Header component speed automatic matching method and device, electronic equipment and harvesting machine

Abstract

The embodiment of the application provides a header component rotating speed automatic matching method, device, electronic equipment and harvesting machinery, and relates to the technical field of agricultural machinery. The header component rotating speed automatic matching method comprises the following steps: acquiring the agronomic parameters of a to-be-picked area in front of a header; the agronomic parameters comprise at least one of to-be-picked object size information, to-be-picked object stem distribution information and a relative position of the to-be-picked object on the stem; obtaining a processing speed of the header on to-be-picked objects according to the agronomic parameters and a traveling speed of the header; and obtaining the running speed of each processing component of the header for performing a picking process respectively based on the processing speed of the header on to-be-picked objects. The embodiment provided by the application realizes the matching between the rotating speed of each component of the header and each monitoring parameter, improves the working efficiency and the working quality.

Description

Technical Field

[0001] This application relates to the field of agricultural machinery technology, specifically to a method for automatically matching the rotation speed of header components, a device for automatically matching the rotation speed of header components, an electronic device, a corresponding storage medium, and a harvesting machine. Background Technology

[0002] The increasing mechanization of modern agriculture has placed higher demands on the performance and intelligence of agricultural machinery. Taking corn harvesters as an example, as an important piece of agricultural machinery, the working efficiency and operation quality of corn harvesters directly affect the harvesting results. Currently, most corn harvesters on the market use fixed-speed header systems. Although these can meet basic harvesting needs, they cannot guarantee optimal working efficiency and operation quality when faced with different terrains, crop densities, and changes in machine speed.

[0003] In existing technology, the harvesting machinery with the header is equipped with an electronic engine speed switch that can correspond to multiple engine speeds. The operator can control the engine speed by rotating the button on the electronic engine speed switch or by pressing the throttle. There is also a control lever with a function handle; pushing the lever controls the displacement of the variable displacement piston pump, thereby controlling the vehicle speed. During operation, the operator selects different engine speeds using the electronic engine speed switch. Once set, the engine speed does not automatically adjust. The header's working parts are connected to the engine via a mechanical transmission mechanism. Due to the fixed transmission ratio of mechanical transmission mechanisms such as chain drives, gear drives, and belt drives, the speed of the header's working parts can only remain proportional to the engine speed and stable within a certain range.

[0004] In the existing technology, because the working parts of the header, such as the stalk puller, auger, and reel chain, cannot adjust their speed according to different working conditions and needs, the equipment may not be able to reach its optimal working state under certain working conditions. During operation, when the engine speed is kept at a certain value, the speed of the header's working parts is also kept at a certain value. It is impossible to adapt and adjust according to the corn harvester's travel speed and the corn agronomic conditions. However, the corn processing capacity per second will fluctuate at different travel speeds. When the processing capacity is low, there will be power waste. When the processing capacity is high, the header will be blocked. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, electronic device, and harvesting machinery for automatically matching the rotational speed of header components. Based on key technologies such as machine vision, intelligent sensors, control algorithms, and electronic control units, it provides a method for automatically adjusting the rotational speed of header components through a hydraulic system while monitoring driving speed, header height, and various agronomic parameters in real time during operation, thereby at least solving some of the problems in the background art.

[0006] To achieve the above objectives, this application provides an automatic rotation speed matching method for a cutting table component, the method comprising:

[0007] Obtain agronomic parameters of the harvesting area in front of the cutter; the agronomic parameters include at least one of the following: the size information of the harvested material, the stem distribution information of the harvested material, and the relative position of the harvested material to its stem; based on the agronomic parameters and the travel speed of the cutter, obtain the processing speed of the cutter for the harvested material; based on the processing speed of the cutter for the harvested material, obtain the operating speed of each processing component of the cutter used to perform the harvesting process.

[0008] Optionally, the processing speed of the cutter for the harvested material is obtained based on the agronomic parameters and the travel speed of the cutter, including: obtaining the plant processing speed based on the travel speed and the stem distribution information of the harvested material in the agronomic parameters; and converting the plant processing speed into the processing speed of the cutter for the harvested material based on the number of harvested material per unit area.

