859 results about "Canopy" patented technology

The invention relates to the technical field of data decision, in particular to an analysis decision method for crop growth monitoring data. The method comprises the following steps: collecting crop phenotypic characteristic data through a multi-source sensing array; dynamically dividing crop growth response stages according to phenotypic characteristics; constructing a growth situation prediction model based on the crop growth response stage; inputting the phenotypic characteristic data into a growth situation prediction model, simulating a crop growth process through a digital twin engine, and generating growth situation evolution data; extracting physiological anomaly characteristics of the growth situation evolution data, and generating stress response signals; obtaining a canopy three-dimensional phenotype map based on the stress response signal; positioning vascular bundle nodes of the canopy three-dimensional phenotype map through morphological topology analysis; according to the invention, through multi-source data acquisition, dynamic growth stage division, accurate model prediction, three-dimensional phenotype monitoring and self-correction decision optimization, the accuracy of analysis decision for crop growth monitoring data is improved.

The invention provides a forest land tree height measurement and determination method and system based on laser radar point cloud data. Stress wave signals are collected based on a trunk base acoustic emission sensor array to generate an acoustic characteristic parameter set, the digital twin model is driven to complete forest stand structure topological optimization, and a three-dimensional growth vector model reflecting the internal mechanical state of a trunk is formed. And synchronously fusing high-precision slope point cloud data returned by the unmanned aerial vehicle laser radar in real time, correcting a terrain distortion error through a dynamic splicing algorithm in combination with stress distribution characteristics, and generating a crown segmentation boundary constrained by physical characteristics. And finally outputting a tree height parameter corrected by the abrupt slope topography through model iterative optimization and space vector analysis. According to the technical scheme, synchronous sensing of the three-dimensional shape and the mechanical state of the tree in the complex terrain environment is achieved, and the tree height measurement error is reduced.

The invention belongs to the technical field of intelligent agriculture, and discloses a canopy-atmospheric environment information-based soil water content prediction method and system, and the method comprises the steps: setting a canopy and atmospheric environment monitoring unit in a field, and synchronously collecting the canopy temperature, wind speed, relative humidity, and six-dimensional environment parameters of atmospheric temperature, wind speed and relative humidity; the crown temperature difference is calculated after preprocessing; the method comprises the following steps: constructing a training set by utilizing measured data of soil relative water content, constructing a soil water content prediction model by adopting a random forest algorithm, screening and confirming an optimal prediction model through grid search and cross validation, and screening key features by combining an SHAP value; the water demand is automatically calculated according to a pre-established crop whole-growth-period drought stress threshold table and a dynamic irrigation decision formula, and meanwhile, the adaptation of a general model to a regional specific model is realized by constructing an environmental parameter-actually measured water content database and transfer learning, so that the soil water content state is accurately predicted, and the soil quality is improved. And a scientific basis is provided for precise irrigation.

The invention relates to the technical field of environment regulation, in particular to a corn cultivation environment intelligent regulation method based on multi-sensor control, which comprises the following steps: S1, generating a soil moisture three-dimensional distribution diagram in real time through humidity sensor arrays arranged at different depths of a corn root zone; s2, combining infrared temperature data of the canopy and the three-dimensional distribution diagram of the soil moisture, and calculating a moisture motion mismatch degree through transpiration-permeation conduction collaborative analysis; s3, generating a user-defined irrigation mode based on the water movement mismatch degree, and controlling the irrigation duration, the stop interval and the water flow rate. According to the method, coupling modeling is carried out on the plant physiological water demand behavior and the soil moisture supply characteristic, the limitation that a traditional irrigation system only depends on a soil humidity threshold value or meteorological index judgment is broken through, and the biological adaptability and the aging responsiveness of field moisture regulation and control are improved.

