254 results about "Cloud detection" patented technology

The invention discloses a weld defect 3D point cloud detection method, and relates to the technical field of defect detection, and the method comprises the following steps: S1, point cloud data acquisition and preprocessing; s2, point cloud data enhancement and feature extraction; s3, weld defect detection and identification; and S4, explaining a detection result. According to the 3D point cloud detection method for the weld defect, the point cloud data is enhanced by means of point cloud completion and density increase, so that incomplete structural information and semantic information of a target due to few obtained target point clouds are avoided, the influence of point cloud sparsity on a detection result is effectively relieved, and the detection accuracy is improved. Therefore, false detection or missing detection of weld defects is effectively reduced, meanwhile, detection results are labeled and explained in various modes of colors, shapes and labels, various presentation modes of generating a three-dimensional model, labeling defect positions and providing detection reports are provided, and the detection results can be presented to users in an easy-to-understand mode.

The invention provides an urban green land coverage rate dynamic monitoring method and device. The method comprises the following steps: acquiring multispectral satellite remote sensing data, and preprocessing the multispectral satellite remote sensing data; carrying out cloud detection and shadow detection on the preprocessed remote sensing image, and calculating an effective pixel proportion index, a spectrum quality index, a time phase matching degree index and a spatial integrity index; based on the four indexes and the corresponding weights, constructing a fuzzy comprehensive evaluation matrix, and selecting an optimal data combination; calculating a normalized difference vegetation index (NDVI) based on the near infrared band and the red light band in the optimal data combination, and performing illumination angle correction and time sequence smoothing processing on the NDVI to obtain an optimized NDVI; performing green space identification on the optimized NDVI by adopting a first deep learning model, and outputting a green space distribution map; and calculating a green land area change rate, an NDVI difference value and connectivity index change based on the green land distribution map. According to the invention, high-precision dynamic monitoring of the green land coverage rate is realized, and the monitoring efficiency and accuracy are improved.

The invention discloses a quality-graded remote sensing image composite cloud removal method, system and device. The method comprises the following steps: preprocessing an acquired remote sensing image; based on the preprocessed data, thin cloud radiation correction is carried out; based on the data after thin cloud radiation correction, thick cloud detection is carried out; based on the data after thick cloud detection, thick cloud missing reconstruction is carried out; performing atmospheric correction based on the data after the thick cloud missing reconstruction; and performing data quality grading based on the data after atmospheric correction. According to the method, a series of standardized processing is realized on data acquired under different space and time conditions, the influence of atmospheric radiation attenuation is eliminated, and the data are formatted into surface reflection data with consistent observation characteristics, so that the utilization rate of remote sensing images is improved, and effective comparison and analysis of subsequent application research are promoted.

The invention relates to the technical field of remote sensing image processing, and discloses a remote sensing image adaptive identification method and system for territorial space planning, and the method comprises the steps: obtaining a multi-source remote sensing image data set of a research region, feature extraction, cloud detection, quality evaluation and adaptive preprocessing are carried out; carrying out prototype network coding, calculating a category prototype and probability, and supporting fine tuning of a set; carrying out multi-scale cavity convolution and category scale attention fusion; evaluating the adaptability score of the comprehensive fusion feature map set, and carrying out weighted fusion, classification and normalization; change detection is carried out, stable and change regions are segmented, and time sequence context features are extracted and constrained optimization is carried out; entropy is fused, a boundary is decided, uncertainty is estimated, and weighted fusion is carried out according to a change area; conditional random field optimization, confidence level grading and connected domain identification are carried out; the automation level, the adaptive capacity and the recognition reliability of remote sensing monitoring of territorial space planning are improved.

