Crop ridge navigation methods, devices, systems, control equipment, and storage media

Abstract

This invention proposes a method, device, system, control equipment, and storage medium for crop ridge navigation, belonging to the field of data processing. The method includes: acquiring crop images of the current working area in real time; identifying the crop images to obtain crop outline information of the current working area; determining whether the current driving path interferes with the crop planting area based on the crop outline information; if so, obtaining a corrected path for the interfering area based on the crop outline information; and performing ridge navigation of the interfering area based on the corrected path, so as to avoid crushing and damaging the crops in the interfering area when the agricultural machinery performs ridge navigation operations, thereby reducing the risk of crushing the crops.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more specifically, to a method, apparatus, system, control device, and storage medium for crop row navigation. Background Technology

[0002] Agricultural machinery refers to all kinds of mechanical equipment used in agricultural production, such as large and small tractors and land leveling machines. The navigation system of agricultural machinery is one of the important factors affecting the quality of agricultural machinery operations.

[0003] Currently, agricultural machinery navigation for crop ridge following includes methods such as offline satellite positioning data navigation and pure visual sensor navigation. Offline satellite positioning data navigation cannot provide real-time information about the growth of crops around the machinery, posing a risk of damaging crops during operation. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, system, control equipment, and storage medium for crop ridge navigation, which can improve the current method of agricultural machinery navigation based on offline satellite positioning data, which poses a risk of damaging crops during operation.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows.

[0006] In a first aspect, embodiments of the present invention provide a crop ridge navigation method, the method comprising:

[0007] Real-time acquisition of crop images in the current work area; recognition of the crop images to obtain crop outline information in the current work area;

[0008] Based on the crop outline information, determine whether the current driving path interferes with the crop planting area;

[0009] If so, a corrected path for the interference area is obtained based on the crop outline information, wherein the interference area is the region where the current driving path and the crop planting area cause interference;

[0010] Based on the correction path, perform row-following navigation in the interference area.

[0011] Optionally, the crop contour information includes crop contour lines and crop planting areas, and the step of obtaining a correction path for the interference area based on the crop contour information includes:

[0012] Take the outline of crops in the interference area as the target outline;

[0013] If the target contour line includes two crop contour lines, then the crop center line of the crop planting area associated with the target contour line is fitted, and the correction path is determined based on the crop center line.

[0014] If the target contour line includes a crop contour line, then the path offset by a set distance from the crop contour line will be used as the correction path.

[0015] Optionally, the step of extracting the crop contour line of the interference area as the target contour line based on the crop contour information includes:

[0016] Based on the crop outline information, the crop outline that is located in the interference area and on both sides of the current driving path or the center line of the field of vision is selected as the target outline.

[0017] The center line of the field of view is the central axis of the agricultural machinery.

[0018] Optionally, the step of fitting the crop centerline of the crop planting area associated with the target contour line and determining the correction path based on the crop centerline includes:

[0019] From the crop planting area, determine the two target crop areas associated with the two crop outlines;

[0020] A fitting method is used to perform center fitting on the two target crop areas to obtain the crop center lines of each of the two target crop areas, and the midline between the two crop center lines is determined to obtain the correction path.

[0021] Optionally, before fitting the crop centerline of the crop planting area associated with the target contour line, the method further includes: determining whether the distance between the two crop contour lines is greater than or equal to a preset distance.

[0022] The step of fitting the crop centerline of the crop planting area associated with the target contour line is performed when it is determined that the distance between the two crop contour lines is greater than or equal to a preset distance.

[0023] Optionally, after the step of determining whether the distance between the two crop outlines is greater than a preset distance, the method further includes:

[0024] When it is determined that the distance between the two crop outlines is less than a preset distance, a detour path is determined based on the pre-stored path points of the current work area. The detour path is used to guide the agricultural machinery to detour around the interference area.

[0025] Optionally, after the step of determining whether the distance between the two crop outlines is greater than a preset distance, the method further includes:

[0026] When it is determined that the distance between the two crop outlines is less than the preset distance, multiple pre-selected paths are identified;

[0027] Calculate the damage value of each of the pre-selected paths to the two target crop areas;

[0028] The pre-selected path with the smallest damage value is chosen as the correction path.

[0029] Optionally, the step of calculating the damage value of each of the pre-selected paths to the two target crop areas includes:

[0030] For each of the pre-selected paths, the interference area between the pre-selected path and the two target crop intervals is calculated to obtain the damage value.

[0031] Optionally, the step of recognizing the crop image to obtain the crop outline information of the current work area includes:

[0032] Using visual algorithms or pre-trained crop region recognition models, the crop planting areas in the crop images are identified;

[0033] Based on the crop planting area, the crop image is segmented to obtain the crop outline;

[0034] Alternatively, a pre-trained contour recognition model can be used to identify the crop outlines and crop planting areas in the crop image.

[0035] Optionally, the step of determining whether the current driving path interferes with the crop planting area based on the crop outline information includes:

[0036] Determine the center line of the field of view of the agricultural machinery in the crop image, and combine the center line of the field of view with a preset field of view range to determine the target field of view from the crop image; or, determine the target field of view from the crop image based on the current driving path and a preset field of view range.