[0009] Optionally, the processing component of the cutting platform for performing the harvesting process includes a stem-pulling roller; the operating speed of each processing component of the cutting platform for performing the harvesting process is obtained based on the processing speed, including: a first constraint condition that the stem-pulling time is not greater than the travel time; a second constraint condition that the processing speed of the stem-pulling roller on the object to be harvested is greater than the processing speed of the cutting platform on the object to be harvested; and the linear speed of the stem-pulling roller that satisfies the first and second constraint conditions is taken as the minimum linear speed of the stem-pulling roller.

[0010] Optionally, the first constraint condition is expressed as:

[0011] ;

[0012] in, V 拉 Let be the linear velocity of the stem-pulling roller, and s be the safety factor. H 结穗 The height of the ear, H 摘穗 t is the height of the harvesting platform for picking ears. 车 The time required for the cutting platform to travel one plant spacing; the second constraint is expressed as:

[0013] ;

[0014] Among them, Q 拉 The processing speed of the stem-pulling roller for the harvested material, n Q represents the number of rows at harvest time, and Q is the processing speed of the cutter for the harvested material.

[0015] Optionally, the processing component of the header for performing the harvesting process includes a reeling chain; obtaining the operating speed of each processing component of the header for performing the harvesting process based on the processing speed includes: obtaining an expression for the processing speed of the reeling chain on the material to be harvested, wherein the parameters of the expression include the linear velocity of the reeling chain; determining the range of values ​​for the linear velocity of the reeling chain with the constraint that the processing speed of the reeling chain on the material to be harvested is greater than the processing speed of the header on the material to be harvested; and obtaining the minimum linear velocity of the reeling chain based on the range of values ​​for the linear velocity of the reeling chain.

[0016] Optionally, the expression for the processing speed of the reeling chain for the harvested material includes:

[0017] ;

[0018] Among them, Q 拨 To improve the processing speed of the harvested materials in the reeling chain, n The number of rows at harvest time. Ψ 1 represents the fullness coefficient, taking into account that the fruit bunches in the picking lane are not completely filled, with the fullness ranging from 0.5 to 1. L 0 represents the length of the corn ear, V 拨 This represents the linear velocity of the reeling chain.

[0019] Optionally, the processing component of the header for performing the harvesting process includes an auger; obtaining the operating speed of each processing component of the header for performing the harvesting process based on the processing speed includes: obtaining an expression for the processing speed of the auger on the material to be harvested, wherein the parameters of the expression include the auger rotation speed; determining the range of values ​​for the auger rotation speed with the constraint that the processing speed of the auger on the material to be harvested is greater than the processing speed of the header on the material to be harvested; and obtaining the minimum rotation speed of the auger based on the range of values ​​for the auger rotation speed.

[0020] Optionally, the expression for the processing speed of the auger towards the harvested material includes:

[0021] ;

[0022] Among them, Q 搅龙 To improve the speed of processing the harvested materials, η This represents the actual efficiency value of the auger. P The pitch of the auger. π Pi d 1 represents the outer diameter of the auger blade. d 2 represents the inner diameter of the auger blades. V 1 represents the volume of the item to be harvested. n 搅龙 This refers to the rotational speed of the auger.

[0023] Optionally, acquiring agronomic parameters of the harvesting area in front of the harvesting platform includes: acquiring a first image and a second image of the harvesting area using a first camera and a second camera respectively; identifying several feature points of the harvested object and its stem from the first image and the second image; determining the depth information of the several feature points based on the position and optical parameters of the first and second cameras; determining the target to be tested based on the agronomic parameters to be determined, and selecting feature points of the target to be tested from the several feature points; and obtaining the value of the agronomic parameters to be determined based on the depth information of the feature points of the target to be tested and the pixel size information of the image of the target to be tested.