Provided is an individual-tree segmentation method of UAV LiDAR point cloud based on canopy morphology. The method uses woodland data obtained by a UAV LiDAR to: extract initial canopies from a CHM based on a region growing algorithm, determine whether each initial canopy is a correct segmentation canopy according to the number of local density maximum points in each initial canopy, finely segment each wrong segmentation canopy according to canopy morphology to obtain an updated set of tree tops, and finally use each of the updated set of tree tops as a seed point for performing the region growing algorithm to thereby obtain a final individual-tree segmentation result. The method make full use of height information and density information contained in a tree point cloud; and under the guidance of the density information, a wrong segmentation tree can be more accurately identified.

The invention discloses a method and system for estimating irrigation water consumption and water utilization efficiency, and relates to the technical field of water resource management, and the method comprises the steps: collecting the plant stem flow rate, canopy temperature and soil profile water content data of a target area through a multi-source sensing device, and obtaining a gradient and permeability distribution diagram of a geographic information system; dividing the farmland of the target area into sub-areas with different irrigation priorities based on a soil conductivity mutation point detection algorithm; constructing a dynamic water demand model fused with the plant transpiration hysteresis effect, performing space-time correlation analysis on the stem flow rate data and the soil moisture content gradient, and calculating the real-time water demand intensity of each sub-region; the method comprises the following steps: accessing short-time rainfall prediction data of a meteorological radar, dynamically correcting a future irrigation decision by adopting a sliding time window mechanism, and triggering a gradient delay irrigation instruction when the predicted rainfall amount exceeds an irrigation threshold value; and calculating the actual moisture utilization efficiency based on the inversion data of the moisture content of the irrigated soil and the unmanned aerial vehicle multispectral image.

The invention discloses a forestry intelligent spraying system and spraying method based on multi-source sensor space perception, and relates to the technical field of intelligent control. A target forest region is scanned through a laser radar and a visual sensor carried by an unmanned aerial vehicle, a three-dimensional forest region map is constructed, and a single tree is identified and positioned by using a tree body identification model; evaluating the leaf density of the canopy; identifying diseases and insect pests by utilizing multispectral imaging, and making a pesticide proportioning decision according to the disease and insect pest types and severity; planning and generating an optimal flight path for spraying of the unmanned aerial vehicle; adjusting nozzle parameters according to the leaf density of the canopy and the severity of diseases and pests, performing variable spraying, and storing the spraying operation parameters of the unmanned aerial vehicle. Through multi-source sensor fusion, an intelligent decision algorithm and precise spraying control, autonomous obstacle avoidance, high-precision map construction, tree body recognition and canopy analysis, pest and disease damage detection and dynamic pesticide dispensing and spraying in a forestry scene are realized, the forestry spraying efficiency is remarkably improved, and pesticide waste is reduced.

The invention discloses a monitoring system for forest ecological carbon sink calculation, and belongs to the field of ecological environment monitoring and carbon sink evaluation. Comprising a foundation optical remote sensing module, a crown biomass calculation module, a soil carbon component identification module, a vertical carbon flux detection module, a regional microclimate analysis module, a time sequence big data coupling module, a carbon source and carbon sink model fusion module and a result correction feedback module. The method comprises the following steps: collecting vegetation three-dimensional structure data through a multi-frequency laser radar, calculating unit-area canopy carbon storage acceleration in combination with seasonal climate interference parameters, and fusing turbulent carbon exchange and soil carbon change data to construct a regional carbon flux coupling model; the system collects cross-rosa chinensis carbon change data to construct a multi-dimensional feature tensor diagram, dynamically updates a weight and a fitting function, realizes carbon sink dynamic estimation and feedback optimization based on a biology-climate-time three-dimensional cooperation mechanism, and improves forest carbon sink monitoring precision and stability. The beneficial effect is that scientificity and accuracy of ecological environment monitoring and carbon sink evaluation are improved.