[0037] Based on the crop outline information, the crop outline line located within the target field of view is obtained;

[0038] Based on the outline of crops within the target field of view, determine whether the current driving path interferes with the crop planting area.

[0039] Secondly, embodiments of the present invention provide a crop ridge navigation device, including an identification module, a path processing module and a navigation module;

[0040] The recognition module is used to acquire crop images of the current work area in real time, recognize the crop images, and obtain the crop outline information of the current work area;

[0041] The path processing module is used to determine whether the current driving path interferes with the crop planting area based on the crop outline information. If so, it obtains a corrected path for the interference area based on the crop outline information.

[0042] The interference zone is the area where the current driving path and the crop planting area cause interference.

[0043] The navigation module is used to perform row-following navigation in the interference area according to the correction path.

[0044] Thirdly, embodiments of the present invention provide a crop ridge navigation system, including control equipment and camera equipment for installation on agricultural machinery;

[0045] The camera device is used to collect real-time images of crops in the current working area of ​​the agricultural machinery and send them to the control device;

[0046] The control device is used to implement the crop ridge navigation method as described in the first aspect.

[0047] Fourthly, embodiments of the present invention provide a control device, including a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the crop ridge navigation method as described in the first aspect.

[0048] Fifthly, embodiments of the present invention provide a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the crop ridge navigation method as described in the first aspect.

[0049] The crop ridge-following navigation method, device, system, control equipment, and storage medium provided in any embodiment of the present invention acquire crop images in real time when the agricultural machinery follows the ridge, and obtain crop outline information after recognizing the crop images. When it is determined that the current driving path of the agricultural machinery interferes with the crop planting area based on the crop outline information, a correction path for the interference area is obtained through the crop outline information. This allows the agricultural machinery to follow the correction path to perform ridge-following operations in the interference area, thereby avoiding crushing and damaging the crops in the interference area and reducing the risk of crushing the crops.

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A block diagram of the crop ridge navigation system provided in an embodiment of the present invention is shown.

[0053] Figure 2 This is a schematic flowchart of one of the crop ridge navigation methods provided in an embodiment of the present invention.

[0054] Figure 3 It shows Figure 2 A flowchart illustrating some of the sub-steps of step S102.

[0055] Figure 4 The second schematic diagram of the crop ridge navigation method provided in the embodiment of the present invention is shown.

[0056] Figure 5 A schematic diagram illustrating an example of agricultural machinery field-of-view calibration provided in an embodiment of the present invention is shown.

[0057] Figure 6 The third schematic diagram of the crop ridge navigation method provided in the embodiment of the present invention is shown.

[0058] Figure 7 It shows Figure 2 or Figure 4 One of the flowcharts for some sub-steps of step S106.

[0059] Figure 8 It shows Figure 2 or Figure 4 The second flowchart of some sub-steps in step S106.

[0060] Figure 9 A schematic diagram of the agricultural machinery following the ridge in the current work area is shown.

[0061] Figure 10 A block diagram of an agricultural machine provided by an embodiment of the present invention is shown.

[0062] Figure 11 A block diagram of the crop ridge navigation device provided in an embodiment of the present invention is shown.

[0063] Figure 12 A block diagram of a control device provided in an embodiment of the present invention is shown.

[0064] Reference numerals: 100-Crop ridge navigation system; 110-Agricultural machinery; 120-Control equipment; 130-Camera equipment; 140-Camera module; 150-Processing module; 160-Navigation module; 170-Operation module; 180-Crop ridge navigation device; 190-Identification module; 200-Path processing module. Detailed Implementation

[0065] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0066] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0067] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0068] The navigation system of agricultural machinery is one of the important factors affecting the quality of agricultural machinery operations. Currently, agricultural machinery navigation generally adopts multi-sensor fusion technology or crop row navigation. Multi-sensor fusion technology refers to fusing information obtained from two or more sensors for navigation. Crop row navigation refers to navigation based on the location information of planted crops.

[0069] Ridging is a common operation performed by agricultural machinery, and it includes tasks such as mulching, covering with soil, and cultivating. When agricultural machinery performs ridge-following operations, high navigation accuracy is required. Prior to ridge-following, tasks such as ridging and sowing may be necessary.

[0070] Currently, offline satellite positioning data is generally used for navigation when agricultural machinery follows the rows. However, when using offline satellite positioning data for navigation, the lack of real-time monitoring of crop growth around the machinery poses a risk of damaging crops during operation.

[0071] Based on the above considerations, embodiments of the present invention provide a crop ridge-following navigation scheme, which can improve the accuracy of navigation and alleviate the problem of high risk of crop damage during current ridge-following navigation processes. The scheme will be described in detail below.

[0072] In one embodiment, refer to Figure 1 A crop ridge navigation system 100 is provided, which includes an agricultural machine 110, a control device 120 for the agricultural machine 110, and a camera device 130 installed on the agricultural machine 110.

[0073] The camera device 130 is used to collect real-time images of crops in the current working area of ​​the agricultural machinery 110 when the agricultural machinery 110 is carrying out ridge-following operations, and send them to the control device 120.

[0074] The control device 120 is used to implement the crop ridge navigation method provided by the present invention.

