A woody forage harvester travel control method, system, terminal and medium

Abstract

The present invention discloses a travel control method, system, terminal and medium for a woody forage harvester, and relates to the field of intelligent control and image processing technology. The key points of the technical solution are: identifying the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjusting the camera angle of the monocular camera; calculating the plant height of the harvested plant according to the adjusted installation parameters of the monocular camera and the position information of the boundary line in the effective image; using an image segmentation algorithm to identify the density information of the harvested plant in the effective image; and regulating the travel speed of the harvester in the normal travel stage according to the plant height and density information. The present invention uses monocular vision technology to simultaneously calculate the plant height and density information of the harvested plant. For different types of plants, the travel speed of the harvester can be adjusted in a timely and accurate manner as the plant height and density change, so that the harvester can operate stably with a higher harvesting efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control and image processing, and more specifically, to a travel control method, system, terminal and medium for a woody forage harvester. Background Art

[0002] Woody feed refers to the branches, leaves, flowers, fruits, seeds and their by-products of woody plants that can be used as livestock and poultry feed. There are many types of woody feed, including but not limited to paper mulberry, mulberry, pine needles, locust trees, caragana, etc. For large-scale planted woody feed, such as hybrid paper mulberry, mechanized harvesting can be used to improve efficiency. Harvesters can directly crush the branches and leaves to a suitable size for subsequent processing.

[0003] The travel speed of the harvester is mainly determined by the feed amount, and the factors affecting the feed amount mainly include plant height and plant density. Some existing technologies record monitoring the actual feed amount of the harvester, and then feedback and adjust the travel speed of the harvester based on the actual feed amount. This method has low harvesting efficiency and overload operation of the machine when the travel speed of the harvester is switched and controlled. In severe cases, it is easy to cause overheating or damage to the machine; in addition, some existing technologies record predicting the feed amount based on information such as plant height and plant density, and then adjusting the travel speed of the harvester based on the predicted feed amount. This method requires measuring the plant height and plant density when harvesting different types of plants, which is not only time-consuming and labor-intensive, but also prone to large errors in the measurement results; and there are certain differences in plant height and plant density in large-scale planting, resulting in the inability of the harvester's travel speed to be adaptively adjusted as the plant height and plant density change.

[0004] Therefore, how to research and design a woody forage harvester travel control method, system, terminal and medium that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention

[0005] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a travel control method, system, terminal and medium for a woody forage harvester. By applying monocular vision technology, combined with the installation parameters of the monocular camera and the position information of the boundary line in the effective image, the plant height and density information of the harvested plants can be simultaneously calculated. For different types of plants, the travel speed of the harvester can be adjusted in time and accurately as the plant height and density change, so that the harvester can operate stably with a higher harvesting efficiency.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions:

[0007] In a first aspect, a method for controlling a woody forage harvester is provided, comprising the following steps:

[0008] An initial image of the harvester in the initial moving stage is collected by a monocular camera in the initial state;

[0009] Identify the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjust the camera angle of the monocular camera according to the identification result;

[0010] The effective images of the harvester in the normal travel stage are collected through the adjusted monocular camera;

[0011] The plant height of the harvested plant is calculated according to the adjusted installation parameters of the monocular camera and the position information of the boundary line in the effective image;

[0012] The image segmentation algorithm is used to identify the density information of the harvested plants in the effective image;

[0013] The travel speed of the harvester during the normal travel phase is regulated according to the plant height and density information.

[0014] Furthermore, if the recognition result is that the initial image only contains the top layer of the plant, the camera angle of the monocular camera is reduced, and the image is repeatedly captured until the initial image contains the boundary line;

[0015] If the recognition result is that the initial image only includes the harvesting interface, the camera angle of the monocular camera is increased, and the image is repeatedly captured until the initial image includes the boundary line;

[0016] The camera angle of the monocular camera is the angle between the center line of the monocular camera's viewing angle and the vertical direction.

[0017] Furthermore, if the recognition result is that the initial image contains a boundary line, the camera angle adjustment process of the monocular camera is specifically as follows:

[0018] Set the width ratio range between the top layer of the plant and the harvesting interface in the image, and the width ratio range is [1,3];

[0019] The camera angle of the monocular camera was adjusted so that the actual width ratio between the top layer of the plant and the harvesting interface in the initial image was within the width ratio range.

[0020] Furthermore, the calculation expression of the plant height of the harvested plants is specifically:

[0021] ;

[0022] in, Indicates the local height of the plant corresponding to the harvesting interface in the effective image; Indicates the horizontal distance between the monocular camera and the harvesting interface; represents the proportionality coefficient; Indicates the angle between the upper boundary of the monocular camera's viewing angle and the vertical direction; Indicates the angle between the lower boundary of the monocular camera's viewing angle and the vertical direction; Indicates the vertical installation height between the monocular camera and the ground; Indicates the plant height at which the plants were harvested.

