Crop ridge following navigation method, device and system, control equipment and storage medium

Abstract

The invention provides a crop ridge following navigation method, device and system, control equipment and a storage medium, and the method comprises the steps: determining a plurality of pre-selected paths in an area between two crop contour lines in target contour lines; the damage value of each preselected path to two target crop areas is calculated, and the two target crop areas are crop planting areas associated with the two crop contour lines; selecting the pre-selected path with the minimum damage value as a correction path; and performing ridge following navigation of the interference area according to the corrected path. The pre-selected path with the minimum damage value serves as the correction path, so that rolling compaction and damage of agricultural machinery to crops in a crop planting area are avoided to a certain extent, and damage to the crops in the ridge following process of the agricultural machinery is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to a crop following ridge navigation method, device, system, control equipment and storage medium. BACKGROUND

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

[0003] At present, the crop following ridge navigation of agricultural machinery includes the navigation based on offline satellite positioning data and the navigation based on pure visual sensor. The navigation based on offline satellite positioning data cannot perceive the growth conditions of crops around the agricultural machinery in real time, and there is a risk of crushing crops during operation. SUMMARY

[0004] The present application aims to provide a crop following ridge navigation method, device, system, control equipment and storage medium, which can improve the current navigation method of agricultural machinery based on offline satellite positioning data, and reduce the risk of crushing crops during operation.

[0005] To achieve the above-mentioned purpose, the technical solutions adopted by the embodiments of the present application are as follows.

[0006] In a first aspect, the embodiments of the present application provide a crop following ridge navigation method, which comprises:

[0007] Determine a plurality of pre-selected paths in the area between the two crop contour lines in the target contour line;

[0008] Calculate the damage value of each pre-selected path to two target crop areas, wherein the two target crop areas are the crop planting areas associated with the two crop contour lines;

[0009] Select the pre-selected path with the smallest damage value as the correction path;

[0010] According to the correction path, the following ridge navigation of the interference area is performed.

[0011] Optionally, the target contour line is a crop contour line located in the interference area and on both sides of the current driving path or the field of view center line.

[0012] Optionally, the calculation of the damage value of each pre-selected path to two target crop areas comprises:

[0013] For each pre-selected path, calculate the interference area of the pre-selected path and the target crop area to obtain the damage value.

[0014] Optionally, the method further comprises:

[0015] determining a middle line between the two target crop area center lines;

[0016] taking the middle line as a first pre-selected path;

[0017] taking a path deviating from the first pre-selected path by a preset distance as a second pre-selected path, to obtain a target number of pre-selected paths, wherein the preset distance gradually increases in the form of an arithmetic sequence each time.

[0018] Optionally, the method further comprises: determining whether the distance between the two crop contour lines in the target contour line is greater than or equal to a preset distance;

[0019] when the distance between the two crop contour lines in the target contour line is less than the preset distance, determining a plurality of pre-selected paths in the region between the two crop contour lines in the target contour line, calculating a damage value of each pre-selected path to the two target crop areas, selecting a pre-selected path with the smallest damage value as a correction path, and performing the ridge-following navigation of the interference area according to the correction path.

[0020] Optionally, the method further comprises: when the distance between the two crop contour lines in the target contour line is greater than or equal to the preset distance, performing center fitting on the two target crop areas by a fitting method to obtain the crop center lines of the two target crop areas and determine a middle line between the two crop center lines to obtain a correction path, and performing the ridge-following navigation of the interference area according to the correction path.

[0021] Optionally, before determining whether the distance between the two crop contour lines in the target contour line is greater than or equal to the preset distance, the method further comprises:

[0022] real-time acquiring a crop image of a current work area, identifying the crop image to obtain crop contour information of the current work area, wherein the crop contour information comprises crop contour lines and a crop planting area;

[0023] determining whether the current driving path interferes with the crop planting area based on the crop contour information;

[0024] if so, extracting the crop contour lines of the interference area as the target contour line according to the crop contour information.

[0025] Optionally, the identifying the crop image to obtain the crop contour information of the current work area comprises:

[0026] The crop planting area in the crop image is identified by using a visual algorithm or a pre-trained crop area identification model.

[0027] The crop image is segmented according to the crop planting area, and a crop contour line is obtained.

[0028] Alternatively, a pre-trained contour identification model is used to identify the crop contour line and the crop planting area in the crop image.

[0029] Optionally, the step of determining whether the current driving path interferes with the crop planting area based on the crop contour information comprises:

[0030] A visual field center line of the agricultural machine in the crop image is determined, and a target visual field is determined from the crop image in combination of the visual field center line and a preset visual field range, or based on the current driving path and the preset visual field range.

[0031] The crop contour line located in the target visual field is obtained based on the crop contour information.

[0032] Whether the current driving path interferes with the crop planting area is determined based on the crop contour line in the target visual field.

[0033] Optionally, when the crop contour line in the target visual field is two, the step of determining whether the current driving path interferes with the crop planting area based on the crop contour line in the target visual field comprises:

[0034] The distance between each crop contour line in the target visual field and the current driving path is calculated, and if at least one of the crop contour lines in the target visual field has a distance to the current driving path less than half of the width of the agricultural machine or half of the wheelbase of the agricultural machine, it is determined that interference occurs.