[0075] In detail, the control device 120 is used to receive crop images of the current working area, and based on the crop outline information of the current working area obtained by recognizing the crop images, it determines when the current driving path of the agricultural machinery 110 interferes with the crop planting area. Then, it obtains a correction path for the interference area based on the crop outline information, and controls the agricultural machinery 110 to perform ridge navigation and ridge operation in the interference area according to the correction path.

[0076] The interference zone is the area where the current driving path and the crop planting area cause interference. The control device 120 can be an automatic driving device for controlling the agricultural machinery 110 to perform automatic driving, or it can be a control device for controlling the agricultural machinery 110 to perform automatic driving and automatic operation. In this embodiment, it is not limited to a single one.

[0077] The current driving path of the agricultural machinery 110 can be obtained based on satellite positioning information, or it can be the corrected path of the previous interference area obtained after the last identification of crop images.

[0078] Compared to agricultural machinery 110 which uses satellite positioning data for navigation, the above-mentioned crop following navigation system 100 analyzes the crop images of the current working area of ​​the agricultural machinery 110 in real time during the following operation. When the current driving path interferes with the crop planting area, it plans a corrective path to avoid the interference based on the crop outline information obtained from the crop images. Thus, when the agricultural machinery 110 follows the corrective path for following operation, it can minimize interference with the planting area and reduce the crushing and damage to the crops.

[0079] In one embodiment, refer to Figure 2 A method for navigating crop ridges is provided, comprising the following steps. This method can be applied to the control device 120 of the crop ridge navigation system 100 provided in the above embodiments.

[0080] S102: Acquire crop images of the current work area in real time, identify the crop images, and obtain the crop outline information of the current work area.

[0081] The crop outline information may include crop outlines and crop planting areas. It should be understood that crop outlines and crop planting areas are related; each crop outline is associated with a crop planting area, and the crop outline is the edge outline of its associated crop planting area.

[0082] For example, using duration T as the duration of each moment, and moment t-1 being the moment preceding moment t, camera device 130 captures one image of the crop at each moment or at a set frequency, and sends the captured crop image to control device 120. At moment t, the agricultural machinery 110 is performing ridging operations in the current work area according to its current travel path, and control device 120 receives the crop image sent by camera device 130. After receiving the crop image, control device 120 immediately analyzes and identifies the crop image to obtain the crop outline information of the current work area.

[0083] The crop image recognition method described above can be selected as needed. For example, it can be recognized using visual algorithms or using a pre-trained crop region recognition model. Based on this, refer to... Figure 3 The following is a flowchart illustrating some sub-steps of step S102 above. The crop image can be identified and the crop outline information of the current work area can be obtained through the following steps:

[0084] S1021 uses visual algorithms or pre-trained crop region recognition models to identify crop planting areas in crop images.

[0085] Visual algorithms can be flexibly selected based on preferences and practical applications. For example, they can be neural networks for recognizing crops or neural networks for recognizing the furrows of crops planted in the field.

[0086] S1022, Based on the crop planting area, the crop image is segmented to obtain the crop outline.

[0087] Alternatively, the crop image recognition in S102 can be achieved in the following way to obtain the crop outline information of the current work area: using the pre-trained outline recognition model, the crop outline and crop planting area in the crop image can be identified.

[0088] It should be understood that the crop region identification model and the contour recognition model can be models trained using machine learning or neural networks. Furthermore, the training methods can be flexibly selected, and this embodiment does not impose specific limitations.

[0089] The method of segmenting crop images can also be flexibly selected according to individual needs and actual scenarios. For example, segmentation can be performed according to preset rules, adaptive threshold segmentation, or segmentation can be performed using neural networks with AI semantic segmentation capabilities.

[0090] The image after segmenting the crop outline and crop planting area can be called a outline image, on which the crop outline is clearly segmented. At this point, based on this outline image, and combined with the pre-calculated scale factor between the pixels of the image captured by the camera device 130 at the field of view and the actual distance, scale transformation can be performed to obtain the crop outline information.

[0091] The crop outline information includes, but is not limited to: crop planting area, number of crop planting areas, crop outline line, number of crop outline lines, actual location set of each crop outline line (it should be understood that a crop outline is composed of multiple location points) and size of each crop planting area.

[0092] S104, Based on the crop outline information, determine whether the current driving path interferes with the crop planting area. If yes, proceed to step S106. If no, proceed to step S105.

[0093] After obtaining the crop outline information, the crop outline closest to the current driving path can be determined based on the location information of the current driving path of the agricultural machinery 110. Then, based on the location information, the distance can be calculated to determine the area where the current driving path interferes with the crop planting area, which is the interference area.

[0094] In the above description, the current driving path can be a corrected path at time t-1 obtained from the crop image at the previous time (i.e., time t-1), a preset navigation path, or a navigation path obtained from satellite positioning data. Regardless of the path, the current driving path is known. The method for determining whether interference occurs can be flexibly chosen. For example, in one possible implementation, the current driving path can be placed into the crop outline information, and the distance between the current driving path and the nearest crop outline lines on both sides at various locations can be compared to see if it is less than half the width of the agricultural machinery 110 or half the wheelbase of the agricultural machinery 110. If so, then interference will occur in that location area.