The invention provides a three-dimensional laser point cloud detection method and system for a tunnel water-endowed area lining wide and thick belt, and the method comprises the steps: detecting the tunnel water-endowed area lining wide and thick belt through a rolling ball method, scanning the tunnel point cloud through three-dimensional laser, and collecting the laser point cloud data of the tunnel water-endowed area lining wide and thick belt; establishing a high-fidelity tunnel twinborn model; simulating tunnel deformation conditions through finite elements, constructing a finite element simulation tunnel deformation analysis model, and outputting a tunnel deformation true value of the tunnel twinning model; building a tunnel simulation scanning virtual simulation platform according to the tunnel twinborn model and the laser scanning characteristic data; performing simulated three-dimensional laser scanning on the tunnel twin model in a virtual environment to obtain large sample detection data; training a deformation detection neural network model in an auxiliary manner according to the large sample detection data; performing tunnel point cloud registration through a neural network model; a tunnel section point cloud is obtained by fitting the central axis of the tunnel, and tunnel deformation analysis is carried out; and the tunnel deformation analysis processing accuracy is obviously improved.

The invention discloses a method and system for assimilating meteorological satellite hyperspectral error non-Gaussian distribution data based on quantum computing, and the method carries out the generalized quality control of meteorological satellite hyperspectral data in consideration of an outlier value on the observation brightness temperature and equivalent data of a satellite hyperspectral infrared detector channel. Comprising the steps of channel optimal selection considering quantum information entropy, deviation correction based on artificial intelligence generalized integration generation type deep learning and cloud detection based on a minimum residual method to remove cloud view field point data, so that quality control data is obtained. And performing quantum space solution on the quantum non-Gaussian increment four-dimensional variational assimilation model compatible with error Gaussian distribution and non-Gaussian distribution based on quality control data to obtain analysis field data, and solving the problem that the brightness temperature assimilation of the hyperspectral infrared channel with error non-Gaussian distribution (or obvious non-Gaussian characteristics) is limited in the prior art. Meanwhile, the method is high in solving speed, and the obtained analysis field data has good precision and calculation timeliness.

The invention discloses a multi-mode sensing fusion intelligent water meter anomaly detection system, and relates to the technical field of industrial production water monitoring, and the system comprises an equipment composition obtaining module which interactively obtains a target production line composition. The production log acquisition module acquires an associated index set. The sensing equipment laying module is used for laying multi-mode sensing equipment for production equipment. The water consumption associated data set acquisition module acquires data to obtain a data set. The water consumption prediction edge node construction module constructs nodes of a local server. The cloud detection module pre-constructs a water meter anomaly detection cloud. The communication connection module connects the cloud and the node. And the dynamic detection module performs water meter abnormity dynamic detection. The technical problems that an existing water meter monitoring technology only depends on water meter reading, water meter abnormity cannot be accurately detected in real time, and water management efficiency and precision are affected are solved, and the technical effects that stable supply and accurate metering of water are guaranteed, and the production interruption risk and water resource waste are reduced are achieved.

The invention discloses a remote sensing cloud layer repairing method based on time-spectral domain fusion and time sequence self-attention enhancement, and relates to the technical field of remote sensing cloud layer image processing. The method comprises the steps of receiving a remote sensing missing image as a source image; the method comprises the following steps: constructing a generator, inputting a remote sensing missing image into the generator for preliminary processing, the generator comprising a feature extractor, a ConformerPlus module and a cloud detection module, and a new multi-head self-attention mechanism being embedded in the ConformerPlus module. According to the method, time-frequency spectrum domain information extraction and fusion can be carried out on data, so that the feature expression ability is enhanced, the edge information capturing ability of the model is improved, the model is guided to realize progressive cloud layer removal from outside to inside, the detail expression can be improved, noise interference can be suppressed, and the method is suitable for large-scale popularization and application. And the detail definition and the texture fidelity of the image are effectively improved.

The invention discloses a ground engineering construction quality supervision digital delivery system, which relates to the technical field of engineering supervision, and comprises the steps of generation and multi-source data checking, activity record structuring and anti-verification before hiding, space-time reference unification and point cloud fusion playback, rule checking and differential rectification, and object-level marshalling delivery and asset authority management. According to the method, a unified data pool, activities, events and evidence chains are constructed through object codes to achieve time-space consistent association, image, point cloud and detection consistency check is conducted before hiding, blocking difference and unified reference fusion point cloud are generated, indexes support three-dimensional playback, rule base batch check is conducted, and issuing rectification is conducted. And the object-level delivery list and fingerprints support cross-platform identification and auditing to form a traceable link.

