Bionic subsoiler control method, terminal and storage medium based on intelligent driving

Abstract

The present invention belongs to the field of intelligent control technology. The present invention provides a bionic subsoiler control method based on intelligent driving, a terminal and a storage medium. First, a soil image of a target area, motion parameters, positioning information and a target path of a subsoiler are obtained; then, a first parameter is determined according to the soil image and the motion parameters; the first parameter represents the jitter parameter caused by soil stress when the subsoiler is working; then, according to the first parameter, the soil image is offset corrected; then, according to the corrected target image and positioning information, the motion control information of the subsoiler is determined; finally, according to the motion control information, the subsoiler is controlled to work along the target path. The present invention corrects the captured soil image by taking into account the jitter during the operation of the subsoiler, and can perform real-time monitoring and intelligent adjustment during the operation of the subsoiler to improve the operation efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control technology, and in particular relates to a bionic deep tiller control method based on intelligent driving, a terminal and a storage medium. Background Art

[0002] Deep loosening of the soil is an important measure in farmland management. It effectively improves the aeration of the soil by breaking the bottom layer of the soil, allowing the roots to breathe better, while increasing the supply of nutrients in the soil, thereby promoting the healthy growth of plants.

[0003] However, traditional deep tillage operations often rely on the subjective experience of operators and fixed parameter settings of the machine, lacking real-time monitoring and intelligent adjustment of the operation process, which not only easily leads to unnecessary waste of resources, but also may reduce operation efficiency and affect the final agricultural production benefits. Therefore, the control of deep tillage machines in the existing technology needs to be optimized. Summary of the invention

[0004] In view of this, the present invention provides a bionic deep tiller control method, terminal and storage medium based on intelligent driving, aiming to solve the problem that deep tiller control in the prior art needs to be optimized.

[0005] A first aspect of an embodiment of the present invention provides a bionic subsoiler control method based on intelligent driving, comprising:

[0006] Obtain soil images of the target area, motion parameters of the deep tiller, positioning information, and target path;

[0007] Determine a first parameter according to the soil image and the motion parameter; the first parameter represents a shaking parameter caused by soil stress when the deep tiller is working;

[0008] performing offset correction on the soil image according to the first parameter;

[0009] Determine the motion control information of the subsoiler according to the corrected target image and positioning information;

[0010] According to the motion control information, the deep tiller is controlled to work along the target path.

[0011] In a possible implementation, determining the first parameter according to the soil image and the motion parameter includes:

[0012] Determine soil characteristic parameters on the target path according to the soil image;

[0013] According to soil characteristic parameters and motion parameters, the direction, speed and amplitude of shaking caused by soil stress are determined.

[0014] In a possible implementation, determining soil characteristic parameters on the target path according to the soil image includes:

[0015] Soil images are identified to determine soil color, soil particle density, particle size, particle number and disturbance surface area.

[0016] In a possible implementation, the motion parameters include working speed, tillage depth, and soil penetration angle; according to the soil characteristic parameters and the motion parameters, the direction, speed, and amplitude of the shaking caused by the soil stress are determined, including:

[0017] Soil color, soil particle density, particle size, particle number, disturbance surface area, working speed, tillage depth and soil penetration angle are input into the first neural network to obtain the direction, speed and amplitude of the shaking caused by soil stress.

[0018] In a possible implementation, performing offset correction on the soil image according to the first parameter includes:

[0019] The soil image is offset corrected according to the first parameter and the block matching algorithm.

[0020] In a possible implementation, performing offset correction on the soil image according to the first parameter and the block matching algorithm includes:

[0021] Determine the compensation direction, compensation amount and compensation frame number according to the direction, speed and amplitude of the jitter;

[0022] The block matching algorithm is used to perform offset correction on the soil image according to the compensation direction, compensation amount and compensation frame number.

[0023] In a possible implementation, the motion control information of the subsoiler is determined according to the corrected target image and positioning information, including:

[0024] According to the corrected target image, the location information of the deep tiller is determined, and the soil characteristic parameters on the target path are predicted;

[0025] Determine the actual coordinates of the deep tiller according to the position information and positioning information of the deep tiller;

[0026] Determine the target motion parameters of the subsoiler based on the predicted values ​​of soil characteristic parameters;

[0027] The motion control information of the deep tiller is determined according to the target motion parameters and the actual coordinates.

