A method, device, system and storage medium for cutting yellow leaves of vegetation

Abstract

The present application provides a method, device, system and storage medium for cutting yellow leaves of vegetation, which relates to the field of computer technology. The method includes: when receiving a vegetation yellow leaf detection instruction, obtaining vegetation image data; performing leaf color recognition on the vegetation image data to determine the yellow leaf area containing yellow leaves; extracting the contour information of each leaf in the yellow leaf area, and the contour information contains multiple azimuth coordinate points; determining the center coordinates of each yellow leaf according to the multiple azimuth coordinate points; counting the center coordinates of all yellow leaves in the yellow leaf area, and planning a cutting path according to all the center coordinates, so as to cut the yellow leaves in the yellow leaf area along the cutting path. The present application realizes the cutting of yellow leaves based on image recognition algorithm and spatial path planning, ensures the healthy growth of vegetation, facilitates the maintenance of vegetation, and reduces the manpower burden of vegetation maintenance.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, system and storage medium for cutting yellow leaves of vegetation. Background Art

[0002] At present, the maintenance system mainly focuses on the maintenance of the entire plant growth environment, such as watering, soil temperature and humidity testing, etc., and does not deal with the abnormal growth of vegetation's green leaves turning yellow, which is not conducive to the healthy growth of vegetation. Summary of the invention

[0003] The purpose of this application is to provide a method, device, system and storage medium for cutting yellow leaves of vegetation, so as to realize automatic cutting of yellow leaves through the vegetation yellow leaf cutting device and achieve healthy maintenance of vegetation.

[0004] In order to solve the above technical problems, the present application provides a method for cutting yellow leaves of vegetation, and the specific technical solution is as follows:

[0005] When receiving a vegetation yellow leaf detection instruction, obtaining vegetation image data;

[0006] Performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves;

[0007] Extracting contour information of each leaf in the yellow leaf area, wherein the contour information includes a plurality of azimuth coordinate points;

[0008] Determine the center coordinates of each yellow leaf according to the multiple azimuth coordinate points;

[0009] The center coordinates of all the yellow leaves in the yellow leaf area are counted, and a cutting path is planned according to all the center coordinates so as to cut the yellow leaves in the yellow leaf area along the cutting path.

[0010] Optionally, before performing leaf color recognition on the vegetation image data to determine the yellow leaf area containing yellow leaves, the method further includes:

[0011] The vegetation image data is subjected to image preprocessing according to input data parameters of the neural network model; the preprocessing includes at least one of image size correction, contrast adjustment and image noise reduction.

[0012] Optionally, performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves includes:

[0013] Extracting leaf parameters from the vegetation image data;

[0014] Determine the vegetation type according to the leaf parameters, and obtain yellow leaf parameters corresponding to the vegetation type;

[0015] The leaf parameters and the yellow leaf parameters are compared to determine the yellow leaf area in the vegetation image data.

[0016] Optionally, counting the center coordinates of all yellow leaves in the yellow leaf area, and planning the cutting path according to all the center coordinates includes:

[0017] Acquiring environmental information of the yellow leaf area;

[0018] Performing environmental modeling based on the environmental information to obtain a grid-based environmental model; the nodes in the grid include traversable nodes and intraversable nodes;

[0019] Determine the starting point coordinates, and use all the center coordinates as the end point coordinates;

[0020] Starting from the coordinates of the starting point, iteratively calculate the cost values ​​of the adjacent nodes; if the total cost of reaching the adjacent node through the current node is less than the known cost, then update the cost value of this node and record the parent node; the cost value represents the actual cost from the starting point to the current node;

[0021] Calculating a heuristic value based on an estimated distance between the current node and the target node; the heuristic value represents a heuristic estimated cost from the current node to the target node;

[0022] Taking the minimum sum of the cost value and the heuristic value as the optimization goal, the node with the minimum optimization goal each time is added to the node operation path, until all center coordinates are added to the node operation path, a cutting path is obtained.

[0023] Optionally, if there is a target yellow leaf that is partially blocked by vegetation, when extracting the contour information of each leaf in the yellow leaf area, it also includes:

[0024] Simulating the complete leaf information of the target yellow leaf according to the spatial information of the petiole of the target yellow leaf;

[0025] The center coordinates of the target yellow leaf are determined according to the complete leaf information.

[0026] Optionally, if there is a target yellow leaf that is partially blocked by vegetation, when executing the step of cutting the yellow leaves in the yellow leaf area along the cutting path, it also includes:

[0027] After the obstruction of the target being obscured by the yellow leaves is removed, the target center coordinates of the target being obscured by the yellow leaves are determined, and the clipping path is updated according to the target center coordinates.

[0028] Optionally, after planning the cutting path according to all the center coordinates, the method further includes:

[0029] The kinematic characteristic data of the shearing component is obtained, and the shearing path is optimized by using a high-order interpolation algorithm according to the kinematic characteristic data; the kinematic characteristic data includes motion restrictions and / or speed constraints.