The invention relates to the technical field of meteorological cloud detection, and discloses a satellite-borne hyperspectral cloud layer identification method based on a dual-band fusion technology, and the method comprises the steps: firstly obtaining a hyperspectral image, carrying out the preprocessing of the hyperspectral image, and obtaining a spectrum calibration image; respectively calculating the visible light wave band transmittance and the near-infrared wave band transmittance of each pixel in the spectrum calibration image; identifying a semitransparent weather phenomenon area and a non-semitransparent weather phenomenon area according to the visible light wave band transmittance and the near-infrared wave band transmittance of each pixel; and finally, constructing a real cloud layer spectral feature model, performing real cloud layer identification on the non-translucent weather phenomenon area by using the model, and fusing the identified real cloud layer area and the translucent weather phenomenon area to generate a final cloud detection result graph. According to the method, spectral information of visible light and near-infrared wavebands is fused, a real cloud layer spectral feature model is constructed for cloud detection, and the cloud detection precision under complex atmospheric conditions is improved.

The invention provides an intraday high-frequency automatic monitoring method and system for lake cyanobacterial bloom based on a GOCI-II satellite, and aims to solve the problems that an existing method is susceptible to interference of thin cloud, low in recognition precision, high in false positive rate, low in efficiency and the like, and the processing flow depends on manpower. The system is based on an improved AFAI index, fine cloud detection, cloud expansion processing and classification correction strategies are combined, misrecognition caused by thin clouds and shadows is effectively restrained, and the extraction accuracy and robustness are improved. The system has the whole-process unattended processing capacity from GOCI-II data automatic downloading, preprocessing, algal bloom recognition, thematic map making to report output, can generate a monitoring report within one hour after satellite imaging, and supports intra-day multi-temporal cyanobacterial bloom dynamic monitoring. The method has been successfully applied to lakes such as Taihu Lake, lakes, Chaohu Lake and Hongze Lake, is particularly suitable for monitoring and early warning cyanobacterial bloom in large and medium lakes, and has wide application prospects in the fields of water environment supervision, water quality risk control, ecological assessment and the like.

The present application relates to a power distribution Internet of Things terminal debugging and testing system. The system comprises a cloud test service center (100), a power distribution Internet of Things terminal debugging device (200) and an intelligent gateway (300); the intelligent gateway (300) is used for acquiring terminal information of power distribution Internet of Things terminals and uploading the terminal information to the cloud test service center (100); the cloud test service center (100) is used for issuing a test command to the power distribution Internet of Things terminal debugging device (200) on the basis of the terminal information; the power distribution Internet of Things terminal debugging device (200) is used for carrying out signal conversion on the test command, determining an analog signal corresponding to the test command, and applying the analog signal to the power distribution Internet of Things terminals; the intelligent gateway (300) is used for acquiring digital signals and transmitting the digital signals to the cloud test service center (100), wherein the digital signals are obtained by converting the analog signal by the power distribution Internet of Things terminals; the cloud test service center (100) is used for determining test results of the power distribution Internet of Things terminals on the basis of the digital signals. Fully-automatic closed-loop debugging can be implemented, and the power distribution efficiency is greatly improved.

The invention provides a cloud condition adaptive geostationary satellite sea surface temperature inversion method based on deep learning, and relates to the technical field of sea surface temperature inversion, and the method specifically comprises the steps: obtaining geostationary satellite observation data, geographic information data, polar orbit satellite sea surface temperature and cloud products, and analyzing the sea surface temperature and atmospheric background data; performing standardization preprocessing on the obtained stationary satellite observation data; constructing a cloud detection data set; a cloud detection model of deep learning is constructed and trained; constructing a clear sky data set; a clear sky inversion model of deep learning is constructed and trained; constructing a data set for under-cloud inversion model training; constructing an under-cloud inversion model of deep learning and training the under-cloud inversion model; and integrating the cloud detection model, the clear sky inversion model and the under-cloud inversion model, adaptively calling the corresponding model according to a real-time cloud detection result, and generating a final sea surface temperature product. According to the technical scheme, the problem that in the prior art, the accuracy of a reconstructed product on the spatial structure cannot be comprehensively reflected is solved.