[0024] Optionally, identifying several feature points of the object to be harvested and its stem from the first image and the second image includes: using a trained real-time target detection algorithm to identify the object to be harvested and its stem from the first image and the second image respectively; using a scale-invariant feature transformation algorithm to identify a set of feature points from the object to be harvested and its stem, obtaining a first set of feature points corresponding to the first image and a second set of feature points corresponding to the second image; and matching the first set of feature points and the second set of feature points to obtain several feature points of the object to be harvested and its stem.

[0025] Optionally, the real-time target detection algorithm is obtained by improving the YOLO algorithm as follows: introducing a channel-priority convolutional attention module into the backbone layer of the YOLO algorithm; and introducing a multi-scale convolution module into the connection layer of the YOLO algorithm.

[0026] Optionally, determining the depth information of the plurality of feature points based on the position parameters and optical parameters of the first camera and the second camera includes: for each of the plurality of feature points, constructing at least one set of similar triangles by selecting several points from the feature point, the optical center of the first camera, the optical center of the second camera, the imaging point of the feature point on the first camera, and the imaging point of the feature point on the second camera; based on the similar triangles, calculating the distance between the feature point and the line connecting the optical center of the camera or the distance between the feature point and the imaging surface using several line lengths from the distance between the optical centers, the focal length of the first camera, the focal length of the second camera, and the distance from the imaging point to the end of the imaging surface; and using the distance between the feature point and the line connecting the optical center of the camera or the distance between the feature point and the imaging surface as the depth information of the feature point.

[0027] Optionally, the target to be measured is determined based on the agronomic parameters to be determined, and feature points of the target to be measured are selected from the plurality of feature points, including: if the agronomic parameters to be determined are the size information of the object to be harvested, the target to be measured is the object to be harvested, and the feature points of the target to be measured include the left end feature point, right end feature point, top end feature point, and bottom end feature point of the object to be harvested; if the agronomic parameters to be determined are the stem distribution information of the object to be harvested, the target to be measured is the stem of the object to be harvested, and the feature points of the target to be measured include the bottom end feature point of the stem of the object to be harvested; if the agronomic parameters to be determined are the relative position of the object to be harvested on its stem, the target to be measured is the object to be harvested and its stem, and the feature points of the target to be measured include the bottom end feature point of the object to be harvested and the bottom end feature point of the stem of the object to be harvested.

[0028] Optionally, obtaining the value of the agronomic parameter to be determined based on the depth information of the feature points of the target under test and the pixel size information of the image of the target under test includes: obtaining the pixel distance between feature points based on the pixel size information of the line segment formed by the feature points of the target under test in the image; obtaining the projection height of the line segment formed by the feature points of the target under test based on the pixel distance and the depth information, and obtaining the value of the agronomic parameter to be determined based on the projection height.

[0029] Optionally, when the depth information of different feature points of the target to be measured is inconsistent, the method further includes: calculating the depth difference between different feature points within the same line segment, correcting the projection height based on the depth difference, and obtaining the value of the agronomic parameter to be determined from the corrected projection height.

[0030] Optionally, after obtaining the operating speed of each processing component used to perform the harvesting process, the method further includes: adjusting the output flow of the hydraulic pump by a control signal, controlling the hydraulic motor to drive each processing component to operate at the operating speed; and obtaining the real-time rotational speed of each working component of the header based on the current engine speed and feedback signal.

[0031] This application also provides an automatic matching device for the rotation speed of header components. The device includes: a parameter acquisition module for acquiring agronomic parameters of the harvesting area in front of the header; the agronomic parameters include at least one of the following: the size information of the harvested material, the stem distribution information of the harvested material, and the relative position of the harvested material on its stem; a processing speed module for obtaining the processing speed of the header for the harvested material based on the agronomic parameters and the traveling speed of the header; and a speed output module for obtaining the operating speed of each processing component of the header used to perform the harvesting process based on the processing speed of the header for the harvested material.

