961 results about "Fog" patented technology

The invention relates to the field of target detection, in particular to a UMFNet-YOLO-based joint detection algorithm under a low-light condition, which adopts a multi-scale decomposition and high-frequency-low-frequency feature collaborative enhancement strategy, separates image details from global features through high / low-pass filtering, realizes multi-resolution feature complementation in combination with dynamic weight distribution, and improves the detection accuracy. Target contour and texture information degraded in severe weather can be effectively recovered; a parallel channel compression and spatial semantic enhancement module is designed, rain and fog noise interference is suppressed through cross-dimensional adaptive feature screening, and significance expression of a key target is enhanced; an image enhancement network UMFNet is cascaded with YOLOv8, and strong correlation between feature expression and a detection task is ensured by synchronously optimizing an enhancement module and detecting network parameters through back propagation. Compared with a baseline YOLOv8 detector, the method has the advantages that the average precision (mAP50) is obviously improved, and the method is obviously superior to a traditional enhancement-detection separation scheme. The method can be applied to robust target detection scenes in complex environments such as automatic driving and security monitoring.

The invention discloses a salt mist airflow field prediction method and system in an ocean atmospheric environment, and relates to the technical field of ocean wind power plant salt mist corrosion trend prediction.The system divides a wind power plant into a plurality of salt mist monitoring areas, collects environmental data, constructs a salt mist airflow field model by adopting three-dimensional modeling and CFD simulation, and obtains the salt mist corrosion trend of the wind power plant. A digital twinborn model is generated through multi-physics field coupling, and dynamic deduction is carried out; constructing an AI corrosion prediction model by using historical data and simulated deduction data, extracting a corrosion risk feature vector FCV, and performing dynamic training to predict a corrosion trend; salt mist concentration and wind speed data are monitored in real time, a corrosion coefficient is calculated and compared with a threshold value for analysis, and a corresponding protection strategy is formulated; in combination with real-time data and digital twinborn deduction, evaluating a wind-driven salt mist coupling deposition risk, triggering early warning and optimizing a strategy; and a test report is automatically generated, future test parameters are optimized through an AI prediction model, and the corrosion resistance and the operation efficiency of the wind turbine are improved.

The invention discloses an accident early warning analysis method and system based on driving data, and relates to the technical field of accident early warning analysis, by extracting a road condition complexity coefficient Cen, a sight distance chaos coefficient Cvs and a dynamic interference coefficient Cdn, the system not only considers the current state, but also analyzes the dynamic interference characteristics of the current state when modeling the external environment, so that the accident early warning analysis accuracy is improved. And the system still has high reliability in the scenes of rain and fog, night, congestion and the like. The comprehensive score value Srisk is not single binary judgment any more, multi-factor fusion interpretation is carried out in combination with information such as operation disturbance, posture deviation and fatigue indexes, a response result WIN with grading characteristics is output, and multi-level early warning from voice reminding to active intervention can be achieved. And the dynamic feedback optimization module constructs a risk response parameter psi stab according to a score fluctuation trend, dynamically adjusts a weight coefficient omega j of the multi-modal model, generates a new coefficient n omega, and realizes self-parameter adjustment and adaptive reinforcement learning.

The invention relates to a pipe network station inspection task execution method and system based on multi-modal fusion, and belongs to the technical field of industrial facility detection. According to the method, multiple types of sensors are carried through an unmanned aerial vehicle and a ground robot, illumination, temperature and humidity, wind speed and rain and fog data are collected in real time, and an optimal sensor combination is dynamically activated; a feature level fusion strategy is adopted, the weight of each modal is adjusted in combination with environmental parameters, and the defect detection accuracy is improved; the system performs digital twinborn simulation verification on an abnormal result, so that the false alarm rate is reduced; an inspection path is adaptively adjusted according to a detection result, and a high-risk area is emphatically scanned; the edge computing nodes realize real-time data processing, and upload key information after compression; the maintainer rechecks the result through the AR glasses and marks a misinformation case; according to the method, the problems of poor environmental adaptability and insufficient utilization of multi-modal data of traditional inspection are solved, and the detection efficiency and reliability are improved.

