94 results about "Orthophoto" patented technology

The invention discloses a method for generating an autonomous inspection orthoimage of an unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicle surveying and mapping and autonomous navigation. Global optimization of an air route is realized through a path optimization strategy fused by a genetic algorithm in combination with grid characteristics of an inspection area and image parameter constraints, and candidate waypoints are used as nodes; redundant waypoints are screened through leg smoothness factors, route complexity is reduced, a genetic algorithm takes flight height and waypoint spacing as constraints, a fitness function containing flight distance, turning times and overlapping rate is constructed, a global optimal path is found through population iteration, multi-target requirements are optimized and balanced, and it is ensured that the route meets the image acquisition precision requirement and also meets the requirement of image acquisition. The flight distance can be shortened, the turning frequency is reduced, the cruising ability of the unmanned aerial vehicle is adapted, efficient propelling of the inspection task is guaranteed, meanwhile, waypoint coordinates output through simulation directly adapt to a flight control system, and it is guaranteed that actual flight parameters are consistent with planning parameters.

The invention relates to the technical field of geological disaster detection, in particular to a geological disaster hidden danger point detection method and system. Comprising the following steps: S1, synchronously acquiring vegetation canopy penetration data, multispectral soil humidity spatial distribution data and lithology distribution data by adopting an unmanned aerial vehicle carried image data acquisition device and a multi-band laser radar, and generating an orthoimage and a three-dimensional point cloud data set; s2, fusing the orthoimage and the three-dimensional point cloud data through an aerial triangulation encryption algorithm to establish a three-dimensional model, loading the multispectral soil humidity spatial distribution data into the three-dimensional model to generate a dynamic digital elevation model, and generating a contour line topological structure through a TIN triangulation network algorithm; s3, extracting a slope factor, topographic relief, vegetation coverage, fracture distance and a lithologic factor based on the three-dimensional model to construct a geological disaster hidden danger system; according to the system, the geological disaster occurrence time can be estimated, and the rescue and protection treatment period can be effectively planned based on the geological disaster occurrence time.

The invention discloses an asphalt pavement disease identification method based on unmanned aerial vehicle scanning, and relates to the field of asphalt pavement disease identification, and the method comprises the steps: employing an unmanned aerial vehicle to carry a multispectral imager, obtaining an orthoimage of a whole road segment through a preset route, and carrying out the preliminary feature extraction and suspected region identification; a flight path is optimized according to a suspicion degree and spatial distribution by intelligently planning a recheck route for a suspicion area, and spectral reflectivity data of a specific wave band is collected for secondary verification; color features, glossiness features and texture features are explicitly extracted for a target asphalt pavement area, quantitative extraction is carried out on disease related physical features through brightness and saturation distribution, highlight area detection, texture structure analysis and other means, the accuracy and reliability of oil flooding disease recognition are improved, meanwhile, the disease degree grade is generated, and the recognition efficiency is improved. And accurate data support is provided for asphalt pavement maintenance decision making.

The invention relates to the technical field of unmanned aerial vehicle remote sensing, in particular to a crop leaf area index estimation method based on unmanned aerial vehicle image processing. The method comprises the following steps: acquiring a remote sensing image of an unmanned aerial vehicle monitoring area; identifying a topographic relief area according to the unmanned aerial vehicle monitoring area remote sensing image, and performing orthoimage reconstruction on the topographic relief area to generate a topographic relief area orthoimage; identifying a terrain shielding area based on an unmanned aerial vehicle monitoring area remote sensing image; image stitching distortion detection is carried out on the terrain occlusion area to obtain image stitching distortion data; performing spectral interpolation on the gap region based on the image splicing distortion data, and determining a plant growth stage of the gap region after the spectral interpolation; and performing lens distortion detection based on the image splicing distortion data to obtain lens distortion data. The precision and accuracy of crop leaf area index (LAI) estimation are improved based on the unmanned aerial vehicle remote sensing technology.

