Intelligent soybean harvesting system

Abstract

The invention discloses an intelligent soybean harvesting system, and relates to the field of agricultural intelligent harvesting equipment.The system comprises a first collecting unit, a second collecting unit, a third collecting unit, a harvesting unit and a control unit.The system can control the harvesting unit to harvest soybean plants according to a harvesting route; in the harvesting process, the cutting height of the harvesting unit is controlled according to the harvesting height data corresponding to the position through which the harvesting route passes; unmanned automatic intelligent soybean harvesting can be achieved, the height of the harvesting cutter can be automatically adjusted according to the terrain, abrasion of the harvesting cutter is reduced, and the loss rate of pod harvesting is reduced.

Description

Technical Field

[0001] The present invention relates to the field of agricultural intelligent harvesting equipment, and in particular to a soybean intelligent harvesting system. Background Art

[0002] Currently, soybeans are harvested by soybean harvesters, and the harvesting method is that a driver drives the soybean harvester to operate the harvesting in the soybean planting area.

[0003] The applicant has found that the current method of manually operating soybean harvesters to harvest soybeans has the following problems: 1. The harvesting method is semi-automatic and requires a driver to drive the harvester for harvesting. Unmanned harvesting is not possible.

[0004] 2. During harvesting, the height of the cutter for cutting soybean plants is fixed and cannot be adjusted. When facing uneven planting areas, the cutting effects are different. For example, if the raised area is cut too deep and close to the root, it is easy to cut the ground or stones, causing the cutter to wear, or cut too many unnecessary rhizomes. For example, if the cut in the depression area is too shallow, the cutting part will be close to the upper part of the soybean plant, resulting in part of the pod area remaining on the remaining stems, resulting in an increase in the harvest loss rate. Summary of the invention

[0005] The purpose of the present invention is to realize unmanned automatic intelligent harvesting of soybeans, and can automatically adjust the height of the harvesting knife according to the terrain, reduce the wear of the harvesting knife, and reduce the loss rate of pod harvesting.

[0006] To achieve the above-mentioned object of the invention, the present invention provides a soybean intelligent harvesting system, the system comprising: The first acquisition unit is used to collect three-dimensional surface data of the planting area when sowing soybeans; A second collection unit is used to collect distribution data of seedlings in the planting area when the soybean plants are in the seedling stage and during the fertilization process of the soybean plants; The third collection unit is used to collect the growth height data of the soybean plants in the planting area before harvesting when the soybean plants are in the edamame harvesting stage; A calculation unit, used for planning a harvesting route based on the distribution data and a harvesting width parameter of the harvesting unit, and for generating harvesting height data in the harvesting unit corresponding to a position passed by the harvesting route based on the three-dimensional surface data and the growth height data; A harvesting unit, used for harvesting soybean plants; The control unit is used to control the harvesting unit to harvest the soybean plants according to the harvesting route, and to control the cutting height of the harvesting unit according to the harvesting height data corresponding to the position passed by the harvesting route during the harvesting process.

[0007] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: The present invention can realize unmanned automatic intelligent harvesting of soybeans, and can automatically adjust the height of the harvesting knife according to the terrain, thereby reducing the wear of the harvesting knife and reducing the loss rate of bean pod harvesting. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation on the embodiments of the present invention; Figure 1 It is a schematic diagram of the composition of a soybean intelligent harvesting system; Figure 2 This is a schematic diagram of the harvesting route; Figure 3 It is a structural diagram of the image acquisition module; Among them, 1-protective cover, 2-electric telescopic pole, 3-camera, 4-bracket, 5-planting area, 6-single soybean plant. DETAILED DESCRIPTION

[0009] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0010] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0011] Those skilled in the art should understand that, in the disclosure of the present invention, the orientation or position relationship indicated by the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. are based on the orientation or position relationship shown in the drawings, which are only for the convenience of describing the present invention 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 operate in a specific orientation. Therefore, the above terms should not be understood as limiting the present invention.