[0030] The present application also provides a vegetation yellow leaf shearing device, comprising:

[0031] A device body comprising a main control module and a mechanical arm connected to the device body; the mechanical arm is used to perform yellow leaf cutting of vegetation according to an operation instruction issued by the main control module; the operation instruction is a cutting path determined after color recognition of vegetation image data and center coordinate positioning of yellow leaves;

[0032] The main control module includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for cutting yellow leaves of vegetation as described above is implemented to generate the operation instruction;

[0033] A camera module is provided in the device body, and is used to obtain the vegetation image data and upload it to the main control module.

[0034] This application also provides a vegetation yellow leaf shearing system, including:

[0035] An image acquisition module is used to acquire vegetation image data when detecting a vegetation yellow leaf detection instruction;

[0036] A leaf recognition module, used for performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves;

[0037] A contour extraction module, used to extract the contour information of each leaf in the yellow leaf area, and determine a number of azimuth coordinate points contained in the contour information;

[0038] A coordinate detection module, used to determine the center coordinates of the yellow leaf according to the plurality of azimuth coordinate points;

[0039] The cutting module is used to count the center coordinates of all yellow leaves and plan a cutting path according to all the center coordinates so as to cut the yellow leaves in the yellow leaf area along the cutting path.

[0040] The present application provides a method for cutting yellow leaves of vegetation, and the specific technical scheme is as follows: when a vegetation yellow leaf detection instruction is received, vegetation image data is acquired; leaf color recognition is performed on the vegetation image data to determine a yellow leaf area containing yellow leaves; contour information of each leaf in the yellow leaf area is extracted, and the contour information includes multiple azimuth coordinate points; the center coordinates of each yellow leaf are determined based on the multiple azimuth coordinate points; the center coordinates of all yellow leaves in the yellow leaf area are counted, and a cutting path is planned based on all the center coordinates, so as to cut the yellow leaves in the yellow leaf area along the cutting path.

[0041] The method for cutting yellow leaves of vegetation provided by the present application first performs color recognition on the leaves to determine the yellow leaf area after obtaining vegetation image data, and then locates the yellow leaves by extracting contour information and locating the center coordinates of the yellow leaves, and plans a cutting path based on the yellow leaf positioning, thereby cutting the yellow leaves along the cutting path. The cutting of yellow leaves is achieved based on image recognition algorithms and spatial path planning, which ensures the healthy growth of vegetation, facilitates the maintenance of vegetation, and reduces the manpower burden of vegetation maintenance.

[0042] The present application also provides a device for cutting yellow leaves of vegetation, a system for cutting yellow leaves of vegetation and a computer-readable storage medium, which have the above-mentioned beneficial effects and are not described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 A flow chart of a method for cutting yellow leaves of vegetation provided in an embodiment of the present application;

[0045] Figure 2 A schematic diagram of a vegetation yellow leaf shearing device provided in an embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the structure of a vegetation yellow leaf cutting system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] The object information involved in this application, including but not limited to the object device information, object personal information, etc., and data, including but not limited to data used for analysis, stored data, displayed data, etc., are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the laws, regulations and standards of relevant countries and regions.

[0049] See also Figure 1 , Figure 1 A flow chart of a method for cutting yellow leaves of vegetation provided in an embodiment of the present application, the method comprising:

[0050] S101: upon receiving a vegetation yellow leaf detection instruction, obtaining vegetation image data;

[0051] S102: performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves;

[0052] S103: extracting contour information of each leaf in the yellow leaf area, wherein the contour information includes a plurality of azimuth coordinate points;

[0053] S104: determining the center coordinates of each yellow leaf according to the multiple azimuth coordinate points;

[0054] S105: Counting the center coordinates of all the yellow leaves in the yellow leaf area, and planning a cutting path according to all the center coordinates, so as to cut the yellow leaves in the yellow leaf area along the cutting path.

[0055] Here, there is no limitation on how to receive the vegetation yellowing leaf detection instruction, and the instruction type and instruction content of the vegetation yellowing leaf detection instruction. The present application can be applied to a vegetation yellowing leaf cutting device, or a central control device using a vegetation yellowing leaf cutting tool.

[0056] In step S101, vegetation image data may be acquired with the aid of a camera, and the camera may be a plurality of cameras distributed at multiple angles around the vegetation, so as to ensure the integrity of the acquired vegetation image data.

[0057] Thereafter, leaf color recognition of the vegetation image data is performed to determine the yellow leaf area containing yellow leaves. Here, as to how to perform the recognition of the vegetation image data, the image recognition processing can be performed by a local processor, or it can be uploaded to a server or cloud for image recognition processing, and the image recognition result returned by the server or cloud is received, and the image recognition result at least includes the yellow leaf area in the vegetation image data. Whether it is processed locally or in the cloud, a trained neural network model can be used for recognition to improve the accuracy of yellow leaf area recognition.