[0035] Optionally, when the current driving area is a non-interference area, the current driving path is a path corresponding to the current driving area in satellite positioning data navigation.

[0036] When the current driving area is the last interference area, the current driving path is a correction path corresponding to the last interference area.

[0037] In a second aspect, an embodiment of the present application provides a crop following ridge navigation device, comprising:

[0038] The path processing module is configured to determine a plurality of preselected paths in a region between two crop contour lines in the target contour lines, calculate a damage value of each of the preselected paths to two target crop areas associated with the two crop contour lines, and select a preselected path with the minimum damage value as a correction path.

[0039] The navigation module is configured to perform the ridge following navigation in the interference region according to the correction path.

[0040] In a third aspect, an embodiment of the present application provides a crop ridge following navigation system, including a control device and a camera device configured to be arranged on a farm machine.

[0041] The camera device is configured to collect a crop image of a current working area of the farm machine in real time and send the crop image to the control device.

[0042] The control device is configured to implement the crop ridge following navigation method.

[0043] In a fourth aspect, an embodiment of the present application provides a control device, including a processor and a memory, the memory storing a computer program executable by the processor, and the processor is configured to execute the computer program to implement the crop ridge following navigation method.

[0044] In a fifth aspect, an embodiment of the present application provides a storage medium, which stores a computer program executable by a processor to implement the crop ridge following navigation method.

[0045] The crop ridge following navigation method, device, system, control device and storage medium provided by any of the embodiments of the present application determine a plurality of preselected paths in a region between two crop contour lines in the target contour lines, calculate a damage value of each of the preselected paths to two target crop areas associated with the two crop contour lines, select a preselected path with the minimum damage value as a correction path, and perform the ridge following navigation in the interference region according to the correction path. By selecting the preselected path with the minimum damage value as the correction path, the damage of the crop ridge following process of the farm machine to the crops in the crop planting area is reduced to a certain extent.

[0046] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are referred to. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as a limitation to the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of the drawings.

[0048] Figure 1 A block schematic diagram of a crop following ridge navigation system provided by the embodiments of the present application is shown.

[0049] Figure 2 A flowchart of one of the crop following ridge navigation methods provided by the embodiments of the present application is shown.

[0050] Figure 3 A flowchart of the crop following ridge navigation method provided by the embodiments of the present application is shown. Figure 2 A flowchart of part of the sub-steps of step S102 is shown.

[0051] Figure 4 A flowchart of another of the crop following ridge navigation methods provided by the embodiments of the present application is shown.

[0052] Figure 5 An example schematic diagram of field of view calibration of an agricultural machine provided by the embodiments of the present application is shown.

[0053] Figure 6 A flowchart of another of the crop following ridge navigation methods provided by the embodiments of the present application is shown.

[0054] Figure 7 A flowchart of part of the sub-steps of step S106 is shown. Figure 2 Or Figure 4 A flowchart of part of the sub-steps of step S106 is shown.

[0055] Figure 8 A flowchart of part of the sub-steps of step S106 is shown. Figure 2 Or Figure 4 A flowchart of part of the sub-steps of step S106 is shown.

[0056] Figure 9 A schematic diagram of a following ridge operation of an agricultural machine in a current work area is shown.

[0057] Figure 10 A block schematic diagram of an agricultural machine provided by the embodiments of the present application is shown.

[0058] Figure 11 A block schematic diagram of a crop following ridge navigation device provided by the embodiments of the present application is shown.

[0059] Figure 12 A block schematic diagram of a control device provided by the embodiments of the present application is shown.

[0060] Reference numerals: 100 - crop row following navigation system; 110 - agricultural machine; 120 - control device; 130 - camera device; 140 - camera module; 150 - processing module; 160 - navigation module; 170 - operation module; 180 - crop row following navigation device; 190 - recognition module; 200 - path processing module. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0062] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0063] It should be noted that the relational terms such as "first" and "second" and the like are used only to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations exist in any such actual relationship or order. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a list of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0064] The navigation system of the agricultural machine is one of the important factors affecting the quality of the agricultural machine operation. At present, the navigation of the agricultural machine generally adopts multi-sensor fusion technology or crop row navigation. The multi-sensor fusion technology refers to fusing the information obtained by two or more sensors, fusing the information obtained by multiple sensors, and navigating. The crop row navigation refers to navigating according to the position information of the planted crops.

[0065] Row following operation is a common operation of the agricultural machine, and the row following includes film covering, soil covering and cultivation operations. The agricultural machine has high precision requirements for navigation when performing the row following operation. The operation before the row following can be ridging and seeding.

[0066] At present, in the following ridge navigation of agricultural machinery, the off-line satellite positioning data navigation method is generally adopted. When the off-line satellite positioning data is used for navigation, the growth condition of crops around the agricultural machinery cannot be perceived in real time, and the crops are prone to be crushed during operation.

[0067] Based on the above considerations, the embodiments of the present application provide a crop following ridge navigation scheme, which can improve the accuracy of navigation and solve the problem of high risk of crushing crops in the current following ridge navigation process. The scheme will be described in detail below.