[0012] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0013] Embodiment 1;

[0014] Please refer to Figure 1 , Figure 1 The present invention provides a soybean intelligent harvesting system, the system comprising: The first acquisition unit is used to collect three-dimensional surface data of the planting area when sowing soybeans; A second collection unit is used to collect distribution data of seedlings in the planting area when the soybean plants are in the seedling stage and during the fertilization process of the soybean plants; The third collection unit is used to collect the growth height data of the soybean plants in the planting area before harvesting when the soybean plants are in the edamame harvesting stage; A calculation unit, used for planning a harvesting route based on the distribution data and a harvesting width parameter of the harvesting unit, and for generating harvesting height data in the harvesting unit corresponding to a position passed by the harvesting route based on the three-dimensional surface data and the growth height data; A harvesting unit, used for harvesting soybean plants; The control unit is used to control the harvesting unit to harvest the soybean plants according to the harvesting route, and to control the cutting height of the harvesting unit according to the harvesting height data corresponding to the position passed by the harvesting route during the harvesting process.

[0015] Among them, the traditional harvesting method is that the harvester drives the harvester to harvest, and the harvester goes back and forth to harvest along a broken line path, turns around after harvesting in one direction each time and then returns to harvest, and unmanned automatic harvesting is realized. In order to realize automatic unmanned harvesting, the idea of ​​the present invention is to understand the planting conditions of soybean plants and their distribution in the planting area. For example, the second collection unit is used to collect the distribution data of seedlings in the planting area during the fertilization process when the soybean plants are in the seedling stage. The soybean plants need to undergo multiple fertilizations in the seedling stage, and the seedling distribution data in the planting area is collected during one or more fertilization processes. The distribution data of seedlings can obtain data such as the spacing between seedlings and the planting area. The purpose of collecting data when the soybean plants are in the seedling stage is that the soybean plants are still in the seedling stage at this time, and the branches and leaves have not grown into shape, and the branches and leaves are not large. Aerial photography or photography from above will not block the roots, and the roots can be clearly photographed, so that the planting coordinates of the seedlings can be accurately obtained, and the distribution data of the seedlings in the planting area can be accurately obtained. If the soybean plants are photographed after they mature, the roots cannot be photographed due to the lush branches and leaves of the soybean plants and the thick leaves, and the distribution data of the seedlings in the planting area cannot be accurately obtained.

[0016] In order to realize unmanned automatic harvesting, after obtaining the distribution data of the seedlings in the planting area, it is necessary to plan a corresponding harvesting route according to the distribution data of the seedlings in the planting area. The method of the present invention is to use a computing unit to plan a harvesting route based on the distribution data and the harvesting width parameters of the harvesting unit. The specific principle is that after the distribution data of the seedlings in the planting area is known, the width of each harvesting of the harvester can be obtained to obtain the range or area that the harvester can harvest in a single direction. After the distribution area and area of ​​the soybean plants in the planting area are known, a harvesting route for harvesting all the soybean plants in the planting area can be quickly planned according to the single harvesting range of the harvester. Then, the harvesting route is transmitted to the control end of the harvester, and the corresponding intelligent driving system is cooperated to realize unmanned automatic intelligent harvesting of soybeans.

[0017] Among them, in order to automatically adjust the height of the harvesting knife according to the terrain, it is necessary to first know the terrain data of the planting area. The present invention uses a first acquisition unit to collect the three-dimensional surface data of the planting area when soybeans are sown. The three-dimensional surface data of the planting area can be obtained by scanning. The purpose of choosing to collect the three-dimensional surface data of the planting area when soybeans are sown is that the planting area is in an exposed stage at this time, and the three-dimensional surface data of the planting area can be obtained clearly and comprehensively. If the soybean plants grow out, the soybean plants will block the surface. At this time, the three-dimensional surface data of the planting area cannot be accurately obtained, and the cutting height of the harvesting unit cannot be accurately controlled.

