147 results about "Haze" patented technology

The invention relates to the technical field of remote sensing monitoring, in particular to a remote sensing target detection method and system for a low-visibility image. The method comprises the following steps: acquiring multi-modal remote sensing image data; carrying out defogging enhancement processing on the low-visibility input image; normalizing the defogged RGB image and the defogged IR image, and then splicing and fusing the RGB image and the IR image; carrying out layer-by-layer coding on the multi-modal fusion image by adopting a mixed trunk structure fusing Transform, Mamba and CNN (Convolutional Neural Network); performing frequency domain decomposition on the trunk output features based on two-dimensional wavelet transform; generating an HR feature map by adaptively selecting a key region; and carrying out cross-scale aggregation on the HR feature map to obtain a detection target frame. Through the multi-modal image defogging enhancement and feature distillation mechanism, the definition and contrast of the remote sensing image in severe weather such as haze and rainy days are effectively enhanced, the shielding interference of environmental degradation on small target detection is weakened, and the stability and adaptability of the model in complex weather scenes are enhanced.

The invention discloses an enhancement method for a foggy day image, which is particularly suitable for an automatic driving scene to solve the influence of the foggy weather on the image quality so as to improve the accuracy of target detection. The method comprises the following steps: firstly, carrying out two-dimensional discrete wavelet transform on a foggy day image, and respectively extracting high-frequency and low-frequency information of the image; for low-frequency information, a low-frequency enhancement model based on half-channel Fourier transform is adopted to enhance the global structure and contrast of the image. For high-frequency information, an adaptive direction detail enhancement module is adopted, and guidance information extracted from low-frequency information is combined, so that edge and texture details in different directions of the image are enhanced. And finally, combining the enhanced low-frequency and high-frequency information, and carrying out two-dimensional discrete wavelet inverse transformation to obtain a preliminary enhanced image. The enhanced image is combined with a standard YOLOX target detection model to form an end-to-end detection framework. Compared with an existing enhancement method, the method can effectively solve the problem of image blurring in automatic driving in foggy days, the generated image is more suitable for machine vision application, and the detection precision and robustness are remarkably improved.

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.

A haze visibility detection method and device based on depth and brightness information and a medium are used for foggy weather visibility detection, a multi-mode visibility detection model comprehensively utilizing image data and meteorological data is provided, the model takes the image data and the meteorological data as inputs at the same time, and the visibility detection accuracy is improved through a parallel network structure. The data of the two modes are respectively sent to different channels to extract respective features, and then the features of the two modes are fused to jointly invert the visibility value. According to the method, the visual information and the environmental parameters are combined by constructing the multi-mode visibility detection model, and the depth information and the brightness information are introduced to optimize the model design, so that the accuracy and the robustness of the model are improved, and the visibility can be detected more accurately and reliably.

The invention discloses a traffic sign recognition and lane line detection method and system for extreme weather, and relates to the technical field of computer vision and artificial intelligence. According to the method, an efficient image restoration algorithm is designed, the influence of haze, rain and snow and other weather noise on the image quality is eliminated, and key detail information of traffic signs and lane lines is reserved; secondly, a YOLOv8 target detection network is improved, the problems of missing detection of small targets and false detection of complex backgrounds are solved, and the detection accuracy of the multi-scale traffic signs is improved; furthermore, a lightweight lane line detection algorithm is designed based on an improved line anchor mechanism, and the detection precision and real-time performance of the lane line in a complex scene are improved; and finally, an image restoration module, a traffic sign recognition module and a lane line detection module are integrated, multi-modal support of images, videos and real-time camera data is realized, an engineering solution adaptive to extreme weather is formed, and practical application of an intelligent traffic system in a complex environment is promoted.

The invention belongs to the technical field of target detection, and particularly relates to a deep learning-based small target detection method in a haze scene, which comprises the following specific steps of: constructing a small target detection original data set in the haze scene, or using an existing disclosed small target detection data set in the haze scene; the method comprises the following steps: firstly, collecting small target image data in a haze environment, then carrying out frame selection on the position of a small target by using a labeling tool, and carrying out label labeling; according to the method, a small target detection original data set in a haze scene is preprocessed, a preprocessed small target data set in the haze scene is obtained, and the data set is divided, so that a deep learning-based small target detection model in the haze scene is trained subsequently. When a small target detection task in a haze scene is processed, detail features of the small target can be captured and recognized more accurately, and interference of haze on the features of the small target is effectively reduced.