[0068] In one embodiment, referring to Figure 1 , a crop following ridge navigation system 100 is provided, which includes an agricultural machine 110, a control device 120 of the agricultural machine 110, and a camera device 130 installed on the agricultural machine 110.

[0069] The camera device 130 is used to collect the crop image of the current operation area of the agricultural machine 110 in real time when the agricultural machine 110 is following the ridge operation, and send it to the control device 120.

[0070] The control device 120 is used to implement the crop following ridge navigation method provided by the present application.

[0071] In detail, the control device 120 is used to receive the crop image of the current operation area, and based on the crop contour information of the current operation area obtained by identifying the crop image, when the current driving path of the agricultural machine 110 interferes with the crop planting area, the correction path of the interference area is obtained according to the crop contour information, and then the agricultural machine 110 is controlled to follow the ridge navigation and ridge operation of the interference area according to the correction path.

[0072] Among them, the interference area is the area where the current driving path and the crop planting area interfere. The control device 120 can be an automatic driving device for controlling the agricultural machine 110 to automatically drive, or a control device for controlling the agricultural machine 110 to automatically drive and automatically operate, and the present embodiment is not limited to only one.

[0073] The current driving path of the agricultural machine 110 can be obtained according to the satellite positioning information, or the correction path of the last interference area obtained after the last identification of the crop image.

[0074] Compared with the agricultural machine 110 adopting satellite positioning data navigation, the crop ridge-following navigation system 100 can analyze the crop image of the current working area in real time during the ridge-following operation, and when the current driving path interferes with the crop planting area, a correction path can be planned according to the crop contour information obtained from the crop image, so that the agricultural machine 110 can perform ridge-following operation according to the correction path, thereby minimizing the interference with the planting area and reducing the rolling and damage to the crops.

[0075] In one embodiment, referring to Figure 2 , a crop ridge-following navigation method is provided, which can be applied to the control device 120 of the crop ridge-following navigation system 100 provided in the above embodiments.

[0076] S102, real-time acquisition of the crop image of the current working area, identification of the crop image, and obtaining of the crop contour information of the current working area.

[0077] The crop contour information can include crop contour lines and crop planting areas. It should be understood that the crop contour lines and the crop planting areas have a correlation relationship, each crop contour line is associated with a crop planting area, and the crop contour line is the edge contour line of the associated crop planting area.

[0078] For example, the time length T is used as the duration of each time, the time t-1 is the previous time of the time t, the camera device 130 shoots a crop image at each time or at a set frequency, and sends the shot crop image to the control device 120. At the time t, the agricultural machine 110 is performing ridge-following operation in the current working area according to the current driving path, and the control device 120 receives the crop image sent by the camera device 130. After receiving the crop image, the control device 120 immediately analyzes and identifies the crop image to obtain the crop contour information of the current working area.

[0079] In the above, the identification method of the crop image can be selected as required, for example, a visual algorithm can be used for identification, or a pre-trained crop area recognition model can be used for identification. Based on this, referring to Figure 3 , the flowchart of part of the sub-steps of the above step S102 can be used to identify the crop image to obtain the crop contour information of the current working area by the following steps:

[0080] S1021, using a visual algorithm or a pre-trained crop area recognition model to identify the crop planting area in the crop image.

[0081] The visual algorithm can be flexibly selected according to preferences and actual application scenarios, for example, it can be a neural network for identifying crops, or a neural network for identifying field ridges where crops are planted in the field.

[0082] In S1022, the crop image is segmented according to the crop planting area to obtain a crop contour line.

[0083] The crop image in S102 can also be identified to obtain the crop contour information of the current work area in the following manner: a pre-trained contour recognition model is used to identify the crop contour line and the crop planting area in the crop image.

[0084] It should be understood that the crop area recognition model and the contour recognition model can be a model trained by machine learning or a neural network. The training method can also be flexibly selected, and the embodiments are not limited in particular.

[0085] The manner of segmenting the crop image can also be flexibly selected according to individual needs and actual scenarios, for example, it can be segmented according to a preset rule, it can be adaptively threshold segmented, or it can be segmented by using a neural network with AI semantic segmentation function.

[0086] The image after the crop contour line and the crop planting area are segmented can be referred to as a contour image, and the crop contour line is clearly segmented on the image. At this time, the contour information can be obtained by performing scale conversion based on the contour image and a scale factor between the pixels and the actual distance of the image captured by the field of view of the camera device 130, which is calculated in advance.

[0087] The crop contour information includes but is not limited to the crop planting area, the number of crop planting areas, the crop contour line, the number of crop contour lines, the actual position set of each crop contour line (it should be understood that a crop contour is composed of multiple position points), and the size of each crop planting area.

[0088] In S104, whether the current driving path interferes with the crop planting area is determined based on the crop contour information. If yes, S106 is performed. If no, S105 is performed.

[0089] After obtaining the crop contour information, the crop contour line closest to the current driving path of the agricultural machine 110 can be determined according to the position information of the current driving path, and then the interference area of the current driving path and the crop planting area, that is, the interference area, can be determined after the distance is calculated according to the position information.