[0018] The control principle of controlling the cutting height of the harvesting unit in the present invention is as follows: after obtaining the three-dimensional surface data of the planting area, it is also necessary to use the third acquisition unit to collect the growth height data of the soybean plants in the planting area before harvesting when the soybean plants are in the edamame harvesting stage. Because although the three-dimensional surface data of the planting area is known, it is impossible to accurately determine the cutting height without knowing the growth conditions of the soybean plants. For example, in an area suitable for the growth of soybean plants, the growth height of the soybean plants may be relatively high, and the cutting height needs to be higher at this time. If the environmental conditions in the area where the soybean plants grow are average, the growth height of the soybean plants may be relatively low, and the cutting height needs to be lower at this time. Therefore, it is necessary to first collect the three-dimensional surface data of the soybean plants in the planting area before harvesting. The growth height data of the plant is obtained, and a standard cutting height is determined according to the growth height data. The cutting height is the height from the ground, that is, the height of the cutting blade from the ground. Then, the height of the cutting blade of the cutter is adjusted accordingly according to the three-dimensional surface data of the planting area during cutting. For example, if it is flat land, cutting is performed according to the standard cutting height. When it reaches a depression, the cutting height is lowered for cutting. When it reaches a convex land, the cutting height is increased, so that the height or length of the cut soybean plants is basically the same. The present invention can automatically adjust the height of the harvesting knife according to the terrain. When encountering a convex land, the height of the cutting knife can be adjusted to reduce the wear of the harvesting knife. When encountering a depression, the height of the cutting knife can be adjusted to avoid cutting too high, thereby reducing the loss rate of pod harvesting.

[0019] The first acquisition unit may be a terrain laser scanner, or other equipment capable of obtaining three-dimensional surface data by scanning. The embodiment of the present invention does not specifically limit the specific implementation of the first acquisition unit.

[0020] Among them, the harvesting unit in the embodiment of the present invention can be an intelligent harvester, or a corresponding harvesting equipment. The present invention is improved by adding corresponding first to third collection units, as well as a computing unit and a control unit on the basis of a traditional intelligent harvester. The embodiment of the present invention does not make corresponding improvements to the structure and composition of the traditional intelligent harvester. Therefore, the embodiment of the present invention does not make corresponding redundant descriptions of the harvesting unit, which can realize basic functions such as harvesting and walking.

[0021] Among them, the specific implementation method of the second acquisition unit can be a camera plus a processor. The camera captures an image of the planting area, calibrates the image of the planting area, and then captures an image of the soybean plant seedlings. The coordinate data of the seedlings in the image of the soybean plant seedlings is obtained through the previously calibrated data. The coordinate data of all soybean plant seedlings in the planting area are obtained by multiple captures in the above method. The coordinate data of all soybean plant seedlings can then be converted to obtain the distribution data of the seedlings in the planting area. The image calibration method and means and the coordinate conversion method are commonly used methods in the field of image processing, and the embodiments of the present invention will not be repeated accordingly.

[0022] The embodiment of the present invention utilizes a computing unit to plan a harvesting route based on distribution data and a harvesting width parameter of a harvesting unit, wherein the shape and area of ​​the planting area and the spacing between soybean plants can be obtained through the distribution data, and the spacing between the harvesting knives of the harvester can be adjusted so that the harvesting knives can harvest the soybean plants well, thereby avoiding the harvesting knives harvesting between two rows of soybean plants, causing wasteful idling of the harvesting knives. In addition, a harvester usually has multiple harvesting knives harvesting side by side, such as 8 harvesting knives harvesting together, so the harvesting width parameter that can be harvested at one time is determined, and the harvesting route can be planned through this parameter and the distribution parameter. The specific route map is as follows: Figure 2 As shown, Figure 2 In the figure, 5 is a planting area, which is assumed to be a rectangle, and the soybean plants in the planting area are evenly arranged and distributed, 6 is a single soybean plant, a is the harvesting width of the harvesting unit, and S1 to S6 are the travel routes of the cutter. Figure 2 The distribution data is known. After the harvester adjusts the spacing between the harvesting knives, the harvesting width of the harvester is greater than 4 rows of soybean plants and less than 5 rows of soybean plants. Then the cutting route planned at this time is as follows: Figure 2 The steps S1 to S6 are shown to be performed sequentially. The speed during the process and the need to turn around after completing a section of the process are performed accordingly, and the present invention will not be described in detail.