[0058] In order to improve the recognition accuracy of leaf color recognition, in a feasible implementation, the vegetation image data can be preprocessed according to the input data parameters of the neural network model. There is no limitation on which neural network model is used. In a feasible implementation, a convolutional neural network (CNN) can be used. A convolutional neural network consists of multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layer uses a learnable filter to perform local perception and feature extraction on the input image, the pooling layer downsamples the output of the convolutional layer to reduce the number of parameters and the amount of calculation, and the fully connected layer flattens the output of the pooling layer and performs tasks such as classification or regression. In addition, improved models of neural network models can also be used, such as residual networks, densely connected networks, etc., which are not limited to examples one by one here. The input data parameters refer to the parameter requirements of the applied neural network model for the input data, including but not limited to image size, image resolution, etc.

[0059] The preprocessing method used is not limited here, for example, it includes at least one of image size correction, contrast adjustment and image noise reduction. Image size correction usually refers to changing the resolution of the image, including upsampling and downsampling. Contrast adjustment is used to enhance or reduce the contrast in the image, making the vegetation image data more suitable for further analysis and processing. Image noise reduction refers to reducing the noise in the image and improving the image quality.

[0060] There is no limitation on how to perform leaf color recognition. In a feasible implementation method, it may include the following steps:

[0061] The first step is to extract leaf parameters from the vegetation image data;

[0062] The second step is to determine the vegetation type according to the leaf parameters, and obtain the yellow leaf parameters corresponding to the vegetation type;

[0063] The third step is to compare the leaf parameters and the yellow leaf parameters to determine the yellow leaf area in the vegetation image data.

[0064] First, extract leaf parameters to determine the vegetation type. The leaf parameters mainly include leaf-stem ratio, leaf shape, etc., which can be used to determine the vegetation type, thereby obtaining the yellow leaf parameters of the vegetation type. The yellow leaf parameters can be obtained from the vegetation information database. The yellow leaf parameters refer to the parameters of the old or diseased leaves of this type of vegetation. For example, the chlorophyll content (which can be directly determined by the color change between normal leaves and old and diseased leaves) or the spectral characteristics of the leaves can be used as yellow leaf parameters. It should be particularly noted that the yellow leaves referred to in this application do not necessarily mean yellow leaves, but refer to old or diseased leaves. For different vegetation types, the yellow leaf parameters may be different.

[0065] After obtaining the yellow leaf parameters, the leaf parameters in the vegetation image data can be compared to determine the yellow leaf area. For example, the yellow leaf area can be directly determined by color comparison.

[0066] The yellow leaf area determined in the above step refers to an area containing yellow leaves, and within the yellow leaf area, normal leaves can be included or excluded through settings.

[0067] After the yellow leaf area is determined, the contour information of the leaves in the yellow leaf area can be further extracted. The contour information can be extracted by means of an image recognition algorithm. The extracted contour information includes at least a plurality of azimuth coordinate points. The azimuth coordinate points are coordinates of different azimuths on the leaf contour information, so that the center coordinates of each yellow leaf can be determined according to the plurality of azimuth coordinate points.

[0068] By determining the center coordinates of the yellow leaves, the position information of each yellow leaf can be determined, especially for the yellow leaves that are partially obscured in the vegetation, the center coordinates can also be located through their partial contour information, so that their position is determined by the center coordinates. For some vegetation with larger leaf areas, the part of the bottom of the leaves containing the petiole is easily obscured by adjacent leaves, so it is difficult to directly locate the petiole. However, in order to carry out photosynthesis, the vegetation has at least part of the unobstructed leaf surface, so the center coordinates can be located by the contour information of the unobstructed leaf surface. Of course, when locating the center coordinates according to the contour information, the leaf shape characteristics of the vegetation type can be used to assist in locating the center coordinates on the basis of determining the vegetation type.

[0069] The center coordinate is used to locate the petiole position information of the leaf, which may be the center of gravity of the leaf. In a feasible implementation, the petiole coordinate can also be selected as the center coordinate. The location of the petiole of the leaf can be quickly determined by combining the center of gravity coordinate with the shape characteristics of the leaf.

[0070] In addition, if the target yellow leaf is partially blocked by vegetation, when extracting the contour information of each leaf in the yellow leaf area, the complete leaf information of the target yellow leaf can be simulated according to the spatial information of the petiole of the target yellow leaf, so as to determine the center coordinate of the target yellow leaf according to the complete leaf information. When simulating the target yellow leaf, the leaf shape characteristics of the vegetation type can be referred to.

[0071] After the center coordinates of all yellow leaves are determined, the cutting path can be planned according to all the center coordinates. The cutting path should cover the center coordinates of all the leaves that have been determined and make the cutting path as short as possible.