The present invention relates to a method for remotely and / or autonomously harvesting a tree from air. The method comprises detecting by at least one sensor on a UAV (100) a tree to be harvested, positioning a harvesting tool (105) comprising delimbing means (114) carried by the UAV (100), by using information from the at least one sensor, at a predetermined distance above a canopy of the tree to be harvested, releasing the harvesting tool (105) in a first mode from the UAV (100) from the predetermined distance above the canopy of the tree to be harvested, setting the harvesting tool (105) in a second mode when the harvesting tool (105) has the tree top (131) within its tree receiving area (177). At least a portion of the harvesting tool (105) is below the tree top (131) of the tree to be harvested while the harvesting tool (105) has a certain speed >0 in a downward direction. The first and second mode differ with respect to the tree receiving area (177) of the delimbing means (114) in the harvesting tool (105). The tree receiving area (177) refers to the area in between open and closed delimbing means (114).

The invention provides a crop planting area intelligent extraction method and system based on multispectral remote sensing, and relates to the field of remote sensing image processing, and the method comprises the steps: obtaining and correcting a multiband remote sensing image; calculating a vegetation index and constructing a crop growth characterization index to extract canopy features; obtaining a multi-period feature map, calculating a spatial distribution entropy, and establishing an evaluation function to determine a time sequence fusion weight; a spatial constraint function is established based on the spectral distance, and a segmentation criterion is constructed by combining the spatial constraint function with time sequence features for classification iteration. According to the method, the accuracy and the discrimination degree of crop planting area extraction are improved, and crop identification requirements in a complex agricultural environment are met.

The invention relates to the technical field of intelligent agriculture, in particular to a variable pesticide spraying method and system based on crop canopy recognition. The method comprises the following steps: acquiring canopy structure data; sparse anchor point data are obtained according to the canopy structure data; performing canopy segmentation according to the sparse anchor point data to obtain canopy segmentation data; performing canopy feature extraction on the canopy segmentation data to obtain canopy feature data; performing penetration demand measurement estimation according to the canopy feature data to obtain penetration demand measurement data; obtaining nozzle parameter data; obtaining nozzle control data according to the nozzle parameter data and the penetration demand measurement data; and performing operation monitoring according to the nozzle control data to obtain nozzle operation data so as to perform spraying uniformity feedback to obtain spraying uniformity data. According to the invention, through fusion of canopy structure identification and spraying path modeling, precise matching of the pesticide spraying direction, the spraying amount and the penetration demand is realized, and the spraying uniformity and the pesticide utilization efficiency are significantly improved.

The invention provides a wind power plant dynamic inertia partition evaluation method based on improved clustering, and relates to the technical field of wind power plants. The method comprises the following steps: taking a Canopy clustering algorithm as a preprocessing step through improved Canopy-Kmeans; the mean value point of the collected data set is calculated, and the measuring point closest to the mean value point is selected as the initial clustering center, so that the result is more reasonable and stable. The grouping precision is improved by considering the wake effect and the time delay effect and measuring multi-dimensional wind turbine generator state variables, in order to avoid a large amount of data dimensionality disasters, PCA principal component analysis is adopted for data dimensionality reduction, components with the variance contribution rate being 85% or above are selected as dominant variables, and the complexity of data collection is reduced. According to the method, the improved Canopy algorithm and the k-means algorithm are combined, the optimal classification number k value and the clustering center can be recognized more accurately, and then large-area wind turbine generator partitioning is achieved quickly and accurately.

The invention belongs to the technical field of chlorophyll content inversion, and discloses a canopy chlorophyll content inversion method based on feature extraction and a machine learning model, and the method comprises the following steps: employing a mode of combining an unmanned plane carrying a multispectral camera and ground actual measurement; collecting and processing the chlorophyll content data of the potato canopies, and planting a quilt index; carrying out feature selection by using a Pearson correlation analysis and competitive self-adaptive reweighted sampling algorithm; constructing a chlorophyll content inversion model based on machine learning; and carrying out chlorophyll content inversion model optimization based on a grey wolf optimization algorithm and a sparrow optimization algorithm, and carrying out precision evaluation. According to the canopy chlorophyll content inversion method based on feature extraction and the machine learning model, comparative study is carried out on the single growth period and the whole growth period of potatoes, the optimal inversion model suitable for the single growth period and the whole growth period is determined, and the accuracy and applicability of the study are guaranteed.