The invention discloses a real haze image defogging method based on a haze degradation model. The method comprises the following steps: constructing a haze degradation model fusing multiple scattering effects and multiple image degradation factors; using the haze degradation model to construct a training data set including the clear image and the corresponding pseudo haze image; constructing a defogging network for a real haze scene; training the defogging network by adopting the training data set until a preset loss function is converged; and inputting a to-be-defogged image into the trained defogging network to obtain a defogging result. According to the haze degradation model constructed by the invention, the difference between a synthetic domain and a real domain is effectively relieved; a designed space-frequency hybrid module improves the adaptability of the model to complex degradation characteristics; the prior-guided feed-forward network fully excavates and fuses dark channel prior information, and the sensing and modeling capability of the model to the haze area is effectively enhanced.

The invention discloses a high-transparency PVB intermediate film and a production process and application thereof, and relates to the technical field of PVB intermediate films, the high-transparency PVB intermediate film comprises the following raw materials by weight: 100 parts of PVB resin, 20-30 parts of a composite plasticizer, 0.5-0.9 part of an LDH-based composite antioxidant, 0.5-1 part of an ultraviolet light absorber, 0.1-1.5 parts of nano lanthanum hexaboride, 0.1-1.5 parts of porous hollow nano copper sulphide, and 0.1-2 parts of nano TiO2 / SiO2 core-shell particles. The PVB intermediate film provided by the invention is relatively high in light transmittance, low in haze value, and excellent in oxidation resistance, weather resistance and mechanical strength.

The invention discloses a semi-solid-state complex no-tillage dry direct seeding method for crop seeds. The no-tillage dry direct seeding method comprises the following steps: S1, keeping a water layer of 1cm-5cm in a ditch, and paving straws obtained by harvesting preceding crops on a ditch surface; S2, applying a base fertilizer on the ditch surface paved with the straws and cleaning the ditch; S3, seeding the crop seeds on the ditch surface, and mixing the crop seeds with semi-solid-state biomass materials, a compound fertilizer and a biopesticide before seeding before seeding seeds, wherein the mixing mass ratio is that the crop seeds to the semi-solid-state biomass materials to the biopesticide is (1-10) to (70-800) to (1-3), and the moisture content of the semi-solid-state biomass materials is 40%-80%; and S4, after seeding the seeds, keeping the ditch surface at a dry state for 3-7 days. According to the semi-solid-state complex no-tillage dry direct seeding method, tillage and combustion of winter crop straws are not carried out, a whole land of field immersing water is not used for irrigation and the water immerses after the seeding, and the biological benefits are obvious; the working energy consumption is reduced, stubbles are not killed by pesticides, haze is reduced and the irrigation water is reduced.

The invention relates to the technical field of environment data processing, in particular to a multi-element cooperative processing method and system for haze environment monitoring and forecasting data. Comprising the following steps: S1, acquiring pollutant data in a CUACE mode, and performing interpolation processing on the pollutant data to obtain hourly pollutant concentration data; s2, acquiring pollutant IAQI data according to the hourly pollutant concentration data, and trimming the hourly data to obtain adjusted hourly pollutant concentration data; and S3, according to the adjusted hourly pollutant concentration data, calculating the primary pollutant and the AQI hour by hour, or calculating the primary pollutant and the AQI 24 hours by 24 hours, and adjusting the primary pollutant and the AQI by using a genetic algorithm. According to the method, primary pollutant sorting is dynamically adjusted by using the genetic algorithm, pollution characteristics under special weather conditions are adapted, and the accuracy and practicability of forecasting are improved.

The invention provides a dust raising haze treatment system and method for environmental protection. The system comprises an environment parameter real-time monitoring module, a flying dust diffusion dynamic modeling module, a multi-mode treatment strategy generation module, a high-pressure atomization dust suppression execution module, an electrostatic adsorption purification module, an intelligent dynamic feedback control module, an energy optimization distribution module and a remote collaborative management platform module. According to the scheme, the turbulence correction model, deep reinforcement learning control and gradient electric field design are systematically fused, and the contradictory problem of low prediction precision and high energy consumption in the traditional technology is solved.