The invention discloses an attention pyramid network-based all-sky cloud picture detection and classification method, and aims to solve the problems of accuracy and efficiency of an existing cloud detection technology in processing multi-cloud layer coverage, cloud type diversity and dynamic cloud layer change. According to the method, a deep learning technology and an advanced attention mechanism are utilized, and a pyramid space pooling (PSP) module and a convolutional block attention module (CBAM) are combined, so that the recognition and classification capability of cloud features is effectively improved. By applying the method, various cloud types including but not limited to cirrus cloud, layer cloud, cumulus cloud and the like can be accurately identified and classified in the all-sky cloud picture, and more accurate data support is provided for meteorological monitoring and climate research. The method has the advantages of being high in precision, high in efficiency, high in adaptability and the like, cloud detection and classification performance can be remarkably improved, and the method is particularly suitable for meteorological analysis under complex weather conditions.

The invention discloses a greenbelt cooling effect evaluation method and system based on a remote sensing image and a streetscape image, and the method comprises the steps: obtaining the data of the streetscape image, carrying out the denoising and cutting, recognizing, extracting and calculating the pixel coverage rate of arbors, grass trees and shrubs, and constructing the greening feature indexes of the streetscape image; acquiring an urban satellite remote sensing image, performing radiometric calibration, correction and identification, and constructing a greening characteristic index of the remote sensing image; acquiring a multispectral remote sensing image of the city, performing cloud detection, and obtaining the surface temperature of the city through surface temperature inversion; and constructing a random forest model and performing iterative training based on greening characteristic indexes of the surface temperature, the streetscape image and the remote sensing image of the city, and evaluating the cooling effect by using the fitted random forest model. The method gives full play to the advantages of wide coverage range of the remote sensing image and rich details of the street scene image, makes up for the limitation of a single data source, and achieves the comprehensive and accurate evaluation of the cooling effect of the green land.

The invention discloses a multi-source data assimilation method based on remote sensing in the technical field of remote sensing data, and the method comprises the following steps: S100: data preprocessing: carrying out the preprocessing of multi-source remote sensing data, including radiation correction, geometric correction and cloud detection, so as to eliminate the noise and error in the data; and S200, feature extraction: extracting useful feature information from the preprocessed data, including spectral features and texture features, so as to facilitate subsequent data analysis and application. And the prediction capability is improved: the model prediction capability can be improved through data assimilation, so that a model result is continuously close to an observation value, and the prediction accuracy is improved. The observation data of different sources and resolutions are fused through data assimilation, information more accurate and richer than single data can be obtained, fuzziness is reduced, and interpretation reliability is improved.

The invention provides a spectrum self-attention and cloud mask guided remote sensing image cross-modal cloud detection method. According to the method, the spectral self-attention sub-network in the remote sensing image cross-modal cloud detection network is constructed, and the dependency relationship between different spectral bands of the remote sensing image is effectively mined and utilized, so that the recognition accuracy of cloud region features is improved. According to the method, cross-modal migration from the source domain image to the target domain image is realized by using the migration sub-network of the unsupervised image domain in the remote sensing image cross-modal cloud detection network, and the multi-spectral image with the target domain features is generated, so that the defect of the source domain image in spectral information is overcome, the false detection and omission ratio is effectively reduced, and the detection efficiency is improved. And the robustness of cloud detection of the model in a complex scene is enhanced.