[0095] For example, the position information of the crop outlines located on both sides of the current driving path of the agricultural machinery 110 and the nearest crop outlines, as well as the position information of the current driving path, can be extracted from the crop outline information. The distance between the current driving path and each position of the crop outlines can be calculated. Based on the relationship between the distance and a preset threshold, it can be determined whether interference has occurred. The preset threshold can be half the width of the agricultural machinery 110 or half the wheelbase of the agricultural machinery 110, or it can be an empirical value.

[0096] The location of the disturbance means that when agricultural machinery 110 travels to that location, it will cause disturbance to the crop planting area, including but not limited to damage and crushing.

[0097] S105, continue following the current driving route for siding navigation.

[0098] S106, Obtain the correction path for the interference area based on the crop outline information.

[0099] The interference zone is the area where the current driving path and the crop planting area cause interference.

[0100] After identifying the current driving path and the interference areas in the crop planting area, a corrective path that can avoid interference can also be determined based on the crop outline information.

[0101] S108, based on the correction path, performs row-following navigation in the interference area.

[0102] Once the correction path is determined, it can be associated with the interference area. This allows the agricultural machinery 110 to immediately switch from the current path to the correction path after it travels to the interference area, thus controlling the machinery to travel through the interference area and complete the ridge-following operation.

[0103] Compared with satellite positioning data navigation, the above-mentioned crop ridge-following navigation method, when the agricultural machinery 110 follows the ridge, the control device 120, based on the crop outline information obtained by recognizing the real-time acquired crop images, confirms that the current driving path of the agricultural machinery 110 interferes with the crop planting area. It then plans a correction path for the interference area according to the crop outline information, and performs ridge-following operations in the interference area according to the correction path, so as to avoid crushing and damaging the crops in the interference area during the driving of the agricultural machinery 110 as much as possible, and reduce the risk of crushing the crops.

[0104] In one implementation, if the current driving path in S104 is a pre-planned path based on satellite positioning data, then the crop ridge navigation method provided by this invention employs a fusion of satellite positioning data and visual recognition. In this approach, satellite positioning data is used for navigation in non-interference areas, while visual recognition is used for navigation in interference areas. This not only improves the high cost of binocular visual recognition navigation due to its high equipment requirements and complex algorithms, and the low accuracy of monocular visual recognition navigation, but also addresses the problem of navigation deviations caused by inaccurate satellite positioning data.

[0105] In this situation, to quickly obtain the current driving route, refer to Figure 4 The crop ridge navigation method provided in this embodiment may further include S103. S103 may be performed before step S102 or S104.

[0106] S103: Obtain the current location information of the agricultural machinery and combine it with the pre-stored path points of the current work area to obtain the current driving path of the agricultural machinery in the work area.

[0107] Among them, the pre-stored path points of the current work area are the path points recorded by the agricultural machinery 110 before performing operations such as sowing or ridging in the current work area.

[0108] The control device 120 can obtain the current location information of the agricultural machinery 110 through satellite navigation systems such as GPS positioning system. Given the current location of the agricultural machinery 110, its heading (center line of view), the locations it has already traveled, and the path points in the current work area, the control device 120 can quickly determine the current travel path of the agricultural machinery 110 in the work area.

[0109] Furthermore, since the crop images captured by the camera device 130 may include not only the crop planting areas currently requiring operation but also crop planting areas not currently requiring operation, in order to avoid the crop planting areas not currently requiring operation affecting the determination of the existence of interference areas, and to reduce the amount of data processed in the images, in some embodiments, the field of view required for the operation of the agricultural machinery 110 can be pre-calibrated according to actual needs before the agricultural machinery 110 performs ridging operations or production. Subsequently, based on this field of view, the corresponding target area can be selected from the crop images captured by the camera device 130, and relevant processing can be performed based on the image information of the target area. The calibration of the field of view can be based on the central axis of the agricultural machinery, and the process of calibrating the field of view can be as follows:

[0110] Please refer to Figure 5 (a) Construct a three-sided support as shown in the diagram using round plastic tubes (composed of OA, OB, and OC, with OB and OC having equal lengths). Position the BC side of the three-sided support close to the front side of the rear wheel of the agricultural machinery 110, making the BC side as parallel as possible to the rear wheel axle of the agricultural machinery 110. Use a tape measure to measure the distance between point B and the outer wall of the left wheel of the agricultural machinery 110, and the distance between point C and the outer wall of the right wheel of the agricultural machinery 110, and determine whether they are equal. If they are not equal, adjust the position of the three-sided support so that the distance between point B and the outer wall of the left wheel of the agricultural machinery 110 is equal to the distance between point C and the outer wall of the right wheel of the agricultural machinery 110. When the distance between point B and the outer wall of the left wheel of the agricultural machinery 110 is equal to the distance between point C and the outer wall of the right wheel of the agricultural machinery 110, take the direction of OA as the flight path direction and the straight line of OA as the centerline of the agricultural machinery 110.