[0028] In a possible implementation, the motion control information of the subsoiler is determined according to the corrected target image and positioning information, including:

[0029] Determine the position information of the deep tiller according to the corrected target image;

[0030] Determine the actual coordinates of the deep tiller according to the position information and positioning information of the deep tiller;

[0031] According to the actual coordinates of the deep tiller and the corrected target image, the soil characteristic parameters on the target path are predicted;

[0032] Determine the target motion parameters of the subsoiler based on the predicted values ​​of soil characteristic parameters;

[0033] The motion control information of the deep tiller is determined according to the target motion parameters and the actual coordinates.

[0034] A second aspect of an embodiment of the present invention provides a bionic subsoiler control device based on intelligent driving, comprising:

[0035] An acquisition module is used to acquire soil images of a target area, motion parameters of a deep tiller, positioning information, and a target path;

[0036] A calculation module is used to determine a first parameter according to the soil image and the motion parameter; the first parameter represents a shaking parameter caused by soil stress when the deep tiller is working;

[0037] A correction module, used for performing offset correction on the soil image according to the first parameter;

[0038] A determination module, used to determine the motion control information of the subsoiler according to the corrected target image and positioning information;

[0039] The control module is used to control the deep tiller to work along the target path according to the motion control information.

[0040] The third aspect of an embodiment of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the bionic deep tiller control method based on intelligent driving as described in the first aspect above are implemented.

[0041] The fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the bionic deep tiller control method based on intelligent driving as described in the first aspect above are implemented.

[0042] The embodiment of the present invention provides a bionic subsoiler control method based on intelligent driving, firstly, the soil image of the target area, the motion parameters, positioning information and target path of the subsoiler are obtained; then, a first parameter is determined according to the soil image and the motion parameters; the first parameter represents the jitter parameter caused by soil stress when the subsoiler is working; then, according to the first parameter, the soil image is offset corrected; then, according to the corrected target image and positioning information, the motion control information of the subsoiler is determined; finally, according to the motion control information, the subsoiler is controlled to work along the target path. The present invention corrects the captured soil image by considering the jitter during the operation of the subsoiler, and can perform real-time monitoring and intelligent adjustment during the operation of the subsoiler to improve the operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0044] Figure 1 This is an application scenario diagram of a bionic deep tiller control method based on intelligent driving provided by an embodiment of the present invention;

[0045] Figure 2 It is a flow chart of the implementation of the bionic subsoiler control method based on intelligent driving provided by an embodiment of the present invention;

[0046] Figure 3 is a structural schematic diagram of a bionic subsoiler control device based on intelligent driving provided by an embodiment of the present invention;

[0047] Figure 4 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0049] Figure 11 is an application scenario diagram of a bionic deep tiller control method based on intelligent driving provided by an embodiment of the present invention. The method of the present invention may be applied to the scenario, including but not limited to the scenario. The system includes a deep tiller 11, a control terminal 12, a camera 13, a sensor module 14 and a GPS module 15.

[0050] Among them, the camera 13, the sensor module 14 and the GPS module 15 are all connected to the control terminal 12, and the control terminal 12 is used to send motion control information to the deep tiller 11 to instruct the deep tiller 11 to work. Now more and more modern deep tillers are equipped with intelligent monitoring systems, which detect the working speed, tillage depth, soil penetration angle and other parameters of the deep tiller by configuring corresponding sensors, and display them on the display screen of the deep tiller for user reference. The present invention directly uses the existing parameters of the deep tiller for calculation, avoiding the introduction of additional sensors to increase costs.

[0051] Figure 2 : is a flowchart of the implementation of the bionic deep tiller control method based on intelligent driving provided by an embodiment of the present invention. Figure 2 As shown, in some embodiments, a bionic deep tiller control method based on intelligent driving includes:

[0052] S210, obtaining a soil image of a target area, motion parameters of a deep tiller, positioning information, and a target path.