The invention relates to the technical field of atmospheric transmission characteristics, and provides a method for acquiring atmospheric transmittance in haze weather, which comprises the following steps of: acquiring a mixed composition ratio of a plurality of preset haze particle groups forming a preset aerosol type, and acquiring diameters and complex refractive indexes of a plurality of wet haze particles contained in the plurality of preset haze particle groups; and determining the extinction efficiency factor of each wet haze particle according to the diameter and the complex refractive index. And determining the total extinction coefficient of the preset aerosol type according to the particle distribution function of the preset aerosol type, the mixing composition ratio and the extinction efficiency factors corresponding to the plurality of wet haze particles. According to the total extinction coefficient, the atmospheric transmittance is calculated through an atmospheric transmittance calculation function. The calculation of the atmospheric transmissivity is carried out based on the diameter and the complex refractive index of the wet haze particles, and the influence of the preset aerosol type composed of the plurality of preset haze particle groups on the calculation of the atmospheric transmissivity is considered, so that the calculation accuracy of the atmospheric transmissivity is improved.

The invention provides a polarization integrated imaging detection module applicable to a severe environment, and relates to the technical field of image detection. The system comprises an optical lens, a polarization CMOS sensor, a data transmission link, a control transmission link and an on-chip integrated processing system. Wherein the exposure consistency of the multi-polarization-angle images is ensured by performing acquisition and exposure adjustment on the images at four polarization angles and executing a brightness normalization algorithm, so that the problem of brightness unbalance during multi-image fusion of a traditional exposure algorithm is avoided; besides, through local dynamic range optimization, global gamma correction and a multi-scale fusion method, texture and brightness characteristics at different polarization angles are reserved, and clear and reasonably exposed image generation is realized. The defects in the aspects of atmospheric haze, underwater imaging and strong reflected light processing in the prior art are overcome, high-resolution and high-frame-rate real-time clear imaging is achieved, and reliable image support is provided for various application scenes.

The invention discloses a mine dust fog image defogging method and system based on three-dimensional inverse interactive intersection, and the method comprises the steps: adding a three-dimensional attention extraction module in a u-net network architecture, and adding a space regularization inverse cross attention and inverse interactive connection module in a downstream task; the three-dimensional attention extraction module enhances the sensing ability of the model to non-uniform haze; the spatial regularization inverse cross attention module dynamically and adaptively highlights residual fog, artifacts and contrast loss areas, enhances the response of the depth estimation network to the areas, and improves the overall performance and robustness of double tasks; the inverse interactive connection module improves the cooperation efficiency of the defogging and depth estimation network, and also solves the problem that error information cannot be fed back to a feature layer. The system is an encoder-decoder architecture, and a three-dimensional attention extraction module, an inverse cross regularization attention module and an inverse interaction connection module are arranged in the encoder-decoder architecture. According to the invention, the accuracy of a monitoring camera system and an intelligent detection system in a mine is improved.

The invention discloses an engineering building deformation monitoring method and system, and the method comprises the steps: obtaining a texture target image on a building, carrying out the preprocessing of the texture target image through employing a self-adaptive illumination compensation algorithm, and adjusting the brightness and contrast of the texture target image if the illumination change is detected, and obtaining a first image; performing denoising processing on the first image, removing noise in the first image by using a Gaussian filtering algorithm, and if rain and fog weather is detected, enhancing the definition of the first image by using a haze removal algorithm to obtain a second image; and carrying out displacement calculation on the fifth image, calculating the displacement amount of the feature points in the fifth image by adopting an optical flow method, and if image drift is detected, correcting the position of the fifth image by using an image registration algorithm to obtain the final deformation displacement amount of the building.

The invention provides a power equipment defect detection system and method based on a multi-mode Transform, and the system comprises a double-flow feature extraction module which is used for carrying out the feature extraction of a collected visible light image and an infrared image of power equipment through employing a double-flow feature extraction network based on YOLOv5, and obtaining a visible light feature pattern and an infrared feature pattern; the multi-modal information interaction module is used for carrying out multi-modal information interaction on the visible light characteristic pattern and the infrared characteristic pattern to obtain a multi-modal fusion characteristic pattern; and the defect classification module is used for carrying out defect detection and classification on the power equipment by adopting a two-stage residual full-connection defect classifier based on the multi-modal fusion feature map to obtain a defect classification result. The method can overcome the influence of environmental factors such as heavy fog, rain, haze and the like, is not limited by illumination conditions, and has relatively high anti-interference capability. In addition, the method can also solve the problems of low resolution and fuzzy texture details of the infrared image.