[0090] In the above, the current travel path can be a corrected path at time t-1 obtained according to the crop image at the last time (i.e., at time t-1), can be a preset navigation path, or can be a navigation path obtained according to satellite positioning data. Regardless of which path, the current travel path is known. The manner of judging whether interference is generated can be flexibly selected. For example, in one possible implementation, whether interference is generated can be judged by comparing the current travel path with the distances between the current travel path and the closest crop contour lines on both sides of the current travel path at each position, and if the distance is less than the width of the agricultural machine 110 or half of the wheelbase of the agricultural machine 110, the position region will generate interference.

[0091] For another example, the position information of the closest crop contour lines on both sides of the current travel path of the agricultural machine 110 in the crop contour information and the position information of the current travel path are extracted, the distances between the current travel path and the crop contour lines at each position are calculated, and whether interference is generated can be judged according to the relationship between the distance and a preset threshold. The preset threshold can be the width of the agricultural machine 110 or half of the wheelbase of the agricultural machine 110, or can be an empirical value.

[0092] In the position region where interference is generated, it means that the agricultural machine 110 will generate interference to the crop planting area when traveling to the position, and the interference includes but is not limited to damage and crushing.

[0093] S105, continue to follow the ridge navigation according to the current travel path.

[0094] S106, obtain a corrected path about the interference region according to the crop contour information.

[0095] The interference region is a region where the current travel path and the crop planting area generate interference.

[0096] After the interference region where the current travel path and the crop planting area generate interference is determined, a corrected path that can avoid interference can also be determined according to the crop contour information.

[0097] S108, follow the ridge navigation of the interference region according to the corrected path.

[0098] After the corrected path is determined, the corrected path and the interference region can be associated, so that after the agricultural machine 110 travels to the interference region according to the current travel path, the current travel path is immediately replaced by the corrected path, so as to control the agricultural machine 110 to travel through the interference region according to the corrected path and complete the ridge operation of the interference region.

[0099] Compared with the satellite positioning data navigation mode, in the crop ridge following navigation method, when the agricultural machine 110 interferes with the crop planting area during the ridge following, the control device 120 confirms the interference between the current driving path of the agricultural machine 110 and the crop planting area based on the crop contour information obtained by identifying the real-time acquired crop image, plans a correction path of the interference area according to the crop contour information, and performs the ridge following operation of the interference area according to the correction path, so as to avoid the crushing and damage of the crop in the interference area during the driving of the agricultural machine 110 as much as possible, and reduce the risk of crushing the crop.

[0100] In an embodiment, if the current driving path in S104 is the driving path planned according to the satellite positioning data in advance, at this time, the crop ridge following navigation method provided by the application adopts the satellite positioning data and visual recognition fusion mode. In this mode, the non-interference area is navigated by the satellite positioning data, and the interference area is navigated by the visual recognition mode, which not only can improve the problem of high cost caused by high requirement for equipment and complex algorithm in the binocular visual recognition navigation mode, and the problem of low precision in the monocular visual recognition navigation mode, but also can improve the problem of deviation in navigation caused by inaccurate satellite positioning data.

[0101] In this case, in order to quickly obtain the current driving path, refer to Figure 4 The crop ridge following navigation method provided by the embodiment can further include S103. S103 can be performed before S102 or S104.

[0102] S103, obtaining the current position information of the agricultural machine, combining the pre-stored path points of the current operation area, obtaining the current driving path of the agricultural machine in the operation area.

[0103] The pre-stored path points of the current operation area are the path points recorded by the agricultural machine 110 before the sowing or ridging operation in the current operation area.

[0104] The control device 120 can obtain the current position information of the agricultural machine 110 through the satellite navigation system such as the GPS positioning system. In the case that the current position of the agricultural machine 110, the heading (visual center line) of the agricultural machine 110, the position that has been driven by the agricultural machine 110, and the path points of the current operation area are known, the current driving path of the agricultural machine 110 in the operation area can be quickly determined.

[0105] In addition, since the crop image captured by the camera device 130 can include not only the crop planting area that currently needs to be worked on, but also the crop planting area that currently does not need to be worked on, in order to avoid the crop planting area that currently does not need to be worked on affecting the judgment of whether the disturbance area exists, while reducing the data amount of image processing, in some embodiments, the field of view range required for the agricultural machine operation can be calibrated in advance according to actual needs before the agricultural machine 110 performs the ridge following operation or enters the production, and in the subsequent process, the corresponding target area can be selected from the crop image captured by the camera device 130 based on the field of view range, so as to perform related processing based on the image information of the target area. The calibration of the field of view range can be based on the center axis of the agricultural machine, and the process of field of view calibration can be as follows:

[0106] Please refer to Figure 5 (a), a three-edge support (composed of OA, OB and OC, the lengths of OB and OC are equal) shown in the figure is built by using a circular plastic tube, the BC edge of the three-edge support is close to the front side of the rear wheel of the agricultural machine 110, and the BC edge is parallel to the rear wheel axis of the agricultural machine 110 as much as possible; the distance length between the B point and the outer side wall of the left wheel of the agricultural machine 110 and the distance length between the C point and the outer side wall of the right wheel of the agricultural machine 110 are measured by using a tape measure, and it is judged whether the two distance lengths are equal, if not, the position of the three-edge support is adjusted so that the distance length between the B point and the outer side wall of the left wheel of the agricultural machine 110 and the distance length between the C point and the outer side wall of the right wheel of the agricultural machine 110 are equal; when the distance length between the B point and the outer side wall of the left wheel of the agricultural machine 110 and the distance length between the C point and the outer side wall of the right wheel of the agricultural machine 110 are equal, the direction in which OA is located is taken as the heading direction, and the straight line in which OA is located is taken as the center axis of the agricultural machine 110.