The invention provides a crop yield prediction method and system based on image analysis, relates to the field of yield prediction, and obtains a farmland multi-view remote sensing image through an unmanned aerial vehicle multispectral sensor, and executes aerial triangulation and ortho-rectification to obtain accurate exterior orientation elements and ortho-images. Then, vegetation indexes are extracted and combined with field yield measurement data, a yield regression model is constructed, and rapid prediction and grading of the crop yield are achieved. In order to reduce multi-view brightness inconsistency and give consideration to crop growth characteristics, prior information such as canopy row direction, leaf angle distribution and sealing degree is introduced, iterative correction is performed on the image by adopting a BRDF model, and radiation difference is corrected while geometric accuracy is guaranteed. Particularly, through staged trend analysis and multiple rounds of detection, priori conflicts can be found in time, incremental images can be flexibly collected, and resolving robustness and yield prediction precision are improved. The method can be widely applied to unmanned aerial vehicle remote sensing agricultural monitoring scenes.

The invention provides a rice growth model construction method and system based on salt stress, and relates to the technical field of growth model.The rice growth model construction method comprises the steps that firstly, monitoring points are arranged in a planting sample area, and soil conductivity data of different depths are obtained through a multi-depth soil conductivity sensor and a Kriging interpolation method; collecting root system density, a multispectral remote sensing image and a leaf area index, and calculating a canopy salt stress index; measuring the concentration of related ions to obtain a sodium adsorption ratio, and establishing a salt stress coefficient by combining the soil conductivity and the irrigation volume; fusing canopy and soil stress indexes to generate a stress comprehensive index, and introducing a salinity feedback item to represent the crop compensation capability; and finally, constructing a hybrid machine learning model by adopting a convolutional neural network and a long-short-term memory network to realize rice growth dynamic prediction. According to the method, multi-dimensional salinity stress quantification of a soil-crop system is realized, and decision support is provided for salinization treatment in precision agriculture.

The invention relates to a variable-depth, variable-position and variable-quantity intelligent fertilizer applicator based on the size of a tree crown, and belongs to the technical field of agricultural and forestry machinery. The machine comprises a power device, a fertilizing device, a spiral ditching device, an intelligent identification device and an intelligent control system which are supported on a rack, wherein the rack is arranged on a walking device. The fertilizer applicator can realize integrated operation of intelligent ditching, fertilizer application and soil and fertilizer stirring in agricultural planting environments such as orchards and the like, and meanwhile, can intelligently find an optimal root zone position and adjust the ditching depth, the fertilizer application position and the fertilizer application amount according to the size of a fruit tree crown and the distance of a tree machine, so that the ditching efficiency and the fertilizer utilization rate are improved.

The invention provides a fruit tree canopy three-dimensional model reconstruction method and a fruit tree canopy three-dimensional model reconstruction system based on multi-modal data, and relates to the technical field of fruit tree canopy three-dimensional model reconstruction based on multi-modal data. Sub-pixel-level space registration is achieved by means of ground control points, voxelization division is carried out based on the range of a point cloud bounding box, and the number of point clouds is screened to construct an initial seed set; and adopting a structure-spectrum collaborative growth strategy, taking the adjacent voxels which are not accessed as candidate voxels, calculating a spectrum similarity mean value of the candidate voxels and directly adjacent voxels in the seed set, stopping growth when no new voxels are added in continuous three times of iteration, and outputting a final seed set. Meanwhile, the set is converted into a three-dimensional canopy model fusing space coordinates and full-wave-band spectral reflectivity, voxel-level pathological labeling is achieved based on the chlorophyll sensitivity index and the blue-red slope, and the whole process of reconstruction and analysis is completed.