[0023] Furthermore, the process of determining the proportionality coefficient is specifically as follows:

[0024] Reading a coefficient sequence corresponding to the camera angle of the monocular camera from a database and / or storage, wherein each coefficient in the coefficient sequence corresponds to a pixel point, and a ratio of two coefficients is equal to a ratio of actual distances represented by the corresponding two pixel points;

[0025] Calculate the sum of the coefficients of the pixel points corresponding to the top layer of the plant in the effective image to obtain the first coefficient;

[0026] Calculate the sum of the coefficients of the pixel points corresponding to the harvesting interface in the effective image to obtain the second coefficient;

[0027] The proportionality coefficient is calculated as the ratio of the first coefficient to the second coefficient.

[0028] Furthermore, the process of using the image segmentation algorithm to identify the density information of the harvested plants in the effective image is specifically as follows:

[0029] An image segmentation algorithm is used to segment the individual plants contained in the harvesting interface in the effective image to obtain the top-level side view features of the individual plants;

[0030] The top-view features corresponding to the top-view features are obtained by matching the top-view features of the plants in the effective image;

[0031] Taking the top-view features as reference objects, the image segmentation algorithm is used to segment the top of the plant in the effective image to obtain all the top-view features.

[0032] The feature quantity of all top-level overlooking features is used to represent the density information of the harvested plants in the effective image.

[0033] Furthermore, the travel speed control process of the harvester in the normal travel stage is specifically as follows:

[0034] When the plant height remains constant, the travel speed is positively correlated with the density information;

[0035] And / or, when density information remains unchanged, travel speed is positively correlated with plant height.

[0036] In a second aspect, a woody forage harvester travel control system is provided, the system being used to implement a woody forage harvester travel control method as described in any one of the first aspects, comprising:

[0037] An initial acquisition module, used to acquire an initial image of the harvester in the initial moving stage through a monocular camera in an initial state;

[0038] An angle adjustment module, used to identify the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjust the camera angle of the monocular camera according to the recognition result;

[0039] An effective acquisition module is used to acquire effective images of the harvester during the normal travel phase through an adjusted monocular camera;

[0040] A height calculation module, used to calculate the plant height of the harvested plants according to the adjusted installation parameters of the monocular camera and the position information of the boundary line in the effective image;

[0041] A density analysis module, used to identify the density information of harvested plants in the effective image using an image segmentation algorithm;

[0042] The speed control module is used to adjust the travel speed of the harvester during the normal travel phase according to the plant height and density information.

[0043] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for controlling the movement of a woody forage harvester as described in any one of the first aspects is implemented.

[0044] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement a woody forage harvester travel control method as described in any one of the first aspects.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. A woody forage harvester travel control method provided by the present invention uses monocular vision technology, combines the installation parameters of the monocular camera and the position information of the boundary line in the effective image to simultaneously calculate the plant height and density information of the harvested plants. For different types of plants, the travel speed of the harvester can be adjusted timely and accurately as the plant height and density change, so that the harvester can operate stably with a higher harvesting efficiency;

[0047] 2. The present invention can make preliminary adjustments to the monocular camera for different types of plants to ensure the reliability of boundary line recognition by identifying the boundary line between the top layer of the plant and the harvesting interface in the initial image and adjusting the camera angle of the monocular camera according to the recognition result; in addition, the camera angle of the monocular camera is accurately adjusted according to the width ratio range, which can effectively ensure the accuracy of the calculated plant height and density information;

[0048] 3. The present invention only needs to determine the position information of the boundary line in the effective image, and then combine it with the coefficient sequence read according to the camera angle of the monocular camera to quickly calculate the plant height of the harvested plant, which effectively reduces the difficulty of controlling the travel speed of the harvester;

[0049] 4. The present invention can quickly and accurately determine the density information of the harvested plants by segmenting the individual plants contained in the harvesting interface in the effective image, and then segmenting the top layer of the plants in the effective image with the top layer overhead features as reference objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0051] Figure 1 is a flow chart of Embodiment 1 of the present invention;

[0052] Figure 2 is a schematic diagram of analyzing plant height in Example 1 of the present invention;

[0053] Figure 3 It is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0055] Embodiment 1: A method for controlling the movement of a woody forage harvester, such as Figure 1 As shown, the following steps are included:

[0056] S1: The initial image of the harvester in the initial moving stage is collected by the monocular camera in the initial state;

[0057] S2: Identify the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjust the camera angle of the monocular camera according to the identification result;

[0058] S3: Collect valid images of the harvester during the normal travel phase through the adjusted monocular camera;

[0059] S4: calculating the plant height of the harvested plant according to the adjusted installation parameters of the monocular camera and the position information of the boundary line in the effective image;

[0060] S5: using image segmentation algorithm to identify the density information of harvested plants in the effective image;

[0061] S6: Regulate the travel speed of the harvester during the normal travel phase according to the plant height and density information.