The invention belongs to the technical field of image processing and computer vision, and particularly relates to a foggy day data set synthesis method and device based on a depth estimation model in a power transmission scene. The method comprises the steps of performing meteorological screening on an original power transmission image through a convolutional neural network classifier to reserve a power transmission image of a cloudy / cloudy scene, and performing feature enhancement processing on the reserved power transmission image by using a python-piq library to obtain a target power transmission image; constructing a double-branch depth estimation network to extract macroscopic structure features of the power transmission equipment and microcosmic texture features of the conductor, and generating an optimized gray depth image through a confidence fusion algorithm constrained by span information; calculating a self-adaptive atmospheric light value by using an improved dark channel prior algorithm, and generating a physical fog field in combination with a depth-guided atmospheric scattering model; and constructing a DISTS-NEW evaluation model oriented to a tower structure, and dynamically adjusting the foggy day concentration coefficient of the physical fog field through a back propagation mechanism until the foggy day concentration coefficient meets a power transmission equipment recognizable degree threshold value.

The invention relates to a sea fog quantitative forecasting method based on a period enhanced Transform, and the method comprises the steps: firstly constructing a Transform model as a forecasting model, enabling the Transform model and a self-attention mechanism to better capture the complex nonlinear relation and long-distance time dependence related to the formation of sea fog, and being superior to a conventional statistical method and an early-stage RNN / LSTM model, a data set for model training is constructed based on a time period enhancement technology and visibility standardization mapping, and the explicit time period enhancement technology enables the model to more accurately learn and forecast seasonal and daily change rules of sea fog; and a sample amplification and training set balancing strategy is executed on the data set, so that the problem of sparse fog samples is effectively solved, and the forecasting capability of the model on key low-visibility events is improved. According to the sea fog quantitative forecasting method based on the period enhanced Transform, the precision, timeliness (forecasting per hour) and spatial resolution of sea fog forecasting of a target area can be improved, and sea fog data characteristics can be effectively processed.

The invention discloses a polarization image defogging method based on double iteration regular separation, and relates to the technical field of image defogging, and the method comprises the following steps: S1, obtaining a polarization image; s2, constructing a representation function of the fog concentration; s3, indirectly solving an intermediate variable T; s4, formula decomposition; s5, judging whether convergence occurs or not; and S6, finally defogging. When the polarization image defogging method based on double-iteration regular separation is used, non-uniformly distributed concentration characteristic differences are analyzed through a large number of polarization images in a non-uniform haze scene, on this basis, a dynamic fog concentration function in the image is effectively constructed in combination with polarization characteristics, estimation of an atmospheric scattering coefficient is achieved, and the defogging effect is improved. Meanwhile, a double-iteration separation algorithm is provided based on the atmospheric scattering coefficient, the optimal transmittance is solved, image sharpening restoration under the non-uniform haze scene is achieved, haze residues are further reduced, and the image restoration quality is also objectively improved.

The invention discloses a target identification method for multi-sensor data fusion, particularly relates to the technical field of data fusion, and comprises a dynamic weight fusion module, a double-branch neural network and an abnormal sensing compensation system. Data are synchronously collected through a visible light camera, a thermal infrared imager and a millimeter wave radar, and a standardized feature map is generated through sensor specificity preprocessing; the dynamic weight fusion module generates an adaptive weight matrix based on the real-time confidence score and the environmental parameters, emphasizes infrared data when illumination suddenly changes, and improves intelligent distribution of radar weights in a rain and fog environment; the combined feature map after weight fusion is input into a double-branch neural network, a channel self-calibration branch suppresses interference noise, and a target category and coordinates are output after residual connection optimization; when the recognition confidence is insufficient, the abnormal compensation system starts visible light Wiener filtering restoration, generative adversarial network infrared compensation and radar multi-frame accumulation algorithms, and the system reliability is ensured when a single sensor fails.