The invention discloses a method and system for processing a circular weld joint based on point cloud data, and belongs to the technical field of machine identification of weld joints, and the method comprises the following steps: collecting the point cloud data of the surface of a workpiece through a visual sensor; preprocessing the collected point cloud data; calculating a normal vector of each point in the point cloud data; segmenting the workpiece surface point cloud and the reflective interference points based on a normal vector, and filtering the interference points deviating from a preset range in the normal direction to obtain a target point cloud and a reference point cloud; projecting the target point cloud to a reference plane obtained by fitting the reference point cloud, generating a target projection point cloud, detecting boundary points of the target projection point cloud, screening candidate weld joints based on distance distribution from the boundary points to the center of mass, and extracting weld information. According to the method, the workpiece made of the material with high light reflection is treated, the finally obtained result can still keep good precision, and the quality of the workpiece is improved.

The invention discloses a thick cloud-thin cloud integrated detection method and system based on spectral features and a multi-scale depth model, and belongs to the technical field of remote sensing image processing, and the method comprises the steps: 1, training a plurality of scene-level models of different scales based on a cloud detection data set, generating a plurality of scene-level cloud probability graphs and scene-level binary cloud masks of different scales; step 2, based on a plurality of scene-level cloud probability graphs of different scales and dark pixel features of the image, pixel-level cloud probability graphs facing thick cloud and thin cloud are generated respectively; and step 3, combining the scene-level binary cloud mask, fusing the pixel-level cloud probability graphs facing the thick cloud and the thin cloud by adopting dark pixel gradient, and then combining an adaptive threshold and distance weighting to generate a pixel-level binary cloud mask so as to realize thick cloud-thin cloud integrated detection. According to the method, manual segmentation threshold setting is avoided, and fusion of the thick cloud probability graph and the thin cloud probability graph and full-automatic accurate detection of the thick cloud, the thin cloud and the cloud edge are realized.

The invention discloses a channel dynamic cloud detection method and system based on a meteorological satellite hyperspectral infrared detector, and the method firstly proposes nonlinear channel optimal selection based on Gaussian mixture model probability approximation quantization relative entropy, and can reduce the error distribution of temperature and humidity. Secondly, based on layer-by-layer cloud simulation and clear sky brightness temperature simulation, a cloud profile inversion method of a weighted L1 norm constraint inverse problem of Gaussian disturbance + numerical approximation signal degree-of-freedom optimization channel weight is provided, cloud amount information of multiple layers from bottom to top is obtained, and the actual condition of actual cloud vertical distribution is met. And finally, a cloud detection result is obtained by customizing each channel of each field point by adopting an adaptive dynamic cloud detection method, which is beneficial for reasonably using the brightness temperature data of the hyperspectral infrared channel and realizing the application of partial cloud region data, so that the data quantity of the brightness temperature of the variational assimilation channel is increased, and the precision of numerical weather forecast is further improved.

The invention discloses a method for polar region all-day cloud detection by using FY-3D infrared channel brightness temperature, and relates to the technical field of cloud detection, and the method comprises the following steps: obtaining CALIOP data and FY-3D / MERS-II data, specifically CALIOP cloud layer product data and MERS-II observation data and positioning data, carrying out the preprocessing, and carrying out the preprocessing to obtain an FY-3D infrared channel brightness temperature; according to the method, space-time matching is carried out according to transit trajectories of CALIOP and FY-3D satellite MERS-II sensors, matched infrared channel radiance information is extracted, calculation is carried out based on the matched infrared channel radiance information, and the brightness temperature and the brightness temperature difference are calculated. CALIOP data are combined with FY-3D / MERS-II data, the CALIOP is used as a truth value standard of cloud detection, space-time matching is carried out with the FY-3D / MERS-II data, and the brightness temperature difference is calculated. The polar region all-time cloud detection is realized, the accuracy of the cloud detection is improved, and a high-quality data set is provided for the training of a subsequent machine learning model, so that the effects of being not limited by the dependence of visible light and stably working under an all-time condition are achieved.

