1497 results about "Image registration" patented technology

The invention relates to the field of image comparison, and discloses a multi-layer PCB alignment deviation detection system and method based on image comparison, and the method comprises the steps: obtaining high-resolution image data before and after lamination of a multi-layer PCB, carrying out the unified registration preprocessing of an original image through the combination of a multi-mode image fusion algorithm and a geometric distortion correction technology, and obtaining a multi-layer PCB alignment deviation detection result; constructing a standardized image registration input set; key alignment feature extraction is carried out on the image registration input set, and a multilayer structure graph model is constructed based on a graph neural network; in combination with the alignment reference map, dynamically adjusting an image comparison window and a search region by adopting a region attention mechanism and a local adaptive matching algorithm, and constructing an alignment deviation mapping map; constructing a deviation evolution model by using a time sequence behavior recognition network according to the constructed alignment deviation mapping graph and historical process deviation data; and performing comprehensive evaluation on the image registration input set based on the deviation evolution model and the generated early warning information. The method has the advantage of improving the accurate detection level.

The invention discloses a visible light-infrared dual-mode image registration method based on deep learning. The method comprises the following steps: acquiring a visible light image and an infrared image in the same scene; preprocessing the image; performing feature extraction on the preprocessed visible light image and the preprocessed infrared image, and performing feature enhancement on a feature extraction result by using a double attention mechanism; performing multi-scale feature fusion on the enhanced visible light image features and the enhanced infrared image features to generate cross-modal fusion features; inputting the cross-modal fusion features into a deformation field estimation network to generate an estimation result of a deformation field; and applying the estimation result of the deformation field to the infrared image to register the corresponding visible light image. According to the method, the problem of cross-modal registration between the visible light image and the infrared thermal imaging of the live pig body temperature non-contact prediction scene is effectively solved, high-precision pixel-level alignment is realized, and a technical basis is provided for non-contact pig body temperature monitoring.

The invention relates to the technical field of geological exploration and three-dimensional modeling, in particular to a mining unmanned aerial vehicle high-precision three-dimensional geological modeling system which comprises a multispectral imaging acquisition module, a point cloud-image high-precision registration module, a geological feature fusion extraction module, a three-dimensional geological model construction module and a geological attribute visualization output module. Wherein the multispectral imaging acquisition module is used for acquiring registration image data and original point cloud data; the point cloud-image high-precision registration module is used for carrying out consistency matching and outputting a registration point cloud-image data set; the geological feature fusion extraction module is used for identifying geological boundaries and outputting geological feature vector data; and the three-dimensional geologic model construction module is used for generating a three-dimensional grid model with attribute topology. According to the method, through accurate three-dimensional modeling and lithology visualization, geological features and lithology information are efficiently combined, and reliable data support is provided for rock mass stability analysis.

The invention relates to the technical field of path planning, in particular to a path planning method and system for an inspection robot, and provides the following scheme: executing an inspection task through an initial electronic map, collecting first image data and pose information, recognizing an inspection target, completing image registration, and generating second image data; inverting and calibrating the optimal observation direction based on the structural sensitivity distribution of the local visual features and the illumination variation trend, and determining the shooting position and angle to form a path node; a multi-objective optimization model is adopted, the path length, the view angle continuity and the illumination interference are comprehensively considered, and an optimal inspection path is generated; the method is suitable for outdoor inspection scenes with complex structures and non-uniform target distribution.

The invention discloses a microscopic image seamless splicing and enhanced reconstruction method based on deep learning, and the method comprises the following steps: S1, collecting a plurality of original images with overlapped regions, and recording the spatial position information and imaging parameters of the original images; s2, preprocessing the original image to generate a standardized image sequence; s3, inputting the standardized image into a structure perception feature extraction network, and extracting a feature map fusing textures and structures; s4, inputting the feature image and the original image into an image registration module; s5, inputting the registration image into the boundary attention splicing network; s6, inputting the seamless image into the residual hierarchy reconstruction network, and enhancing image details through hole convolution and multi-scale branches; s7, image quality evaluation is executed, and the structural similarity, the signal-to-noise ratio and the edge retention rate are calculated; and S8, constructing a training set and carrying out end-to-end training optimization based on a joint loss function. According to the method, a multi-module deep network is fused, and seamless splicing and high-quality enhanced reconstruction of microscopic images are realized.

