813 results about "Orchard" patented technology

The invention discloses a bird identification method based on sound-image multi-modal fusion. The bird identification method comprises the following steps: S1, carrying out standardized frame-level preprocessing on bird audio signals; s2, acoustic features are extracted and enhanced, and an acoustic high-level feature vector which highlights birdsong discrimination information and suppresses environmental noise is obtained; s3, visual image standardization preprocessing; s4, performing visual feature extraction and multi-scale fusion to obtain a visual high-level feature vector which enhances correspondence to the bird key form area and inhibits background interference; s5, performing dynamic weighted fusion on the decision-making layer to obtain a bird existence probability; and S6, comparing the bird existence probability with a preset threshold value of the corresponding bird, and judging whether the bird exists or not and the type of the existing bird. Through cross-modal feature enhancement and adaptive fusion, the precision, robustness and real-time performance of bird recognition in a complex orchard environment are significantly improved, and a core technical support is provided for green intelligent bird repelling.

The invention relates to the technical field of intelligent agriculture, and particularly discloses an orchard intelligent water and fertilizer integration-based edge end fruit tree fertilizer demand prediction method, which comprises the following steps of: constructing each fruit tree as a graph node, and fusing canopy spatial characteristics extracted by unmanned aerial vehicle multispectral remote sensing and nutrient time sequence characteristics monitored by a soil sensor; space influence weights among nodes are calculated according to the terrain, the soil texture and the space distance, and a fruit tree individual relation graph is established; then, through a space-time diagram convolutional network, aggregating space neighborhood features and capturing time dynamic changes, and outputting target state features subjected to multi-scale enhancement; when the canopy conflicts with the soil characteristic indication, combined diagnosis is carried out based on a neighborhood consistency index and an adjacent node state, systematic nutrient stress and local non-nutrient factors are distinguished, and final fertilizer demand prediction is generated after the conflict is eliminated; a digital fertilization prescription map is generated through spatial interpolation, soil characteristics and slope correction, and the water and fertilizer integrated equipment is driven to execute precise operation.

The invention discloses a juicy peach yield prediction method based on comprehensive data analysis, and particularly relates to the technical field of agricultural intelligent perception. The method comprises the following steps: collecting multi-source data of an orchard, and constructing a data set containing meteorological, physiological, remote sensing and soil information; fruit tree physiological response parameters are extracted, and a bimodal diagram structure fusing the spatial adjacency relation and the physiological state similarity is established in combination with the dynamic climate anomaly index; inputting the graph structure into a graph neural network model, extracting spatial-temporal characteristics, dynamically adjusting an edge weight and a propagation layer number, and constructing an adaptive model; performing region division and weighted summarization according to a model output result, and finally obtaining a predicted value of the total yield of the orchard; the method improves the prediction accuracy under the conditions of complex climate and unstable data, and is suitable for refined orchard management.

The invention belongs to the technical field of remote sensing, and discloses a wolfberry planting distribution high-precision remote sensing monitoring method based on multi-temporal fusion and spectral feature optimization. According to the method, a multi-temporal and multi-spectral satellite image is used as a data source, and preprocessing and multi-temporal image fusion are firstly carried out; the method comprises the following core steps: establishing a time sequence characteristic curve according to a unique phenological period (such as bare soil characteristics in a dormancy period and high vegetation coverage in a rapid growth period) of wolfberry; in a spectral domain, screening out a characteristic spectrum dimension combination with the highest discrimination degree between the wolfberry and other crops through a characteristic wave band optimization algorithm (such as vegetation index difference degree and red edge characteristics); and in combination with an object-oriented classification or deep learning classification model, constructing a space-time coupling classifier, and performing high-precision extraction and distribution mapping on the Chinese wolfberry planting region. The method can effectively solve the problem of confusion classification of Chinese wolfberry and similar ground features (such as other shrubs and orchards), and realizes rapid and accurate monitoring of Chinese wolfberry planting area and spatial distribution.