[0023] Among them, the control unit can be a controller or a corresponding control system. When the harvesting route is known, the existing intelligent driving system can be used to realize the harvester to move according to the set route. Automatic unmanned harvesting can be realized by turning on the harvester of the harvester during the moving process. The intelligent driving part is a commonly used driving system in this field, and the present invention does not make corresponding redundant descriptions. In addition, the currently available intelligent harvesters on the market can be used in the embodiments of the present invention. The harvesting height and the width between multiple harvesting knives are adjustable. The harvesting height can be adjusted by the height adjustment mechanism for the harvester as a whole. The harvester can include several separate harvesting modules, which can be operated separately for harvesting. The spacing between separate harvesting modules can be adjusted by the lateral adjustment mechanism. The adjustment of the harvesting height and the width between multiple harvesting knives belongs to the commonly used technical means in this field. Other adjustment methods can also be used. The embodiments of the present invention do not make specific limitations or redundant descriptions. In actual applications, they can be adjusted according to actual needs.

[0024] In this embodiment of the present invention, the first acquisition unit is specifically used for: A spatial three-dimensional coordinate system, an xyz coordinate system, is established for the planting area; the purpose of establishing the spatial three-dimensional coordinate system is to facilitate accurate positioning of the seedling planting point to obtain coordinates, and then accurately digitize the distribution data of the seedlings in the planting area, and to facilitate accurate digital representation of the three-dimensional surface data; A reference horizontal plane is set on the ground of the planting area, such as the horizontal plane o, and the horizontal xy coordinates of the seedlings are reflected in the reference horizontal plane. In addition, the z-axis coordinates in the z direction are used to indicate the pits and convex shapes of the terrain in the planting area. For example, the z coordinate of the reference horizontal plane is 0, the z coordinate of the pit area is the corresponding negative value, and the z coordinate of the convex area is the corresponding positive value. The specific values ​​are determined according to the scanning data. For example, the coordinates of seedling A are (3, 5, 0), the coordinates of seedling B are (2, 3, 3), the coordinates of seedling C are (7, 4, -2), and the coordinates of seedling D are (9, 5, 0), etc. The specific coordinates are determined according to the actual situation. Scan the ground of the planting area to obtain scanning data; the ground topographic data of the planting area can be accurately obtained through scanning; Based on the scanning data and the reference horizontal plane, the difference data between each coordinate point in the planting area and the reference horizontal plane in the height direction is obtained; the data in the z-axis direction is reflected by the difference data to reflect the potholes and bulges on the ground; The three-dimensional surface data is obtained based on the coordinate data of each coordinate point in the planting area and the corresponding difference data, wherein the three-dimensional surface data is composed of a number of surface point data, and each surface point data includes coordinate data in three directions of xyz.

[0025] In the embodiment of the present invention, the distribution data of the seedlings in the planting area includes: the planting coordinate data of the seedlings and the distance data between the seedlings. The planting coordinate data of the seedlings can be used to plan the harvesting route, and the distance data between the seedlings can be used to adjust the spacing between the collected cutting knives, thereby accurately achieving cutting and avoiding missing cutting.

[0026] Among them, in the embodiment of the present invention, the third acquisition unit is specifically used to take pictures of soybean plants in the edamame harvesting stage, obtain soybean plant images, identify the height of the soybean plants in the image, and calculate the growth height data of the soybean plants in the planting area before harvesting based on the recognition results. Among them, using image shooting to obtain the height of the target belongs to conventional technical means in the field of image processing, such as image size calibration and target recognition. The embodiment of the present invention does not make corresponding redundant descriptions. Specifically, when there are multiple soybean plants in the image, multiple height recognition results are obtained by shooting, and the growth height data of the soybean plants can be obtained by averaging. The image can be shot by a camera or a video camera or a drone carrying a camera, and the embodiment of the present invention does not make specific limitations.

[0027] The present invention uses image recognition and calibration technology to obtain soybean plant images by taking pictures of soybean plants in the edamame harvesting stage, and then identifies the height of the soybean plants in the images to obtain the growth height data of the soybean plants.

[0028] In this embodiment of the present invention, the system further includes: a fourth detection unit, configured to monitor obstacles on the ground in a moving direction of the harvesting unit and obtain obstacle monitoring data; The control unit is also used to analyze the obstacle monitoring data to obtain obstacle information, and control and warn the progress of the harvesting unit based on the obstacle information.