[0032] This application also provides an electronic device, including: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the aforementioned automatic rotation speed matching method for the cutting table component by executing the instructions stored in the memory.

[0033] This application also provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned automatic rotation speed matching method for the cutting table component.

[0034] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned automatic rotation speed matching method for the cutting table components.

[0035] This application also provides a harvesting machine in which a PLC is configured to execute the aforementioned automatic matching method for the rotational speed of the header components.

[0036] The above technical solution has the following beneficial effects:

[0037] (1) Improve work efficiency and ensure work quality. By detecting the working status and actual working conditions of the header, the rotation speed of the header components is automatically adjusted, which improves work efficiency, prevents abnormal blockage of the header, reduces the missed harvesting and damage of crops, and improves work quality.

[0038] (2) Reduced human intervention. Automatic control systems reduce human intervention and improve the convenience and accuracy of operation.

[0039] (3) Adaptability to different conditions. The system used to implement the method of this application can maintain optimal operating conditions under different terrains and working conditions, and is highly adaptable.

[0040] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0041] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0042] Figure 1 This illustration schematically shows the steps of the automatic rotation speed matching method for the cutting table component according to an embodiment of this application;

[0043] Figure 2 The schematic diagram illustrates the principle of the multi-scale convolution module according to the embodiments of this application;

[0044] Figure 3 This illustration shows a schematic diagram of the model structure of the real-time target detection algorithm according to the embodiments of this application;

[0045] Figure 4 A flowchart based on the SIFT algorithm according to an embodiment of this application is illustrated schematically;

[0046] Figure 5 A schematic diagram of a binocular vision ranging model according to an embodiment of this application is shown.

[0047] Figure 6 The schematic diagram illustrates the principle of pinhole imaging according to the embodiments of this application;

[0048] Figure 7 This schematic diagram illustrates the structure of the automatic speed matching device for the cutting table component according to an embodiment of this application;

[0049] Figure 8 This schematic diagram illustrates the internal structure of an electronic device according to an embodiment of the present application;

[0050] Figure 9 A schematic diagram of the system structure of the harvesting machinery according to an embodiment of this application is shown. Detailed Implementation

[0051] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the embodiments of this application.

[0052] Figure 1 The diagram illustrates the steps of an automatic rotation speed matching method for a cutter head component according to an embodiment of this application. For example... Figure 1 As shown, an automatic rotation speed matching method for a cutting table component includes:

[0053] S01. Obtain agronomic parameters of the harvesting area in front of the cutter; the agronomic parameters include at least one of the following: the size information of the harvested object, the stem distribution information of the harvested object, and the relative position of the harvested object to its stem.

[0054] S02. Based on the agronomic parameters and the traveling speed of the cutting platform, obtain the processing speed of the cutting platform for the harvested material;

[0055] S03. Based on the processing speed of the cutting platform for the harvested material, obtain the operating speed of each processing component of the cutting platform used to perform the harvesting process.

[0056] Through the above implementation methods, the agronomic parameters of the crop to be harvested are identified, and the required rotation speed of each component of the header is calculated based on the agronomic parameters. Then, the rotation speed of the header components is adjusted through the hydraulic system to ensure that the machine works in the best condition and improve the overall operating efficiency.

[0057] For example, the crop to be harvested is corn, and the stalk containing the crop is the corn stalk. Subsequent embodiments of this application will be described using corn as an example; other crops with similar harvesting methods can also be implemented using the methods described in this application.

[0058] In some embodiments of this application, agronomic parameters of the harvesting area in front of the header can be obtained through a visual recognition unit. This visual recognition unit includes a camera and a deep learning object detection model. The camera uses two area-array cameras to form a binocular camera for taking pictures. The object detection model is trained to accurately identify corn ears and stalks and is then embedded into the intelligent control unit. Specifically, a first image and a second image of the harvesting area are obtained through a first camera and a second camera, respectively; the first camera and the second camera can be two cameras in a binocular camera system.