The invention relates to a fruit tree growth phenotype dynamic acquisition method and system based on multi-modal perception fusion. Belongs to the field of fruit tree growth detection, and establishes a fruit tree whole growth period growth dynamic knowledge graph by fusing structure and growth phenotype data of fruit tree individuals and groups collected by laser radar, machine vision, remote sensing and other multi-source sensors to realize space-time modeling and automatic identification of tree body structures, growth states and key growth periods. Knowledge reasoning and decision-making algorithms are further combined, and intelligent management services such as fruit tree nutrition diagnosis, pruning suggestion and yield prediction are provided. The fruit tree phenotype data acquisition, analysis and utilization efficiency is improved, refined, intelligent and digital management of fruit trees is realized, and the method can be widely applied to the field of modern orchard digital twinning and intelligent agriculture.

The invention relates to the technical field of mobile robot autonomous navigation path planning, and discloses a complex orchard scene-oriented hybrid sampling global path planning method, which comprises the steps of adopting a Gaussian hybrid sampling strategy, switching between global uniform sampling and Gaussian offset sampling through a probability threshold, and considering global exploration and key area guidance; a dynamic node expansion strategy is adopted, the expansion step length is adaptively adjusted according to the distance between the expansion step length and a target point, and the expansion direction is optimized by fusing vectors facing a sampling point and the target point and introducing an obstacle influence factor; a layered collision detection strategy is adopted, and step-by-step filtering is carried out through rough detection based on a quadtree, secondary screening based on an axis alignment bounding box and accurate geometric judgment in sequence so as to improve the efficiency; and a dynamic iteration termination mechanism is adopted, and the minimum number of iterations and the path quality convergence state are combined as composite termination conditions. The method can quickly generate a smooth and safe path, and is especially suitable for structured scenes such as orchards.

The invention discloses an early-stage intelligent monitoring system for citrus reiculata Blanco canopy diseases and insect pests based on multispectral imaging, and belongs to the technical field of agricultural information. The system comprises a multispectral imaging module, a three-dimensional point cloud acquisition module, a data fusion module, a time sequence data analysis module, an intelligent identification module and a monitoring result output module. The method comprises the following steps: synchronously acquiring a multispectral image and laser radar point cloud data of a citrus reiculata tree canopy, and generating a point cloud model through spatial registration fusion; continuously recording model data of a plurality of time points, and extracting a time sequence feature vector; identifying disease and pest types and severity by using a deep learning model; and outputting a result to the user terminal. According to the invention, the problem that large-range and high-precision early monitoring of diseases and insect pests of citrus reiculata canopies is difficult to realize in the prior art is solved, early discovery, precise positioning and trend early warning of the diseases and insect pests are realized through air-space-ground integrated data fusion and intelligent analysis, and the intelligent level of orchard management and the disease and insect pest control efficiency are effectively improved.

The invention provides a method for identifying and picking flat peaches in a growth period in a natural orchard environment, and belongs to the technical field of computer vision and intelligent agriculture. The problems that branches and leaves in a natural orchard are seriously shielded, characteristics of flat peaches in different growth periods are different, identification is difficult, and positioning accuracy is low are solved. In order to solve the problem, the invention constructs an identification model OGD-Net for the growth period of the flat peach in the natural orchard environment; the method comprises the following steps: firstly, enhancing data through Cutout, and improving the detection robustness of a model under the shielding of branches and leaves; lightweight context is introduced into the backbone network to guide down-sampling and gate control frequency domain dynamic convolution, and perception of texture and color is enhanced while the calculation amount is reduced; an orchard adaptive feature fusion pyramid is designed, and a space-channel dual attention mechanism is combined, so that the positioning error is effectively reduced; the detection head introduces space to enhance attention, and the attention degree of a key area is improved. Precise recognition and center point positioning of the flat peach growing period are achieved, automatic operation from recognition to picking is achieved in combination with coordinate transformation and mechanical arm control, and the picking success rate is remarkably increased.