According to the permanent basic farmland quality intelligent monitoring system and method provided by the invention, accurate monitoring and dynamic management are realized through multi-module cooperation, the terrain gradient and canopy height are calculated based on LiDAR point cloud, the complexity index is generated in combination with meteorological data, and the A * algorithm is improved to optimize the unmanned aerial vehicle inspection path. The method comprises the following steps: extracting hyperspectral data to analyze soil and crop states, calibrating an electrode response curve, calculating a bio-availability index in combination with temperature and humidity, dynamically adjusting an early warning threshold value, identifying abnormal data by adopting an isolated forest algorithm and carrying out grading processing, and constructing a space-time cube by adopting space-time Kriging interpolation and CNMF algorithm and fusing multi-source data. According to the method, indexes such as ecological protection grades and economic values are integrated to generate a graded soil quality index model, a disease thermodynamic diagram is generated, key data are stored in a chaining mode, and farmland quality real-time monitoring, risk early warning and ecological economic balance decision making are achieved through multi-source heterogeneous data fusion, dynamic weight optimization and block chain technologies.

The invention discloses a winter wheat LAI and SPAD estimation method based on a lightweight semi-supervised model, and relates to the technical field of agricultural remote sensing monitoring, and the method comprises the steps: obtaining multispectral image data of a winter wheat key growth period, and carrying out the preprocessing of the multispectral image data to generate a standardized multichannel vegetation index image; the method comprises the following steps: constructing a lightweight semi-supervised model MCVI-SANet, and carrying out self-supervised training on the MCVI-SANet by adopting a semi-supervised training strategy driven by VICReg; and inputting the multi-channel vegetation index image into the trained MCVI-SANet, and outputting quantitative estimation results of the LAI and SPAD of the winter wheat. Through combination of a saturation perception mechanism and semi-supervised learning, estimation deviation caused by dense canopy vegetation index saturation and data noise is effectively eliminated, and the estimation precision and generalization ability in a complex agricultural scene are improved while the lightweight deployment characteristic of the model is ensured.

The invention discloses a method and equipment for monitoring crop growth, and belongs to the technical field of crop growth monitoring. The method for monitoring crop growth comprises the following steps: acquiring a multispectral image of crop vegetation and environmental data of a crop canopy and below the canopy; processing the multispectral image of the crop vegetation to calculate a vegetation index; selecting a specific vegetation index from the vegetation indexes; obtaining environment data after dimension reduction; environment data and vegetation indexes with high correlation with the CGI are extracted; and inputting the environmental data and the vegetation index into the CGI prediction model to obtain a CGI prediction value of the monitored crop. The equipment for monitoring the growth vigor of the crops can comprehensively monitor the crops in a close planting environment. According to the method, the crop growth is represented by adopting the comprehensive growth vigor grade evaluation index CGI, the crop growth vigor can be reflected more comprehensively and accurately, and the combined CGI prediction model is adopted, so that the method has the capability of accurately predicting the growth vigor of close-planting crops in a complex environment, especially in a complex environment.

The invention provides a cultivated land quality monitoring system based on cultivated land protection. The cultivated land quality monitoring system comprises a multi-source sensing module, a heterogeneous transmission module, a space-time database module, a quality degradation prediction module, a dynamic early warning module, a repair decision module and a quality traceability block chain module. The multi-source sensing module collects data such as soil pH value, organic matter content, heavy metal concentration, crop canopy temperature and vegetation index; the heterogeneous transmission module carries out encryption packaging and format standardization on the data; the space-time database module stores the processed data and space-time associated information; the quality degradation prediction module generates multi-dimensional monitoring data and predicts a degradation risk; the dynamic early warning module generates a multi-stage early warning signal according to the risk value; the restoration decision module outputs soil improvement engineering technical parameters and ecological compensation schemes; and the quality traceability block chain module realizes data verifiable evidence storage. The intelligent level of cultivated land protection can be improved, and comprehensive technical support is provided for sustainable utilization of cultivated land quality.