The invention discloses a two-stage infrared and visible light image registration method, system and device. The method comprises the following steps of image preprocessing, contour extraction, angular point detection, feature description and matching, affine transformation estimation, multi-scale optical flow estimation, optical flow constraint and loss function, reverse resampling and fusion and error evaluation. According to the invention, rough registration is carried out by using contour angular point features, so that a preliminary alignment result can be quickly obtained; refined alignment is carried out in combination with an unsupervised optical flow network, and sub-pixel-level registration precision is achieved. The contour angular points are based on shape information of an image target, are natural and are not influenced by spectral differences, and the matching stability is enhanced through main direction and angle features. The unsupervised depth optical flow model estimates a pixel displacement field by learning consistency characteristics of an input image, and does not need to depend on annotation data. The combination can effectively eliminate the difference between infrared light and visible light, and improves the robustness and adaptability of registration.

The invention discloses a small target recognition method and system for a multi-modal fusion image in a complex environment, and belongs to the technical field of computer vision and image recognition, and the method comprises the steps: obtaining a visible light image, an infrared image and environment sensor data; image registration is carried out on visible light and infrared images, and a multi-scale image feature pyramid is constructed. And respectively extracting visible light and infrared image features to obtain visible light and infrared imaging feature data. And performing multi-modal data fusion on the visible light and infrared imaging feature data based on a cross-modal attention mechanism, and adaptively adjusting a fusion weight based on environmental sensor data to generate fusion features. And performing space-time enhancement processing on the fusion feature to obtain an enhanced fusion feature. And performing target tracking detection on the small target, and outputting position and category information of the small target. According to the method, the small target recognition capability in a severe environment is remarkably improved, and high precision and robustness can still be kept in a foggy, low-visibility and dark scene.

The invention relates to the technical field of surface defect detection, in particular to a structure surface disease diagnosis method and system based on multi-modal edge calculation, and the method comprises the following steps: obtaining an infrared thermal image frame image and constructing a temperature difference image group, enhancing visible light texture features to generate an enhanced image group, carrying out image registration, extracting a combined feature vector, and carrying out classification and recognition. And mapping the boundary of the defect area to generate a coordinate set, counting disease information and generating a visual display layer. According to the method, thermal anomaly features in different areas can be visually expressed through temperature mapping and space division operation of the infrared thermal imaging image, accurate judgment of defect types is realized through a trained neural network model, a boundary coordinate point set of structure surface defects is extracted through an image mapping means, and the accuracy of the structure surface defects is improved. And in combination with connectivity operation and a rectangular frame construction mode, defect positions are labeled and positioned, so that the accuracy of building surface disease identification, the reliability of boundary extraction and the integrity of zoning risk presentation are effectively improved.

The invention discloses an unaligned infrared and visible light image fusion method based on modal transformation and an attention mechanism, and belongs to the field of computer vision. The invention provides an image registration network model based on modal transformation for the problems of motion deformation and geometric dislocation in infrared and visible light image registration. By introducing a cross-modal style migration network, a visible light image is converted into a pseudo-infrared image, and a cross-modal registration problem is converted into a single-modal registration task, so that the influence of modal difference on registration precision is reduced. And then, a multi-scale refined registration strategy is adopted, a deformation field is gradually optimized through multi-level feature extraction and a deformation field estimation network, and the registration precision and robustness are improved. The invention further provides a lightweight image fusion network based on multi-scale feature representation and attention guidance, and the network extracts image deep features through different scales and comprehensively captures global and local information.