[0059] In some implementations, two area array cameras can be installed under the header cab, with the two cameras on the same horizontal plane and a horizontal distance of X1. The area array camera takes a picture every 1 second of driving. The header width of this corn harvester model is X2, and its detection field of view is approximately a square area of ​​X1*X2, so as to detect the area that is about to be harvested or picked.

[0060] Every second the header travels, subsequent deep learning and binocular vision algorithms are used to analyze various agronomic parameters of the corn in the detection area. These agronomic parameters are used for statistical analysis and to calculate the required rotational speed of each component of the header, thereby performing matching adjustments. Several feature points of the corn to be harvested and its stalk are identified from the first and second images; these feature points mainly represent the positional and shape characteristics of the corn to be harvested and its stalk. The depth information of these feature points is determined based on the positional and optical parameters of the first and second cameras. Since camera imaging is planar while the harvesting area is three-dimensional, the depth information of the feature points is necessary for subsequent calculations of size, length, distance, etc. The target to be measured is determined based on the agronomic parameters to be determined, and feature points of the target to be measured are selected from the several feature points. Since different agronomic parameters represent different meanings, different feature points need to be selected to calculate different agronomic parameters. The values ​​of the agronomic parameters to be determined are obtained based on the depth information of the feature points of the target to be measured and the pixel size information of the image of the target to be measured. Based on the imaging distance between feature points, the actual distance represented by the feature points in the area to be harvested is obtained, and finally, the values ​​of the required agronomic parameters are obtained.

[0061] In some embodiments of this application, the YOLOv8 (YouOnly Look Once) real-time object detection algorithm based on deep learning is used to identify corn ears and corn stalks. The algorithm is improved based on the characteristics of corn ears and corn stalks to improve the recognition and detection effect, so that it can accurately identify corn ears and corn stalks and mark them in the image. The recognition accuracy can reach 99.5%. The trained model is embedded into the intelligent control unit of the corn harvester to achieve end-to-end real-time detection.

[0062] The training process of this real-time object detection algorithm is as follows: In actual work, images of cornfields during corn harvesting are collected, and the collected images are augmented using methods such as image rotation, brightness adjustment, Gaussian noise addition, and filling rectangular regions, expanding the number of images to 2000. Annotation software is used to label the corn ears and stalks in the images to form a dataset. After annotation, a corresponding annotation file is generated based on the labeled images, containing information such as the size, coordinates, and category of the corn ears and stalks to facilitate model recognition training. Finally, the dataset is divided into training, validation, and test sets in a 7:2:1 ratio. This implementation also designs a training algorithm for the object detection network model, including: training the improved model on the training set for 100 iterations. During training, the training parameters are validated using the validation set after each iteration, and the model parameters are corrected using a loss function and gradient descent algorithm. This process is repeated 100 times to obtain the final trained model. The training results are then tested using the test set to verify the model's accuracy. The resulting real-time target detection algorithm can accurately identify corn ears and corn stalks.

[0063] The real-time target detection algorithm used in this invention is an improved version of YOLOv8. In order to further improve the recognition accuracy of YOLOv8 algorithm on corn ears and corn stalks, and to realize real-time detection during the corn harvester's operation and accelerate its recognition speed, this embodiment proposes two innovative improvement measures to replace modules in YOLOv8, so that it has better performance on corn stalks and corn ears.

[0064] Measure 1: Introduce a multi-scale convolution module into the connection layer of the YOLO algorithm. Figure 2 A schematic diagram illustrating the principle of a multi-scale convolution module according to an embodiment of this application is shown. Figure 2As shown, the basic principle of the Multi-Scale Convolution (MSConv) module is to divide the input feature map channels into three parts at a ratio of 1 / 2, 1 / 4, and 1 / 4, respectively, and perform standard convolution with convolution kernels of 1×1, 3×3, and 5×5 sizes. Then, all the convolved feature maps are stitched together in the channel direction, and further feature fusion is performed by point-by-point convolution with a 1×1 convolution kernel. This convolution method enables the generation of more feature maps that can extract the required information from the features of corn ears and corn stalks at a lower cost, reduces the model parameters, and increases the model's ability to extract feature information, thereby making the model more accurate and faster in recognition, which is more in line with the requirements of real-time detection during the corn harvester's operation.