[0111] After obtaining the centerline of the agricultural machinery 110, the target field of view is determined based on the centerline of the agricultural machinery 110, using a preset field of view size. For example, a preset field of view size of 2×2m, located 1m in front of the agricultural machinery, is used as the target field of view. Figure 5 As shown in (b), the distance between the target field of view and the agricultural machinery 110 is 1m, and the distance between the two sides of the target field of view and the central axis is also 1m. Therefore, the range shown by the target field of view is the target area. The preset field of view range can be related to the width of the crop rows and / or the wheelbase or width of the agricultural machinery. In practical applications, it can be adaptively adjusted according to actual needs.

[0112] After determining the target field of view, in order to obtain the actual size of the target area corresponding to the target field of view, so as to facilitate the subsequent conversion of the interference area and the correction path, the coordinates of the four corner points of the target field of view can be extracted as calibration parameters. Based on the calibration parameters, the image is converted into a bird's-eye view, and the scale factor of the target field of view can be determined based on the bird's-eye view.

[0113] Wherein, the scale factor in the x-direction is: The scaling factor in the y-direction is: I x L represents the actual width of the target's field of view within the actual crop area. x I represents the width of the target field of view within the image. y L represents the actual length of the target's field of view within the actual crop area. y This indicates the length of the target's field of view within the image.

[0114] In the embodiment of selecting the corresponding target region in the crop image using the target field of view, step S104 can be adjusted accordingly. Based on this, referring to... Figure 6 Step S104 may include the following steps:

[0115] S1041, determine the center line of the field of view of the agricultural machinery in the crop image, and combine the center line of the field of view with the preset field of view range to determine the target field of view from the crop image.

[0116] The center line of vision is the straight line where the central axis of the agricultural machinery 110 is located.

[0117] Alternatively, the target field of view can be determined by identifying the crop image based on the current driving path and the preset field of view range.

[0118] It should be understood that the current navigation path and the center line of view may not be on the same straight line.

[0119] S1042, Based on the crop outline information, obtain the crop outline line located within the target field of view.

[0120] When there is a need to simplify calculations, there can be no more than two crop outlines within the target field of view. However, if it is necessary to determine in advance whether the next driving path will interfere with the corresponding crop outline, there can be more than two crop outlines within the target field of view.

[0121] S1043, based on the outline of crops within the target's field of view, determine whether the current driving path interferes with the crop planting area.

[0122] In detail, when there are two crop outlines in the target field of view, the following can be done: calculate the distance between each crop outline and the current driving path. If the distance between at least one crop outline and the current driving path is less than half the width of the agricultural machinery 100 or half the wheel track of the agricultural machinery 110, then interference is determined to have occurred; otherwise, no interference is caused.

[0123] When there is only one outline of crops in the target field of view, the following can be done: calculate the distance between the outline of crops and the current driving path. If the distance is less than half the width of the agricultural machine 100 or half the wheel track of the agricultural machine 110, then it is determined that interference has occurred; otherwise, no interference has occurred.

[0124] After identifying the area causing the interference, the area containing the interference is designated as the interference zone. However, it should be noted that since the agricultural machinery 110 has already stored the coordinate information of its current travel path before operation, and the agricultural machinery 110 will inevitably operate along the current travel path during operation, the target field of view can be determined from the crop image by directly replacing the center line of the field of view with the current travel path after obtaining the required field of view range.

[0125] After identifying the interference zone, in one possible implementation, refer to Figure 7 The correction path for the interference area can be obtained through the following steps, i.e., S106 is achieved.

[0126] S1061, Based on the crop outline information, extract the crop outline of the interference area as the target outline. If the target outline includes two crop outlines, proceed to step S1063 or S1067; if the target outline includes a single-sided crop outline, proceed to step S1065.

[0127] The target outline is the outline of the crop that is closest to the current driving path. The acquisition method can be flexibly selected. For example, it can be the outline of the crop within the target field of view, or it can be extracted according to preset rules, or it can be extracted after calculating the distance.

[0128] In one implementation, this can be achieved by selecting, based on crop outline information, crop outlines located in the interference zone and on either side of the center line of the field of view or the current driving path as target outlines.

[0129] The center line of the field of view is the central axis of the agricultural machinery 110. It should be understood that the outline of the crops closest to the center line of the field of view and located in the interference zone is the target outline.

[0130] S1063, fit the crop centerline of the crop planting area associated with the target contour line, and determine the correction path based on the crop centerline.

[0131] The crop planting area associated with the target outline is the crop planting area associated with two crop outlines, and the crop outline is the edge outline of the crop planting area it is associated with.

[0132] Generally, the selected agricultural machinery 110 is adapted to the row spacing of crops in the work area. In this case, if the target outline is two crop outlines, the center line between the two crop outlines can be fitted and then used as the correction path.

[0133] In detail, the correction path can be obtained in the following way: From the crop planting area, identify two target crop areas associated with two crop outlines; use a fitting method to perform center fitting on the two target crop areas to obtain the crop center lines of the two target crop areas, and determine the midline between the two crop center lines to obtain the correction path.

[0134] S1065, use the path that offsets the crop outline by a set distance as the correction path.