The invention relates to a forest cultivation dynamic monitoring method and system based on a remote sensing technology, and the method comprises the steps: collecting point cloud and multi-source topographic data of a complex topographic region through the fusion of an airborne laser radar and a satellite radar technology, and generating a high-precision point cloud and topographic parameter matrix through denoising and registration; a segmentation threshold value is dynamically optimized in combination with topographic features, the canopy point cloud penetration rate of abrupt slope and valley areas is improved, and the problem of canopy missegmentation caused by uneven point cloud density under a complex terrain is solved; constructing a penetration rate compensation model driven by terrain influence factors, correcting laser radar point cloud deviation and inverting high-precision tree height, crown breadth and biomass parameters; and based on fusion analysis of the multi-temporal vegetation index and a machine learning model, early warning of diseases and insect pests and fire hazards and dynamic evaluation of a man-made forest cultivation effect are realized. According to the method, the bottleneck of complex terrain monitoring is broken through, the forest parameter inversion precision and the real-time response capability are remarkably improved, and technical support is provided for precise management of forestry resources.

The present invention discloses a multi-modal system for real-time plant hydration monitoring and irrigation management. The system comprises at least one acoustic sensor configured to emit controlled sound waves through plant tissues and detect corresponding vibrations and resonance frequencies using sensitive microphones or piezoelectric sensors to assess plant hydration. The system includes at least one bioelectrical sensor for monitoring bioelectrical signals. At least one nanotechnology-based sensor is configured to detect molecular changes in water content within plant cells through embedded or externally applied nanosensors. An aerial imaging device mounted on an unmanned aerial vehicle captures data related to canopy temperature, leaf color, and hydration indicators using infrared, multi-spectral, and thermal cameras. A central processing unit receives and analyzes data using predictive models, integrates the data via data fusion algorithm to generate a plant hydration profile, and controls water delivery through an irrigation management unit based on the hydration profile.

An insect monitoring system for use in agricultural fields is provided. The monitoring system has a chemical lure to attract insects to the monitoring system, and an adhesive material on which insects drawn to the lure can be trapped for later evaluation. The monitoring system also has a three-piece canopy made of two opposing sides and a cover. The parallel sides are roughly triangular and the cover sits above, and is attached to, the sides. The adhesive trap is held vertically between the two opposing sides of the canopy. The lure is held horizontally above the adhesive trap by being inserted through slits in the cover. The canopy can be assembled from a flat sheet of a prepatterned rigid material.

The invention relates to the technical field of biomass monitoring, and provides a forest above-ground biomass estimation method and device based on stereo density, and the method comprises the steps: obtaining various canopy height information and quadrat AGB stereo density from ground survey data, and obtaining forest features from airborne laser radar data; carrying out regression analysis on at least one of the various canopy height information and the quadrat AGB stereo density and the forest features to obtain the AGB stereo density of the flight area; stepwise linear regression analysis based on the regional scale is carried out on the AGB stereo density and the target parameters of the flight area to obtain an AGB stereo density estimation result, and a regional scale AGB estimation result is determined according to the AGB stereo density estimation result, the various canopy height information and the corresponding pixel areas. According to the method, planar AGB density calculation is converted into three-dimensional AGB density estimation, and the accuracy of the forest above-ground biomass estimation result in a complex scene is improved.

The invention relates to the technical field of crop monitoring, in particular to a crop phenotypic parameter automatic calculation and extraction method based on a multi-source remote sensing image. Comprising the steps that all images are determined to be in the same coordinate system through geographical registration, point cloud file conversion and ground specific point matching, and image registration is achieved; performing automatic or semi-automatic segmentation on the images determined in the same coordinate system to obtain a multi-source crop remote sensing image cell segmentation map; extracting plant phenotypic parameters, physical parameters and chemical parameters from the multisource crop remote sensing image cell segmentation map by using an algorithm; the plant phenotype parameters comprise a vegetation index, a plant height, a surface area, a volume, a canopy coverage degree and a vegetation projection area; the physical parameters comprise a canopy average temperature value, a canopy temperature standard deviation and a canopy temperature variation coefficient; the chemical parameters comprise chemical elements such as nitrogen, phosphorus, potassium, calcium and magnesium in soil and vegetation. The method has the advantages that large-scale data processing and high-precision area prediction are realized, and the crop growth monitoring capability is enhanced.