The invention discloses a lingual surface diagnostic information acquisition, diagnosis and analysis method and system, and belongs to the technical field of medical auxiliary diagnos.The method comprises the steps that an acquired lingual surface image is matched with patient information, a symptom associated lingual surface area is determined, the associated lingual surface area is subjected to priority division, and whether the acquired image meets a clear standard or not is judged; the method comprises the steps of constructing an image index evaluation model based on tongue vibration and image texture, performing tongue vibration, texture stability and water vapor fuzzy interference evaluation on an image needing to be processed, constructing a stable frame evaluation model, and importing vibration intensity, texture stability and a water vapor proportion into the stable frame evaluation model to evaluate image area stability. Image registration is carried out on the stable frame set, multi-frame registration and fusion are carried out based on an image stable region, region stability and processing information are recorded, a high-quality image for tongue picture analysis is generated, the image definition of a key diagnosis region is improved, and the accuracy and stability of tongue picture analysis are improved.

The invention discloses a weight-sharing double-flow attention registration method and system based on large kernel convolution LKA, and particularly relates to the technical field of medical image registration, an input brain fixed image and a moving image enter a double-flow structure of DELCA-Net, the DELCA-Net combines the advantages of a convolutional neural network CNN and Transformer, and the weight-sharing double-flow attention registration method and system based on the large kernel convolution LKA are obtained. Semantic information of an image is deeply mined through a self-attention mechanism, more general and rich feature representation can be learned by means of a weight-sharing encoder design and a network, on the basis, accurate feature matching of common features is realized by using a cross self-attention mechanism and DELCA-Net, and the accuracy of registration is remarkably improved; in order to reduce the calculation complexity, the DELCA-Net decomposes a large convolution kernel into a deep convolution module and a deep cavity convolution module which are cascaded. In addition, through a multi-scale attention optimization mechanism, the DELCA-Net effectively fuses spatial correspondence and anatomical semantic association under different scales.

The invention relates to an infectious bacterium detection method and system based on double effects of a reflection spectrum and autofluorescence, and belongs to the field of biomedical detection. The method comprises the following steps: acquiring hyperspectral images of different samples under different light sources; performing data preprocessing on the collected sample hyperspectral image, realizing pixel-level alignment of the dual-effect image based on feature matching and image registration, and constructing a data set; the method comprises the following steps: constructing a wound infection bacterium detection model based on double effects of a reflection spectrum and autofluorescence, and comprising a double-branch feature extraction module which comprises a reflection branch and a fluorescence branch which are respectively used for extracting reflection hyperspectral image features and fluorescence hyperspectral image features; the redundant feature screening module screens the features extracted by the reflection branch and the fluorescence branch through a channel attention mechanism; and the feature fusion module adopts a cross-branch cross attention mechanism to fuse the features of the double branches. According to the method, learning is carried out from two physicochemical characteristics, and the effectiveness and adaptability of the technology are improved.

The invention provides a data registration method and device for a space transcriptome and a space metabolome, electronic equipment and a storage medium. The method comprises the steps of obtaining a space transcriptome image and a space metabolome image to be registered; performing image registration on the space transcriptome image and the space metabolome image through an image registration model to obtain an optimal registration parameter; and performing space coordinate registration on the data points of the space transcriptome image and the space metabolome image after image registration by using the optimal registration parameter. According to the method, the tedious process of manual registration can be eliminated, and the unification of the space coordinates of the two groups of data points can be quickly and accurately completed. In addition, the data registration method provided by the invention is low in cost and extremely short in time consumption, does not depend on any closed source business software, reduces the use cost, provides space and freedom for subsequent algorithm upgrading and iteration, and can flexibly adapt to continuously changing research requirements.

