk level, embedding a virtual risk point, capturing and analyzing the operation of the nursing personnel, and generating a score value; 5, if the report exceeds the threshold value, triggering early warning and pushing a guidance scheme to a VR platform. According to the method, the influence of seasonal factors is considered, basic information of a patient, environment data of an inpatient area, medical operation data and meteorological information are fused, a seasonal fluctuation rule is analyzed and extracted by using a time sequence, a hybrid prediction model is constructed, and the risk of an infectious disease department is analyzed more accurately.

The invention discloses a training-free plant leaf disease segmentation method and system based on multiple visual basis models, and the method comprises the steps: extracting disease visual features of a disease region according to a disease reference image provided by a user and a corresponding disease region mask, and constructing a visual prompt memory; obtaining a to-be-segmented image, and performing disease candidate region positioning and screening on the to-be-segmented image in combination with the open vocabulary target detection model to obtain a candidate region set; and obtaining a disease segmentation result based on the visual prompt memory and the candidate region set. According to the method, a visual prompt mechanism is introduced, stable visual prior information highly related to the disease is provided for the visual basic model in the reasoning stage, the accuracy of disease area positioning and segmentation is effectively improved, and dependence on a large amount of labeled data and the model training process is avoided.