The invention provides a lodging area determination method and system based on a lodging monitoring spectral index image, and relates to the field of crop form prediction.The method comprises the steps that firstly, a target farmland remote sensing image and a digital surface model are obtained, radiation and geometric correction are completed in combination with GNSS positioning data and meteorological data, and a standardized orthoimage is generated; calculating a vegetation index on the image and carrying out difference to obtain change information; executing opening and closing operation by adopting a structural element adaptive to the image resolution and the crop row spacing, filtering noise according to the area of a connected domain or a pixel number threshold value, and extracting a spectral index abnormal region and a boundary thereof; and then fusing the boundary and the digital surface model under a unified coordinate reference, accumulating the area according to the pixel resolution, and outputting the area of the abnormal region. The method has parameter self-adaption and multi-source data fusion capabilities, can stably obtain a consistent abnormal region area in a multi-resolution and complex field environment, and provides reliable technical support for agricultural condition monitoring and disaster assessment.

The invention discloses a building height extraction method, device and equipment, a medium and a program product, and the method comprises the steps: carrying out the matching positioning of a remote sensing satellite image of a target region through a digital elevation model and a digital orthoimage of the target region; then obtaining the bottom elevation of a target building in the target area through the digital elevation model; according to the bottom elevation, the vector contour of a target building in a digital line map is registered with the digital orthoimage and the remote sensing satellite image after matching and positioning, and the absolute roof elevation of the target building is obtained; and finally, determining the building height of the target building according to the bottom elevation and the absolute roof elevation, thereby realizing accurate registration of the vector contour of the building and improving the automatic extraction accuracy of the building height data of the building.

The invention relates to the technical field of collapse hill identification methods, in particular to an unmanned aerial vehicle image collapse hill intelligent identification method based on a coordinate attention mechanism. The system comprises an unmanned aerial vehicle image acquisition and preprocessing module, a CA-Unet model construction module, a coordinate attention calculation module and an intelligent collapse hill identification output module. According to the method, a high-resolution image and laser radar point cloud data are collected through an unmanned aerial vehicle, a digital orthoimage and a digital elevation model are generated through orthorectification, and a deep learning data set is constructed; a coordinate attention mechanism is embedded in a U-Net model, the recognition capability of long-distance gullies and steep edges of collapse hills is enhanced through feature coding and dynamic weighting in the horizontal and vertical directions, direction-sensitive feature enhancement is achieved through a coordinate attention calculation module, and finally collapse hill boundary vectors and morphological parameters are output. According to the method, the limitation of a traditional method in the aspects of spatial dependence modeling and boundary extraction is broken through, and accurate recognition and surveying and mapping of the collapse slope erosion landform are achieved.

The invention relates to the technical field of remote sensing images, in particular to a method, device and equipment for generating an orthoimage based on point cloud and a storage medium. Comprising the following steps: S1, acquiring point cloud data; s2, carrying out grid processing on the point cloud data; s3, sorting single grid units comprising a plurality of points according to elevation values, retaining top point clouds, determining pixel color values of the grid units, generating a three-channel image with a plurality of pixels, and constructing a preliminary ortho-image map; s4, traversing the three-channel image to identify null value pixel points, extracting coordinate values of a plurality of non-null value pixel points in the neighborhood, and calculating a coordinate azimuth angle difference value; and S5, according to the coordinate azimuth angle difference value, judging whether the null value pixel point is a hole pixel point located in the image, when the hole pixel point exists, carrying out image repairing, and outputting a repaired orthoimage. According to the method, the high-fidelity orthoimage map can be quickly generated, and the processing efficiency is remarkably improved while the authenticity and the integrity of the ground feature color are ensured.

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

The invention belongs to the technical field of remote sensing measurement, and discloses a farmland shelter cross measurement method fusing unmanned aerial vehicle laser point cloud and images. The method comprises the steps that cultivated land point cloud data and cultivated land image data are collected and fused, and fused point cloud data are generated; processing the fused point cloud data, and identifying first green land data in the fused point cloud data; calculating a visible light vegetation index, and identifying second green land data in the fused point cloud data; integrating the first green land data and the second green land data to generate green land point cloud data, and performing regionalization processing to form a discrete green land region; performing vertical structure analysis on the green land area, identifying and deleting a suspension area in the green land area, and obtaining cultivated land area data; according to the cultivated land area data, generating a cultivated land area orthoimage; according to the invention, high-precision identification and removal of vegetation shelters in cultivated land can be realized, and misjudgment in topographic relief or vegetation dense areas can be avoided.