[0072] In a feasible implementation, the cutting path may be planned in the following manner:

[0073] The first step is to obtain environmental information of the yellow leaf area;

[0074] Step 2: Perform environmental modeling based on the environmental information to obtain a grid-based environmental model; the nodes in the grid include passable nodes and inpassable nodes;

[0075] Step 3: determine the starting point coordinates, and use all the center coordinates as the end point coordinates;

[0076] Step 4: Starting from the coordinates of the starting point, iteratively calculate the cost values ​​of the adjacent nodes; if the total cost of reaching the adjacent node through the current node is less than the known cost, update the cost value of this node and record the parent node; the cost value represents the actual cost from the starting point to the current node;

[0077] Step 5: Calculate a heuristic value based on the estimated distance between the current node and the target node; the heuristic value represents the heuristic estimated cost from the current node to the target node;

[0078] Step 6: Taking the minimum sum of the cost value and the heuristic value as the optimization goal, add the node with the minimum optimization goal each time to the node operation path until all center coordinates are added to the node operation path to obtain the cutting path.

[0079] First, collect environmental data, which may include information such as terrain and obstacle locations. This information will be used for subsequent environmental modeling and path planning. Use the collected environmental information to create a grid model, in which each grid cell represents a part of the environment. The nodes in the grid are divided into traversable nodes and intraversable nodes, which helps to determine which areas are safe to pass during subsequent path searches. After that, set the starting point of the path planning first, and use the central coordinates of all target locations that need to be reached as the end point. Starting from the starting point, calculate the cost (such as distance or time) to reach each adjacent node. If the total cost of reaching a certain adjacent node through the current node is less than the previously known minimum cost, update the cost value of this adjacent node and record its parent node. Use a heuristic function (such as Euclidean distance) to estimate the distance from the current node to the target node, that is, the heuristic value. In each iteration, select those nodes with the smallest sum of the cost value plus the heuristic value as the next node to be processed to determine the nodes for priority operations.

[0080] In addition, an RRT (Rapidly-exploring Random Tree) algorithm may be used to plan a collision-free cutting path based on the center coordinates of the blade.

[0081] In addition, when it comes to multiple operable cutting components, such as multiple robotic arms, when planning the cutting path, a corresponding cutting path can be determined for each robotic arm, or only one cutting path can be planned and different robotic arms can execute part of the cutting path respectively.

[0082] After the cutting path is determined, a cutting component or a cutting device, such as a cutting robot, may be used to cut the yellow leaves in the yellow leaf area along the cutting path.

[0083] The method for cutting yellow leaves of vegetation provided in the embodiment of the present application first performs color recognition on the leaves to determine the yellow leaf area after obtaining vegetation image data, and then locates the yellow leaves by extracting contour information and locating the center coordinates of the yellow leaves, and plans a cutting path based on the yellow leaf positioning, thereby cutting the yellow leaves along the cutting path. The cutting of yellow leaves is achieved based on image recognition algorithms and spatial path planning, which ensures the healthy growth of vegetation, facilitates the maintenance of vegetation, and reduces the manpower burden of vegetation maintenance.

[0084] Based on the above embodiment, as a preferred embodiment, for the partially obscured yellow leaves, it may be difficult to determine their center coordinates. In this case, when performing the shearing operation, after the obstruction of the yellow leaves is removed, the target center coordinates of the yellow leaves can be determined, and the shearing path can be updated according to the target center coordinates. This process can be performed in real time during the shearing operation to improve the accuracy and efficiency of shearing yellow leaves and avoid repeated operations.

[0085] On the basis of the above embodiment, as a preferred embodiment, after planning the shearing path according to all the central coordinates, the kinematic characteristic data of the shearing component can be obtained, and the shearing path can be optimized by a high-order interpolation algorithm according to the kinematic characteristic data. The kinematic characteristic data includes motion restrictions and / or speed constraints. After determining the basic path planning, the shearing path needs to be optimized to ensure the efficiency and accuracy of the shearing operation. For example, when a mechanical arm is used to perform a shearing operation, the restrictions and speed constraints of the joints in the mechanical arm, as well as dynamic factors in the shearing process, such as the movement or deformation of the blade, can be considered. Through the high-order interpolation method, the path can be further optimized to make it smoother and more efficient. In addition, in practical applications, environmental factors and the actual operation capabilities of the mechanical arm need to be considered. For example, if the blade is located in a complex environment, it may be necessary to combine global path planning and local path planning to ensure that the mechanical arm can complete the shearing task safely and effectively. In addition, actual testing and adjustment can also be performed to verify the accuracy and feasibility of the shearing path planning. Through the above steps, the shearing path of the mechanical arm can be effectively planned according to the position information of the yellow blade to ensure the smooth progress of the shearing operation.