The present application discloses a comprehensive meteorological detection device for a highway and a detection method thereof, including: a plurality of meteorological test units, a remote computer and a cloud server arranged on the highway. The meteorological test unit is used to transmit and calculate meteorological test data; the remote computer is used to issue test instructions to the meteorological test units at both ends; the cloud server is used to receive the test data of the entire test link composed of multiple meteorological test units, and analyze and calculate the final meteorological results. The present application can quickly, comprehensively and accurately understand the comprehensive meteorological conditions along the highway, realize quantitative testing of meteorological weather such as rainfall, snowfall, fog or haze, and solve the deficiency that the existing image recognition software is difficult to realize quantitative recognition. It is able to transmit data or commands from one end of the link to the other end, and only needs to configure a wireless modem in the endpoint unit to connect to the Internet of Things, so as to realize the uploading of test data and the issuance of commands such as test maintenance, with low cost.

The invention provides a photovoltaic output prediction method considering haze / dust factors. The method comprises the following steps: firstly, preprocessing data, screening out abnormal data and invalid data, and complementing missing data; the method comprises the following steps: firstly, analyzing haze / sand dust data, then classifying weather data by using a decision tree algorithm, then deeply understanding an internal rule and an operation mechanism by analyzing a haze / sand dust formation mechanism and a photovoltaic power generation principle, determining main characteristics, and then firstly establishing a haze / sand dust influence model 1 and a photovoltaic power generation power prediction model 2 for the haze / sand dust data; the model 1 obtains influence parameters of haze / dust factors on the photovoltaic power generation power, and the model 2 outputs a predicted value of the photovoltaic power generation power. The advantages of mechanism analysis and a data driving model are combined, and the accuracy and reliability of the model are improved.

The invention discloses an intelligent networking driving recording system based on multi-mode perception. The intelligent networking driving recording system comprises a perception layer, a processing layer, an application layer and a block chain evidence storage module. The invention further discloses a data tamper-proofing method of the intelligent networked driving recording system based on multi-mode perception, which comprises the following steps: S1, synchronously acquiring thermal radiation data, radar point cloud data and video image data in a driving environment through the infrared thermal imaging sensor, the 4D millimeter wave radar and the high-definition optical camera; s2, infrared thermal imaging data are optimized, radar point cloud clustering is optimized through a DBSCAN algorithm, and target tracking is achieved based on UKF. The system can cover the whole temperature range of-30 DEG C to 85 DEG C and severe weather such as rain, snow and haze, effectively reduces the false alarm rate of infrared thermal imaging and the missed detection rate of a millimeter wave radar static target, avoids the loss of accident key evidence caused by environmental factors, greatly improves the evidence obtaining reliability at night and in severe weather, and reduces traffic accident disputes.

This invention discloses a method and system for intelligent weather image acquisition and recognition, specifically relating to the field of weather image recognition technology. It involves continuous polarization imaging of the sky region while simultaneously acquiring spatial attitude and temporal information; preprocessing the polarization image data and extracting Stokes parameters to obtain standardized sky polarization light field data; then using a theoretical Rayleigh scattering model to analyze the polarization degree distribution pattern at different wavelengths to obtain theoretical sky polarization pattern characteristics; based on the polarization light field data, identifying the spatial distribution of actual clouds, aerosols, and haze in the sky to form actual atmospheric composition distribution characteristics; extracting anomalous polarization regions through difference analysis between theoretical and actual characteristics, and accurately classifying halo polarization anomalies and scattering polarization anomalies based on geometric and spectral characteristics; generating ultralocal weather change early warning signals based on the classification results; thus improving the accuracy and real-time performance of early warnings for ultralocal anomalous weather phenomena.

The invention relates to a track defect detection method based on an infrared image under a low-visibility condition. The method comprises the steps that active pulse type thermal excitation is applied to the surface of a track, an infrared image sequence and a visible light image are synchronously collected and preprocessed, feature level fusion is carried out on the preprocessed infrared image and visible light image, track defect recognition is carried out in combination with an improved cross-scale polymorphic self-adaptive detection network, and the track defect recognition accuracy is improved. Outputting a defect bounding box and a corresponding defect category label; and then sub-pixel-level edge contour positioning processing is carried out on the defect area, geometric parameters of the defect area are calculated based on a positioning result, and a track defect detection report is generated by combining the geometric parameters, a defect category label and a track structure health state evaluation result. By adopting the method, the bottleneck of failure of visible light detection in a low-visibility environment can be effectively overcome, and high-precision and high-efficiency detection and evaluation of track defects in severe environments such as night, haze, rain and snow and the like can be realized.