[0053] In the embodiment of the present invention, the target area may be the current working area of ​​the deep tiller, or the current working area and the deep tilled area, or the current working area, the deep tilled area, and the un-deep tilled area ahead, which is not limited here. The soil image of the target area is obtained by photographing the camera 13. The number of cameras 13 may be one or more, which is specifically determined by the shooting requirements and is not limited here.

[0054] S220, determining a first parameter according to the soil image and the motion parameter; the first parameter represents a shaking parameter caused by soil stress when the deep tiller is working.

[0055] In an embodiment of the present invention, when the subsoiler is operating, its working parts such as the subsoiler shovel must go deep into the soil to perform crushing and loosening operations. Due to the unevenness of the soil texture, for example, when encountering hard clods, stones or changes in resistance of different soil layers, the subsoiler will produce vibrations and shakes. In addition, the power transmission system and walking device of the subsoiler itself will also produce certain mechanical vibrations during operation. These vibrations and shakes will be transmitted to various components installed on the subsoiler, including the camera. Shaking will cause the camera lens to shake, resulting in blurred images. When photographing soil conditions, blurred images will affect the accurate judgment of the soil subsoil effect. For example, originally wanted to observe the size and porosity of soil particles, but due to the blurred image, these details cannot be clearly presented. Therefore, the present invention sets a corresponding first parameter to evaluate the impact of jitter on imaging.

[0056] In some embodiments, determining the first parameter based on the soil image and motion parameters includes: determining soil characteristic parameters on the target path based on the soil image; determining the direction, speed and amplitude of the jitter caused by soil stress based on the soil characteristic parameters and motion parameters.

[0057] In some embodiments, soil characteristic parameters on the target path are determined based on the soil image, including: identifying the soil image, determining soil color, soil particle density, particle size, particle number and disturbance surface area.

[0058] In an embodiment of the present invention, a general image recognition model, such as a support vector machine and deep learning, can be used to complete feature recognition of soil images. On the target area image, the soil particle density, particle size, number of particles and disturbed surface area of ​​the area where deep tillage is completed can be identified. Among them, the disturbed surface area is the working area of ​​the deep tiller per unit time. The soil color can be at least one of the following: soil surface color, soil deep tillage color and soil layer colors.

[0059] Among them, according to the soil surface image of the current working area and the soil surface image of the un-deeply loosened area in front, the image recognition model can identify the soil surface color. Correspondingly, according to the image of the deep-loosened soil in the current working area and the deep-loosened area, the image recognition model can identify the soil deep-loosening color. However, the actual soil is not completely uniform, but gradually softens from top to bottom. The soil in the upper layer is the driest and hardest, and there are the most foreign objects such as small stones. The soil in the middle and lower layers is more moist and soft, and there are fewer foreign objects. Therefore, the present invention can divide the depth of deep loosening into several levels, with the soil surface color and the soil deep loosening color as the upper and lower limits, and interpolation filling is performed according to the preset rules to obtain the color of each layer of soil.

[0060] Soil color often reflects its composition and texture. For example, dark soil (such as black soil) usually contains more organic matter, and the texture of this type of soil may be relatively loose and elastic. When subjected to soil stress, the loose and elastic soil structure makes the bond between soil particles relatively weak, and it is more likely to deform, resulting in a relatively large shaking amplitude. On the contrary, light-colored and compact soil (such as some clays) has particles that are tightly bound together, and it is relatively difficult to deform under stress, so the shaking amplitude is relatively small.

[0061] The density of soil particles directly reflects the compactness of the soil. A higher particle density means that the distance between soil particles is smaller and the soil structure is more compact. In this case, when subjected to soil stress, compact soil can transmit stress more efficiently, and the stress is relatively concentrated in the soil, resulting in relatively small shaking speed and amplitude. Because the closely arranged particles limit the overall deformation space of the soil, it is not easy for the vibration energy to cause large particle displacement during the transmission process, so the shaking amplitude is limited; at the same time, the concentrated stress transmission also allows the shaking to propagate faster in the soil, so the speed is relatively stable but will not change too quickly.