The invention discloses a coastal tidal flat elevation measurement method based on an orthographic reconstruction technology, and the method comprises the following steps: laying image control points in a target monitoring area of a muddy tidal flat, and then measuring the elevation information of each image control point; an unmanned aerial vehicle is adopted to collect aerial photos of the area according to the planned flight route; an RTK base station is erected in the area to collect static POS data; obtaining static POS data and airborne POS data to calculate flight POS data; flight POS data and aerial photos are obtained, modeling is carried out in combination with elevation information of an image control point, and point cloud data and an orthoimage of the area are generated; and identifying a ponding area from the orthoimage, removing the ponding area from the point cloud data, and establishing a digital elevation model of the area to obtain tidal flat elevation information of the area. Therefore, the problem that large-range tidal flat elevation measurement cannot be carried out due to the limitation of the tidal falling time of the muddy tidal flat in the traditional artificial beach running is solved.

The invention discloses an unmanned aerial vehicle multispectral system error calibration and correction method based on a Boolean model, and belongs to the technical field of photogrammetry and remote sensing. Comprising the following steps: acquiring a multispectral image, acquiring original POS data, and performing band registration preprocessing on the image to generate a first orthoimage to confirm a system error magnitude; carrying out bundle method strict adjustment by using ground control points to obtain reference POS data, and solving seven-parameter conversion parameters; correcting the original POS data by using seven parameters and generating a high-precision orthoimage; and generating a simplified multispectral camera calibration and verification formula according to the difference value of the POS data before and after correction. Complex coordinate conversion is simplified into fixed value addition and subtraction operation, one-button calibration and batch correction of system errors of the multi-spectral camera of the unmanned aerial vehicle are achieved, the positioning precision is improved to the centimeter level from the meter level, dependence on ground control points is greatly reduced, and an efficient standardized solution is provided for large-scale engineering data processing.

The invention discloses a multi-spectrum-based unmanned aerial vehicle bridge appearance inspection method and system. The method comprises the steps that ground control point reflective stickers and bridge floor linear reflective stickers are arranged on a bridge; acquiring laser point cloud data by adopting a basic route, and constructing a bridge three-dimensional model; a refined route is planned based on the bridge three-dimensional model, an orthographic image is screened from shot bridge images, two reflective sticker marks are detected, and reflective sticker circle center pixel coordinates and corresponding reflective sticker orthographic images are output; reading metadata of an orthographic image of the reflective sticker, and obtaining three-dimensional coordinates and pixel coordinates of ground control points; calculating to obtain three-dimensional coordinates of the circle center of the reflective sticker; carrying out disease detection on the bridge photos by adopting a bridge apparent disease recognition model, screening disease photos, and taking central coordinates of a disease bounding box as disease positions; extracting the same disease in the plurality of photos, and calculating three-dimensional coordinates of a central point of a disease bounding box; and based on the disease three-dimensional coordinate set and the change condition of the position of the bridge floor reflective sticker, planning a reinspection route of the key area.

The present invention provides an artificial intelligence-based digital orthophoto and DSM registration method and system. The method generates point cloud density distribution parameters based on mountain terrain complexity parameters, and combines artificial intelligence to perform gain adjustment on weak signals below a preset signal strength to obtain an adjusted signal and generate a DSM elevation dataset. The method also uses a preset affine transformation image geometric correction parameter library to match the DSM elevation dataset with the digital orthophoto, and establish an initial coordinate mapping relationship. The method then repairs the digital orthophoto based on the initial coordinate mapping relationship and the DSM elevation dataset to generate a repaired digital orthophoto. The repaired digital orthophoto is then automatically registered with the DSM based on geometric consistency constraints between the repaired digital orthophoto and the DSM elevation dataset. The method realizes automatic registration of digital orthophotos with the DSM in complex mountainous terrain, improving the repair quality of cloud-obstructed areas and the reliability of global registration.

The invention provides a rice leaf area index inversion method based on an unmanned aerial vehicle, and relates to the technical field of smart agriculture, and the method comprises the steps: S1, obtaining an RGB image of a to-be-detected rice canopy, a training feature set, and a corresponding rice leaf area index measured value; s2, processing the RGB image of the rice canopy to be measured to generate a digital orthoimage and a digital earth surface model; s3, generating spectral features, height features and texture features based on at least one of the RGB image, the digital orthoimage and the digital earth surface model of the rice canopy to be measured; s4, training a machine learning model by using the training feature set and the corresponding rice leaf area index measured value to obtain a rice leaf area index inversion model; and S5, inputting the spectral features, the height features and the texture features into a rice leaf area index inversion model to obtain a leaf area index prediction value of the rice canopy to be detected. And rice leaf area index inversion is carried out only by using the RGB sensor to collect images.