The invention discloses a medical image registration method based on large model robust features, and the method comprises the following steps: constructing a large model registration network which comprises a structure perception feature encoder module and a pyramid deformation field prediction module; acquiring a medical input image, and performing feature extraction on the medical input image through a structure perception feature encoder module to obtain image extraction features; performing deformation and registration on image extraction features based on a pyramid deformation field prediction module to obtain a medical registration image; and training based on the complete loss function pair to optimize the registration model. According to the method, the registration network SAMIR is utilized, universal visual features across anatomical regions can be effectively extracted, the registration accuracy is improved, the anatomical rationality of a deformation field is improved, the migration potential of a natural image pre-training model to a medical registration task is proved in the absence of medical priori knowledge, a feature-level loss function is proposed, and the medical registration efficiency is improved. And the registration consistency is further enhanced.

The invention discloses an unmanned aerial vehicle inspection image registration and alignment method based on deep learning, and belongs to the technical field of image processing. Comprising the steps of video acquisition and segmentation processing, semantic-space-time alignment and synchronization subsequence selection, content enhancement and alignment frame pair extraction, multi-source key point extraction and fusion, cross-video high-quality feature matching and geometric transformation estimation and registration, and solves the technical problem of high-precision frame alignment and matching in cross-view and asynchronous image sequences. The invention provides a semantic-spatio-temporal combined image sequence alignment method, which realizes high-robustness alignment of cross-sequence image frames, and enables matching to be more inclined to frame pairs in time proximity, thereby effectively inhibiting semantic interference of cross-time drift, enhancing physical rationality of a matching path, and improving matching accuracy. The robust alignment capability under asymmetric sampling, speed change and visual angle deviation in the real flight process is remarkably improved.

The invention discloses an automatic identification method and system for power transmission and transformation equipment based on visible light and infrared dual-light fusion. The method comprises the following steps that a visible light image and an infrared image of the same scene are synchronously collected through a dual-light camera carried by an unmanned aerial vehicle; preprocessing the visible light image and the infrared image, including denoising, geometric correction and spatial alignment, in the spatial alignment, feature points are extracted through an SURF algorithm, and image registration is optimized through an RANSAC algorithm; and feature extraction is carried out on the fused image by using a deep convolutional neural network OfficientNet-Lite, and a multi-scale feature map is generated. The method has the beneficial effects that high-precision identification is realized; a dynamic fusion strategy and an attention mechanism enable the insulator crack (gt; 0.1 mm), the detection rate reaches 92%; the anti-interference capability is high, the false alarm rate is reduced from 15% to 4% through a dust compensation algorithm, and the influence of emissivity errors is reduced through material self-adaptive calibration; the whole process from data acquisition to report generation is free of human intervention, and the labor cost is reduced by 70%.

The invention discloses a swallowing function evaluation method and system based on tongue motion nuclear magnetic image registration, and belongs to the technical field of medical image processing. The system comprises a time sequence nuclear magnetic image reading module, a tongue body dynamic mask generation module, a tongue body dynamic image extraction module, a dynamic tongue body sequence registration module and a patient swallowing recovery evaluation module. Through an automatic segmentation and image registration technology, the system can accurately extract tongue motion displacement and calculate a local displacement vector, and evaluate the swallowing function recovery condition of a tongue cancer postoperative patient. The method comprises the steps of image reading, image screening, data set making, model training and tongue swallowing recovery evaluation, and the system can identify a tongue motion abnormal mode and provide an objective and quantitative evaluation result. According to the method, the accuracy and efficiency of tongue motion feature analysis are remarkably improved, and the method has a wide clinical application prospect.

The invention belongs to the technical field of injection mold detection, and discloses an injection mold surface defect detection method based on visual inspection, and the method comprises the following steps: S1, adaptively adjusting collection parameters according to mold process parameters, and ensuring clear collection of different process surface defect features; s2, a deformation matrix is output through the mold thermal deformation finite element model, image registration is guided in combination with a deformation field, and the defect position deviation of the thermal-state mold is corrected; the method comprises the following steps: constructing a vibration-fuzzy kernel mapping model based on vibration sensor data, and restoring a fuzzy image by using an improved Richardson-Lucy algorithm; s3, a process exclusive texture primitive library is constructed, and unified threshold positioning deviation is avoided; s4, converting process parameters into feature extraction weights through a process perception attention CNN model, and accurately capturing defect core features under different processes; according to the design, the detection method can adapt to the surface of a multi-process mold without replacing a model, and the debugging cost of cross-process detection is greatly reduced.