[0062] Soil particles of different sizes have different contact points and movement patterns between particles. Soil composed of larger particles has relatively fewer contact points between particles. When subjected to stress, these large particles are more likely to roll and slide relative to each other because they are larger in size, have relatively greater weight and inertia, and are more difficult to maintain a stable state under stress. This relative rolling and sliding movement makes the direction of the shake more difficult to predict, and random shakes in multiple directions may occur. Moreover, since the movement of a single large particle has a greater disturbance to the overall soil, the amplitude of the shake may be relatively large.

[0063] A large number of soil particles means that the soil structure is relatively complex, and the interactions between the numerous particles are intricate. When subjected to stress, a large number of particles makes it easier to disperse the stress during the transmission process, because the stress will be distributed and propagated among multiple particles. This results in a relatively small shaking speed and amplitude, because no single particle or local area is subjected to excessive stress and causes severe deformation and vibration. However, due to the large number of particles, stress concentration may occur in local areas due to reasons such as uneven particle arrangement. When this happens, a relatively large amplitude of shaking will occur in the local area, and the direction of the shaking may be affected, causing it to change irregularly and deviate from the normal direction of stress application.

[0064] The larger the disturbed surface area, the more soil is loosened each time by the deep tiller, and the greater the stress it is subjected to.

[0065] In some embodiments, the motion parameters include working speed, tillage depth, and soil penetration angle; based on the soil characteristic parameters and motion parameters, the direction, speed, and amplitude of the shaking caused by soil stress are determined, including: inputting soil color, soil particle density, particle size, number of particles, disturbance surface area, working speed, tillage depth, and soil penetration angle into the first neural network to obtain the direction, speed, and amplitude of the shaking caused by soil stress.

[0066] In the embodiment of the present invention, the first neural network can be a convolutional neural network model, an adversarial neural network, etc., which is not limited here. An acceleration sensor, a gyroscope and other devices can be set on the deep tillage machine to perform experimental deep tillage work, record the direction, speed and amplitude of the shaking, and take images during the test to form training samples to train the first neural network.

[0067] S230: Perform offset correction on the soil image according to the first parameter.

[0068] In some embodiments, performing offset correction on the soil image according to the first parameter includes: performing offset correction on the soil image according to the first parameter and a block matching algorithm.

[0069] In some embodiments, the soil image is offset corrected according to the first parameter and the block matching algorithm, including: determining the compensation direction, compensation amount and compensation frame number according to the direction, speed and amplitude of the jitter; and using the block matching algorithm to perform offset correction on the soil image according to the compensation direction, compensation amount and compensation frame number.

[0070] In the embodiment of the present invention, the direction of image compensation is determined according to the known shaking direction. If the shaking direction is horizontally to the right, then the image needs to be translated to the left during compensation. For example, if the shaking direction is 30° to the upper right with respect to the horizontal direction, then the image needs to be translated to the lower left for compensation. This is because the object or scene in the image needs to be returned to the relative position before the shaking.

[0071] In an embodiment of the present invention, the jitter amplitude determines the specific number of pixels for image compensation. Assuming that the jitter amplitude is known to correspond to a movement of n pixels in a certain direction, then when compensating, it is necessary to move the image in the opposite direction by n pixels. The jitter speed is used to determine the degree of compensation for each frame of the image in the video sequence. If the jitter speed is fast, the displacement change of the image between adjacent frames is large. The proportion of each frame of the image that needs to be compensated can be calculated based on the jitter speed. For example, if the jitter speed causes the image to move 30 pixels in 1 second, and the video frame rate is 30fps (30 frames per second), then on average each frame of the image needs to be compensated by 1 pixel. If the jitter speed is uneven, for example, first fast and then slow, then the compensation amount for each frame of the image can be dynamically adjusted according to the speed change curve.

[0072] In an embodiment of the present invention, the image is first divided into a plurality of small blocks, such as the aforementioned blocks of 8×8 pixels or 16×16 pixels. This is done to track the motion of the image more accurately, because small blocks are easier to match and track than the entire image. For each small block, matching is performed at the predicted position of the adjacent frame according to the known shaking direction and amplitude. For example, if it is known that the image has shaken to the right by a certain amplitude, then a matching block is searched to the left at the corresponding small block position of the previous frame image. The matching criterion is usually the minimum sum of squares of pixel differences. The actual displacement of each small block is determined by finding the best matching block within a certain search area. After determining the displacement of each small block, the entire image is compensated according to these displacements. If the displacement trends of all small blocks are the same, for example, they are all moved to the right by a certain pixel, then the entire image can be moved to the left by the corresponding pixel for compensation. If the displacement of the small blocks is inconsistent, a more complex interpolation method, such as bilinear interpolation or bicubic interpolation, may be required to adjust the image so that the compensated image looks smoother and more natural.