[0029] Among them, due to the dense planting of soybeans, luxuriant branches and leaves, and large leaves, traditional drivers cannot see the ground in the cab, and can only see the dense soybean planting surface. There may be obstacles on the ground below the soybean planting surface, such as tools left after farm work. At this time, if the harvester's harvesting blade contacts these obstacles, it may cause damage to the harvester. To this end, the present invention designs a fourth detection unit to monitor obstacles on the ground in the direction of travel when the harvesting unit is moving, and obtain obstacle monitoring data; the control unit is used to analyze the obstacle monitoring data to obtain obstacle information, and the movement of the harvesting unit is controlled and alarmed based on the obstacle information. The purpose of analyzing the obstacle monitoring data is that some obstacles will not cause damage to the cutter, such as dead leaves, fallen leaves, branches and stems, etc., so these can not stop the cutter or alarm, and if it is a target that will cause damage to the cutter, the cutter will be stopped or an alarm will be issued, such as stones, tools, etc.

[0030] Among them, in the embodiment of the present invention, the fourth detection unit includes: a plurality of image acquisition modules, each of which includes: an electric telescopic rod 2, a camera 3, a protective cover 1 and a data transmission module, such as Figure 3 As shown, Figure 3 : is a structural schematic diagram of an image acquisition module; one end of the electric telescopic rod is fixedly connected to the harvesting unit, and the other end of the electric telescopic rod is extended toward the ground in front of the harvesting unit and then fixedly connected to the back of the protective cover. The ideal distance is the distance between the soybean planting leaf layer below and the ground above, and the distance from the ground is better, which can provide a better field of view for the camera; the camera is fixed in the protective cover, and is used to take pictures of the ground in front of the harvesting unit to obtain obstacle monitoring data. The fixing method can be fixed overhead using a bracket 4; the data transmission module is used to transmit the obstacle monitoring data to the control unit, and the data transmission module can use wired transmission and wireless transmission, which is not specifically limited in the embodiment of the present invention; the control unit is also used to adjust the length of the electric telescopic rod based on the growth height data, wherein, in the embodiment of the present invention, the image is obtained by shooting with a camera, and the target recognition model carried in the control unit is used to perform target recognition, wherein the corresponding target recognition model is obtained by training the recognition model using an image set, and the corresponding target is annotated in the image set, such as tools, stones, leaves, dead leaves, fallen leaves, branches and leaves, and stems, etc. After the annotation is completed, a training set is obtained, and the corresponding target recognition model can be obtained by training the model using the training set.

[0031] In order to accurately obtain obstacle data in front of the harvester's traveling direction during harvesting, the present invention designs the specific composition of the fourth detection unit and designs multiple image acquisition modules. Different image acquisition modules collect images of different areas in the traveling direction and analyze whether there are obstacles respectively, thereby realizing comprehensive obstacle monitoring in the foreground direction.

[0032] Furthermore, since the soybean plants have lush branches and leaves, it is impossible to accurately obtain the situation of obstacles below the soybean plants near the ground by shooting from above the soybean plants. Therefore, the present invention is designed to use an electric telescopic rod to provide extension and support for the camera, extending the camera to below the branches and leaves of the soybean plants. This can avoid the branches and leaves of the soybean plants from blocking the camera's shooting angle, and thus clearly capture the image of the soybean plants corresponding to the ground, and accurately determine whether there are obstacles on the ground.

[0033] Among them, when the harvester is moving, the camera located in front of the harvester will inevitably collide with the branches and leaves of the soybean plants, so the present invention designs a protective cover to protect the camera.

[0034] Among them, different soybean plants grow to different heights, and the heights of the upper layer of lush branches and leaves from the ground are also different. Therefore, the control unit in the present invention is also used to adjust the length of the electric telescopic rod based on the growth height data, so as to accurately adjust the length of the electric telescopic rod to achieve the purpose of accurately making the camera avoid the upper layer of lush branches and leaves. For example, when the soybean plant grows taller, the electric telescopic rod can be extended shorter, because the electric telescopic rod is inclined downward toward the ground, and the shorter extension is higher from the ground, which also corresponds to the soybean plant growing taller and the leaf layer is higher from the ground. For example, when the soybean plant grows shorter, the electric telescopic rod can be extended longer, because the electric telescopic rod is inclined downward toward the ground, and the longer extension is closer to the ground, which also corresponds to the soybean plant growing taller and the leaf layer is closer to the ground. The specific adjustment range and amplitude can be adjusted according to actual needs, and the embodiments of the present invention do not make specific limitations.