The invention relates to the field of navigation signal processing, and discloses a radiation therapy bolus dose feedback and tracking system based on image registration, the system comprises an image acquisition module, an image registration module, a bolus identification module, a dose recalculation module, a dose deviation analysis module and a feedback and adjustment module, space registration is carried out through an FBCT image acquired every day and an original plan CT, and the radiation therapy bolus dose feedback and tracking system based on image registration is obtained. The fitting state between the bolus and the skin is automatically identified, the position of an air gap is detected, and dose recalculation is carried out based on an actual structure. Through comparison with an original planned dose, the system can output a deviation index of a key dose parameter and provide visual feedback, if the deviation exceeds a set threshold value, a prompt is automatically sent out, and a radiotherapy technician and a physician are supported to carry out bolus adjustment or call an adaptive planning engine to reconstruct a treatment plan. Quantitative analysis of bolus fitting quality and closed-loop control of dose delivery consistency are realized, radiotherapy precision and safety are effectively improved, and the method is suitable for superficial radiotherapy scenes containing bolus design.

The present invention belongs to the field of steel structure building construction detection. Disclosed are a prefabricated steel structure welding data transmission system based on digital twin, and a method. The prefabricated steel structure welding data real-time transmission system based on digital twin comprises an unmanned aerial vehicle, which is used for flying to a high point of a prefabricated steel structure, wherein an RFID tag positioning identifier is provided at the top of the unmanned aerial vehicle, and is used for identifying RFID tags attached to edges of welding positions. By using an image registration and superposition module, an image, which is processed in real time, is matched and superposed with ultrasonic feedback array points having array point coordinate information; and by means of a result generation module, defective parts are marked on a matched and superposed image which has array point coordinate information, and continuous welding seam length data, height difference data between adjacent array points and a lack-of-welding length value are attached, such that a welding seam quality inspection error is avoided, and the defect situation of each welding point can be effectively uploaded to a computer for checking, thereby avoiding the quality problem of a steel structure building that is caused by an error of a welder.

The invention discloses an unmanned aerial vehicle infrared thermal imaging method and device for cold leakage detection of a low-temperature storage tank, and relates to the field of automatic inspection and detection of storage tanks, and the method comprises the steps: determining the inspection range and detection distance of an unmanned aerial vehicle based on geometric parameters, a cold leakage frequency region and environment parameters of a site; calculating the distance between the shooting points and the vertical coverage height of single-circle flight, further dividing flight elevation layering, and calculating the number of the shooting points of each circle of flight; establishing a three-dimensional model; collecting a visible light image and an infrared thermal imaging image of each shooting point; the method comprises the following steps: performing multi-dimensional correction and temperature image conversion on an acquired infrared thermal imaging image, performing image registration on a temperature image with a temperature scale and a visible light image, performing cold leakage area identification to obtain a cold leakage area, performing quantitative calculation to obtain three-dimensional positioning of a cold leakage position and a cold leakage area, and performing cold leakage area identification on the cold leakage area. And generating a visual detection result, a detection report and a maintenance suggestion. According to the invention, automatic detection and accurate analysis of the cold leakage area of the low-temperature storage tank can be realized.

The invention discloses an ultra-thin glass defect detection system and positioning method based on line scanning and phase deflection, and the system comprises a line scanning camera module, a distortionless phase deflection detection module, a high-magnification microscope module and a central processing unit. The line scanning camera module is used for collecting a 2D grayscale image of the ultrathin glass; the distortionless phase deflection technology detection module is used for collecting a surface height map of the ultra-thin glass; the high-magnification microscope module is used for carrying out depth positioning on the interlayer defect judged by the central processing unit; the central processing unit is used for receiving the 2D gray level image and the surface height map, executing an image registration and defect classification algorithm and sending a depth positioning control instruction to the high-magnification microscope module, a multi-module cooperative work detection system is constructed, the detection efficiency and the detection precision are both considered, and data support is provided for production process improvement.