The disclosure provides an improved canopy height correction method. The method includes: obtaining GEDI LiDAR data, airborne canopy height data, GDEM with high resolution and land cover product within the selected target area and timeframe; performing quality filtering and spatial-scale filtering on GEDI footprints; extracting laser pointing parameters and waveform parameters; extracting reference canopy height from airborne data for each footprint; extracting laser pointing parameters and waveform parameters; preprocessing the GDEM and calculating topographic parameters, including topographic variability index (TVI); constructing the Laser Pointing and Topographic Index (LPTI) according to the 3D forest-ground geometry model; inputting the waveform parameters, even topographic parameters, TVI and LPTI as independent variables, and the reference canopy height as the dependent variable to modeling an improved forest canopy height extraction, and utilizing the improved canopy height extraction model to correct the twofold influence of topographic on GEDI canopy height extraction.

The invention discloses an apple anthracnose leaf blight recognition five-dimensional data fusion method based on a patrol robot, relates to the technical field of anthracnose leaf blight recognition, and solves the problems of limited sensing dimension, large illumination interference and inaccurate spatial positioning in the prior art. Comprising the following steps: S1, acquiring surface curvature characteristics of apple leaves, collecting RGB-D images of the leaves, constructing a three-dimensional topological structure of the leaves, and positioning scab space distribution; s2, acquiring spectral reflection information of apple leaves, quantifying biochemical components of chlorophyll a and carotenoid, and constructing a vegetation index feature set sensitive to diseases; s3, apple tree canopy temperature information is collected, a transpiration anomaly detection model is constructed, and multi-modal fusion of thermal infrared and point cloud data is realized; and S4, integrating spatial distribution, spectral reflection and thermal radiation information, constructing a five-dimensional phenotypic characteristic matrix model, and comprehensively analyzing apple phenotypic characteristics. According to the method, the recognition accuracy under the conditions of blade shielding, uneven illumination, blade posture change and environment interference can be remarkably improved.

The invention discloses a vision-based agricultural unmanned aerial vehicle terrain following method and device. The method comprises the steps of S1, performing off-line adversarial training on a GAN network; s2, fusing infrared and visible light images obtained in real time by using a trained GAN network generator to enhance terrain information; s3, estimating the crop canopy distance by using the depth estimation model; s4, taking the obtained crop canopy depth map Dp as a constraint of an objective function, and comprehensively considering other constraint conditions to construct the objective function so as to optimize trajectory planning; s5, optimizing the objective function by adopting a genetic algorithm, and taking an optimized curve as a flight path of the unmanned aerial vehicle to realize terrain following flight; the system can be applied to crop monitoring, pesticide spraying and the like, is particularly suitable for agricultural operation in complex terrains such as hills and mountainous regions, improves the production efficiency and the operation quality, and promotes informatization and intelligentization development of agricultural machinery equipment in China.

The invention provides a small-region forest carbon sink accurate estimation method and system based on multiple constraints, and the method comprises the steps: respectively generating a canopy height model, a leaf area index and a chlorophyll content through obtaining unmanned plane laser radar data and multispectral data; generating a digital elevation model by adopting a lowest point filtering technology, realizing individual tree segmentation in combination with a gradient map and a watershed algorithm, and extracting individual tree geometric parameters; and constructing a carbon sink estimation model by using the geometric parameters and the physical and chemical parameters, and comprehensively calculating the carbon sink amount of the small region. The problems that a traditional carbon sink estimation method is insufficient in precision and low in automation level are solved, the single-tree segmentation precision and the carbon sink amount calculation precision are improved through deep fusion of geometric information and spectral information, full-process automation of data acquisition, data processing and carbon sink estimation is achieved, and the method is suitable for large-scale popularization and application. The method is suitable for carbon sink monitoring requirements of various forest types and complex terrain scenes.