[0035] The protective cover is hemispherical, and the lower end is open, which is convenient for camera shooting. Since the lush branches and leaves on the upper layer will block most of the light, a number of light sources facing the ground are provided in the protective cover. The light source can provide a good shooting environment for the camera, ensure the image quality obtained by shooting, and improve the accuracy of target recognition. The camera is set up in the protective cover by a bracket to protect the camera and fix it firmly. The protective cover is preferably a transparent cover, which can provide better lighting conditions for the camera. The diameter of the protective cover is preferably greater than 0.5b and less than 0.7b, where b is the spacing between two rows of soybean plants. The purpose of the design greater than 0.5b is to enable the protective cover to open part of the leaves between the two rows of soybean plants to provide conditions for the camera to take pictures. The purpose of being less than 0.7b is to avoid excessive size and damage to the leaves of the soybean plants.

[0036] The system further includes: a baling unit for baling the harvested soybean plants. After the harvesting is completed, the harvester uses a conveyor belt to transmit the harvested soybeans to the baling unit. Harvesting and baling are commonly used equipment in intelligent agricultural equipment. The embodiment of the present invention does not describe the baling unit accordingly, and a corresponding baler or baler can be used.

[0037] Among them, the difference from the existing soybean harvesting method is that the existing soybean harvesting generally involves peeling the pods from the rhizomes after the soybeans are harvested, placing them in a collection box for storage, and then transporting them to a sorting workshop for sorting, packaging, and processing. However, the pods have a short shelf life and are easily damaged or corrupted during long-distance transportation, resulting in the pods being stale and having an unsatisfactory selling price. Preservatives are sprayed during processing in the workshop, but as food safety issues become more prominent and green food is promoted, the use of preservatives is gradually not accepted by people. Therefore, the present invention uses the method of harvesting the soybean plants and carrying the pods together for sorting, packaging, and processing. The soybean plants are not separated from the pods during transportation. The purpose of doing this is that the soybean plants with stems and branches can effectively cushion the impact during transportation and can protect the pods well. Traditional edamame harvesters directly screen and peel the pods after harvesting in the field, which causes great damage to the pods and there will be losses during peeling. The pods have a short shelf life and are not easy to transport. The soybean plants and pods are not separated and bundled for transportation. The liquid and branches preserved in the soybean plants can provide supply for the pods within a certain period of time, ensuring their freshness within a certain period of time, increasing their shelf life, and facilitating long-term transportation and storage.

[0038] Among them, in the embodiment of the present invention, the number of image acquisition modules in the fourth detection unit corresponds to the number of soybean plant rows corresponding to the harvesting width parameter. In this way, it is convenient to assume that the harvesting width corresponds to 5 rows of soybean plants, then the number of image acquisition modules in the fourth detection unit is 4, and each image acquisition module corresponds to collecting images of the space between 2 rows of soybean plants, that is, the number of image acquisition modules in the fourth detection unit is equal to the number of soybean plant rows corresponding to the harvesting width parameter minus 1.

[0039] In this embodiment of the present invention, the control unit is further used for: The obstacle monitoring data collected by each image acquisition module are spliced ​​to obtain obstacle monitoring splicing data, the obstacle monitoring splicing data are analyzed to obtain obstacle splicing information, and the movement of the harvesting unit is controlled and alarmed based on the obstacle splicing information.

[0040] Among them, since in the real-time scheme of the above-mentioned embodiment, the obstacle monitoring data collected by each image acquisition module is the image data of the space between the corresponding two rows of soybean plants, therefore, if a tool is long, such as a hoe or a fence or other long strip tool, its length will span several rows of soybean plants, and each image acquisition module can only capture the image of the space between the two rows of soybean plants, that is, the image data corresponding to the partial length of the long strip tool, and it is impossible to form a whole shooting and recognition of the long strip tool. Relying solely on the identification of each split part is likely to cause wrong identification. For example, a hoe cannot be accurately identified when the hoe blade of the hoe is not photographed. For example, when the hoe rod of the hoe is photographed, it may be identified as a wooden rod or a dead rod, etc., thereby causing wrong identification. In order to solve this problem, the present invention splices the obstacle monitoring data collected by each image acquisition module to obtain obstacle monitoring splicing data. In this way, a relatively complete image of the obstacle in front of the harvester can be obtained, and the obstacle can be accurately identified.