[0107] After obtaining the center axis of the agricultural machine 110, a region with a preset field of view range size is determined as a target field of view based on the center axis of the agricultural machine 110. For example, the preset field of view range size is 2*2m, and the target field of view is located 1m in front of the agricultural machine, as shown in Figure 5 (b), the distance between the target field of view and the agricultural machine 110 is 1m, and the distance between the two side edges of the target field of view and the center axis is 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 row and / or the wheel track or width of the agricultural machine, and in actual application, adaptive adjustment can be made according to actual needs.

[0108] After the target field of view is determined, in order to obtain the actual size of the target area corresponding to the target field of view, so as to facilitate the conversion of the disturbance area and the correction path in the subsequent process, the coordinates of the four corner points of the target field of view can be extracted as calibration parameters, the image is converted into a bird's eye view according to the calibration parameters, and the scale factor of the target field of view can be determined based on the bird's eye view.

[0109] The scale factor in the x direction is: The scale factor in the y direction is:

[0110] I x represents the actual width of the target field of view within the actual crop area, L x represents the width of the target field of view within the image, I y represents the actual length of the target field of view within the actual crop area, L y represents the length of the target field of view within the image.

[0111] In the embodiment of selecting the corresponding target region in the crop image by using the target field of view, the step S104 can be adjusted accordingly, based on which, referring to Figure 6 , the step S104 can include the following steps:

[0112] S1041, determining the field of view center line of the agricultural machine in the crop image, and determining the target field of view from the crop image in combination with the field of view center line and the preset field of view range.

[0113] The field of view center line is a straight line where the center axis of the agricultural machine 110 is located.

[0114] Alternatively, the target field of view can also be determined by the following method: determining the target field of view from the crop image based on the current driving path and the preset field of view range.

[0115] It should be understood that the current navigation path and the field of view center line can not be located on the same straight line.

[0116] S1042, obtaining the crop contour line located in the target field of view based on the crop contour information.

[0117] In the case of the need for simplified operation, the crop contour line located in the target field of view can be no more than two. But in the case of the need to determine in advance whether the next row driving path will interfere with the corresponding crop contour line, the crop contour line located in the target field of view can be more than two.

[0118] S1043, judging whether the current driving path interferes with the crop planting area based on the crop contour line in the target field of view.

[0119] In detail, when the crop contour line in the target field of view is two, it can be that the distance between each crop contour line and the current driving path is calculated, and if the distance between at least one crop contour line and the current driving path is less than half the width of the agricultural machine 110 or half the wheel base of the agricultural machine 110, it is determined that interference occurs, otherwise, no interference occurs.

[0120] When the crop contour line in the target field of view is one line, the following can be performed: the distance between the crop contour line and the current driving path is calculated, if the distance is less than half of the width of the agricultural machine 110 or half of the wheel base of the agricultural machine 110, it is determined that interference occurs, otherwise, no interference occurs.

[0121] After it is determined that interference occurs, the region where interference exists is taken as the interference region. However, it should be noted that, since the agricultural machine 110 has stored the coordinate information of the current driving path before operation, and the agricultural machine 110 must operate along the current driving path during operation, the current driving path can be directly replaced by the field of view center line to determine the target field of view from the crop image after the required field of view range is obtained.

[0122] After the interference region is determined, in a possible implementation, the following is performed with reference to Figure 7 The correction path of the interference region can be obtained by the following steps, that is, S106 is implemented.

[0123] S1061, the crop contour line of the interference region is extracted as the target contour line according to the crop contour information. If the target contour line includes two crop contour lines, S1063 or S1067 is performed, and if the target contour includes a single crop contour line, S1065 is performed.

[0124] The target contour line is the crop contour line closest to the current driving path, and the acquisition manner can be flexibly selected, for example, it can be the crop contour line in the target field of view, it can be extracted according to a preset rule, or it can be extracted after distance calculation.

[0125] In an implementation, the following manner can be used: based on the crop contour information, the crop contour line in the interference region and located on both sides of the field of view center line or the current driving path is selected as the target contour line.

[0126] The field of view center line is the center axis of the agricultural machine 110. It should be understood that the crop contour line closest to both sides of the field of view center line and in the interference region is the target contour line.

[0127] S1063, 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.

[0128] The crop planting area associated with the target contour line is the crop planting area associated with the two crop contour lines, and the crop contour line is the edge contour line of the crop planting area associated with the crop contour line.