[0135] When the agricultural machinery 110 is at the boundary of the work area, there may only be a crop outline on one side of the machinery, while the other side may not have a crop outline. In this case, the target outline is the crop outline on one side. The center line of the agricultural machinery 110's field of vision, relative to the outlines on both sides, represents the boundary line of the work area and the crop outline, respectively. Therefore, it is only necessary to focus on whether the agricultural machinery 110 interferes with the crop outline. Thus, the path after deviating from this single-sided crop outline by a set distance is the correction path. The set distance should be at least half the width of the agricultural machinery 110 or half the wheelbase of the agricultural machinery 110.

[0136] When the width of the agricultural machinery 110 is less than the width of the two rows of crops in the work area, that is, when the influence of vigorous crop growth is not considered, and the relationship between the spacing between crop rows and the width and wheel track of the agricultural machinery 110 is not considered, the above step S1063 can also be: fitting the center line between the two crop outlines and using the center line as the correction path.

[0137] In special circumstances such as when crops are growing vigorously, the distance between the outlines of two crops may be less than a preset distance. If the agricultural machinery 110 continues to operate in this situation, it may crush crops on one or even both sides. To avoid crushing crops by the agricultural machinery 110 in this case, the distance between the outlines of the two crops can be determined before executing step S1063. Based on this, referring to... Figure 8 S106 may also include the following steps.

[0138] S1062, determine whether the distance between the two crop outlines is greater than or equal to the preset distance.

[0139] Accordingly, step S1063 is executed when it is determined that the distance between the two crop outlines is greater than or equal to a preset distance. That is, when the distance between the two crop outlines is greater than the preset distance, the center line between the two crop center lines is used as the correction path, wherein the distance from the center line to the two crop center lines is equal.

[0140] The inner edge spacing is relative to the agricultural machinery 110, and the inner edge is the side of the target outline closer to the agricultural machinery 110.

[0141] After determining whether the distance between the two crop outlines is greater than the preset distance, step S1064 may also be included.

[0142] S1064, when it is determined that the distance between the two crop outlines is less than the preset distance, a bypass path is determined based on the pre-stored path points of the current work area.

[0143] The bypass path is used to guide agricultural machinery to avoid interference areas.

[0144] The pre-stored path points of the current work area refer to the path points recorded by the agricultural machinery 110 when performing sowing, ridging and other pre-ridge operations in the current work area, or they can be the path points of the preset navigation path.

[0145] The method of determining the bypass path can be flexibly chosen; for example, the ridge in the interference area can be abandoned.

[0146] In one implementation, the bypass path can be obtained by: acquiring the current position information of the agricultural machinery 110, determining the initial path point of the next row of crops from the pre-stored path points of the current work area, returning from the current position to the initial path point of the current row of crops, and using the path formed by the current position to the initial path point of the next row of crops as the bypass path.

[0147] The next row of crops refers to the next row of crops to be followed. The starting point of the already followed path within the current row of crops is taken as the initial path point of the current row of crops. The starting point of the next row of crops that is on the same side as the starting path point of the current row of crops is taken as the starting path point of the next row of crops.

[0148] For example, refer to Figure 9 Assuming there are 6 rows of crops in the current work area, and the agricultural machinery 110 is currently positioned between the third and fourth rows, an interference zone is detected ahead. Here, A1 is the starting path point for the fourth row of crops, and A2 is the starting path point for the fifth row of crops, located on the same side as A1. The path from the current position of the agricultural machinery 110 to A1 and then to A2 is the bypass path point.

[0149] When bypassing the interference zone, the location information of the bypassed interference zone can be recorded, and a bypass reminder can be generated to remind manual ridge following or agricultural machinery 110 to follow the interference zone.

[0150] Through the above steps, when the distance between the two crop outlines is greater than or equal to a preset distance, a correction path is determined; when the distance between the two crop outlines is less than a preset distance, a detour path is determined to avoid the interference area.

[0151] In other embodiments, when the distance between the two crop outlines of the target outline is less than a preset distance, multiple pre-selected paths can be determined in the area between the two crop outlines, and the damage value of each pre-selected path to the two target crop areas can be calculated. The pre-selected path with the smallest damage value is selected as the correction path.

[0152] The damage value can be the area of ​​interference. In this case, for each pre-selected path, the interference area between the pre-selected path and the two target crop areas is calculated to obtain the damage value. The damage value can also be other metrics such as interference probability. In specific applications, it can be adjusted according to actual needs. This embodiment is not the only one.

[0153] The pre-selected paths can be obtained as follows: using the methods described in steps S202 to S203 above, the centerline of the two crop centerlines is determined, and this centerline is used as the first pre-selected path. Next, a path that deviates from the first pre-selected path by a preset distance is used as the second pre-selected path, and so on, to obtain the target number of pre-selected paths. The preset distance for each step can gradually increase in the form of an arithmetic sequence.

[0154] The crop ridge navigation method provided in this embodiment can integrate satellite positioning and visual recognition for navigation, which can effectively solve the problem of actual crop positioning, improve navigation accuracy, and to a certain extent avoid the crushing and damage of crops in the crop planting area by the agricultural machinery 110, and reduce the damage to crops during the ridge following process of the agricultural machinery 110.

[0155] It should be understood that, although Figures 2-8 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order in which these steps are executed, and they can be performed in other orders.