[0062] In step S1, the harvester is set with an initialization speed, and the monocular camera is also set with an initial camera angle. When the harvester is initially started, it will move at the initialization speed to harvest the plants. The purpose of this initial movement stage is to form a clear boundary line to provide basic information for the subsequent adjustment of the camera angle of the monocular camera.

[0063] In step S2, considering that different types of plants have different heights, when the camera captures images at the initial camera angle, it cannot be sure that the image must contain a boundary line. Therefore, it is necessary to identify the boundary line between the top layer of the plant and the harvesting interface in the initial image and adjust the camera angle of the monocular camera according to the recognition result.

[0064] It should be noted that the boundary line refers to the line reflected in the image where the intersection edge of the harvesting interface and the top layer of the plant meet.

[0065] Specifically, if the recognition result is that the initial image only contains the top layer of the plant, the camera angle of the monocular camera is reduced, and the image is repeatedly acquired until the boundary line is included in the initial image; if the recognition result is that the initial image only includes the harvesting interface, the camera angle of the monocular camera is increased, and the image is repeatedly acquired until the boundary line is included in the initial image; wherein, the camera angle of the monocular camera is the angle between the center line of the viewing angle of the monocular camera and the vertical direction.

[0066] In addition, in order to prevent the position of the boundary line from being too marginal, the present invention also accurately adjusts the shooting angle of the monocular camera.

[0067] Specifically, if the recognition result is that the initial image contains a boundary line, the camera angle adjustment process of the monocular camera is as follows: set the width ratio range of the top layer of the plant and the harvesting interface in the image, and the width ratio range is [1,3]; adjust the camera angle of the monocular camera so that the actual width ratio of the top layer of the plant and the harvesting interface in the initial image is within the width ratio range.

[0068] like Figure 2 As shown in the figure, when n is 2, the actual width ratio is 2, indicating that the camera angle of the monocular camera does not need to be adjusted. When n is 5, the actual width ratio is 5, indicating that the proportion of the harvesting interface in the image is small, and the recognition error of the harvesting interface is likely to have a greater impact on the calculation result of the plant height. The camera angle of the monocular camera needs to be adjusted. At this time, the camera angle of the monocular camera needs to be reduced.

[0069] In step S3, for the same plant, the camera angle of the monocular camera generally does not need to be adjusted again after being adjusted. Therefore, when subsequently calculating the plant height of the harvested plants, it is only necessary to determine the position of the boundary line, and then substitute the proportional coefficient determined according to the position of the boundary line into the calculation model to quickly calculate the plant height of the harvested plants.

[0070] In step S4, although the existing image processing technology can identify the height of the plant, the premise is that the image needs to include the entire plant. However, due to the limited viewing angle of the camera, the top range of the plant that can be photographed after the image includes the entire plant is small, and it is difficult to analyze the density of the plant on this basis; on the contrary, when the image includes a sufficient range of the top range of the plant, it generally cannot include the entire plant, so the height of the plant cannot be calculated. Therefore, binocular vision technology is generally used to synchronously analyze the height and density of the plant. Based on this, the present invention designs a method for synchronously analyzing the height and density of the plant based on monocular vision technology.

[0071] like Figure 2 As shown, the plant height calculation model for harvested plants is constructed with the following logic:

[0072] (1) The local height y of the plant corresponding to the harvesting interface in the effective image and Figure 2 The pixels occupied by x in the image are consistent, and x and y can be obtained by to convert.

[0073] (2) x and kx correspond to the harvesting interface and the top layer of the plant in the effective image, respectively, and the calculation model can be established based on this.

[0074] After the camera angle of the monocular camera is determined, the ratio of the collected real object distances between different pixel points in the image is determined, so after k is determined, the plant height of the harvested plant can be calculated.

[0075] Specifically, the calculation expression for the plant height of the harvested plants is:

[0076] ;

[0077] in, Indicates the local height of the plant corresponding to the harvesting interface in the effective image; Indicates the horizontal distance between the monocular camera and the harvesting interface; represents the proportionality coefficient; Indicates the angle between the upper boundary of the monocular camera's viewing angle and the vertical direction; Indicates the angle between the lower boundary of the monocular camera's viewing angle and the vertical direction; Indicates the vertical installation height between the monocular camera and the ground; Indicates the plant height at which the plants were harvested.