[0129] Generally, the agricultural machine 110 selected is adapted to the row spacing of the crops in the work area. When the target contour line is two crop contour lines, the center line between the two crop contour lines is fitted, and the center line is directly used as the correction path.

[0130] In detail, the correction path can be obtained by the following method: from the crop planting area, two target crop areas associated with the two crop contour lines are determined; a fitting method is used to fit the centers of the two target crop areas to obtain the crop center lines of the two target crop areas, and a center line between the two crop center lines is determined to obtain the correction path.

[0131] S1065, the path offset by the set distance from the edge crop contour line is used as the correction path.

[0132] When the agricultural machine 110 is at the boundary of the work area, only one side of the agricultural machine 110 may have a crop contour line, and the other side may not have a crop contour line. In this case, the target contour line is a single-sided crop contour line. In this case, the center line of the field of view of the agricultural machine 110 is the boundary line of the work area and the contour line of the crops on the two sides, respectively. At this time, only the interference between the agricultural machine 110 and the contour line of the crops needs to be considered. Therefore, the path offset by the set distance from the single-sided crop contour line is the correction path. The set distance is at least half the width of the agricultural machine 110 or half the track of the agricultural machine 110.

[0133] When the width of the agricultural machine 110 is less than the width of the two rows of crops in the work area, i.e., without considering the influence of vigorous crop growth, and without considering the relationship between the spacing between the rows of crops and the width of the agricultural machine 110 and the track of the agricultural machine 110, the above step S1063 can also be: fitting the center line between the two crop contour lines, and using the center line as the correction path.

[0134] In special cases such as vigorous crop growth, the spacing between the two crop contour lines may be less than the preset spacing. In this case, if the agricultural machine 110 continues to work, it may crush the crops on one side or both sides. To avoid crushing the crops by the agricultural machine 110 in this case, the spacing between the two crop contour lines can be judged before step S1063 is performed. Based on this, referring to Figure 8 , S106 can also include the following steps.

[0135] S1062, determining whether the spacing between the two crop contour lines is greater than or equal to the preset spacing.

[0136] Correspondingly, the step S1063 is executed when it is determined that the distance between the two crop contour lines is greater than or equal to the preset distance. That is, when the distance between the two crop contour lines is greater than the preset distance, the middle line between the two crop center lines is taken as the correction path, wherein the distance from the middle line to the two crop center lines is equal.

[0137] wherein the inner edge distance is relative to the agricultural machine 110, and the inner edge of the target contour is the side close to the agricultural machine 110.

[0138] After the step of determining whether the distance between the two crop contour lines is greater than the preset distance, the method can further include a step S1064.

[0139] S1064, when it is determined that the distance between the two crop contour lines is less than the preset distance, determining the bypass path based on the pre-stored path points of the current work area.

[0140] wherein the bypass path is used to guide the agricultural machine to bypass the interference area.

[0141] The pre-stored path points of the current work area refer to the path points recorded by the agricultural machine 110 when performing the pre-ridge operation such as seeding and ridging on the current work area, and can also be the path points of the preset navigation path.

[0142] The way of determining the bypass path can be flexibly selected, for example, the ridge of the interference area can be abandoned.

[0143] In an embodiment, the bypass path can be obtained by the following way: obtaining the current position information of the agricultural machine 110, determining the initial path point of the next row of crops from the pre-stored path points of the current work area, returning to the initial path point of the current row of crops from the current position, and taking the path formed from the initial path point of the next row of crops as the bypass path.

[0144] wherein the next row of crops refers to the next row of crops to be ridged, and the initial path point of the current row of crops is taken as the initial path point of the current row of crops in the initial path point of the ridged path in the current row of crops area, and the starting point on the next row of crops which is on the same side as the initial path point of the current row of crops is the initial path point of the next row of crops.

[0145] For example, referring to Figure 9 , it is assumed that the current work area has a total of 6 rows of crops, and the agricultural machine 110 is currently located at the middle position of the third and fourth rows of crops. It is detected that there is an interference area in the front direction, wherein A1 is the initial path point of the fourth row of crops, and A2 is the initial path point of the fifth row of crops which is on the same side as A1. At this time, the path formed from the current position of the agricultural machine 110 to A1 and then to A2 is the bypass path point.

[0146] When bypassing, the position information of the bypassed interference area can be recorded together, and a bypassing reminder can be generated to remind the manual ridge following or the agricultural machine 110 to follow the ridge of the interference area.

[0147] Through the above steps, when the distance between the two crop contour lines is greater than or equal to the preset distance, the correction path is determined, and when the distance between the two crop contour lines is less than the preset distance, the bypass path is determined to bypass the interference area.

[0148] In other embodiments, when the distance between the two crop contour lines of the target contour line is less than the preset distance, a plurality of preselected paths can be determined in the area between the two crop contour lines, and the damage value of each preselected path to the two target crop areas can be calculated, and the preselected path with the smallest damage value is selected as the correction path.