[0073] After the compensation is completed, the compensated image needs to be verified. The effectiveness of the compensation can be determined by observing whether some fixed reference points in the image (such as distant landmarks, specific soil texture patterns, etc.) have returned to their original positions. If it is found that the compensated image is still blurry or the position of the object is inaccurate, it may be necessary to re-evaluate the jitter parameters or adjust the parameters in the compensation algorithm, such as the search area size, the weight of the matching standard, etc., until a satisfactory compensation effect is obtained.

[0074] In some embodiments, performing offset correction on the soil image according to the first parameter includes: performing offset correction on the soil image according to the first parameter and an algorithm based on feature point tracking.

[0075] In an embodiment of the present invention, feature points are first extracted from an image. These feature points are usually points with obvious geometric features in the image, such as corner points and edge points of an object. For example, when shooting a soil scene, the edge intersection of soil particles, the end points of crop residues, etc. can all be used as feature points. Then, the movement of these feature points is tracked between adjacent frames. The movement trajectory of the feature points is fitted by mathematical methods such as the least squares method to determine the direction and amplitude of the camera shake. The advantage of this algorithm is that it has good adaptability to local and irregular shakes and can intuitively reflect the actual movement of objects in the image. However, it relies on the accurate extraction and tracking of feature points. If the feature points are not extracted accurately or are lost during the tracking process, the effect of shake compensation will be affected.

[0076] S240, determining motion control information of the subsoiler according to the corrected target image and positioning information;

[0077] In some embodiments, the motion control information of the subsoiler is determined based on the corrected target image and positioning information, including: determining the position information of the subsoiler based on the corrected target image, and predicting the soil characteristic parameters on the target path; determining the actual coordinates of the subsoiler based on the position information and positioning information of the subsoiler; determining the target motion parameters of the subsoiler based on the predicted values ​​of the soil characteristic parameters; determining the motion control information of the subsoiler based on the target motion parameters and the actual coordinates.

[0078] In an embodiment of the present invention, the corrected image can be used to re-extract soil characteristic parameters such as soil color, soil particle density, particle size, number of particles, and disturbed surface area in the manner of the above-mentioned image recognition. The current working area and the deep-plowed area can extract the above-mentioned soil characteristic parameters, but the un-deep-plowed area ahead can usually only extract the color of the surface soil. Therefore, a prediction model, such as a deep learning model, can be set. The input of the prediction model is the color of the surface soil, and the output is the soil color after deep plowing or in each layer, soil particle density, particle size, number of particles, and disturbed surface area. The soil characteristic parameters that can be extracted from the current working area and the deep-plowed area are used as training samples, so that the model can predict the soil characteristic parameters on the target path based on the parameters of the deep-plowed soil.

[0079] In an embodiment of the present invention, the subsoiler is absolutely positioned based on GPS, but GPS has errors and the absolute positioning is inaccurate, so relative positioning can be performed by using image recognition position. Specifically, the SIFT algorithm can be used to extract feature points from the image. The SIFT algorithm can extract stable feature points with scale invariance and rotation invariance in the image, and these feature points can be used for subsequent positioning and matching. The obtained machine vision and GPS positioning information are converted to the same coordinate system, and the two data are fused using information fusion technology to generate new positioning information, i.e., actual coordinates.

[0080] In the combined navigation and positioning system, the information of different sensors needs to be converted into the same data format and coordinate system to fuse them. By converting the data of each sensor into the same data format and using an appropriate fusion algorithm for data fusion, the advantages of different sensors can be maximized and the performance and accuracy of the navigation and positioning system can be improved.