[0078] It should be noted that the upper boundary of the viewing angle of a monocular camera refers to the upper edge of the viewing angle range.

[0079] The process of determining the proportional coefficient is specifically as follows: reading a coefficient sequence corresponding to the camera angle of the monocular camera from a database and / or storage, wherein each coefficient in the coefficient sequence corresponds to a pixel point, and the ratio of two coefficients is equal to the ratio of actual distances represented by the corresponding two pixel points; calculating the sum of the coefficients of the pixel points corresponding to the top layer of the plant in the effective image to obtain a first coefficient; calculating the sum of the coefficients of the pixel points corresponding to the harvesting interface in the effective image to obtain a second coefficient; and calculating the proportional coefficient as the ratio of the first coefficient to the second coefficient.

[0080] In step S5, the density information of harvested plants can be identified by using existing image processing techniques, such as: (1) performing preprocessing on the collected images, such as image cropping, rotation correction, contrast enhancement, and noise removal, to improve image quality and prepare for subsequent analysis; (2) using image processing algorithms to extract features related to plant density, such as color, texture, shape, and size; (3) applying machine learning or deep learning algorithms, such as support vector machines (SVM), convolutional neural networks (CNN), deep belief networks (DBN), etc., to analyze the extracted features to identify and count plants.

[0081] As another optional implementation, the process of using an image segmentation algorithm to identify the density information of harvested plants in an effective image is specifically as follows: using an image segmentation algorithm to segment individual plants contained in the harvesting interface in the effective image to obtain top-level side-view features of the individual plants; obtaining top-level top-view features corresponding to the top-level side-view features from the top layers of the plants in the effective image; using the top-level top-view features as reference objects, using an image segmentation algorithm to segment the top layers of the plants in the effective image to obtain all top-level top-view features; and using the feature quantity of all top-level top-view features to characterize the density information of the harvested plants in the effective image.

[0082] The present invention takes into account the differences in top-layer features of different types of plants. In the past, complex models were required to process the identification and counting of plants. The present invention uses the top-layer overhead features as a reference object to segment the top layers of plants in the effective image, which can quickly and accurately determine the density information of the harvested plants.

[0083] In step S5, the travel speed control process of the harvester in the normal travel stage is specifically as follows: when the plant height remains unchanged, the travel speed is positively correlated with the density information; and / or, when the density information remains unchanged, the travel speed is positively correlated with the plant height.

[0084] It should be noted that the travel speed control of the harvester during the normal travel stage can also take into account the harvesting width, harvester performance parameters, environmental conditions, loss rate, etc., and is not restricted here.

[0085] Embodiment 2: A woody forage harvester travel control system, the system is used to implement a woody forage harvester travel control method as described in Embodiment 1, such as Figure 3 As shown, it includes an initial acquisition module, an angle adjustment module, an effective acquisition module, a height calculation module, a density analysis module and a speed control module.

[0086] Among them, the initial acquisition module is used to collect the initial image of the harvester in the initial travel stage through the monocular camera in the initial state; the angle adjustment module is used to identify the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjust the camera angle of the monocular camera according to the recognition result; the effective acquisition module is used to collect the effective image of the harvester in the normal travel stage through the adjusted monocular camera; the height calculation module is used to calculate the plant height of the harvested plant according to the installation parameters of the adjusted monocular camera and the position information of the boundary line in the effective image; the density analysis module is used to identify the density information of the harvested plant in the effective image by using the image segmentation algorithm; the speed control module is used to adjust the travel speed of the harvester in the normal travel stage according to the plant height and density information.

[0087] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for controlling the movement of a woody forage harvester as described in Example 1 is implemented.

[0088] The present invention also records a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement a woody forage harvester travel control method as described in Example 1.

[0089] Working principle: The present invention applies monocular vision technology, combines the installation parameters of the monocular camera and the position information of the boundary line in the effective image to simultaneously calculate the plant height and density information of the harvested plants. For different types of plants, the travel speed of the harvester can be adjusted in time and accurately as the plant height and density change, so that the harvester can operate stably with a higher harvesting efficiency.