[0149] The damage value can be the interference area, and the damage value can be obtained by calculating the interference area of the preselected path and the two target crop areas for each preselected path. The damage value can also be an interference probability or other measurement index, which can be adjusted according to actual needs in specific applications, and the present embodiment is not limited thereto.

[0150] The preselected path can be obtained by determining the center line of the two crop center lines using the above method, taking the center line as the first preselected path, and then taking a path deviating from the first preselected path by a preset distance as the second preselected path, and so on, to obtain a target number of preselected paths. The preset distance can gradually increase in the form of an arithmetic sequence.

[0151] The crop ridge following navigation method provided in the present embodiment can integrate satellite positioning and visual recognition for navigation, effectively solve the actual positioning problem of crops, improve the accuracy of navigation, and to some extent, avoid the crushing and damage of the agricultural machine 110 to the crops in the crop planting area, and reduce the damage of the agricultural machine 110 to the crops during the ridge following process.

[0152] It should be understood that, although Figures 2-8 The steps in the flowchart are displayed in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders.

[0153] Based on the above concept of crop ridge following 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 a working module 170.

[0154] The operation module 170 is configured to perform a following operation. The following operation includes, but is not limited to, film covering, soil covering, cultivation and weeding.

[0155] The camera module 140 is configured to acquire a crop image of a current operation area in real time, and send the crop image to the controller.

[0156] The processing module 150 is configured to receive the crop image sent by the camera module 140 in real time, identify the crop image, and obtain crop contour information of the current operation area.

[0157] The processing module 150 is further configured to determine, based on the crop contour information, whether the current driving path interferes with a crop planting area, and if so, obtain a correction path for an interference area according to the crop contour information, and send the correction path to the navigation module 160.

[0158] The interference area is an area where the current driving path interferes with the crop planting area.

[0159] The navigation module 160 is configured to navigate the interference area according to the correction path.

[0160] In the agricultural machine 110, when it is determined that the current driving path of the agricultural machine 110 interferes with the crop planting area, the processing module 150 can obtain the correction path for the interference area according to the crop contour information, so that the navigation module 160 navigates the interference area according to the correction path, thereby avoiding, to a certain extent, the crushing and damage of the crops in the interference area by the agricultural machine 110 when the following module performs the following operation on the interference area, and reducing the risk of crushing the crops.

[0161] Based on the above crop following navigation method, in an embodiment, referring to Figure 11 A crop following navigation device 180 is also provided, which can be applied to the control device 120 in Figure 1 The crop following navigation device 180 includes an identification module 190, a path processing module 200 and the navigation module 160.

[0162] The identification module 190 is configured to acquire a crop image of a current operation area in real time, and identify the crop image to obtain crop contour information of the current operation area.

[0163] The path processing module 200 is configured to determine, based on the crop contour information, whether the current driving path interferes with a crop planting area, and if so, obtain a correction path for an interference area according to the crop contour information.

[0164] The interference area is an area where the current driving path interferes with the crop planting area.

[0165] The navigation module 160 is configured to navigate the interference area according to the corrected path.

[0166] In the crop following navigation device 180, the identification module 190 identifies the crop contour information of the crop image, and the path processing module 200 is capable of obtaining the corrected path of the interference area according to the crop contour information when it is determined that the current travel path of the agricultural machine 110 interferes with the crop planting area, so that the navigation module 160 navigates the interference area according to the corrected path, so as to avoid, to a certain extent, the crushing and damage of the crops in the interference area by the agricultural machine 110 when the operation module 170 follows the ridge of the interference area, and reduce the risk of crushing the crops.

[0167] For specific definitions of the crop following navigation device 180, refer to the definitions of the crop following navigation method in the foregoing, which will not be repeated here. Each module in the crop following navigation device 180 can be realized by software, hardware, or a combination thereof, in whole or in part. Each module can be embedded in or independent of the processor in the control device 120 in hardware form, or stored in the memory in the control device 120 in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0168] In one embodiment, a control device 120 is provided, the internal structure of which can be as shown in Figure 12 The control device 120 includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. The processor of the control device 120 is configured to provide computing and control capabilities. The memory of the control device 120 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the control device 120 is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, a carrier network, near field communication (NFC), or other technologies. The computer program is executed by the processor to implement a crop following navigation method. The display screen of the control device 120 can be a liquid crystal display screen or an electronic ink display screen. The input device of the control device 120 can be a touch layer overlaid on the display screen, or a key, trackball, or touchpad arranged on the housing of the control device 120, or an external keyboard, touchpad, or mouse, etc.

[0169] It should be understood that Figure 12 The structure shown in the above is only a block diagram of part of the structure related to the present application, and does not constitute a limitation on the control device 120 to which the present application is applied. The specific control device 120 can include more Figure 12more or fewer components, or combinations of components, or with varying placements of components.

[0170] In one embodiment, the crop row following device 180 provided by the present application can be implemented in the form of a computer program which can run on the control device 120 as shown. Figure 11 The memory of the control device 120 can store various program modules constituting the crop row following device 180, such as the recognition module 190, the path processing module 200 and the navigation module 160 as shown. Figure 11 The computer program constituted by the various program modules enables the processor to perform the steps in the crop row following method of various embodiments of the present application described in the present specification.