A cross-modal cross-dimension prostate nuclear magnetic ultrasound image registration method belongs to the technical field of medical image processing and artificial intelligence auxiliary diagnosis and treatment, and comprises the following steps: firstly, equivalently reconstructing a registration task into two sub-tasks; providing a cross-modal double-branch attention mechanism to realize semantic alignment according to modal differences; and aiming at the dimension difference, designing a lightweight rigid positioning network to carry out affine slice transformation. According to the method, through equivalent problem reconstruction, the modeling difficulty and the calculation complexity are remarkably reduced; a dual-module structure combining elastic and rigid registration is designed, and the registration precision and clinical adaptability are comprehensively improved; a cross-modal double-branch attention mechanism is introduced, and the overall transformation effect is optimized while the precision of the local anatomical structure is kept; a three-stage combined training strategy is adopted, the three-stage combined training strategy comprises contrast learning pre-training, module-level training and whole-network fine tuning, optimization is carried out in combination with weak supervision signals (segmentation labels), a high-quality registration result can be obtained under the condition of no registration labels or a small number of labels, and data dependence and training cost are reduced.

The invention provides an optical and acoustic image registration method for underwater structure crack detection, and the method comprises the steps: collecting a multi-mode image through the vision field and time synchronization, building a one-to-one correspondence relation according to the pose and time metadata, and improving the image quality through the denoising, distortion correction and other means; optical and acoustic multi-scale features are respectively extracted through a dual-channel network, and cross-modal semantic alignment is realized in combination with a shared weight and a channel attention mechanism; generating a high-resolution scale offset field by using local cross-correlation and micro-upsampling, and introducing manifold regularization constraint to ensure that a vector field is smooth and continuous; according to the method, the local scale field and the affine parameters are combined, non-rigid space mapping is achieved through thin-plate spline interpolation, feedback iterative optimization based on edge structure consistency is assisted, the registration precision of a key structure is enhanced, the automatic registration effect of the underwater multi-modal image is improved, and the method has high robustness and practical application value.

The invention discloses a multi-modal iconography evaluation method suitable for atrial fibrillation cardiac stroke. The method comprises the following steps: acquiring and preprocessing heart and brain multi-modal image data; carrying out multi-modal image registration on the preprocessed data; feature extraction and fusion are carried out on the registered heart and brain multi-mode image data; performing cross-modal feature alignment and fusion on the heart and brain image data; constructing a heart and cerebral vessel integrated evaluation interaction model based on a graph neural network; predicting the risk of the end-to-end cardiac stroke; according to the multi-modal iconography evaluation method, multi-modal heart image data and multi-modal brain image data are combined, a heart and cerebral vessel integrated evaluation framework is established, image features and clinical data are fused through an artificial intelligence method, and end-to-end stroke risk prediction and evaluation are achieved. According to the method, artificial intelligence and medical technologies are comprehensively utilized, and the accurate cardiac stroke assessment method is provided.

The invention discloses a wafer defect detection method and a computer program product, and relates to the technical field of semiconductor defect detection. The wafer defect detection method comprises the following steps: acquiring single-mode images acquired from a target wafer under a dark field condition and a bright field condition respectively, and then determining the image features of each single-mode image through a feature extraction model, so that the defect of the target wafer can be detected through image registration and image fusion on the basis of the image features of all the single-mode images. And a multi-modal image is obtained. The multi-modal image deeply fuses the image information of the single-modal image in the bright field and the dark field, so that the multi-modal image retains the macroscopic structure characteristics in the bright field and the microscopic scattering characteristics in the dark field, and the defect detection result is obtained by performing defect detection based on the multi-modal image. The omission ratio and the false detection rate of wafer defect detection are reduced, and the accuracy of wafer defect detection is improved.