The invention discloses an orchard unmanned aerial vehicle multispectral image noise restoration method based on a generative adversarial network, and relates to the technical field of multispectral image noise restoration, and the method comprises the steps: synthesizing a noisy sample containing stripes, photon particles, thermal noise, Rayleigh, shielding, compression artifacts, overexposure and waveband crosstalk on a noise-free reference image through a conditional generative adversarial network; a crosstalk matrix T obtained through optical calibration is introduced; based on the canopy / soil / sky semantic partition, main-cooperation-subdivision level superposition is implemented; generating hierarchical labels by taking energy conservation consistency and thermal noise correlation as thresholds; a branch and region self-adaptive repair module corresponding to classification is arranged in the image-to-image generative adversarial network, and joint loss training containing T regularization is adopted; and outputting the repaired image subjected to physical consistency checking. The method gives consideration to visual quality and spectral fidelity, inhibits cross-band pollution, improves the stability of indexes such as NDVI and NDRE, and is suitable for precision agricultural monitoring.

The invention discloses a self-adaptive apple maturity lossless picking flexible claw and a picking method. The device comprises a base assembly, and a visual recognition module, a flexible clamping jaw assembly, a distributed pressure sensing module, a transmission execution module and a control unit are integrated on the base assembly. And the visual module adopts a depth camera and a YOLO11n model, judges the maturity grade in real time based on the apple red area proportion and is matched with the corresponding grabbing threshold force. The pressure sensing module is a thin film pressure sensor, and multi-point pressure feedback is achieved through a plurality of pressure detection points. The transmission module adopts a single motor to drive a lead screw nut lifting table, opening and closing of clamping jaws are synchronously controlled, the structure is light and simple, and cost is low. The picking method follows the process of recognition, matching, force control and picking, a cutter is not needed, lossless and high-success-rate self-adaptive picking is achieved, the problem of damage or failure caused by traditional fixed force control is effectively solved, the method is suitable for dense orchards, and the intelligent and lossless levels of apple picking are improved. The control unit is low in response delay and small in overshoot, and it is ensured that the grabbing force is accurately matched with the fruit state.

The invention discloses an orchard crawler differential robot trajectory tracking method based on adaptive incremental control, and relates to the technical field of agricultural robot control. The method comprises the following steps: receiving environmental data collected by a robot sensor, constructing a probability grid map of an orchard environment according to the environmental data, and aligning the probability grid map with a pre-constructed map inertial coordinate system; the course angle error and the distance error between the current position and a target point are calculated based on the pose of the robot, an error vector is formed, and the target point is dynamically planned according to the fruit maturity and reachability priority detected by a visual system and a laser radar point cloud. According to the method, coordinate transformation is not needed, and different from traditional tracking control, a control instruction is generated directly based on pose increment, the course and distance error of a target point is calculated directly based on an inertial coordinate system, and real-time matrix projection operation is avoided.

The invention relates to an intelligent soil regulation and control method based on soil data and image processing. The method comprises the following steps: acquiring and standardizing soil data; orchard global multispectral image acquisition: acquiring and preprocessing an orchard image, and acquiring an orchard global multispectral image; vegetation region identification and parameter calculation: calculating NDVI based on red light and near infrared bands, distinguishing green manure and fruit tree regions through a threshold segmentation method, and calculating green manure coverage, a green manure normalized vegetation index and a fruit tree canopy area; carrying out soil-vegetation data fusion and parameter extraction; distributing weights based on the three types of core parameters, calculating the application amount and type ratio of nitrogen, phosphorus and potassium fertilizers, and generating an initial regulation and control scheme; and repeating the steps every specified time period to realize dynamic iterative optimization of the scheme. Through deep fusion of soil data and an image processing technology, intelligent soil regulation and control are realized, regulation and control accuracy and timeliness are remarkably improved, and fertilizer waste and environmental risks are reduced.

The invention discloses an unmanned aerial vehicle plant protection path optimization method in a hillside orchard environment. The method comprises the following steps: acquiring parameter information of mountain terrain, terraced fields and obstacles in the hillside orchard environment; clustering the terraced fields according to the parameter information of the mountain terrain, the terraced fields and the obstacles to obtain a clustering result of the terraced fields and risk grade evaluation indexes of clustering clusters; allocating an unmanned aerial vehicle to each terrace in each cluster based on a terrace clustering result and a risk grade evaluation index of the cluster; a global path optimization model is constructed with the purpose of minimizing the cross-regional operation cost, and a global path of the unmanned aerial vehicle and the served terraced field is obtained; and constructing a local path optimization model, and obtaining the spraying path of the unmanned aerial vehicle in the single terrace. The problems of path planning, task scheduling, resource allocation, multi-target optimization and the like caused by complex terrains, various obstacles, limited unmanned aerial vehicle resources and the like in a hillside orchard scene are solved, and efficient, safe and accurate orchard plant protection operation is achieved.