[0086] See also Figure 2 , Figure 2 A schematic diagram of a vegetation yellow leaf shearing device provided in an embodiment of the present application, the device comprising:

[0087] A device body 2 comprising a main control module 1, and a mechanical arm 3 connected to the device body 2; the mechanical arm 3 is used to perform yellow leaf cutting of vegetation according to an operation instruction issued by the main control module 1; the operation instruction is a cutting path determined after color recognition of vegetation image data and center coordinate positioning of yellow leaves;

[0088] The main control module includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for cutting yellow leaves of vegetation as described in the above embodiment is implemented to generate the operation instruction;

[0089] In addition, the vegetation yellow leaf cutting device can also include a camera module 4 and a space detection module 5 arranged on the device body 2, the camera module 4 is used to obtain the vegetation image data and upload it to the main control module 1; the space detection module 5 is used to perform spatial distance detection of the vegetation yellow leaf cutting device.

[0090] Figure 2 It can be seen that a driving module 6 is provided under the device body 2 , and the driving module 6 is used to control the vegetation yellow leaf cutting device to move to the working position according to the movement control instruction issued by the main control module 1 .

[0091] The vegetation yellow leaf cutting device described in the present application is used to perform yellow leaf cutting in vegetation. Among them, the main control module 1 serves as the control center of the driving module 6 and the mechanical arm 3, and the camera module 4 is used to obtain the vegetation image data and transmit it to the main control module 1. As for how to perform the recognition of vegetation image data, the processing unit included in the main control module 1 can perform image recognition processing, and the main control module 1 can also upload the image recognition processing to the server or the cloud for image recognition processing, and receive the image recognition result returned by the server or the cloud, and the image recognition result at least includes the location information of the yellow leaves in the vegetation picture. It is even possible to directly receive the cutting path fed back by the server or the cloud.

[0092] For vegetation with other specific colors, yellow leaves can be identified by confirming the type of vegetation during image recognition processing. If vegetation images are uploaded to the server, not only can vegetation images of different operation periods be saved, but it can also help analyze the growth characteristics of vegetation in different environments and at different times, providing a data basis for further vegetation maintenance.

[0093] The specific structure of the robot arm 3 is not limited here. Figure 2The structure of the robot arm 3 is only an exemplary structure. In addition, this embodiment does not limit the number of robot arms 3 included in the vegetation yellow leaf shearing device, and it can include one or more robot arms 3. When the vegetation yellow leaf shearing device includes multiple robot arms 3, the efficiency of its yellow leaf shearing operation can be improved, and some of the robot arms 3 can be used to perform auxiliary shearing actions, such as moving obstacles or obstructive branches and leaves on the shearing path.

[0094] In addition, the robot arm 3 may include several servos, for example, four servos. The servos adjust the internal motor by receiving the control voltage signal to rotate the output shaft to a specified position, ensuring that the robot arm 3 can flexibly adapt to different work tasks and maintain high accuracy and stability. The servos can achieve complex and delicate yellow leaf shearing operations through precise position feedback and control algorithms.

[0095] It is easy to understand that in order to avoid damaging the normal branches and leaves of the vegetation when the robotic arm 3 is inserted into the vegetation to cut the yellow leaves, the robotic arm 3 should not be too thick. And in a feasible embodiment, it can include multiple moving joints or rotating joints to ensure the flexibility of movement and steering of the robotic arm 3. In addition, the robotic arm 3 can adopt a series robotic arm 3 or a parallel robotic arm 3. A yellow leaf cutting component, such as a pair of scissors, is provided at the end of the robotic arm 3 to cut off the yellow leaves of the vegetation.

[0096] The camera module 4 is used to collect vegetation pictures of vegetation and upload them to the main control module 1. No limitation is made to the camera parameters used herein.

[0097] The space detection module 5 is used to perform space distance detection of the vegetation yellow leaf cutting device to avoid collision with obstacles or vegetation during the movement of the vegetation yellow leaf cutting device. The specific composition of the space detection module 5 is not limited here. In a feasible implementation, it may include an infrared module and / or an ultrasonic module. The infrared module is used to perform obstacle distance detection of the vegetation yellow leaf cutting device, and the ultrasonic module is used to perform auxiliary obstacle detection of the vegetation yellow leaf cutting device.

[0098] The infrared module mainly emits infrared rays and uses the infrared rays reflected by obstacles to calculate the distance. The ultrasonic sensor determines the distance by emitting ultrasonic waves and calculating the time difference between the emission and reception of sound waves. Since the infrared module is sensitive to light during detection, it is easily interfered by strong light or direct sunlight and cannot work in the dark. The ultrasonic module works in a dark environment and is insensitive to environmental factors such as light, dust, and smoke.

[0099] The specific installation position of the space detection module 5 is not limited here. For example, if the space detection module 5 includes an infrared module, the infrared module can be installed at the top of the equipment body 2, that is, the "head" of the vegetation yellow leaf cutting device, to perform environmental monitoring near the top. When the vegetation yellow leaf cutting device is about to collide with an obstacle, its infrared module will produce a level change, thereby stopping the vegetation yellow leaf cutting device from moving, so as to protect the safety of the vegetation or the vegetation yellow leaf cutting device and avoid the collision of the vegetation yellow leaf cutting device with the vegetation or obstacles.