The invention belongs to the field of cultural heritage digital protection, and discloses an ancient building three-dimensional modeling method based on three-dimensional laser scanning, which comprises the steps of extracting feature points of a point cloud data set and texture image data, and performing registration in combination with a flight log of an unmanned aerial vehicle; performing image restoration and feature extraction on the texture image data and the point cloud-image registration result through a convolutional neural network-probability Markov random field (CNN-PMRF) model; performing geometric feature extraction on the point cloud data set, fusing the texture image feature vector to obtain a geometric-texture joint feature vector, and optimizing a rough mesh model generated based on the point cloud data set; mapping the repaired texture image data to the optimized grid model to obtain a preliminary three-dimensional grid model; and processing the preliminary model parameters through a gradient boosting decision tree (GBDT) model to obtain a correction value, and adjusting the preliminary three-dimensional grid model based on the correction value to obtain an optimal three-dimensional model. The precision of three-dimensional modeling of the ancient building can be improved.

The invention discloses a registration method and system for an optical image and an SAR image of the moon, and relates to the technical field of image registration, and the method comprises the steps: firstly determining the same typical moon appearance object in an image to be registered, and enabling the corresponding optical and SAR region images to form a region image pair; performing feature extraction and matching on each regional image pair by using a feature-based registration algorithm to obtain a preliminary matching point pair, and screening out a high-confidence matching point pair; and calculating a region affine transformation matrix of each region image pair based on the high-confidence matching point pairs, constructing a global optimization objective function according to all region affine transformation matrixes, solving an optimal affine transformation matrix, and finally realizing accurate registration of the to-be-registered image.

The invention belongs to the technical field of medical image detection, and particularly relates to an esophageal flora image intelligent detection method for risk prediction of gastroesophageal reflux disease, which comprises the following steps: acquiring flora images and clinical data, and constructing a perception network; quantifying flora displacement characteristics by using image registration; the method comprises the following steps of: extracting flora density, aggregation degree and fluorescence gradient characteristics by combining improved U-Net + + segmentation, fusing flora and epithelial cell lesion characteristics through space-time attention, generating a flora-host association map, constructing a flora dynamic evolution model by utilizing a space-time map convolutional network, predicting Barrett esophageal occurrence probability and flora diffusion trend, and predicting the occurrence probability of the Barrett esophagus. Calculating a lesion risk level through a flora imbalance quantification algorithm; in combination with reflux frequency and pH fluctuation, a flora-environment interaction model is used for simulating a field planting coefficient and correcting parameters, the parameters are transmitted to a diagnosis platform to deduce canceration risks, grading suggestions are triggered, and a visual report is generated. Therefore, the problems of long detection period, weak microscopic analysis capability and the like in the prior art are solved.

The invention relates to the field of new energy, and discloses a photovoltaic system efficiency evaluation method and system based on unmanned aerial vehicle multi-source image fusion, and the method comprises the steps: collecting a visible light orthoimage, thermal imaging data and environment parameters of a photovoltaic system, and obtaining a registration result through employing an improved feature point matching algorithm; based on a registration result, combining spatial features of a visible light image and temperature features of thermal imaging, realizing accurate segmentation of the photovoltaic panel through a deep learning model, and identifying the type, the arrangement mode and the installation angle of the photovoltaic panel at the same time; establishing a mathematical model of the relation between the photovoltaic panel temperature distribution and the power generation efficiency, distinguishing the normal working temperature difference and the fault hot spot, and analyzing and determining the efficiency attenuation degree and the fault type of the photovoltaic system through a heat distribution mode. The method is accurate in image registration, good in data fusion effect, accurate in temperature anomaly detection and comprehensive in efficiency evaluation, and provides more efficient and accurate technical support for management and maintenance of the distributed photovoltaic system.