[0156] Based on the above concept of crop ridge navigation method, in one embodiment, referring to Figure 10 An agricultural machine 110 is provided, which includes a camera module 140, a processing module 150, a navigation module 160, and an operation module 170.

[0157] The operation module 170 is used for ridging operations. The ridging operations include, but are not limited to: mulching, covering with soil, inter-row cultivation, and weeding.

[0158] The camera module 140 is used to acquire real-time images of crops in the current work area and send the crop images to the controller.

[0159] The processing module 150 is used to receive crop images sent by the camera module 140 in real time, identify the crop images, and obtain the crop outline information of the current working area.

[0160] The processing module 150 is also used to determine whether the current driving path interferes with the crop planting area based on the crop outline information. If so, it obtains a corrected path for the interference area based on the crop outline information and sends the corrected path to the navigation module 160.

[0161] The interference zone is the area where the current driving path and the crop planting area cause interference.

[0162] Navigation module 160 is used for navigation in the interference area according to the corrected path.

[0163] In the aforementioned agricultural machinery 110, the processing module 150 can determine the interference between the current driving path of the agricultural machinery 110 and the crop planting area, and obtain the correction path of the interference area based on the crop outline information. Then, the navigation module 160 navigates the interference area according to the correction path, so as to a certain extent avoid the crushing and damage of the crops in the interference area by the agricultural machinery 110 when the ridge-following module follows the ridge, and reduce the risk of crushing the crops.

[0164] Based on the above concept of crop ridge navigation method, in one embodiment, referring to Figure 11 It also provides a crop ridge navigation device 180, which can be applied to... Figure 1 The control device 120 in the middle, the crop ridge navigation device 180 includes an identification module 190, a path processing module 200 and a navigation module 160.

[0165] The recognition module 190 is used to acquire crop images of the current work area in real time, recognize the crop images, and obtain the crop outline information of the current work area.

[0166] The path processing module 200 is used to determine whether the current driving path interferes with the crop planting area based on the crop outline information. If so, it obtains a corrected path for the interference area based on the crop outline information.

[0167] The interference zone is the area where the current driving path and the crop planting area cause interference.

[0168] The navigation module 160 is used for following the ridges in the interference area according to the correction path.

[0169] In the aforementioned crop ridge-following navigation device 180, the identification module 190 identifies the crop outline information of the crop image. When the path processing module 200 determines that the current driving path of the agricultural machinery 110 interferes with the crop planting area, it obtains a corrected path for the interference area based on the crop outline information. Thus, the navigation module 160 navigates the interference area based on the corrected path, thereby avoiding, to a certain extent, the crushing and damage to the crops in the interference area by the agricultural machinery 110 when the operation module 170 follows the ridges in the interference area, reducing the risk of crushing the crops.

[0170] Specific limitations regarding the crop ridge navigation device 180 can be found in the above description of the crop ridge navigation method, and will not be repeated here. Each module in the crop ridge navigation device 180 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the control device 120 in hardware form or independently of it, or they can be stored in the memory of the control device 120 in software form, so that the processor can call and execute the corresponding operations of each module.

[0171] In one embodiment, a control device 120 is provided, the internal structure of which can be as follows: Figure 12 As shown, the control device 120 includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor of the control device 120 provides computing and control capabilities. The memory of the control device 120 includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the control device 120 is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, carrier networks, near-field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a crop row navigation method. The display screen of the control device 120 can be an LCD screen or an e-ink screen. The input devices of the control device 120 can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the casing of the control device 120, or an external keyboard, touchpad, or mouse.

[0172] Understandable Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the control device 120 to which the present invention is applied. The specific control device 120 may include, but is not limited to, the control device 120. Figure 12The diagram shows more or fewer components, or combinations of certain components, or different component arrangements.

[0173] In one embodiment, the crop ridge navigation device 180 provided by the present invention can be implemented as a computer program, and the computer program can be implemented in the form of, for example, Figure 11 The control device 120 shown operates on this device. The memory of the control device 120 can store the various program modules that make up the crop-following navigation device 180, for example, Figure 11 The identification module 190, path processing module 200, and navigation module 160 are shown. The computer program comprised of these modules causes the processor to execute the steps in the crop ridge navigation methods of the various embodiments of the present invention described in this specification.

[0174] For example, Figure 12 The control device 120 shown can be controlled by, for example Figure 11 The identification module 190 in the crop ridge navigation device 180 shown executes step S102. The control device 120 can execute steps S104-S106 through the path processing module 200. The control device 120 can execute step S108 through the navigation module 160.

[0175] In one embodiment, a control device 120 is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring crop images of the current work area in real time, recognizing the crop images to obtain crop outline information of the current work area; determining, based on the crop outline information, whether the current driving path interferes with the crop planting area; if so, obtaining a corrective path for the interference area based on the crop outline information, wherein the interference area is the region where the current driving path and the crop planting area interfere; and performing row-following navigation in the interference area based on the corrective path.