The invention belongs to the technical field of agricultural informatization, and particularly relates to a non-destructive testing method and system for the preharvest citrus sugar degree based on a hyperspectral image. The method comprises the following steps: acquiring hyperspectral image data and sugar degree data of pre-harvest citrus samples; based on an improved CNN-FA-RB model, constructing a sugar degree detection model; constructing a training data set based on the hyperspectral image data and the sugar degree data, and training the sugar degree detection model by using the training data set; and based on the trained sugar degree detection model, realizing nondestructive detection and spatial distribution visualization of the pre-harvest citrus sugar degree. According to the method, an improved deep learning model is used, nondestructive testing of the preharvest citrus sugar degree in the outdoor orchard environment is achieved, and the method can be applied to preharvest citrus maturity judgment and analysis.

The invention provides a method for regulating and controlling phenological periods of outdoor pear trees, and belongs to the technical field of pear tree cultivation. According to the phenological period delaying method suitable for the outdoor cultivation pear orchard in the south, the phenological period of pears can be delayed by 5-7 days through grass growing in winter, grass covering in early spring and irrigation in early spring, soil temperature rising is restrained, root activity recovery is restrained, and the phenological period of pears can be delayed by 5-7 days. Specifically, by maintaining high soil water content and low soil temperature, inhibiting respiration and physiological activity recovery speed of root systems of pear trees in spring and delaying absorption and transfer of moisture and nutrients by the root systems, the metabolism level of the tree bodies is reduced, and the phenological period of the pear trees is delayed by about 7 days. Through the synergistic effect of vegetation covering and moisture regulation, accurate delay of the phenological period of the pear tree is achieved, operation is easy and convenient, the ecological cultivation requirement is met, and the method is suitable for open-air pear cultivation areas in the south.

The invention discloses a method for improving soil fertility of an orchard in a Yellow River old lane area. The orchard is covered with green grass; after the fruits are harvested and before leaves fall, a first fertilization ditch is dug at a crown water drip, and smashed straw, base fertilizer and surface soil are sequentially laid in the first fertilization ditch from bottom to top; meanwhile, digging 3-4 radial second fertilization ditches according to a water drip from a trunk to a crown, sequentially laying dry branches and fallen leaves, wheat straws and livestock and poultry manure in the second fertilization ditches from bottom to top, and putting earthworms into surface straws of the second fertilization ditches; a humic acid-containing water-soluble fertilizer is applied in a drip irrigation manner during topdressing. Therefore, through the synergistic effect of multiple technical measures such as orchard grass covering, organic fertilizer layer application, earthworm density increasing and bio-fertilizer application increasing, a benign soil ecological system is constructed, and therefore the problems that the content of organic matter in orchard soil in the Yellow River old road area is low, and the water and fertilizer retention capacity is weak are effectively solved, the soil fertility is remarkably improved, and the yield of the orchard is increased. And the fruit yield and quality are improved.

The invention provides an orchard building method and a pruning method of a double-layer dwarf open-center-shaped high-photosynthetic-efficiency cultivation pear orchard, and belongs to the technical field of fruit tree cultivation. According to the orchard building method for the high-photosynthetic-efficiency cultivation pear orchard, multiple factors such as the sun drift angle, the day photosynthetic efficiency change around pear trees, the geographic latitude of the orchard and the growth period of pear varieties are comprehensively considered, and the planting row direction and the high-photosynthetic-efficiency tree form are determined and pruned according to the latitude of the place where the orchard is located and the day photosynthetic efficiency change around the pear trees. By means of the orchard building method, by selecting a high-light-effect tree form and a scientific pruning method, controlling the height and size of a tree crown, thinning and removing over-dense branches on the upper portion and adjusting a fruiting branch group, the ventilation and light transmission conditions in the tree crown can be effectively improved, shielding of the tree crown to lower leaves is reduced, and illumination of the lower leaves is further improved. The method is simple and easy to implement, convenient to popularize and apply, and capable of remarkably improving the pear tree photosynthesis efficiency and improving the fruit yield and quality of pears.