[0100] The ultrasonic module can assist the infrared module in identifying the surrounding environment of the vegetation yellow leaf cutting device, so as to prevent the vegetation from being damaged by collisions caused by environmental factors when the vegetation yellow leaf cutting device is working. If the surrounding environment of the vegetation yellow leaf cutting device is complex and changeable, the vegetation yellow leaf cutting device will remain stable and motionless, and continue to work after confirming that the environment has not changed.

[0101] The driving module 6 is used to control the moving direction and moving distance of the vegetation yellow leaf shearing device according to the mobile control instruction issued by the main control module 1. In a feasible implementation, the driving module 6 may include a Mecanum wheel, an angle sensor, a driving motor, an encoding disc and a gyroscope. The driving motor is used to drive the Mecanum wheel; the encoding disc is used to convert the change of direction or displacement of the vegetation yellow leaf shearing device into an electrical signal; the gyroscope is used to confirm the moving stability of the vegetation yellow leaf shearing device, and the angle sensor is used to control the forward direction of the Mecanum wheel. There is no limitation on the number of Mecanum wheels here, for example, three, four or even more Mecanum wheels can be used. Multiple Mecanum wheels provide stable movement while increasing the steerable property, solving the need for small turns when the vegetation yellow leaf shearing device is working. The forward direction and balance degree of the vegetation yellow leaf shearing device are confirmed by obtaining the gyroscope and the angle sensor, and the proportional integral is calculated by the PID algorithm to ensure the stability of the movement of the vegetation yellow leaf shearing device. It should be noted that the main control module 1 is used to calculate the proportional integral differential through the PID control algorithm, so as to apply the proportional integral differential to regulate the movement of the driving module 6.

[0102] The vegetation yellow leaf cutting device provided in the embodiment of the present application can automatically detect and cut off the yellow leaves of vegetation with the help of sensors such as the camera module 4 and the space detection module 5, realize the intelligent removal of yellow leaves of vegetation, ensure the healthy growth of vegetation, facilitate the maintenance of vegetation, and reduce the manpower burden of vegetation maintenance.

[0103] On the basis of the above-mentioned embodiments, the vegetation yellow leaf cutting device may further include a display component provided on the device body 2, which is used to display the control information of the vegetation yellow leaf cutting device, and / or display the interactive information with the operating user. The display component may display interactive information with the user. For example, after the vegetation yellow leaf cutting device is started, the corresponding operation information may be displayed on the display component for the user to select or set. The specific type of interactive information is not limited here. For example, it may include the selection of the working mode, and the corresponding buttons such as the start, pause and end of the work for the user to click and operate. The display component may be a touch screen or be configured with corresponding operation buttons. By applying the display component, a visual workflow of vegetation yellow leaf cutting is realized. The user can communicate with the vegetation yellow leaf cutting device through the mobile terminal at any time to confirm the vegetation status and yellow leaf cutting progress captured by the vegetation yellow leaf cutting device, which greatly improves the user experience and reduces the user's workload.

[0104] In a feasible implementation, during the operation of the vegetation yellow leaf device, including movement and operation of the mechanical arm according to the cutting path, the space detection module 5 can be used to detect the position information between the vegetation yellow leaf cutting device and the obstacle, and generate an interrupt command when the position information is less than the set distance threshold. The obstacle refers to an object that hinders the operation, including the vegetation itself and obstacles that may exist during the movement. When the space detection module 5 includes an infrared module and an ultrasonic module, their functions and applications can be found in the above embodiments, and will not be repeated here. There is no specific limitation on setting the distance threshold, which can be set by technicians in this field.

[0105] When the space detection module 5 detects an obstacle, an interruption command may be generated, which is used to interrupt the operation process of the vegetation yellow leaf device. If an interruption command is generated during the movement of the vegetation yellow leaf device, the device operation may be re-executed after the obstacle is removed or moved. If an interruption command is generated during the cutting process of the vegetation yellow leaf device, other mechanical arms may be used to move the vegetation branches or obstacles that hinder the operation so as to continue the yellow leaf cutting operation.

[0106] In addition, when performing yellow leaf cutting operations, the working mode of the vegetation yellow leaf device can be determined first. The working mode can be pre-set, such as setting a range working mode, or determining the working mode based on duration. In the range working mode, the vegetation range for the required operation can be set to limit the vegetation yellow leaf device to perform operations within the vegetation range. When the working mode is determined based on duration, the maximum working duration of the vegetation yellow leaf device can be set. In addition, a normal mode can also be set. In normal mode, the vegetation yellow leaf device can automatically remove yellow leaves when they are detected until an interrupt command or a job termination instruction is received.