The invention discloses a tree positioning calculation method based on unmanned aerial vehicle remote sensing, and relates to the technical field of agriculture and forestry vegetation positioning. According to the method, firstly, a digital orthoimage and a digital earth surface model (DSM) are generated through aerial photography of an unmanned aerial vehicle, a crown mask is obtained by using an instance segmentation technology, and a trunk position is accurately positioned by calculating a fusion score in the mask by using a joint resolving mechanism of a DSM local peak domain and an iterative corrosion morphological core. The method improves the positioning precision and efficiency through a DSM highest point * iterative corrosion combined optimization strategy, and improves the positioning stability of dense crowns through the corrosion depth constraint space position. According to the method, the positioning precision and efficiency of a complex forest environment are remarkably improved, and the problems of insufficient positioning precision, difficulty in positioning trunks under dense crowns and the like in the existing unmanned aerial vehicle remote sensing technology are solved.

The present invention relates to the fields of computer vision, image processing, etc., and provides a seam line network generation method and apparatus, an electronic device, and a medium. The specific implementation solution comprises: determining respective effective areas of a plurality of orthophotos to be mosaicked; performing mosaicking processing multiple times on the basis of the respective effective areas of the plurality of orthophotos to obtain a target effective polygon group; and generating a seam line network for the plurality of orthophotos on the basis of the target effective polygon group.

The invention discloses a map conversion method and apparatus. The method comprises the steps of obtaining original data of unmanned aerial vehicle patrol flight; performing conversion processing on the coordinate data to obtain target coordinate data, and performing correction processing on the original image according to the target coordinate data and the flight attitude parameters to obtain an orthoimage; performing feature preprocessing on the orthoimage to obtain target vector data and target raster data; carrying out topological relation map construction according to the target vector data and the target raster data to obtain electronic map data; performing error correction on the electronic map data according to the high-precision reference map to obtain a corrected electronic map; and carrying out data integration on the corrected electronic map and the electronic map data to obtain a target electronic map. Therefore, by integrating the corrected electronic map data and the uncorrected electronic map data, the integrity and consistency of the data can be further improved, and the precision of the generated final electronic map is ensured to be higher.

The present invention discloses a deformation monitoring method based on DSM data. The method comprises the following steps: performing aerial survey of the object to be measured, generating orthophotos using photogrammetric modeling software, and extracting at least two phases of DSM data; determining a resampling interval d, and resampling the DSM data; cropping the resampled DSM data, calculating similar points, and obtaining displacement change data in the x, y, and z directions; filtering the obtained displacement change data to remove noise from the data and obtain displacement data; and uniformly performing error correction on the displacement data using correction data to obtain the displacement amount. The present invention utilizes current aerial photogrammetry results, has a low overall cost, quickly obtains large-area data, has a wide monitoring range, and can monitor three-dimensional surface deformation data. While its accuracy is somewhat lower than that of traditional and GNSS measurements, it is higher than that of InSAR measurements, and its error can be controlled to the centimeter and decimeter levels.

The application discloses a kind of unmanned aerial vehicle autonomous inspection orthographic image generation method, it is related to unmanned aerial vehicle surveying and mapping and autonomous navigation technical field, the path optimization strategy of the present application is fused by genetic algorithm, global optimization is realized to route in combination with the image parameter constraint of inspection area grid feature, with candidate navigation point as node, through the smoothness factor of navigation section, redundant navigation point is filtered, and the complexity of route is reduced, genetic algorithm is constrained with flight height, navigation point spacing, constructs fitness function including flight distance, number of turns, overlap rate, finds global optimal path by population iteration, optimizes and balances multi-objective demand, ensures that route meets image acquisition accuracy requirement, can also shorten flight distance, reduce number of turns, adapt to the endurance of unmanned aerial vehicle, guarantee that inspection task is efficiently promoted, simultaneously, the navigation point coordinates of simulation output are directly adapted to flight control system, ensure that actual flight parameter is consistent with planning parameter.