[0081] In an embodiment of the present invention, the target motion parameters include a target working speed, a target tillage depth, and a target soil penetration angle. Different deep tillage speeds and depths are used for soils with different characteristics, and the soil in the farmland can be homogenized as much as possible to improve the deep tillage efficiency. At the same time, the actual coordinates are used to ensure that the deep tillage machine works on the target path without deviation. The control signals corresponding to the two are the above-mentioned motion control information.

[0082] In some embodiments, the motion control information of the subsoiler is determined based on the corrected target image and positioning information, including: determining the position information of the subsoiler based on the corrected target image; determining the actual coordinates of the subsoiler based on the position information and positioning information of the subsoiler; predicting the soil characteristic parameters on the target path based on the actual coordinates of the subsoiler and the corrected target image; determining the target motion parameters of the subsoiler based on the predicted values ​​of the soil characteristic parameters; determining the motion control information of the subsoiler based on the target motion parameters and the actual coordinates.

[0083] In an embodiment of the present invention, the actual coordinates of the deep tiller can be located first, and then converted to the image coordinate system according to the actual coordinates, and the target path can be marked and drawn in the image. With the target path as the center and the disturbance surface as the sliding surface, an area can be slid out in the image, and the background can be removed and the soil characteristic parameters of the area can be extracted, that is, the soil characteristic parameters on the target path. The rest is the same as the above embodiment. Through the above technical means, the background outside the target path can be removed with the corrected image, leaving only the position to be deep tilled for parameter extraction, which can avoid interference.

[0084] S250, controlling the deep tiller to work along the target path according to the motion control information.

[0085] In summary, the beneficial effects of the present invention are as follows: the present invention corrects the captured soil image by taking into account the jitter during the operation of the deep tiller, and can perform real-time monitoring and intelligent adjustment during the operation of the deep tiller to improve operating efficiency.

[0086] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0087] Figure 3 Schematic diagram of the structure of the bionic deep tiller control device based on intelligent driving provided by an embodiment of the present invention. Figure 3 As shown, in some embodiments, the bionic deep tiller control device 3 based on intelligent driving includes:

[0088] An acquisition module 310 is used to acquire a soil image of a target area, motion parameters of a deep tiller, positioning information, and a target path;

[0089] The calculation module 320 is used to determine a first parameter according to the soil image and the motion parameter; the first parameter represents a shaking parameter caused by soil stress when the subsoiler is working;

[0090] A correction module 330, configured to perform offset correction on the soil image according to the first parameter;

[0091] A determination module 340 is used to determine the motion control information of the subsoiler according to the corrected target image and positioning information;

[0092] The control module 350 is used to control the deep tiller to work along the target path according to the motion control information.

[0093] Optionally, the calculation module 320 is used to determine soil characteristic parameters on the target path based on the soil image; and determine the direction, speed and amplitude of the shaking caused by soil stress based on the soil characteristic parameters and motion parameters.

[0094] Optionally, the computing module 320 is used to identify the soil image and determine the soil color, soil particle density, particle size, particle number and disturbance surface area.

[0095] Optionally, the motion parameters include working speed, tillage depth, and soil penetration angle; the calculation module 320 is used to input soil color, soil particle density, particle size, number of particles, disturbance surface area, working speed, tillage depth and soil penetration angle into the first neural network to obtain the direction, speed and amplitude of the shaking caused by soil stress.

[0096] Optionally, the correction module 330 is used to perform offset correction on the soil image according to the first parameter and the block matching algorithm.

[0097] Optionally, the correction module 330 is used to determine the compensation direction, compensation amount and compensation frame number according to the direction, speed and amplitude of the jitter; and use a block matching algorithm to perform offset correction on the soil image according to the compensation direction, compensation amount and compensation frame number.

[0098] Optionally, a determination module 340 is used to determine the position information of the deep plowing machine based on the corrected target image, and predict the soil characteristic parameters on the target path; determine the actual coordinates of the deep plowing machine based on the position information and positioning information of the deep plowing machine; determine the target motion parameters of the deep plowing machine based on the predicted values ​​of the soil characteristic parameters; and determine the motion control information of the deep plowing machine based on the target motion parameters and the actual coordinates.