The invention discloses a transformer substation intelligent patrol recognition algorithm optimization method based on multi-modal fusion, and belongs to the technical field of transformer substation patrol, and the method comprises the following steps: synchronously obtaining a visible light image, an infrared thermal imaging spectrum, an ultrasonic partial discharge signal and environmental parameters, and building a four-dimensional space-time calibration matrix; a dual-channel attention mechanism is adopted to realize multi-source data fusion, a spatial alignment channel and a feature enhancement channel are included, the spatial alignment channel realizes pixel-level registration of visible light and infrared images through affine transformation, and the feature enhancement channel utilizes a graph neural network to construct topological correlation mapping of acoustic, thermal and optical features; constructing a three-stage training architecture containing noise injection; and adding an adversarial generative network in a preprocessing layer to simulate rain fog and electromagnetic interference environments. According to the method, the identification threshold is updated online by deploying a sliding time window mechanism in an output layer, and the problems of poor feature extraction robustness and high false alarm rate of a traditional algorithm in complex environments such as strong electromagnetic fields and rain and fog are solved.

The invention relates to the technical field of deodorization control, in particular to an air dust suppression, haze reduction and deodorization control system and method based on the Internet of Things. The method comprises the following steps: acquiring three-dimensional point cloud data and point cloud echo signals of a target area; analyzing the abnormal weakening trend of the echo intensity of the point cloud echo signal to calculate the dust concentration of the air in the target area; calibrating the dust concentration by using the three-dimensional point cloud data to obtain dust concentration three-dimensional gradient distribution data; acquiring a wind speed vector of the target area; constructing an air vortex field model based on the wind speed vector; performing dust migration path prediction on the dust concentration three-dimensional gradient distribution data by using an air vortex field model to generate dust migration path prediction data; and determining mobile positioning data of the fog gun based on the dust concentration three-dimensional gradient distribution data. According to the method, refined and dynamic air dust suppression, haze reduction and deodorization control is realized through point cloud modeling, air vortex field prediction and intelligent spraying optimization.

The invention relates to the technical field of new energy power plant construction data processing, in particular to a construction site personnel track recognition system based on a two-dimensional code, which adopts laser etching to dynamically encrypt a two-dimensional code label, and improves the weather resistance of the label in a salt fog environment through a salt-dredging nano coating and antistatic packaging. And a double-fixing structure combining the elastic binding band and the magnetic fastener is suitable for high-strength operation scenes. Industrial-grade scanning base stations are deployed in a construction area in a gridding mode, three-dimensional coordinate data are captured through a multi-base-station cooperative scanning mechanism, high-reflection interference of photovoltaic panels is eliminated through a signal intensity difference algorithm, and a de-noising coordinate set is generated. The closed-loop calibration module corrects scanning angle offset and earth surface reflection weight parameters through a three-level check link, the environment adaptation module triggers an ultrasonic multi-frequency cleaning program to maintain optical performance, and the cooperative control unit adjusts the light supplementing intensity and the data fusion proportion in a linkage mode. Accurate identification of personnel tracks and multi-working-plane dynamic management and control in a complex environment are realized.

The invention provides a sea fog detection method and device based on a satellite-borne laser radar, and belongs to the field of atmosphere remote sensing monitoring. The method comprises the following steps: setting a multi-parameter joint threshold value for cloud-aerosol distinguishing; based on a set multi-parameter combined threshold value, primary distinguishing of cloud-aerosol is completed, and the number of cloud layers within the specified height from the sea surface is screened out from the cloud-aerosol range; in combination with the cloud base height and the scattering characteristic parameters of the cloud layer, the area meeting the scattering characteristic criterion is calibrated as a sea fog layer; calculating continuity characteristics of sea fog levels in vertical and horizontal distribution, and identifying signal interruption points and abnormal distribution areas; and carrying out interpolation completion on scattering characteristic data of a signal interruption point region, eliminating an abnormal distribution region, re-correcting hierarchical characteristics of vertical and horizontal distribution, and outputting an optimized sea fog hierarchical distribution result. According to the sea fog detection method and device based on the satellite-borne laser radar provided by the invention, detection of vertical distribution of sea fog can be accurately and effectively realized.