[0171] For example, Figure 12 The control device 120 can perform step S102 through the recognition module 190 in the crop row following device 180 as shown. Figure 11 The control device 120 can perform steps S104-S106 through the path processing module 200. The control device 120 can perform step S108 through the navigation module 160.

[0172] In one embodiment, a control device 120 is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: acquiring a crop image of a current work area in real time, recognizing the crop image to obtain crop contour information of the current work area; judging whether a current driving path interferes with a crop planting area based on the crop contour information; if so, obtaining a correction path for an interference area according to the crop contour information, wherein the interference area is a region where the current driving path and the crop planting area interfere with each other; and performing row following navigation of the interference area according to the correction path.

[0173] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the following steps: acquiring a crop image of a current work area in real time, recognizing the crop image to obtain crop contour information of the current work area; judging whether a current driving path interferes with a crop planting area based on the crop contour information; if so, obtaining a correction path for an interference area according to the crop contour information, wherein the interference area is a region where the current driving path and the crop planting area interfere with each other; and performing row following navigation of the interference area according to the correction path.

[0174] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the drawings show the possible implementation architecture, function and operation of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders from those noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can also be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system for executing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0175] In addition, each functional module in the embodiments of the present application 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.

[0176] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0177] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for ridge navigation in crop cultivation, characterized in that, The method includes: Within the area between two crop outlines in the target outline, multiple pre-selected paths are identified; Calculate the damage value of each of the pre-selected paths to two target crop areas, wherein the two target crop areas are the crop planting areas associated with the two crop outlines; Select the pre-selected path with the minimum damage value as the correction path; Based on the correction path, perform row-following navigation in the interference area.

2. The crop ridge navigation method as described in claim 1, characterized in that, The target outline is the outline of crops located in the interference zone and on both sides of the current driving path or the center line of vision.

3. The crop ridge navigation method as described in claim 1, characterized in that, The calculation of 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 the target crop area is calculated to obtain the damage value.

4. The crop ridge navigation method as described in claim 1, characterized in that, Within the area between two crop outlines in the target outline, multiple pre-selected paths are determined, including: Determine the centerline between the crop centerlines of the two target crop areas; The centerline is used as the first pre-selected path; The path that deviates from the first pre-selected path by a preset distance is used as the second pre-selected path to obtain the target number of pre-selected paths, wherein the preset distance gradually increases in the form of an arithmetic sequence each time.

5. The crop ridge navigation method as described in claim 1, characterized in that, The method further includes: Determine whether the distance between the two crop outlines in the target outline is greater than or equal to a preset distance; When the distance between two crop outlines in the target outline is less than a preset distance, multiple pre-selected paths are determined in the area between the two crop outlines in the target outline. The damage value of each pre-selected path to the two target crop areas is calculated. The pre-selected path with the smallest damage value is selected as the correction path. Based on the correction path, the row navigation of the interference area is performed.

6. The crop ridge navigation method as described in claim 1, characterized in that, The method further includes: When the distance between two crop outlines in the target outline is greater than or equal to a preset distance, a fitting method is used to perform center fitting on the two target crop areas to obtain the crop center lines of the two target crop areas, and the midline between the two crop center lines is determined to obtain a correction path. Based on the correction path, the row-following navigation of the interference area is performed.

7. The crop ridge navigation method as described in claim 5 or 6, characterized in that, Before determining whether the distance between two crop outlines in the target outline is greater than or equal to a preset distance, the method further includes: The system acquires real-time images of crops in the current work area, identifies the crop images, and obtains crop outline information for the current work area, wherein the crop outline information includes crop outline lines and crop planting areas. Based on the crop outline information, determine whether the current driving path interferes with the crop planting area; If so, then based on the crop outline information, the crop outline of the interference area is extracted as the target outline.

8. The crop ridge navigation method as described in claim 7, 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.

9. The crop ridge navigation method as described in claim 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.

10. The crop ridge navigation method as described in claim 9, characterized in that, When there are two crop outlines within the target field of view, the step of determining whether the current driving path interferes with the crop planting area based on the crop outlines within the target field of view includes: Calculate the distance between each crop outline in the target field of view and the current driving path. If at least one crop outline in the target field of view has a distance between its distance and the current driving path that is less than half the width of the agricultural machinery or half the wheelbase of the agricultural machinery, then it is determined that interference has occurred.

11. The crop ridge navigation method as described in claim 1, characterized in that, When the current driving area is a non-interference zone, the current driving path is the path corresponding to the current driving area in the satellite positioning data navigation. When the current driving area is the previous interference zone, the current driving path is the correction path corresponding to the previous interference zone.

12. A crop ridge navigation device, characterized in that, include: The path processing module is used to determine multiple pre-selected paths within the area between two crop outlines in the target outline. Calculate the damage value of each of the pre-selected paths to the two target crop areas, wherein the two target crop areas are the crop planting areas associated with the two crop outlines; select the pre-selected path with the smallest damage value as the correction path; The navigation module is used to perform row-following navigation in the interference area according to the correction path.

13. 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 11.

14. 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 1-11.

15. 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 1-11.

Images