[0107] The interruption command or the operation termination command can be issued by the user through the touch screen included in the vegetation yellowing leaf device, or can be issued by remote command through the remote communication component included in the vegetation yellowing leaf device. At this time, the vegetation yellowing leaf cutting method provided in this embodiment adds emergency processing. When the user sets the error mode or wants to stop the vegetation yellowing leaf cutting device from working, he only needs to input the interruption command. The vegetation yellowing leaf cutting device receives the interruption signal and can stop working after confirming that it will not damage the vegetation.

[0108] See also Figure 3 , Figure 3 A schematic diagram of the structure of a vegetation yellow leaf shearing system provided in an embodiment of the present application, the system comprising:

[0109] An image acquisition module is used to acquire vegetation image data when detecting a vegetation yellow leaf detection instruction;

[0110] A leaf recognition module, used for performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves;

[0111] A contour extraction module, used to extract the contour information of each leaf in the yellow leaf area, and determine a number of azimuth coordinate points contained in the contour information;

[0112] A coordinate detection module, used to determine the center coordinates of the yellow leaf according to the plurality of azimuth coordinate points;

[0113] The cutting module is used to count the center coordinates of all yellow leaves and plan a cutting path according to all the center coordinates so as to cut the yellow leaves in the yellow leaf area along the cutting path.

[0114] Based on the above embodiment, as an optional embodiment, it also includes:

[0115] The image preprocessing module is used to perform image preprocessing on the vegetation image data according to the input data parameters of the neural network model; the preprocessing includes at least one of image size correction, contrast adjustment and image noise reduction.

[0116] Based on the above embodiment, as an optional embodiment, the blade identification module includes:

[0117] A parameter extraction unit, used for extracting leaf parameters from the vegetation image data;

[0118] A yellow leaf parameter extraction unit, used to determine the vegetation type according to the leaf parameters, and obtain the yellow leaf parameters corresponding to the vegetation type;

[0119] The area positioning unit is used to compare the leaf parameters and the yellow leaf parameters to determine the yellow leaf area in the vegetation image data.

[0120] Based on the above embodiment, as an optional embodiment, the cutting module is a module for performing the following steps:

[0121] Acquiring environmental information of the yellow leaf area;

[0122] Performing environmental modeling based on the environmental information to obtain a grid-based environmental model; the nodes in the grid include traversable nodes and intraversable nodes;

[0123] Determine the starting point coordinates, and use all the center coordinates as the end point coordinates;

[0124] Starting from the coordinates of the starting point, iteratively calculate the cost values ​​of the adjacent nodes; if the total cost of reaching the adjacent node through the current node is less than the known cost, then update the cost value of this node and record the parent node; the cost value represents the actual cost from the starting point to the current node;

[0125] Calculating a heuristic value based on an estimated distance between the current node and the target node; the heuristic value represents a heuristic estimated cost from the current node to the target node;

[0126] Taking the minimum sum of the cost value and the heuristic value as the optimization goal, the node with the minimum optimization goal each time is added to the node operation path, until all center coordinates are added to the node operation path, a cutting path is obtained.

[0127] Based on the above embodiment, as an optional embodiment, it also includes:

[0128] The first occluded leaf processing module is used to simulate the complete leaf information of the target yellow leaf according to the spatial information of the petiole of the target yellow leaf; and determine the center coordinates of the target yellow leaf according to the complete leaf information.

[0129] Based on the above embodiment, as an optional embodiment, it also includes:

[0130] The second occluding leaf processing module is used to determine the target center coordinates of the target occluded by the yellow leaves after the occluder of the target occluded by the yellow leaves is removed, and update the clipping path according to the target center coordinates.

[0131] Based on the above embodiment, as an optional embodiment, it also includes:

[0132] The path optimization module is used to obtain kinematic characteristic data of the shearing component and optimize the shearing path using a high-order interpolation algorithm according to the kinematic characteristic data; the kinematic characteristic data includes motion restrictions and / or speed constraints.

[0133] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed, the steps of the vegetation yellow leaf cutting method provided in the above embodiment can be implemented. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0134] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the system provided in the embodiment, since it corresponds to the method provided in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0135] Specific examples are used herein to illustrate the principles and implementation methods of the present application, and the description of the above embodiments is only used to help understand the method and core ideas of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the present application.