The invention provides an orchard robot collision avoidance track method based on a multi-modal algorithm, and aims to solve the problem of high vehicle branch collision risk caused by narrow fruit tree walkway channel and lateral invasion of tree crowns and branches, and the orchard robot collision avoidance track method based on the multi-modal algorithm is provided. Fusing a front sensing trail rectification strategy to generate a branch collision risk value, a danger direction mark and an avoidance sequence, and setting a risk threshold value associated with a safety transverse margin; the method comprises the following steps of: expanding according to a sequence under traffic constraint, rejecting over-threshold actions, generating a candidate track fitting a side line, selecting a main track according to a fitting degree threshold value, performing transverse correction in combination with a crown edge distance threshold value, finally forming a track, and outputting a steering and speed instruction. According to the method, the track which is continuous in curvature, meets the safety transverse allowance and does not enter the dangerous direction can be generated in the short-distance front range, the branch collision risk is reduced, and the traffic safety and trafficability of the orchard robot in the walkway are improved.

The invention provides an unmanned aerial vehicle remote sensing monitoring and evaluating method and system for field orchard diseases and insect pests, and relates to the technical field of orchard disease and insect pest monitoring and evaluating. The interference of complex background noise is effectively eliminated by constructing a ternary separation index integrating feature enhancement, background suppression and brightness normalization; a threshold value is determined based on the exponential distribution, pixels are accurately divided into a non-canopy background, a shadow canopy and an illumination canopy, and fine segmentation of an unstructured scene is achieved; constructing a gain compensation item by using a local illumination reference mean value, correcting a shadow canopy reflectivity curve, and eliminating illumination non-uniform interference; selecting a local high quantile to establish a health reference basis, coupling a discriminant item and an attenuation item, and resolving to obtain a physiological stress index, so as to realize acute capture of early weak disease characteristics; and performing power weighted accumulation on the abnormal pixel difference value, outputting a regional hazard level index, and objectively quantifying the overall disaster risk of the region through nonlinear aggregation.

The invention provides a humanoid apple picking robot which comprises a first humanoid picking mechanism, the first humanoid picking mechanism is installed on a power chassis through a first supporting stand column, and apple picking operation is conducted through two first end effectors on the first humanoid picking mechanism; the second humanoid picking mechanism is installed on the power chassis through a second supporting stand column, two second end executors are movably connected to the second humanoid picking mechanism, and apple picking operation is conducted through the two second end executors. The robot is composed of the two humanoid picking mechanisms, the advantages of a Cartesian mechanical arm and a joint mechanical arm are fused, a heterogeneous complementary cooperative structure is used for replacing a traditional picking mechanical arm with the single height adjustment function, the robot operation space is expanded, the upper-layer and lower-layer operation coverage range is achieved, and the picking efficiency is improved. The fruit picking device is suitable for automatic picking operation in different orchard environments, convenient to use and practical.

The invention discloses hillside orchard fertilization equipment with intelligent detection and precise fertilization, and belongs to the technical field of agricultural fertilization equipment. The hillside orchard fertilization equipment with the intelligent detection and precise fertilization functions comprises a frame, wheel carriers are installed on the two sides of the bottom end of the frame, crawler wheels are installed at the two ends of one side of each wheel carrier, a crawler sleeves the outer sides of the pair of crawler wheels, a first motor is installed on one side of each wheel carrier, and the output end of each first motor is connected with one end of the corresponding crawler wheel; one side of the top end of the frame is provided with an extension arm, one end of the extension arm is provided with a fixing plate, the bottom end of the fixing plate is provided with an extension rod, the bottom end of the extension rod is provided with a soil nutrient sensor, one end of the extension arm is provided with a height adjusting mechanism used for adjusting the height of the fixing plate, and the other side of the top end of the frame is provided with a liquid storage tank. The system can effectively realize integration of intelligent detection and precise fertilization, improves the fertilization efficiency and the fertilizer utilization rate, and has a relatively high practical value.

