Sprinkling machine walking control system and control method

Abstract

The invention relates to the technical field of machine vision and image processing, in particular to a sprinkling machine walking control system and method, and the system comprises an industrial camera which is used for obtaining the image information of a working environment where a sprinkling machine is located; the image processing unit is used for acquiring image information and processing the image information; the controller is used for receiving the processed image information and sending out a control signal based on the image information; the motor driving module is used for receiving the control signal and controlling the sprinkling machine to walk according to the control signal; the communication module is electrically connected with the controller, and the controller performs data transmission with a remote control center through the communication module; the application of the system promotes the development of agricultural irrigation towards a more accurate and efficient direction, facilitates the improvement of agricultural production efficiency and resource utilization efficiency, and promotes the realization of an agricultural modernization process and a sustainable development target.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision and image processing, and in particular to a sprinkler travel control system and a control method. Background Art

[0002] Sprinklers play a vital role in modern agriculture, efficiently and evenly irrigating farmland and significantly improving agricultural production efficiency and water resource utilization. However, with the acceleration of agricultural modernization, the working environment faced by sprinklers is becoming increasingly complex and variable. Ensuring that they can accurately and efficiently move and complete irrigation tasks under various conditions has become a pressing issue. Traditional sprinkler travel control relies on preset paths or simple sensor feedback, which is inadequate when faced with practical situations such as irregular crop rows and frequent field obstacles. Inaccurate crop row recognition can lead to uneven irrigation, affecting crop growth; the sudden appearance of obstacles can damage the sprinkler or prevent it from continuing to operate, reducing irrigation efficiency. Therefore, it is particularly important to develop a sprinkler travel control system that can intelligently identify the working environment, autonomously plan paths, and flexibly respond to obstacles. Summary of the Invention

[0003] In view of this, the present invention addresses the deficiencies in the prior art and proposes a sprinkler travel control system and control method, aiming to solve at least one of the problems raised in the above background technology.

[0004] In a first aspect, the present invention provides a sprinkler travel control system, comprising: an industrial camera for acquiring image information of a working environment of the sprinkler;

[0005] an image processing unit, configured to obtain the image information and process the image information;

[0006] a controller, configured to receive the processed image information and issue a control signal based on the image information;

[0007] A motor drive module, configured to receive the control signal and control the movement of the sprinkler according to the control signal;

[0008] The communication module is electrically connected to the controller, and the controller transmits data with the remote control center through the communication module.

[0009] In a second aspect, the present invention provides a method for controlling the movement of a sprinkler, comprising the following steps:

[0010] S1. Process and analyze image information;

[0011] S2. Path planning is performed based on the results of processing and analyzing the image information.

[0012] In some embodiments, the processing and analyzing of the image information in step S1 includes:

[0013] Perform denoising, filtering and grayscale processing on image information.

[0014] In some embodiments, the processing and analyzing of the image information in step S1 further includes:

[0015] The key features in the image information are labeled to generate a training set for training the CNN model to obtain a trained CNN model, and the key features of the working environment of the sprinkler are identified by the trained CNN model.

[0016] In some embodiments, the key features include crop rows, obstacles, and path boundaries.

[0017] In some embodiments, performing path planning based on the results of processing and analyzing the image information in step S2 includes:

[0018] The centerline coordinates of each row of crops output by the CNN model are obtained and smoothed. A row of crops is selected as the reference path, a parallel path is generated based on the crop row spacing, and the path is smoothed using a spline curve.

[0019] In some embodiments, if an obstacle is detected in the path, basic information of the obstacle is determined, and the controller controls the sprinkler to adjust according to the basic information of the obstacle, including:

[0020] When the height of the obstacle is greater than or equal to the travel height of the sprinkler, the first warning signal is issued, and the width of the obstacle and the path width are identified;

[0021] When the height of the obstacle is less than the travel height of the sprinkler, the controller controls the sprinkler to travel normally.