The invention provides a bird's-eye view orthographic image generation method and device and a computer readable storage medium. The method comprises the following steps: generating a three-dimensional ground triangulation network model according to three-dimensional ground point cloud data; penetrating dotting is conducted on the three-dimensional ground triangulation network model, multi-layer tile data are generated, the position information of tiles in the multi-layer tile data comprises row numbers, column numbers and elevation values, the row numbers and the column numbers indicate the horizontal positions of the tiles, and the elevation values indicate the vertical heights of the tiles; and according to the multi-layer tile data, generating a hierarchical aerial view orthographic image corresponding to the elevation data of the track points. Through the three-dimensional ground triangulation network model, penetrating dotting is carried out, the multi-layer tile data including the row number, the column number and the elevation value can be generated, the information capable of covering the multi-layer road surface can be generated, the aerial view orthographic image of the level corresponding to the elevation data of the track point can be generated according to the multi-layer tile data, and the aerial view orthographic image can be conveniently displayed to a user.

The present invention provides a method for estimating forest aboveground biomass by combining multi-source remote sensing data and an integrated model, relating to the field of forest management technology. The method comprises: obtaining airborne LiDAR data, high-resolution orthophotos, and multi-source remote sensing data of a predetermined sample plot; using the high-resolution orthophotos as an aid, obtaining the forest aboveground biomass of the predetermined sample plot based on the airborne LiDAR data; performing feature optimization on the multi-source remote sensing data to obtain an optimal combination of remote sensing feature variables; constructing and stacking multiple models based on the optimal combination of remote sensing feature variables and the forest aboveground biomass of the predetermined sample plot using an extreme gradient boosting algorithm, an adaptive boosting algorithm, a random forest algorithm, and a gradient boosting decision tree algorithm; determining the model with the highest accuracy among all the models and using it to estimate the forest aboveground biomass of the predetermined study area to obtain an estimated result. The present invention solves the problem of low accuracy in forest biomass estimation in the prior art.

This invention relates to the field of data analysis technology, and more specifically, to a method for identifying forest pests and diseases based on data analysis. The method includes: Step 1: acquiring aerial orthophotos of the target forest area and counting trapping points within a set time interval, and associating the trapping counts with the nearest-nearest-assigned sample area units; Step 2: constructing a complex simplex on a forest map grid, consisting of a patch layer, a sample area layer, and a trapping layer, and outputting suspected pest and disease triggering units after filtering out negative examples using a two-stage verifier; Step 3: establishing a pest and disease map database, describing typical patterns using disease type topological fingerprints; performing similarity assessment between the topological evidence package and the disease type topological fingerprints to generate disease type, extent, and confidence level, and labeling the data in layers on the forest map grid. This invention can capture fine-grained structural changes in pests and diseases at an early stage, and improves identification accuracy and interpretability by utilizing multi-source evidence synthesis.

This invention discloses a method and system for identifying apparent damage to bridge concrete based on texture analysis, belonging to the interdisciplinary field of bridge engineering inspection and computer vision technology. The method includes: acquiring surface images of bridge components using a drone and generating orthophotos; extracting contrast, correlation, and entropy features based on the gray-level co-occurrence matrix; extracting histogram features based on local binary patterns; detecting corrosion and seepage areas based on the HSV color space; fusing multi-dimensional features and inputting them into a multi-label classifier, simultaneously outputting pixel-level segmentation masks for multiple types of damage such as cracks, spalling, exposed rebar corrosion, and seepage; generating a damage level score and maintenance recommendation report according to bridge technical condition assessment standards. This invention integrates complementary texture features to achieve simultaneous identification of multiple types of damage, outputs pixel-level segmentation results, and automatically generates an assessment report that conforms to engineering specifications.

The present invention relates to a method and device for quickly generating a digital orthophoto map based on point cloud. The method divides point cloud data into blocks according to a preset size to obtain a plurality of digital elevation model data blocks. The camera imaging model is used to calculate the world coordinates of each pixel point in the frame image, and the weight of the world coordinate point corresponding to each pixel point on the frame image is calculated. If the world coordinate point P corresponding to the pixel point M is in the frame image I, the weight of the world coordinate point P corresponding to the pixel point M is calculated. i The weight #imgabs0# on the image is greater than P in the frame I i‑1 The weight #imgabs1# assigns the pixel value of pixel point M in the frame image to the world coordinate point P, otherwise skipping. This step is repeated until all pixels in all frames are traversed, obtaining the pixel value corresponding to any point in the point cloud data, and generating a digital orthophoto. This processing method uses less memory and improves CPU utilization. It eliminates the need for phased array and aerial triangulation, and can process areas with weak or no texture, making it more applicable than conventional software.