The invention discloses an efficient composite intercropping method for pomegranate, dry rice and broad bean grain, which scientifically combines pomegranate (economic output), dry rice (grain output) and broad bean (partial economic output and biological nitrogen fixation and land cultivation), realizes functional complementation, and breaks through the single target limitation of the traditional intercropping mode. Through effective connection of crops for rotation of'broad bean sowing in winter and upland rice sowing in spring ', full utilization of light and heat resources and land in the orchard from winter to spring, summer and autumn in the next year is realized, and the multiple cropping index is remarkably improved; the pomegranate utilizes the upper-layer three-dimensional space, and the upland rice and the broad beans utilize the middle-lower-layer space, so that an efficient three-dimensional lighting structure and space combination are formed; the nitrogen fixation effect of the rhizobium of the broad beans can directly increase the nitrogen nutrition of the soil, the straw returning can increase the organic matters of the soil, and the built-in fertilizing mechanism of the orchard effectively relieves the consumption of the intercropping system on the soil fertility and ensures the sustainability of the mode.

The invention discloses a robot orchard inter-row positioning method based on multi-modal semantic graph optimization, and aims to solve the problems of inter-row leakage and inter-row jump in positioning in orchard moving operation. Time synchronization and external parameter calibration are carried out on multi-sensor data, semantic analysis and geometric preprocessing are carried out, and the positioning accuracy of the orchard inter-row positioning method is improved. The method comprises the following steps: generating tree trunk, pile body, tree wall and ground boundary observation, constructing a semantic factor graph containing row identifiers and continuous variables, adopting a graph converter to perform adaptive weighting and covariance calibration, combining soft and hard two-stage increment optimization of anti-fact mutual exclusion gating and discrete continuous combination, outputting the row identifiers, robot trajectories, transverse deviation and course angles, and constructing a semantic factor graph containing the row identifiers and the continuous variables. The technical effects of stably inhibiting the inter-row jump and improving the row identification judgment accuracy and the transverse deviation and course angle estimation precision are achieved.

The invention discloses a single-chain alkylamino glycerol compound, a preparation method and application. The structural general formula of the single-chain alkylamino glycerol compound is R-NH-CH2-CHOH-CH2OH, the single-chain alkylamino glycerol compound is used for preventing and controlling peach monilinia and / or botryosphaeria dothidea, and R is a C8-C18 straight chain or branched chain and saturated or unsaturated alkyl. The single-chain alkylamino glycerol compound provided by the invention can be prepared by reacting glycidol and alkylamine under mild conditions, has a remarkable inhibition effect on peach monilinia and botryosphaeria dothidea, and can induce fungal membrane rupture, anti-oxidation system imbalance and lipid peroxidation, so that fungus killing is realized. The device can be widely used for fruit and vegetable postharvest preservation, orchard spraying and green pesticide development.

The invention relates to an orchard intelligent decision-making method and system based on edge cloud collaboration and multi-modal big data, and belongs to the technical field of agricultural artificial intelligence. Multi-modal time series data such as images, environments and geographic positions are systematically collected through various heterogeneous sensing devices deployed in an orchard, data preprocessing is carried out at edge computing nodes, and the edge cloud collaboration and multi-modal big data are obtained; real-time joint reasoning is carried out by using a lightweight multi-task visual identification model, multi-dimensional information such as fruits, diseases and insect pests and growth states is synchronously obtained, and an identification result and associated data are transmitted to a cloud platform for constructing and updating an orchard knowledge graph and a digital twinborn model; the model can simulate the influence of different management strategies to generate optimal decision suggestions, the decision suggestions are issued to a field intelligent execution terminal, and continuous increment optimization is performed on the model by using feedback data of the field intelligent execution terminal, so that a complete closed loop from perception, decision, execution to feedback optimization is formed, and the optimal decision suggestions are obtained. The intelligent level and the decision-making precision of orchard management are obviously improved.