[0022] In some embodiments, when the height of the obstacle is greater than or equal to the travel height of the sprinkler, the controller issues a first warning signal and identifies the width of the obstacle and the width of the path, including:

[0023] When the width of the obstacle is greater than or equal to the path width, the controller sends a second warning signal and controls the electric drive module to stop working;

[0024] When the width of the obstacle is smaller than the path width and smaller than the travel width of the sprinkler, the controller controls the sprinkler to travel normally;

[0025] When the obstacle width is smaller than the path width and greater than or equal to the travel width of the sprinkler, the distance between the two sides of the obstacle and the path boundary is identified.

[0026] In some embodiments, when the width of the obstacle is less than the path width and greater than or equal to the travel width of the sprinkler, identifying the distance between both sides of the obstacle and the path boundary includes:

[0027] When the distance between the left side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and travel normally from the left or right side of the obstacle;

[0028] When the distance between the left side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and move normally from the left side of the obstacle;

[0029] When the distance between the left side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and travel normally from the right side of the obstacle.

[0030] In some embodiments, when the width of the obstacle is less than the path width and greater than or equal to the travel width of the sprinkler, identifying the distance between both sides of the obstacle and the path boundary further includes:

[0031] When the distance between the left side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, the controller sends a second warning signal and controls the electric drive module to stop working.

[0032] Compared with the existing technology, the beneficial effects of the present invention are: through industrial cameras and image processing units, the system can accurately identify key features such as crop rows and obstacles in the farmland, ensure that the sprinkler moves accurately along the crop rows, achieve uniform irrigation, and improve water resource utilization and crop growth quality. Based on the recognition results of the CNN model, the system can autonomously plan the travel path, flexibly avoid obstacles in the field, reduce downtime or detour time caused by obstacles, and improve the continuity and efficiency of irrigation operations. The system integrates advanced image processing technology and deep learning algorithms to achieve intelligent perception and autonomous decision-making of complex working environments, reduce dependence on manual operation, and improve the intelligence and automation level of the sprinkler. Through data interaction between the communication module and the remote control center, the system supports remote monitoring and intelligent scheduling, allowing managers to understand the working status of the sprinkler in real time, and make adjustments and optimizations as needed to further improve work efficiency.

[0033] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0034] Other features and aspects of the present disclosure will become more apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a functional block diagram of the sprinkler travel control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0038] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0039] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0040] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0041] See Figure 1 As shown, the first embodiment:

[0042] A sprinkler travel control system according to an embodiment of the present application includes:

[0043] Industrial cameras are used to obtain image information of the working environment of the sprinkler;

[0044] an image processing unit, configured to obtain the image information and process the image information;

[0045] a controller, configured to receive the processed image information and issue a control signal based on the image information;

[0046] A motor drive module, configured to receive the control signal and control the movement of the sprinkler according to the control signal;

[0047] The communication module is electrically connected to the controller, and the controller transmits data with the remote control center through the communication module.

[0048] Second embodiment:

[0049] A method for controlling the movement of a sprinkler according to an embodiment of the present application includes the following steps:

[0050] S1. Process and analyze image information;

[0051] S2. Path planning is performed based on the results of processing and analyzing the image information.

[0052] In some specific embodiments, the processing and analyzing of the image information in step S1 includes:

[0053] Perform denoising, filtering and grayscale processing on image information.

[0054] It should be understood that farmland environments may contain noise such as uneven lighting, dust, and leaf occlusion. Denoising can effectively filter out these interferences while preserving key features (such as crop rows and obstacles). However, noise can degrade image quality and affect the accuracy of subsequent CNN model recognition of crop rows and obstacles. Denoising results in clearer images and more prominent features, improving the model's recognition rate. In complex environments (such as overcast skies and strong sunlight), denoising can make images more stable and avoid misjudgments caused by noise. Filtering can remove high-frequency noise (such as salt and pepper noise and random noise) from images while preserving the edge information of key features, making the image easier to analyze. Filtered images are more suitable for subsequent grayscale processing and feature annotation, helping CNN models more efficiently extract key information such as crop rows and obstacles. Converting color images to grayscale reduces data volume (from three channels to one), reduces computational complexity, and improves processing speed. Grayscale processing eliminates color interference, making key features such as crop rows and obstacles more distinct in the grayscale image, facilitating subsequent annotation and model training. Grayscale processing can reduce the impact of lighting changes on images (such as shadows, reflections, etc.), so that the CNN model can still work stably under different lighting conditions.