[0176] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: acquiring crop images of the current work area in real time, recognizing the crop images to obtain crop outline information of the current work area; determining, based on the crop outline information, whether the current driving path interferes with the crop planting area; if so, obtaining a corrected path for the interference area based on the crop outline information, wherein the interference area is the region where the current driving path and the crop planting area interfere; and performing row-following navigation in the interference area based on the corrected path.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0178] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0179] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0180] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for ridge navigation in crop cultivation, characterized in that, The method includes: Real-time acquisition of crop images in the current work area; recognition of the crop images to obtain crop outline information in the current work area; Based on the crop outline information, determine whether the current driving path interferes with the crop planting area; If so, when the distance between the two crop outlines in the interference area is greater than or equal to a preset distance, a correction path is determined; when the distance between the two crop outlines is less than the preset distance, an bypass path is determined based on the pre-stored path points of the current work area to bypass the interference area; when the bypass path cannot be determined, multiple pre-selected paths are determined in the area between the two crop outlines, and the damage value of each pre-selected path to the two target crop areas associated with the two crop outlines is calculated. The pre-selected path with the smallest damage value is selected as the correction path. The interference area is the area where the current driving path and the crop planting area cause interference. Based on the corrected path or the bypass path, perform ridge-following navigation in the interference area.

2. The crop ridge navigation method according to claim 1, characterized in that, The crop contour information includes crop outlines and crop planting areas. The step of obtaining a correction path for the interference area based on the crop contour information includes: Based on the crop outline information, the crop outline line in the interference area is extracted as the target outline line; If the target contour line includes two crop contour lines, then the crop center line of the crop planting area associated with the target contour line is fitted, and the correction path is determined based on the crop center line. If the target contour line includes a crop contour line, then the path offset by a set distance from the crop contour line will be used as the correction path.

3. The crop ridge navigation method according to claim 2, characterized in that, The step of extracting the crop contour lines of the interference area as the target contour lines based on the crop contour information includes: Based on the crop outline information, the crop outline that is located in the interference area and on both sides of the current driving path or the center line of the field of vision is selected as the target outline. The center line of the field of view is the central axis of the agricultural machinery.

4. The crop ridge navigation method according to claim 2 or 3, characterized in that, The step of fitting the crop centerline of the crop planting area associated with the target contour line and determining the correction path based on the crop centerline includes: From the crop planting area, determine the two target crop areas associated with the two crop outlines; A fitting method is used to perform center fitting on the two target crop areas to obtain the crop center lines of each of the two target crop areas, and the midline between the two crop center lines is determined to obtain the correction path.

5. The crop ridge navigation method according to claim 3, characterized in that, Before fitting the crop centerline of the crop planting area associated with the target contour line, the method further includes: determining whether the distance between the two crop contour lines is greater than or equal to a preset distance. The step of fitting the crop centerline of the crop planting area associated with the target contour line is performed when it is determined that the distance between the two crop contour lines is greater than or equal to a preset distance.

6. The crop ridge navigation method according to claim 5, characterized in that, The step of calculating the damage value of each of the pre-selected paths to the two target crop areas includes: For each of the pre-selected paths, the interference area between the pre-selected path and each of the target crop areas is calculated to obtain the damage value.

7. The crop ridge navigation method according to claim 1, characterized in that, The step of recognizing the crop image to obtain the crop outline information of the current work area includes: Using visual algorithms or pre-trained crop region recognition models, the crop planting areas in the crop images are identified; Based on the crop planting area, the crop image is segmented to obtain the crop outline; Alternatively, a pre-trained contour recognition model can be used to identify the crop outlines and crop planting areas in the crop image.

8. The crop ridge navigation method according to claim 1 or 7, characterized in that, The step of determining whether the current driving path interferes with the crop planting area based on the crop outline information includes: Determine the center line of the field of view of the agricultural machinery in the crop image, and combine the center line of the field of view with a preset field of view range to determine the target field of view from the crop image; or, determine the target field of view from the crop image based on the current driving path and a preset field of view range. Based on the crop outline information, the crop outline line located within the target field of view is obtained; Based on the outline of crops within the target field of view, determine whether the current driving path interferes with the crop planting area.

9. A crop ridge navigation device, characterized in that, The apparatus for implementing the crop ridge navigation method according to any one of claims 1-8 includes an identification module, a path processing module, and a navigation module; The recognition module is used to acquire crop images of the current work area in real time, recognize the crop images, and obtain the crop outline information of the current work area; The path processing module is used to determine whether the current driving path interferes with the crop planting area based on the crop outline information. If so, it obtains a corrected path or a bypass path for the interference area based on the crop outline information. The interference zone is the area where the current driving path and the crop planting area cause interference; the detour path is used to guide the agricultural machinery to detour around the interference zone, and is determined based on the pre-stored path points of the current working area when there are two crop outlines in the interference zone and the distance between the two crop outlines is less than a preset distance. The navigation module is used to perform ridge-following navigation in the interference area according to the corrected path or bypass path.

10. A crop ridge navigation system, characterized in that, This includes control equipment and camera equipment installed on agricultural machinery; The camera device is used to collect real-time images of crops in the current working area of ​​the agricultural machinery and send them to the control device; The control device is used to implement the crop ridge navigation method as described in any one of claims 1 to 8.

11. A control device, characterized in that, It includes a processor and a memory, the memory storing a computer program that can be executed by the processor to implement the crop ridge navigation method as described in any one of claims 1-8.

12. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the crop ridge navigation method as described in any one of claims 1-8.

Images