[0099] Optionally, a determination module 340 is used to determine the position information of the deep plowing machine based on the corrected target image; determine the actual coordinates of the deep plowing machine based on the position information and positioning information of the deep plowing machine; predict the soil characteristic parameters on the target path based on the actual coordinates of the deep plowing machine and the corrected target image; determine the target motion parameters of the deep plowing machine based on the predicted values ​​of the soil characteristic parameters; and determine the motion control information of the deep plowing machine based on the target motion parameters and the actual coordinates.

[0100] The bionic deep tiller control device based on intelligent driving provided in this embodiment can be used to execute the above method embodiments. Its implementation principle and technical effects are similar, and this embodiment will not be repeated here.

[0101] Figure 4 Schematic diagram of the structure of the terminal provided by the embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides a terminal 4, and the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiments of the bionic deep tiller control method based on intelligent driving are implemented, for example Figure 2 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned system embodiments are realized, for example Figure 3 The functions of each module are shown.

[0102] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units are stored in the memory 41, and are executed by the processor 40 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4.

[0103] The terminal 4 may be a mobile phone, MCU, ECU, industrial computer, etc., which is not limited here. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0104] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0105] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0106] An embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned LLC-based output voltage calibration method embodiment are implemented.

[0107] The computer readable storage medium stores a computer program 42, which includes program instructions. When the program instructions are executed by the processor 40, all or part of the processes in the above-mentioned embodiment method are implemented. The computer program 42 can also be used to instruct related hardware to complete. The computer program 42 can be stored in a computer readable storage medium. When the computer program 42 is executed by the processor 40, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program 42 includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium.

[0108] The computer-readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0109] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0110] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0113] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media can include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A bionic subsoiler control method based on intelligent driving, characterized in that: include: Obtain soil images of the target area, motion parameters of the deep tiller, positioning information, and target path; Determine a first parameter according to the soil image and the motion parameter; the first parameter represents a shaking parameter caused by soil stress when the deep tiller is working; performing offset correction on the soil image according to the first parameter; Determining motion control information of the subsoiler according to the corrected target image and the positioning information; According to the motion control information, controlling the subsoiler to work along a target path; Determining a first parameter according to the soil image and the motion parameter includes: Identify the soil image to determine soil color, soil particle density, particle size, particle quantity and disturbance surface area; The movement parameters include working speed, tillage depth, and soil penetration angle; Inputting the soil color, soil particle density, particle size, particle number, disturbance surface area, working speed, tillage depth and soil penetration angle into the first neural network to obtain the direction, speed and amplitude of the shaking caused by soil stress; Performing offset correction on the soil image according to the first parameter includes: Determine the compensation direction, compensation amount and compensation frame number according to the direction, speed and amplitude of the jitter; According to the compensation direction, compensation amount and compensation frame number, a block matching algorithm is used to perform offset correction on the soil image.

2. The bionic subsoiler control method based on intelligent driving according to claim 1 is characterized in that: According to the corrected target image and the positioning information, the motion control information of the subsoiler is determined, including: According to the corrected target image, the location information of the deep tiller is determined, and the soil characteristic parameters on the target path are predicted; Determine the actual coordinates of the deep tiller according to the position information and positioning information of the deep tiller; Determine the target motion parameters of the subsoiler based on the predicted values ​​of soil characteristic parameters; The motion control information of the deep tiller is determined according to the target motion parameters and the actual coordinates.

3. The bionic subsoiler control method based on intelligent driving according to claim 1 is characterized in that: According to the corrected target image and the positioning information, the motion control information of the subsoiler is determined, including: Determine the position information of the deep tiller according to the corrected target image; Determine the actual coordinates of the deep tiller according to the position information and positioning information of the deep tiller; According to the actual coordinates of the deep tiller and the corrected target image, the soil characteristic parameters on the target path are predicted; Determine the target motion parameters of the subsoiler based on the predicted values ​​of soil characteristic parameters; The motion control information of the deep tiller is determined according to the target motion parameters and the actual coordinates.

4. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the bionic deep tiller control method based on intelligent driving as described in any one of claims 1 to 3 above are implemented.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the bionic deep tiller control method based on intelligent driving as described in any one of claims 1 to 3 above are implemented.

Images