[0090] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0091] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0094] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling the movement of a woody forage harvester, characterized in that: The following steps are involved: An initial image of the harvester in the initial moving stage is collected by a monocular camera in the initial state; Identify the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjust the camera angle of the monocular camera according to the identification result; The effective images of the harvester in the normal travel stage are collected through the adjusted monocular camera; The plant height of the harvested plant is calculated according to the adjusted installation parameters of the monocular camera and the position information of the boundary line in the effective image; The image segmentation algorithm is used to identify the density information of the harvested plants in the effective image; According to the plant height and density information, the travel speed of the harvester in the normal travel stage is regulated; The specific calculation expression of the plant height of the harvested plants is: ； in, Indicates the local height of the plant corresponding to the harvesting interface in the effective image; Indicates the horizontal distance between the monocular camera and the harvesting interface; represents the proportionality coefficient; Indicates the angle between the upper boundary of the monocular camera's viewing angle and the vertical direction; Indicates the angle between the lower boundary of the monocular camera's viewing angle and the vertical direction; Indicates the vertical installation height between the monocular camera and the ground; indicates the plant height at which the plants were harvested; If the recognition result is that the initial image only contains the top layer of the plant, the camera angle of the monocular camera is reduced, and the image is repeatedly collected until the initial image contains the boundary line; If the recognition result is that the initial image only includes the harvesting interface, the camera angle of the monocular camera is increased, and the image is repeatedly captured until the initial image includes the boundary line; The camera angle of the monocular camera is the angle between the center line of the monocular camera's viewing angle and the vertical direction; If the recognition result is that the initial image contains a boundary line, the camera angle adjustment process of the monocular camera is specifically as follows: Set the width ratio range between the top layer of the plant and the harvesting interface in the image, and the width ratio range is [1,3]; Adjust the camera angle of the monocular camera so that the actual width ratio between the top layer of the plant and the harvesting interface in the initial image is within the width ratio range; The specific process of determining the proportional coefficient is as follows: Reading a coefficient sequence corresponding to the camera angle of the monocular camera from a database and / or storage, wherein each coefficient in the coefficient sequence corresponds to a pixel point, and a ratio of two coefficients is equal to a ratio of actual distances represented by the corresponding two pixel points; Calculate the sum of the coefficients of the pixel points corresponding to the top layer of the plant in the effective image to obtain the first coefficient; Calculate the sum of the coefficients of the pixel points corresponding to the harvesting interface in the effective image to obtain the second coefficient; The proportionality coefficient is calculated as the ratio of the first coefficient to the second coefficient.

2. A woody forage harvester travel control method according to claim 1, characterized in that: The process of using the image segmentation algorithm to identify the density information of the harvested plants in the effective image is specifically as follows: An image segmentation algorithm is used to segment the individual plants contained in the harvesting interface in the effective image to obtain the top-level side view features of the individual plants; The top-view features corresponding to the top-view features are obtained by matching the top-view features of the plants in the effective image; Taking the top-view features as reference objects, the image segmentation algorithm is used to segment the top of the plant in the effective image to obtain all the top-view features. The feature quantity of all top-level overlooking features is used to represent the density information of the harvested plants in the effective image.

3. A woody forage harvester travel control method according to claim 1, characterized in that: The specific process of controlling the travel speed of the harvester in the normal travel stage is as follows: When the plant height remains constant, the travel speed is positively correlated with the density information; And / or, when density information remains unchanged, travel speed is positively correlated with plant height.

4. A woody forage harvester travel control system, characterized in that: The system is used to implement a woody forage harvester travel control method as described in any one of claims 1 to 3, comprising: An initial acquisition module, used to acquire an initial image of the harvester in the initial moving stage through a monocular camera in an initial state; An angle adjustment module, used to identify the boundary line between the top layer of the plant and the harvesting interface in the initial image, and adjust the camera angle of the monocular camera according to the recognition result; An effective acquisition module is used to acquire effective images of the harvester during the normal travel phase through an adjusted monocular camera; A height calculation module, used to calculate the plant height of the harvested plants according to the adjusted installation parameters of the monocular camera and the position information of the boundary line in the effective image; A density analysis module, used to identify the density information of harvested plants in the effective image using an image segmentation algorithm; A speed control module is used to adjust the travel speed of the harvester in the normal travel stage according to plant height and density information; The specific calculation expression of the plant height of the harvested plants is: ； in, Indicates the local height of the plant corresponding to the harvesting interface in the effective image; Indicates the horizontal distance between the monocular camera and the harvesting interface; represents the proportionality coefficient; Indicates the angle between the upper boundary of the monocular camera's viewing angle and the vertical direction; Indicates the angle between the lower boundary of the monocular camera's viewing angle and the vertical direction; Indicates the vertical installation height between the monocular camera and the ground; Indicates the plant height at which the plants were harvested.

5. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for controlling the movement of a woody forage harvester as described in any one of claims 1 to 3 is implemented.

6. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a woody forage harvester travel control method as described in any one of claims 1-3.

Images