The invention relates to the technical field of intelligent traffic, in particular to an integrated fog measurement type highway safe driving guidance device and method, and provides the following scheme that local visibility data is acquired based on a plurality of highway safe driving guidance devices and uploaded to a region controller to generate guidance information. And the regional controller performs research and judgment calibration and gradient calibration on the data, corrects measurement errors and generates road visibility space distribution information by screening calibration anchor points and adopting an exponential attenuation function and iterative gradient calculation. Based on the information, a connectivity algorithm is used to identify a fog area, and in combination with road environment and historical accident data, an optimal induction strategy is matched, and induction information is dynamically adjusted. The fog area detection accuracy is improved, the induction information matching is optimized, and the driving safety and the passing efficiency under the low-visibility condition are improved.

The invention discloses a fog boundary layer parameterization scheme correction method based on a multi-scale physical coupling network, relates to the crossing field of numerical weather forecast and artificial intelligence, and aims to improve the performance of different boundary layer parameterization schemes in a WRF mode, construct a fusion framework of a physical mode and deep learning, adopt a double-branch heterogeneous network structure, and improve the performance of a fog boundary layer parameterization scheme. Establishing a nonlinear mapping relation between different parameterization scheme deviations and large eddy simulation turbulence characteristics by combining a space-time attention mechanism; by correcting systematic deviation existing in a parameterization scheme, the analysis capability of a turbulence structure is improved, and physical description of a boundary layer process is optimized; compared with a traditional boundary layer scheme, the method has the advantages that the fog zone simulation precision is remarkably improved, the fog zone visibility, the liquid water content and the root-mean-square error of a liquid water path are reduced by 66.7%, 50% and 58.3% respectively, the problem that turbulence intermittent characterization is insufficient under a stable boundary layer in a traditional method is effectively solved, and a new normal form is provided for refined forecasting of the fog generation and elimination process.

The invention belongs to the technical field of computer vision, and particularly relates to a time sequence sea fog detection method based on stationary meteorological satellite multichannel brightness temperature difference driving, which comprises the following steps: acquiring meteorological satellite remote sensing data, and marking sea fog; preprocessing meteorological satellite remote sensing data according to the data source; extracting motion features by using the preprocessed meteorological satellite remote sensing data, and constructing a sea fog motion feature data set; inputting the model training set into a sea fog segmentation neural network model based on time sequence characteristics for training to obtain a training model; and preprocessing data of the test set, inputting the data into the training model for testing, and outputting a prediction result after segmentation, namely a final sea fog detection result. According to the method, the difficulty of motion feature extraction is reduced, the accuracy of sea fog monitoring tasks is improved, the consistency of continuous moment segmentation results is enhanced by comparing learning loss, and better generalization and performance are achieved.

The invention relates to the field of photovoltaic module detection, and discloses a module hot spot defect infrared and visible light fusion detection method, which comprises the following steps: multi-mode acquisition: multi-mode data of a photovoltaic module are synchronously acquired, and the multi-mode data comprise infrared temperature original data, visible light polarization images and environmental parameters; data preprocessing: preprocessing the multi-modal data based on a radiation transmission model and a polarization optical principle to obtain preprocessed data including an infrared temperature field and a visible light image; and dynamic feature extraction: extracting a space-time gradient tensor and a Riemannian curvature tensor of the infrared temperature field from the preprocessed data based on differential geometry and a computer vision algorithm. By synchronously acquiring multi-modal data, based on a radiation transmission model and a polarization optical principle, interference of atmospheric attenuation and environment temperature and humidity on infrared temperature measurement and influence of uneven illumination and fog effect on a visible light image are eliminated, and dynamic characteristics of an infrared temperature field and structural characteristics of visible light are mined.

The invention relates to the technical field of intelligent environmental protection, in particular to an unmanned aerial vehicle urban atmospheric pollution monitoring and preventing system based on radar and AI cooperation, which comprises a laser radar scanning module, an edge computing gateway, a cloud server, a small unmanned aerial vehicle inspection module, an unmanned aerial vehicle spraying module and a fog gun vehicle module, the laser radar scanning module scans and generates point cloud data in real time, and pollution information is obtained by combining positioning and aerosol inversion; the edge computing gateway uses a DBSCAN clustering algorithm and an improved YOLOv8 model to determine pollution hot spot coordinates, grades and pollution source types; the cloud server dynamically dispatches all the modules in sequence, an improved ant colony algorithm is adopted to plan a route, and real-time obstacle avoidance and accurate spraying are achieved; the small unmanned aerial vehicle inspection module obtains an image of a polluted area, the unmanned aerial vehicle spraying module carries out precise spraying treatment, and the fog gun vehicle module carries out dust suppressant spraying on a dust raising source. The defects of a traditional atmospheric pollution monitoring and treatment means are overcome, and accurate monitoring and efficient treatment are achieved.