The invention provides a hyperspectral remote sensing image cloud detection method based on a space-spectrum dual-coding U-shaped network, and relates to the technical field of remote sensing image processing, and the method comprises the steps: collecting a hyperspectral image, carrying out the preprocessing and manual marking, and obtaining a cloud detection data set; constructing a hyperspectral cloud detection model based on the space-spectrum dual-coding U-shaped network; training a hyperspectral cloud detection model through the marked cloud detection data set; and obtaining a to-be-detected hyperspectral image and inputting the to-be-detected hyperspectral image into the trained hyperspectral cloud detection model to obtain a cloud detection result. Through the hyperspectral cloud detection model, the recognition accuracy and efficiency of the hyperspectral image are improved, and the problem that a current cloud detection method only pays attention to spatial information features and ignores spectral discrimination information extraction is solved.

The invention discloses a cloud detection method based on double-branch fusion feature enhancement, and relates to the technical field of remote sensing image processing, and the method comprises the following steps: obtaining a cloud detection data set, and carrying out the preprocessing of the data set; constructing a cloud detection network model based on double-branch fusion feature enhancement; the preprocessed data set is used for training a cloud detection model, and model parameters are saved; and predicting the images of the test set from the model parameters stored in the step 3, and quantifying the model performance through evaluation indexes. The cloud boundary detail extraction and thin cloud positioning capability can be improved, the analysis capability of the model on a cloud layer complex structure is effectively improved, the advantages of convolution operation and an attention mechanism are ingeniously fused, the feature expression of a key region can be dynamically highlighted and strengthened while the local spatial features of the image are extracted, and the method is suitable for the cloud boundary feature extraction and thin cloud positioning. Therefore, the detail features and the spatial dependency relationship of the cloud layer are more accurately captured, and it is ensured that image details are finely reconstructed in the gradual recovery process of the image spatial resolution.

The invention relates to the technical field of intelligent driving, and particularly discloses a 4D millimeter-wave radar dynamic and static point cloud detection method based on deep learning, and the method comprises the steps: obtaining the multi-dimensional features of a target point cloud of the surrounding environment of a vehicle; processing to obtain a two-dimensional feature aerial view corresponding to a single frame of target point cloud and a two-dimensional feature aerial view corresponding to multiple frames of target point clouds; when the sizes of the two two-dimensional feature aerial view views are consistent, the features in the two-dimensional feature aerial view view corresponding to the single-frame target point cloud are used to associate the features in the two-dimensional feature aerial view views corresponding to the multi-frame target point cloud; after feature association, fusing the two two-dimensional feature aerial view views to generate a fused feature map, and performing convolution operation on the fused feature map; and detecting the fused feature map after the convolution operation, and outputting a feature detection result. Single-frame and multi-frame information is fused based on deep learning, and the detection precision and the detection efficiency of the 4D millimeter wave radar are optimized.

The invention provides a large mountain photovoltaic environment fire danger identification method based on a meteorological satellite, and the method comprises the steps: carrying out the radiometric calibration processing based on the Himawari-8 data of a detection region, obtaining the spectral reflectivity or spectral radiation brightness of each wave band of the detection region, and obtaining a cloud shielding pixel through a cloud detection method; a normalized brightness temperature time sequence change function is established based on the time sequence change of the background brightness temperature, a brightness temperature estimation value is estimated, the maximum assumed threshold value of each stage is determined according to the brightness temperature time sequence change function, and then a time sequence method is used for distinguishing fire point pixels. And finally, carrying out credibility grading on the extracted fire point pixels to obtain a fire point grading graph, and sending out corresponding early warning according to fire point grades.

The invention provides a target detection credibility estimation method fusing data and model uncertainty, and belongs to the field of data processing, and the method comprises the steps: obtaining an image quality score through an image quality evaluation model; outputting a target frame by using a two-dimensional detection model, and performing Bayesian correction of confidence in combination with an image quality score and a weather perception model result; meanwhile, outputting a three-dimensional target frame by using a laser radar point cloud detection model, and correcting three-dimensional detection confidence in combination with a target distance and weather conditions; according to the statistical relationship between the number of point clouds in the detection frame and the detection accuracy, constructing the point number confidence coefficient based on Bayesian reasoning; and performing structural consistency analysis according to the spatial size of the detection frame and the prior size distribution of the target category, and outputting structural matching confidence. And finally, the five indexes are fused, and the overall credibility of the sensing result is calculated. According to the method, the credible judgment capability of a sensing system in a complex environment can be improved, and the method has good practicability and engineering value.