The application discloses a deep learning-based artillery barrel target image defogging method and system, which comprises the following steps: inputting an original artillery barrel target image into a trained defogging enhancement network model for processing, wherein the defogging enhancement network model comprises an improved U-Net module, an AOD-Net module and an atmospheric scattering model layer connected in sequence; the improved U-Net module is used to extract multi-scale features of the original artillery barrel target image, and output the multi-scale feature maps to the AOD-Net module; the AOD-Net module is used to extract features under different receptive fields of the multi-scale feature maps through different convolution layers, realize multi-scale feature fusion, and output input values of the atmospheric scattering model layer; and the atmospheric scattering model layer is used to obtain the defogged artillery barrel target image based on the input values. The model is constructed by connecting the U-Net and the AOD-Net in series, a new model optimizer is proposed, the algorithm of gradient descent is optimized, and a self-adaptive weight loss function is introduced, so that efficient defogging processing under complex fog and haze conditions is realized.

The method for removing fog based on inter-layer multi-scale sequence interaction and Fourier domain frequency-space enhancement comprises the following steps: step S1: collect a public fog data set containing different concentrations of fog and haze, and pre-process the images therein to improve data quality and model training effect; step S2: construct a network framework for removing fog based on inter-layer multi-scale sequence interaction and Fourier domain frequency-space enhancement, which comprises a U-shaped fog removal network, an inter-layer multi-scale sequence interaction module IMSIM and a Fourier domain frequency-space enhancement module FDFSEM; step S3: train the network using the labeled image data set, define a suitable loss function and use an optimizer to train; step S4: evaluate the fog removal effect using two indicators of peak signal-to-noise ratio PSNR and structural similarity index SSIM, optimize the trained model, and deploy it to the actual application for online inference and real-time fog removal; through the above steps, the input feature map can be removed.

The invention relates to the field of high polymer materials, in particular to a high-definition perspective TPEE film, a preparation method and application. The invention discloses a high-definition perspective TPEE film which is prepared from the following components in percentage by weight: basic resin TPEE, a high-definition additive, a weather-resistant stabilizer, an antioxidant, an antistatic agent, an anti-scraping agent and a compatilizer, and further provides a preparation method of the TPEE film, the preparation method comprises the following steps: pre-mixing the components, performing melt blending through a twin-screw extruder, and finally forming the film through a tape casting method or a film blowing method, so as to obtain the high-definition perspective TPEE film. Meanwhile, the invention discloses application of the TPEE film in a high-definition display screen, a high-end packaging material or special optical equipment. The prepared TPEE film has high-definition perspective performance, the film thickness is 50-200 microns, the light transmittance is larger than or equal to 91%, the haze is smaller than or equal to 1.2%, the yellowing index delta b is smaller than or equal to 0.6, and the TPEE film has the effects of weather resistance, oxidation resistance, static electricity resistance, scraping resistance and the like.

The invention discloses an experimental device for simulating surface dirt accumulation and detection of an intelligent coal caving camera, and relates to the technical field of coal mine engineering, the experimental device comprises an air duct model group, a dust generator, an air draft mechanism, a power supply, a controller, a sensor assembly, a haze meter and a plurality of camera type dust collectors; the air duct model group with the transparent side wall is provided with a simulation air duct for simulating a coal caving space at the rear part of an underground fully mechanized caving face; the air draft opening of the air draft mechanism is connected with the outlet of the simulation air duct and has adjustable power; the sensor assembly comprises a wind speed sensor and at least one concentration sensor; the camera type dust collectors are respectively arranged at different positions of a dust flowing path; the haze meter is used for detecting the haze of each simulation lens for at least three times, the controller is in communication connection with the dust generator, the air draft mechanism, each sensor and the haze meter, and the power supply is used for powering on each component. The system can simulate the coal dust attachment characteristics on the surface of the camera, provides support for the research of reducing the dust attachment of the camera, and improves the precision of a visual system of an underground intelligent coal caving machine.