[0055] In some specific embodiments, the processing and analyzing of the image information in step S1 further includes:

[0056] The key features in the image information are labeled to generate a training set for training the CNN model to obtain a trained CNN model, and the key features of the working environment of the sprinkler are identified by the trained CNN model.

[0057] It should be understood that in the pre-processed images, key features (such as crop rows, obstacles, and path boundaries) are manually or semi-automatically annotated. The annotation information includes the location, shape, category, etc. of the features to form structured data, and the annotated images and their corresponding labels (such as the centerline of the crop row and the location of the obstacle) are organized into a training set. The training set needs to cover a variety of farmland scenes (such as different lighting, crop growth stages, and obstacle types) to improve the generalization ability of the model. The annotated training set is used to supervise the learning of the convolutional neural network (CNN). The model learns the rules for extracting key features (such as crop rows and obstacles) from the image and outputs the recognition results (such as the coordinates of the centerline of the crop row and the location of the obstacle).

[0058] Optimize model performance through cross-validation and adjustment of hyperparameters (such as learning rate and network structure). Use the test set to evaluate model accuracy and ensure its reliability in practical applications.

[0059] In some embodiments, the key features include crop rows, obstacles, and path boundaries.

[0060] In some specific embodiments, performing path planning based on the results of processing and analyzing the image information in step S2 includes:

[0061] The centerline coordinates of each row of crops output by the CNN model are obtained and smoothed. A row of crops is selected as the reference path, a parallel path is generated based on the crop row spacing, and the path is smoothed using a spline curve.

[0062] It should be understood that the CNN model identifies the location of each row of crops and outputs the centerline coordinates of each row (e.g., a set of points in a two-dimensional plane). These coordinates reflect the spatial distribution of the crop rows and are the basis for path planning. The centerline coordinates are smoothed (e.g., using a moving average filter, Gaussian filter, or spline interpolation) to eliminate noise and local fluctuations. The smoothed centerline is more continuous and stable, avoiding path planning errors caused by minor disturbances. The centerline of a row of crops is selected from multiple rows as the reference path (e.g., the straightest and longest crop row). The reference path serves as a reference for the subsequent generation of parallel paths.

[0063] Based on the baseline path, multiple parallel paths are generated based on the crop row spacing (such as the distance between the centerlines of two adjacent crop rows). These parallel paths cover the entire farmland, ensuring that the sprinkler can evenly irrigate all crop rows. Spline curves (such as Bezier curves and B-splines) are fitted to the generated parallel paths to further smooth the path shape. This smoothed path better matches the sprinkler's motion characteristics, reduces sharp turns and jitter, and improves travel stability.

[0064] In some specific embodiments, if an obstacle is detected in the path, basic information of the obstacle is determined, and the controller controls the sprinkler to adjust according to the basic information of the obstacle, including:

[0065] When the height of the obstacle is greater than or equal to the travel height of the sprinkler, the first warning signal is issued, and the width of the obstacle and the path width are identified;

[0066] When the height of the obstacle is less than the travel height of the sprinkler, the controller controls the sprinkler to travel normally.

[0067] In some specific embodiments, when the height of the obstacle is greater than or equal to the travel height of the sprinkler, the controller issues a first warning signal and identifies the width of the obstacle and the width of the path, including:

[0068] When the width of the obstacle is greater than or equal to the path width, the controller sends a second warning signal and controls the electric drive module to stop working;

[0069] When the width of the obstacle is smaller than the path width and smaller than the travel width of the sprinkler, the controller controls the sprinkler to travel normally;

[0070] When the obstacle width is smaller than the path width and greater than or equal to the travel width of the sprinkler, the distance between the two sides of the obstacle and the path boundary is identified.

[0071] In some specific embodiments, when the width of the obstacle is smaller than the path width and greater than or equal to the travel width of the sprinkler, identifying the distance between both sides of the obstacle and the path boundary includes:

[0072] When the distance between the left side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and travel normally from the left or right side of the obstacle;

[0073] When the distance between the left side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and move normally from the left side of the obstacle;

[0074] When the distance between the left side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and travel normally from the right side of the obstacle.