The invention discloses a deep learning inversion AOD-assisted atmospheric correction-based method and device and a medium, and relates to the field of atmospheric remote sensing and deep learning cross technologies, and the method comprises the steps: constructing a multi-type training sample set fusing actual measurement and physical simulation data, and carrying out mass screening and layering processing to obtain a multi-type training sample set; obtaining a pre-training sample, a fine tuning sample and an extreme scene sample matched with the satellite remote sensing data; establishing a deep learning network model taking data loss and inverse operator constraint loss weighted fusion as a total loss function, and adopting a cross-satellite transfer learning strategy to sequentially complete pre-training, satellite exclusive fine tuning and extreme scene enhancement training to obtain a trained aerosol optical thickness inversion model; radiometric calibration, cloud detection, geometric correction preprocessing and input model reasoning calculation are carried out on satellite remote sensing original data, post-processing and quality grading are carried out on an output result, and an aerosol optical thickness inversion result used for assisting atmospheric correction is obtained.

The invention discloses a 3D confrontation point cloud-based target capturing method, electronic equipment and medium, and the method comprises the steps: obtaining an original first point cloud data set X0, inputting the first point cloud data set X0 into a diffusion model, and outputting to obtain a second point cloud data set XT; adding disturbance to each point cloud data in the second point cloud data set XT to generate disturbance point cloud, and obtaining a confrontation point cloud point cloud data set X 'T; constructing a 3D point cloud detection model, taking the confrontation point cloud data set X 'T as a training set of the 3D point cloud detection model, and training the 3D point cloud detection model through zero-order random coordinate descent and a multi-scale attack method; inputting to-be-processed point cloud data into the trained 3D point cloud detection model for target detection, and performing pose estimation on an identified target to obtain a target object coordinate; and the coordinates of the target object are converted into a robot coordinate system, the motion path of a mechanical arm is planned, and the mechanical arm is controlled to complete target grabbing.

The invention discloses a deep learning remote sensing data cloud detection method based on physical guidance, which belongs to the technical field of data processing, and comprises the following steps: step 1, preprocessing satellite remote sensing observation data and background field data, step 2, calculating cloud probability based on a radiation transmission physical process, and step 3, calculating cloud probability based on the radiation transmission physical process. And a physically-guided image segmentation deep learning large model cloud detection step. According to the satellite remote sensing data cloud detection method based on physical guidance, radiation transmission physical simulation is adopted, and Bayesian maximum posteriori optimization is used for estimating the probability of cloud appearance. On the basis, constraint information is introduced into a prompt encoder of an SAM large model in a point prompt and frame prompt mode, so that the deep learning image segmentation large model SAM has physical priori knowledge, more accurate cloud detection is achieved, and the method can flexibly adapt to different atmosphere and ocean conditions.

The invention discloses an offshore floating type low-altitude waveguide all-weather detection method and system, and relates to the technical field of marine environment monitoring and electronic information engineering.The method comprises the steps that the current weather condition is judged according to a rain intensity sensor, a miniature weather station, a visibility sensor and an infrared cloud measurement sensor; obtaining a temperature and humidity value range according to the current weather condition, and adding liquid water for correction according to the weather condition; a simulated brightness temperature is obtained according to a MonoRTM model by combining an air pressure profile constructed by sea surface air pressure and a pressure height formula; designing a multi-objective genetic inversion algorithm, constructing an objective function, and when the objective function obtains a minimum value, obtaining an inverted atmospheric parameter profile group; and according to the atmospheric parameter profile group, calculating an atmospheric refractive index profile, judging whether a low-altitude waveguide occurs or not, and uploading a result to a shore station data management center. According to the invention, the atmospheric absorption coefficient is corrected according to different weathers, and all-weather and high-precision monitoring of the low-altitude waveguide on the offshore floating platform is realized.