According to the severe weather adaptive road violation real-time monitoring method and system provided by the invention, the image quality is dynamically judged by using the visibility index, and accurate traffic target identification and violation behavior detection are realized by combining image enhancement and a gating feature fusion mechanism. The system comprises a video acquisition module, a visibility evaluation module, an image enhancement module, a feature extraction and fusion module, a target detection module and a violation recognition module, can maintain high-accuracy recognition performance in various severe weathers (such as rain and fog), and is suitable for the field of intelligent traffic and urban safety management.

The invention provides a sea fog forecasting method, medium and system based on ocean station observation data, and belongs to the technical field of electrical digital data processing, and the method comprises the steps: firstly, obtaining years of continuous hydro meteorological observation data of an observation station, including air temperature, dew point temperature, seawater temperature, wind direction and wind speed and other data; performing multi-scale decomposition through wavelet transform to obtain variable components of different time scales; then, forecasting factors including temperature difference, stability index and the like are calculated, and layered Fisher discriminant analysis is carried out according to seasons and weather system types. A polynomial discrimination equation set is established by calculating a weight coefficient, and a discrimination critical value is determined by combining a probability density function, so that whether the weather is foggy or not is judged. And finally, verifying by adopting a three-level inspection system, and constructing a complete forecast product release system including the strength grade of fog, the space-time evolution and the like, thereby realizing the accurate forecast of the sea fog. The technical problem that the accuracy of a traditional forecasting method fluctuates greatly under different conditions is solved.

The invention discloses an unmanned aerial vehicle intelligent obstacle avoidance decision-making method and system for a complex environment, and belongs to the technical field of unmanned aerial vehicle obstacle avoidance. The method comprises the steps of S1, environment perception and data acquisition, S2, multi-source data hierarchical fusion processing, S3, complex environment obstacle recognition and risk assessment, S4, dynamic obstacle avoidance path decision and optimization, and S5, obstacle avoidance execution and real-time adjustment. Omnibearing acquisition of obstacle distance, environment images, unmanned aerial vehicle attitude and position data is realized; the method combines an improved YOLOv8 model (adding a CBAM attention mechanism), strengthens the obstacle feature extraction capability under complex weathers such as rain and fog, strong light and dust, can accurately distinguish static obstacles such as buildings and trees from dynamic obstacles such as pedestrians, vehicles and other aircrafts, and solves the problems that a single sensor perceives blind areas and is insufficient in precision in a complex environment.

The invention discloses a visibility inversion method based on millimeter wave cloud radar and laser radar data fusion, and relates to the technical field of meteorology, and the method comprises the steps: guiding a millimeter wave cloud radar and a laser radar to carry out data correction and equivalent relation construction through employing a fog drop particle size distribution function measured by a fog drop spectrometer in a sample scene in advance; and then applying the correction coefficient and the equivalent function relationship to a target scene to perform multi-source data correction and fusion on the millimeter wave cloud radar and the laser radar and invert visibility. The method can fuse complementary advantages of the laser radar and the millimeter wave cloud radar; the introduction of the fogdrop particle size distribution function effectively avoids the distribution hypothesis of fogdrop shapes in the traditional model, can weaken the seasonal drift of the traditional empirical coefficient, significantly improves the accuracy and reliability of visibility inversion, and achieves the high-precision visibility monitoring under various weather conditions from clear sky to dense fog.