[0136] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A method for cutting yellow leaves of vegetation, characterized in that: include: When receiving a vegetation yellow leaf detection instruction, obtaining vegetation image data; Performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves; Extracting contour information of each leaf in the yellow leaf area, wherein the contour information includes a plurality of azimuth coordinate points; Determine the center coordinates of each yellow leaf according to the multiple azimuth coordinate points; Counting the center coordinates of all the yellow leaves in the yellow leaf area, and planning a cutting path according to all the center coordinates, so as to cut the yellow leaves in the yellow leaf area along the cutting path; The step of counting the center coordinates of all yellow leaves in the yellow leaf area and planning the cutting path according to all the center coordinates includes: Obtaining environmental information of the yellow leaf area; Performing environmental modeling based on the environmental information to obtain a grid-based environmental model; the nodes in the grid include traversable nodes and intraversable nodes; Determine the starting point coordinates, and use all the center coordinates as the end point coordinates; Starting from the coordinates of the starting point, iteratively calculate the cost values ​​of the adjacent nodes; if the total cost of reaching the adjacent node through the current node is less than the known cost, then update the cost value of this node and record the parent node; the cost value represents the actual cost from the starting point to the current node; Calculating a heuristic value based on an estimated distance between the current node and the target node; the heuristic value represents a heuristic estimated cost from the current node to the target node; Taking the minimum sum of the cost value and the heuristic value as the optimization goal, the node with the minimum optimization goal each time is added to the node operation path, until all center coordinates are added to the node operation path, a cutting path is obtained.

2. The method for cutting yellow leaves of vegetation according to claim 1, characterized in that: Before performing leaf color recognition on the vegetation image data and determining the yellow leaf area containing yellow leaves, the method further includes: The vegetation image data is subjected to image preprocessing according to input data parameters of the neural network model; the preprocessing includes at least one of image size correction, contrast adjustment and image noise reduction.

3. The method for cutting yellow leaves of vegetation according to claim 1 or 2, characterized in that: Performing leaf color recognition on the vegetation image data to determine that the yellow leaf area includes yellow leaves includes: Extracting leaf parameters from the vegetation image data; Determine the vegetation type according to the leaf parameters, and obtain yellow leaf parameters corresponding to the vegetation type; The leaf parameters and the yellow leaf parameters are compared to determine the yellow leaf area in the vegetation image data.

4. The method for cutting yellow leaves of vegetation according to claim 1, characterized in that: If the target yellow leaf is partially blocked by vegetation, the contour information of each leaf in the yellow leaf area is extracted, and the following steps are also included: Simulating the complete leaf information of the target yellow leaf according to the spatial information of the petiole of the target yellow leaf; The center coordinates of the target yellow leaf are determined according to the complete leaf information.

5. The method for cutting yellow leaves of vegetation according to claim 1, characterized in that: If there is a target yellow leaf that is partially blocked by vegetation, when executing the step of cutting the yellow leaves in the yellow leaf area along the cutting path, it also includes: After the obstruction of the target being obscured by the yellow leaves is removed, the target center coordinates of the target being obscured by the yellow leaves are determined, and the clipping path is updated according to the target center coordinates.

6. The method for cutting yellow leaves of vegetation according to claim 1, characterized in that: After planning the cutting path according to all the center coordinates, it also includes: The kinematic characteristic data of the shearing component is obtained, and the shearing path is optimized by using a high-order interpolation algorithm according to the kinematic characteristic data; the kinematic characteristic data includes motion restrictions and / or speed constraints.

7. A vegetation yellow leaf shearing device, characterized in that: include: A device body comprising a main control module and a mechanical arm connected to the device body; the mechanical arm is used to perform yellow leaf cutting of vegetation according to an operation instruction issued by the main control module; the operation instruction is a cutting path determined after color recognition of vegetation image data and center coordinate positioning of yellow leaves; The main control module includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for cutting yellow leaves of vegetation according to any one of claims 1 to 6 is implemented to generate the operation instruction; A camera module is provided in the device body, and is used to obtain the vegetation image data and upload it to the main control module.

8. A vegetation yellow leaf shearing system, characterized in that: include: An image acquisition module is used to acquire vegetation image data when detecting a vegetation yellow leaf detection instruction; A leaf recognition module, used for performing leaf color recognition on the vegetation image data to determine a yellow leaf area containing yellow leaves; A contour extraction module, used to extract the contour information of each leaf in the yellow leaf area, and determine a number of azimuth coordinate points contained in the contour information; A coordinate detection module, used to determine the center coordinates of the yellow leaf according to the plurality of azimuth coordinate points; A cutting module, used for counting the center coordinates of all yellow leaves, and planning a cutting path according to all the center coordinates, so as to cut the yellow leaves in the yellow leaf area along the cutting path; The shearing module is a module for performing the following steps: Obtaining environmental information of the yellow leaf area; Performing environmental modeling based on the environmental information to obtain a grid-based environmental model; the nodes in the grid include traversable nodes and intraversable nodes; Determine the starting point coordinates, and use all the center coordinates as the end point coordinates; Starting from the coordinates of the starting point, iteratively calculate the cost values ​​of the adjacent nodes; if the total cost of reaching the adjacent node through the current node is less than the known cost, then update the cost value of this node and record the parent node; the cost value represents the actual cost from the starting point to the current node; A heuristic value is calculated based on an estimated distance between the current node and the target node; the heuristic value represents a heuristic estimated cost from the current node to the target node.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vegetation yellow leaf cutting method as described in any one of claims 1-6 are implemented.

Images