This invention relates to a method and medium for detecting building changes based on UAV imagery. By using UAV images of the same target area acquired at different times, the method incorporates UAV ground control points and aerial POS information into an aerial triangulation system to jointly calculate the camera's exterior orientation elements and imaging geometry. Orthophotos of the preceding and following times are generated under a unified coordinate reference, and building probability maps of the preceding and following times are obtained through processing. The merged orthophoto obtained after combining the preceding and following times UAV images is used to construct multiple object units based on cross-temporal consistency. Furthermore, the average first and second semantic confidence scores corresponding to the preceding and following times orthophotos are obtained. Based on whether the two average confidence scores meet three preset judgment conditions, each object unit is determined and labeled as belonging to a specific type of building change area. Thus, stable and accurate detection of building changes based on UAV imagery is achieved.

The invention provides a digital orthoimage and DSM registration method and system based on artificial intelligence, and the method comprises the steps: generating a point cloud density distribution parameter based on a mountain terrain complexity parameter, combining artificial intelligence, carrying out the gain adjustment of a weak signal with the intensity lower than a preset signal intensity, obtaining an adjusted signal, and generating a DSM elevation data set; matching the DSM elevation data set with the digital orthoimage by using a preset affine transformation image geometric correction parameter library, and establishing an initial coordinate mapping relationship; according to the initial coordinate mapping relation and the DSM elevation data set, repairing the digital orthoimage to generate a repaired digital orthoimage, and according to the geometric consistency constraint between the repaired digital orthoimage and the DSM elevation data set, performing automatic registration of the repaired digital orthoimage and the DSM; according to the method, automatic registration of the digital orthoimage and the DSM under the complex mountain terrain is realized, and the cloud and mist shielding area restoration quality and the global registration reliability are improved.

This invention discloses a method, system, and storage medium for LOD2 building reconstruction from single-view orthophotos. The method inputs a single-view orthophoto remote sensing image into a shared backbone network to generate a footprint mask probability map; constructs a first modulation factor, performs element-wise gating on the multi-scale feature map, and inputs it into a height decoder to output a height field; normalizes the height field to obtain a normalized height map and constructs a second modulation factor; fuses the second modulation factor with the first modulation factor to form a composite modulation factor, performs dual element-wise gating on the multi-scale feature map, and inputs it into a structure line decoder to output a distance field and orientation field; recovers the roof structure line based on the distance field and orientation field; and constructs the roof surface, walls, and ground by combining the roof structure line, height field, and footprint boundary to generate a LOD2 3D model of the building. This invention can automatically generate a topologically complete and geometrically accurate LOD2 3D model relying solely on a single orthophoto.

The invention relates to the technical field of building detection, and provides a house indoor defect intelligent detection and graphic file output method and system. The method comprises the following steps: acquiring millimeter-level three-dimensional point cloud data through handheld SLAM laser scanning, generating an orthoimage after preprocessing, carrying out defect identification and classification by adopting an unsupervised-weak supervised neural network in which a MobileNetV3-SOM and a stacked auto-encoder are connected in series, calculating three-dimensional coordinates and quantization parameters of a defect center through pixel-point cloud back projection, and carrying out defect identification and classification on the defect center. And finally generating a CAD vector file containing defect types, three-dimensional coordinates and quantization parameters. According to the method, only normal wall surface sample training is needed, the problem of insufficient model generalization caused by defect sample scarcity is solved, meanwhile, accurate three-dimensional positioning and complete parameter description of defects are achieved, the output standardized CAD file can be directly used for repairing design, the detection efficiency is improved, and the application range is widened.

A method for classifying disturbing plants using drone orthophotos is disclosed, and the method for classifying disturbing plants using drone orthophotos may include: (a) forming a drone orthophoto in which a target area is shown during a preset period; and (b) determining a candidate object of a disturbing plant from the drone orthophoto as the disturbing plant.