The invention discloses an air pollution emission distribution method based on environmental quality improvement, and relates to the technical field of ozone pollution emission management. The air pollution emission distribution method based on environmental quality improvement comprises the following steps of ozone emission pollution judgment, ozone generation distribution adjustment and ozone diffusion distribution adjustment. According to the method, whether ozone generation pollutant emission distribution adjustment is executed or not is judged according to the ozone emission pollution judgment result, if yes, whether precursor pollutant emission distribution optimization is executed or not is judged according to the obtained ozone generation evaluation result, and if not, whether ozone diffusion emission distribution optimization is executed or not is judged according to the ozone diffusion evaluation result. The reasonable emission distribution of the nitric oxide emission amount and the volatile organic compound emission amount of the industrial park under the haze weather is effectively improved, and the problem that in the prior art, the emission distribution of the nitric oxide emission amount and the volatile organic compound emission amount of the industrial park under the haze weather is not sufficiently associated with ozone pollution is solved.

The invention relates to the field of environmental monitoring, and discloses a PM2.5 concentration weighting-based dust-haze discrimination standard construction method, equipment and a medium. Compared with the existing three common dust-haze discrimination standards for setting a single threshold value based on visibility and relative humidity, the PM2.5 concentration weighting-based dust-haze discrimination standard construction method has the advantages that the PM2.5 concentration weighting-based dust-haze discrimination standard construction method is established by establishing the relationship between the PM2.5 mass concentration and the visibility and the relationship between the PM2.5 mass concentration and the relative humidity; and analyzing the occurrence frequency of fine particle aerosol pollution, providing a new standard of assigning different threshold values to different relative humidity intervals, and accurately identifying the haze day. According to the method, the characteristics of dust-haze fine particle aerosol pollution can be better represented, and fine particle aerosol pollution and non-fine particle aerosol pollution can be more accurately distinguished.

The present invention relates to a method for removing haze from land, sea and air battlefield images based on parametric modeling and gradient guidance. Natural battlefield images and remote sensing battlefield images are collected, and fog synthesis strategies are used to generate natural battlefield haze-removing datasets and remote sensing battlefield haze-removing datasets, and an underwater image enhancement dataset is obtained. A battlefield image haze-removing network is constructed, in which the fog concentration estimation network combines the dark channel prior and the Swin Transformer model to generate fog concentration parameters, the medium transmission estimation network estimates the medium transmission parameters based on the encoder-decoder model, and the ambient light estimation network collaborates with the encoder and local minimum filtering to estimate the ambient light parameters. The estimated parameters are substituted into the imaging model, and the imaging model is inversely solved to generate the battlefield haze-removing result. A gradient guidance module is used to further enhance the image details, and clear and detailed battlefield images are obtained. The present invention integrates the complementary advantages of physical model methods and deep learning methods, effectively improves the visual effect of battlefield fog images, and can achieve multi-scene haze removal in a single framework, which is convenient for popularization and use.

The invention provides a natural disaster monitoring and early warning device utilizing Beidou satellite positioning, and belongs to the field of monitoring and early warning, the natural disaster monitoring and early warning device comprises a base, the upper end face of the base is fixedly connected with a fixed rod, the fixed rod is internally provided with a lifting groove, the lifting groove is internally slidably connected with a lifting rod, the fixed rod is provided with an adjusting assembly, and the adjusting assembly is fixedly connected with the lifting rod. A connecting plate is fixedly connected to the side wall of the lifting rod, two fixing assemblies are installed on the connecting plate, two photovoltaic panels are installed on the connecting plate, a water level monitoring assembly is installed on the fixing rod, and a control room is fixedly installed on the side wall of the lifting rod; a camera monitoring assembly; the camera shooting monitoring assembly comprises a rotating groove formed in the side wall of the lifting rod. A user can conveniently adjust the height of the device, so that the device can adapt to different terrains for adjustment, the portability of the device is improved, the user can conveniently mount and dismount the photovoltaic panel, the portability of the device is improved, and meanwhile, the water level, haze, thunderstorm and the like can be monitored.

The embodiment of the invention provides a haze weather image processing method and device based on a deep convolutional network, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed original haze image, carrying out the channel processing of the original haze image, generating an R-channel image, a G-channel image and a B-channel image, calling a feature extraction algorithm, carrying out the recognition of the R-channel image, the G-channel image and the B-channel image, and carrying out the recognition of the G-channel image and the B-channel image. Generating a first target image according to the G channel image and the B channel image, generating a second target image according to a multi-scale mapping algorithm, a local extremum algorithm and the first target image, and calling a bilateral correction linear unit to generate a target defogging image corresponding to the second target image, the defogging effect is enhanced by calling a feature extraction algorithm, a multi-scale mapping algorithm, a local extremum algorithm and a bilateral correction linear unit.