The invention discloses a laser robot system for removing harmful insects in a large area. The system integrates an autonomous mobile platform, a multi-sensor sensing system, an intelligent decision and control unit and an accurate laser removing device. The system adopts a layered sensing architecture, and comprises a millimeter wave radar used for global human and animal safety monitoring, a two-dimensional laser radar used for planar pest searching and coarse positioning, and a precise tracking radar used for precise positioning and tracking of pests. Through a multi-sensor fusion technology, efficient target identification and accurate removal are realized. The method has the beneficial effects that real global automatic operation is realized, a multi-level high-reliability safety protection system is constructed, the searching and clearing efficiency is improved, and the method has high intelligence and environmental adaptability. The system can be widely applied to harmful insect removal operation in large-area areas such as farmlands, orchards and warehouses.

The application discloses a UWB navigation system and method based on visual feature fusion, and the system comprises four modules of UWB positioning, visual perception, data fusion processing and navigation control. The UWB positioning module adaptively generates a UWB anchor point layout, and after calculating UWB coordinates in real time, UWB positioning data are obtained by calibration according to the coverage rate of fruit trees and soil humidity. The visual perception module collects orchard images, identifies fruit trees and obstacles, obtains visual coordinates and corrects visual positioning data. The data fusion processing module calculates the weight of UWB positioning data and visual positioning data, fuses UWB positioning data and visual positioning data according to the weight to obtain fusion coordinates, and corrects errors to obtain optimal coordinates. The navigation control module calculates target path points according to the optimal coordinates, obstacle recognition results and weeding operation paths, and controls the weeding robot to travel to the target path points. The application realizes high-precision navigation of the weeding robot in the complex environment of the orchard.

The application discloses a kind of semi-structured orchard field ridge area detection method, this method is by picking robot along field ridge with stereo vision camera Real-time acquisition field ridge area image, utilize field ridge shadow area and the different of non-shadow area color and gradient field feature, combined with Gaussian mixture model can realize the detection of shadow area, again through the shadow color weighting compensation algorithm proposed in this paper to remove shadow area, finally through to image denoising filtering, by to image secondary segmentation, again after morphological processing, finally get complete field ridge area;Finally, through edge detection operator to the image after segmentation Edge detection, again to edge point optimization fitting, based on least squares method is carried out edge point fitting, obtains the edge line of field ridge area.This method can be under any illumination conditions 100% detection field ridge area.

The application discloses a kind of orchard environment based on fusion GCNv2 network binocular vision SLAM method and system, comprising: using binocular camera to shoot the stereo image pair of orchard environment;Depth map is generated using stereo matching algorithm as label, construct and train GCNv2 network architecture including attention mechanism and multi-scale feature fusion;Input orchard environment image and extract key point, find left-right image corresponding relationship by descriptor matching, assign corresponding depth value to each matching key point using the depth map predicted by GCNv2 network;Filter feature points and update map with depth information;Loop detection and perform geometric consistency check, execute BA global optimization algorithm to correct errors in the entire trajectory and map;The application provides a kind of efficient, robust and suitable for orchard environment binocular vision SLAM method to improve the navigation ability and automation level of robot in complex orchard environment.

The utility model belongs to the technical field of weeding equipment, and discloses walking orchard weeding equipment which comprises a frame, a walking mechanism is arranged at the bottom of the frame, a power mechanism, a transmission mechanism, a control mechanism and a weeding mechanism are arranged on the frame, the weeding mechanism comprises a fixing pipe fixedly arranged on the lower portion of the frame, and a weeding cutter shaft is rotationally arranged in the fixing pipe; the top end of the weeding cutter shaft is connected with the transmission mechanism, the bottom end of the weeding cutter shaft extends out of the fixing pipe and is provided with a horizontally-arranged main blade, the middle of the main blade is fixed to the weeding cutter shaft, the two ends of the main blade are each rotationally provided with an auxiliary blade, and the main blade and the auxiliary blades are higher than the bottom face of the walking mechanism. The weeding cutter shaft, the main blades and the auxiliary blades are arranged, a certain distance exists between the blades and the ground, only the leaf diameter of weeds on the ground can be cut off in the weeding process, the surface layer of soil and the root system of the weeds cannot be damaged, the ecological environment of a plantation is protected, and therefore the purposes of reducing water and soil loss and storing water and preserving soil moisture are achieved.