[0041] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0042] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A soybean intelligent harvesting system, characterized in that: The system comprises: The first acquisition unit is used to collect three-dimensional surface data of the planting area when sowing soybeans; A second collection unit is used to collect distribution data of seedlings in the planting area when the soybean plants are in the seedling stage and during the fertilization process of the soybean plants; The third collection unit is used to collect the growth height data of the soybean plants in the planting area before harvesting when the soybean plants are in the edamame harvesting stage; A calculation unit, used for planning a harvesting route based on the distribution data and a harvesting width parameter of the harvesting unit, and for generating harvesting height data in the harvesting unit corresponding to a position passed by the harvesting route based on the three-dimensional surface data and the growth height data; A harvesting unit, used for harvesting soybean plants; The control unit is used to control the harvesting unit to harvest the soybean plants according to the harvesting route, and to control the cutting height of the harvesting unit according to the harvesting height data corresponding to the position passed by the harvesting route during the harvesting process.

2. The soybean intelligent harvesting system according to claim 1, characterized in that: The first acquisition unit is specifically used for: Establish a spatial three-dimensional coordinate system for the planting area; Set a reference level on the ground in the planting area; Scan the ground of the planting area to obtain scanning data; Based on the scanning data and the reference horizontal plane, the difference data between each coordinate point in the planting area and the reference horizontal plane in the height direction is obtained; The three-dimensional data of the ground surface is obtained based on the coordinate data of each coordinate point in the planting area and the corresponding difference data.

3. The soybean intelligent harvesting system according to claim 1, characterized in that: The distribution data of the seedlings in the planting area includes: the planting coordinate data of the seedlings and the interval distance data between the seedlings.

4. The soybean intelligent harvesting system according to claim 1, characterized in that: The third acquisition unit is specifically used to take pictures of soybean plants in the edamame harvesting stage to obtain soybean plant images, identify the height of the soybean plants in the images, and calculate and obtain the growth height data of the soybean plants in the planting area before harvesting based on the identification results.

5. The soybean intelligent harvesting system according to claim 1, characterized in that: The system further comprises: a fourth detection unit, configured to monitor obstacles on the ground in a moving direction of the harvesting unit when the harvesting unit is moving, and obtain obstacle monitoring data; The control unit is also used to analyze the obstacle monitoring data to obtain obstacle information, and control and warn the progress of the harvesting unit based on the obstacle information.

6. The soybean intelligent harvesting system according to claim 5, characterized in that: The fourth detection unit includes: a plurality of image acquisition modules, each of which includes: an electric telescopic rod, a camera, a protective cover and a data transmission module; one end of the electric telescopic rod is fixedly connected to the harvesting unit, and the other end of the electric telescopic rod extends toward the ground in front of the harvesting unit and is fixedly connected to the back of the protective cover; the camera is fixed in the protective cover, and is used to take pictures of the ground in front of the harvesting unit to obtain obstacle monitoring data; the data transmission module is used to transmit the obstacle monitoring data to the control unit; the control unit is also used to adjust the length of the electric telescopic rod based on the growth height data.

7. The soybean intelligent harvesting system according to claim 6, characterized in that: The protective cover is hemispherical, the camera is mounted in the protective cover through a bracket, and a plurality of light sources facing the ground are arranged in the protective cover.

8. The soybean intelligent harvesting system according to claim 1, characterized in that: The system further comprises a baling unit for baling the harvested soybean plants.

9. The soybean intelligent harvesting system according to claim 6, characterized in that: The number of image acquisition modules in the fourth detection unit corresponds to the number of soybean plant rows corresponding to the harvesting width parameter.

10. The soybean intelligent harvesting system according to claim 6, characterized in that: The control unit is also used for: The obstacle monitoring data collected by each image acquisition module are spliced ​​to obtain obstacle monitoring splicing data, the obstacle monitoring splicing data are analyzed to obtain obstacle splicing information, and the movement of the harvesting unit is controlled and alarmed based on the obstacle splicing information.

Images