[0075] In some specific embodiments, when the obstacle width is smaller than the path width and greater than or equal to the travel width of the sprinkler, identifying the distance between both sides of the obstacle and the path boundary further includes:

[0076] When the distance between the left side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, the controller sends a second warning signal and controls the electric drive module to stop working.

[0077] It should be understood that the travel width of the sprinkler is the physical width occupied by the sprinkler body or spraying device in the horizontal direction when the sprinkler is operating in the field.

[0078] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A sprinkler travel control system, characterized in that: include: Industrial cameras are used to obtain image information of the working environment of the sprinkler; an image processing unit, configured to obtain the image information and process the image information; a controller, configured to receive the processed image information and issue a control signal based on the image information; A motor drive module, configured to receive the control signal and control the movement of the sprinkler according to the control signal; The communication module is electrically connected to the controller, and the controller transmits data with the remote control center through the communication module.

2. A method for controlling the movement of a sprinkler, characterized in that: A sprinkler travel control system as claimed in claim 1 comprises the following steps: S1, process and analyze image information; S2. Path planning is performed based on the results of processing and analyzing the image information.

3. A sprinkler travel control method according to claim 2, characterized in that: The processing and analysis of the image information in step S1 includes: Perform denoising, filtering and grayscale processing on image information.

4. A sprinkler travel control method according to claim 3, characterized in that: The processing and analysis of the image information in step S1 further includes: The key features in the image information are labeled to generate a training set for training the CNN model to obtain the trained CNN model. The trained CNN model is used to identify the key features of the working environment of the sprinkler.

5. A sprinkler travel control method according to claim 4, characterized in that: The key features include crop rows, obstacles, and path boundaries.

6. A sprinkler travel control method according to claim 5, characterized in that: The path planning according to the result of processing and analyzing the image information in step S2 includes: The centerline coordinates of each row of crops output by the CNN model are obtained and smoothed. A row of crops is selected as the reference path, a parallel path is generated based on the crop row spacing, and the path is smoothed using a spline curve.

7. A sprinkler travel control method according to claim 6, characterized in that: If an obstacle is detected in the path, the basic information of the obstacle is determined, and the controller controls the sprinkler to make adjustments based on the basic information of the obstacle, including: When the height of the obstacle is greater than or equal to the travel height of the sprinkler, the first warning signal is issued, and the width of the obstacle and the path width are identified; When the height of the obstacle is less than the travel height of the sprinkler, the controller controls the sprinkler to travel normally.

8. A sprinkler travel control method according to claim 7, characterized in that: When the height of the obstacle is greater than or equal to the travel height of the sprinkler, the controller sends a first warning signal and identifies the width of the obstacle and the width of the path, including: When the width of the obstacle is greater than or equal to the path width, the controller sends a second warning signal and controls the electric drive module to stop working; When the width of the obstacle is smaller than the path width and smaller than the travel width of the sprinkler, the controller controls the sprinkler to travel normally; When the obstacle width is smaller than the path width and greater than or equal to the travel width of the sprinkler, the distance between the two sides of the obstacle and the path boundary is identified.

9. A sprinkler travel control method according to claim 8, characterized in that: When the width of the obstacle is smaller than the path width and greater than or equal to the travel width of the sprinkler, identifying the distance between both sides of the obstacle and the path boundary includes: When the distance between the left side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and travel normally from the left or right side of the obstacle; When the distance between the left side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and move normally from the left side of the obstacle; When the distance between the left side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is greater than or equal to the travel width of the sprinkler, the controller controls the sprinkler to adjust its direction and travel normally from the right side of the obstacle.

10. A sprinkler travel control method according to claim 9, characterized in that: When the width of the obstacle is smaller than the path width and greater than or equal to the travel width of the sprinkler, the distance between the two sides of the obstacle and the path boundary is identified, further comprising: When the distance between the left side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, and the distance between the right side of the obstacle and its corresponding path boundary is less than the travel width of the sprinkler, the controller sends a second warning signal and controls the electric drive module to stop working.

Images