The invention belongs to the technical field of sea fog monitoring, and particularly relates to a sea fog monitoring method and system based on multi-source satellite remote sensing data, and the method comprises the steps: collecting satellite radiation and microwave observation data, discriminating the cloud top phase state in combination with infrared ground microwave channel response differences, dividing clear sky and low cloud shielding scenes, and outputting identification data. And sea fog is detected in combination with the single-time infrared brightness temperature difference and the empty pixel parameters, optical parameters are inverted, and a sub-scene sea fog physical parameter set is formed. Carrying out normalized coupling reconstruction on the parameter set, constructing a sea fog exclusive feature space, separating a fog region from a non-fog region through phase state constraint to obtain an initial judgment feature field, correcting the edge of the fog region through neighborhood correlation and brightness temperature gradient constraint, strengthening spatial continuity to generate a spatial distribution field, locking a credible region, and outputting a final sea fog detection result. According to the invention, through layer-by-layer progressive design of scene division, feature optimization and multi-source verification, the precision and integrity of sea fog identification are significantly improved.

The present invention discloses a method for detecting forest disturbances based on a full-polarization SAR image, which includes obtaining a full-polarization SAR image within a target area, performing image classification for the reference time phase and the monitoring time phase, performing pre-processing including introduction of the SAR image, polarization matrix transformation of the SAR image, Refined Lee filtering, and false-color synthesis on the classified full-polarization SAR image to obtain a false-color synthesized SAR image, inputting the false-color synthesized SAR image into an optimized surface change detection model to extract surface change patches, combining with a radar vegetation index RVI image to obtain initial forest disturbance patches, performing an overlay check on the initial forest disturbance patches to obtain forest disturbance patches within the target area, and generating a visualization result. It has efficient, accurate, and reliable detection capabilities, can observe the ground all day long, all-weather, and penetrate clouds and fog, can be widely applied in fields such as forest resource monitoring and environmental protection, and can better serve ecological protection restoration supervision and management.

The invention discloses a low-altitude remote sensing target recognition method based on artificial intelligence, and belongs to the technical field of image analysis, and the method comprises the steps: dividing a remote sensing image into sub-regions with different fog concentrations, matching a defogging weight according to a clear score and a detail score of each sub-region, and dynamically adjusting the defogging weight of each sub-region in a two-dimensional manner, thereby achieving the target recognition. The problem of local overexposure or under-processing caused by the same weight is effectively avoided, then the atmospheric light estimated value of each sub-region and the transmissivity estimated value of each pixel are analyzed in sequence, and the fog concentration of each sub-region is effectively reflected, so that the effectiveness of the optimized brightness value of subsequent calculation is improved. Defogging processing is completed on the basis of optimizing the brightness values of the pixels in the RGB three channels, color shift is effectively avoided, the image quality is ensured while the defogging effect is improved, and then the target analysis accuracy is improved.

The invention discloses a target sheet identification method based on point cloud data, and belongs to the field of target sheet identification methods, and the method comprises the following steps: 1, collecting original point cloud data of a target range environment through a laser radar; step 2, anti-rain and anti-fog interference processing; step 3, carrying out gale shake compensation; 4, reconstructing a basic curved surface, and executing random sampling consistency plane fitting; step 5, enhancing and reconstructing a wrinkle region, specifically, detecting a region with a curvature change rate of greater than 0.05 mm <-2 > on the basic curved surface; marking as a to-be-enhanced area and transmitting to a sub-curved surface processing flow; step 6, bullet hole identification: calculating the local curvature of the point cloud, and screening abrupt change points of which the curvature values are greater than 0.25 mm <-1 >; fitting the three-dimensional coordinates of the bullet hole by adopting a least square method; and step 7, outputting target sheet attitude parameters and bullet hole ring values. According to the invention, interference of rain, fog and strong wind can be reduced, and identification precision is improved.

According to the expressway self-adaptive agglomerate fog early warning and response control method and system, meteorological data and traffic flow data of an expressway are collected in real time, and a reinforcement learning algorithm is utilized to predict a space-time mode of occurrence of agglomerate fog. By calculating the agglomerate fog risk index, if the risk exceeds the standard, the system triggers agglomerate fog early warning and dynamically adjusts the traffic management strategy, so that the driving safety is improved to the maximum extent and the traffic jam is reduced to the maximum extent. The system continuously optimizes decisions through traffic flow and visibility information fed back in real time, realizes adaptive adjustment through reinforcement learning, and adapts to changes under different weather and traffic conditions. The method can accurately predict the occurrence of agglomerate fog, optimizes the traffic flow, reduces the occurrence rate of traffic accidents, improves the passing efficiency and safety of the expressway, and has a wide application prospect.

The invention discloses an attitude detection method and system for a photovoltaic panel. The method comprises the following steps: S1, scanning through a laser radar to obtain light point cloud data; s2, segmenting the point cloud data through a clustering algorithm, and determining and storing clustering point cloud data to which the photovoltaic panel belongs; s3, performing plane fitting on the clustering point cloud data to which the photovoltaic panel belongs to obtain a plane equation, and projecting the point cloud data to the plane equation; s4, performing edge extraction on the point cloud of the photovoltaic panel to obtain a top edge linear equation; s5, postures are combined according to the vectors. According to the invention, the laser radar is used for data acquisition, the stability of equipment is improved, the operation is simple, other sensors are not depended on, a training set is not needed to train a model, the use stability and reliability are high, the system can be used in extreme environments such as night, heavy fog and rainy days, and the real-time analysis effect is achieved through algorithm optimization of point cloud processing. And the calculation efficiency of the attitude of the photovoltaic panel is improved.

The invention relates to sensing and tracking of intelligent driving in rain, snow, fog, night and large shielding scenes. In order to solve the problems of target invisibility, track interruption and misconnection caused by low visibility, a shielded dynamic target identification and tracking method based on deep learning is provided; according to the method, under a unified spatial index, sparse point cloud and road topology, passable and traverse areas, static shielding volume coding, ray marking visibility boundary and shielding entrance and exit are carried out; generating a motion voting field with consistent visibility through multi-agent situation reasoning, performing normal directional enhancement according to a passable boundary, and extracting a risk corridor; voxelization is carried out on the multi-frame point cloud in the corridor, a dynamic sparse voxel map is constructed, a voting field is used for gating cross-frame edge connection, occupation changes and infinitesimal displacement are aggregated, and three-dimensional verification candidates, limited state estimation and a time continuous track are obtained; outputting the target and the corridor to which the target belongs, and forming a potential conflict zone according to the intersection of the target and the own vehicle path; the reproduction rate and the advance are improved, and cross-lane misconnection is reduced.

A density perception image defogging method in combination with physical prior comprises the following steps: S1, acquiring a fog-containing image, marking a fog area and a fog-affected area, constructing a data set D1 through size unification, normalization and multi-dimensional data enhancement, and dividing the data set D1 into a training set and a verification set according to a proportion; s2, a density perception defogging network is constructed, the density perception defogging network comprises an encoder sub-network, a middle layer sub-network and a decoder sub-network, core modules are a gridding atmospheric light attention module and a space detail enhancement module, and a GAAB integrates a multi-scale density perception convolution module, a grid perception atmospheric attention module and a feature fusion module; fog density features can be accurately captured, and physical prior can be fused; s3, inputting the data set into a defogging network to generate a multi-scale feature map; s4, carrying out training optimization on the network by adopting a combined loss function of L1 loss and perception loss; s5, evaluating the network performance through the verification set; according to the invention, adaptive defogging in different fog concentration scenes is realized, and the definition of the defogged image is effectively improved.

The invention relates to the field of sea fog image recognition, discloses a high-precision sea fog image recognition and prediction method based on ensemble learning, and aims to improve multi-source data fusion efficiency and reasonable utilization and improve the stability of a model so as to realize accurate recognition of sea fog and more accurate time-space evolution prediction. According to the method, a three-dimensional feature space is constructed through visible light wavelet texture analysis, infrared dynamic temperature correction and microwave liquid water path inversion, an image branch adopts improved DeepLabV3 + to carry out fog region semantic segmentation, and fog region identification and trajectory prediction are realized in combination with a thermodynamic phase change criterion and a fluid mechanics diffusion model. And finally, a high-precision sea fog image identification and prediction system is formed. A black box model is replaced with a physical equation, and the defects that a traditional method is poor in interpretability and insufficient in real-time performance are overcome.