[0065] Measure 2: A Channel Prior Convolutional Attention (CPCA) module is introduced into the backbone layer of the YOLO algorithm. This mechanism supports the dynamic distribution of attention weights across the channel and spatial dimensions, with its overall structure including a sequential arrangement of channel and spatial attention. Channel information from the feature map is aggregated using methods such as average pooling and max pooling. Next, the channel information is processed by a shared Multilayer Perceptron (MLP) to generate a channel attention map. The input features are then element-wise multiplied with the channel attention map to obtain the channel prior. This channel prior is then fed into a deep convolutional module to generate a spatial attention map. The deep convolutional module receives the spatial attention map and performs channel blending. Finally, the channel blending result is element-wise multiplied with the channel prior to obtain refined features as the output. Figure 3 A schematic diagram illustrating the model structure of a real-time target detection algorithm according to an embodiment of this application is shown. Figure 3 As shown, the real-time object detection algorithm includes a backbone layer, a neck layer, and a head layer. MSConv is set in the neck layer, and the CPCA module is set after the SPPF (Spatial Pyramid Pooling – Fast) module in the backbone layer. The addition of the CPCA mechanism allows the model to focus on the features of corn ears and corn stalks with high weight when extracting features, while ignoring other irrelevant features in the image, making the model more accurate and more adaptable to the more complex working conditions of corn.

[0066] In some embodiments of this application, identifying several feature points of the object to be harvested and its stalk from the first image and the second image includes: using a trained real-time target detection algorithm to identify the object to be harvested and its stalk from the first image and the second image respectively; using a scale-invariant feature transformation algorithm to identify a set of feature points from the object to be harvested and its stalk, obtaining a first set of feature points corresponding to the first image and a second set of feature points corresponding to the second image; and matching the first set of feature points and the second set of feature points to obtain several feature points of the object to be harvested and its stalk. For example, after accurately identifying and labeling the corn ears and corn stalks in the image, it is necessary to match the feature points of the corn ears and corn stalks in the labeling box. In the subsequent agronomic calculation process, only the area containing 2*2 corn stalks needs to be selected to represent the entire detection area, so it is only necessary to match the feature points within the labeling box of this area.

[0067] Figure 4 The flowchart illustrating the SIFT algorithm according to an embodiment of this application is shown. The SIFT (Scale-invariant feature transform) algorithm is used to detect features of the corn ears and stalks within the bounding box, and Euclidean distance constraints are used to match feature points on the left and right views of the corn ears and stalks captured by two cameras. Detecting feature points in an image using the SIFT algorithm first requires constructing a Gaussian pyramid, including the following steps:

[0068] Step 1: First, enlarge the image by a factor of 1, using this as the first layer of the first group in the Gaussian pyramid. Then, perform Gaussian convolutions sequentially to obtain a total of 6 layers. The Gaussian convolution process is expressed as follows:

[0069] ,

[0070] Where G(x,y,σ) is the Gaussian convolution function, I(x,y) is the value of each coordinate pixel in the image, and σ is a fixed parameter value.

[0071] Step 2: Downsample the third-to-last layer of the first group as the first layer of the second group. That is, for each row, take one pixel every other pixel to get an image with half the number of rows and columns of the original image.

[0072] Step 3: Repeat Step 1 to obtain the second set of images.

[0073] Step 4: Repeat Step 2 to obtain O groups of images, totaling O×6 images, which constitute the Gaussian pyramid. The Difference of Gaussian (DOG) pyramid can be obtained by subtracting pixels from adjacent groups. Feature points are composed of local extrema found in the DOG space. Therefore, to detect extrema in the DOG, each pixel needs to be compared with all its neighbors to obtain the feature points in the image.

[0074] After obtaining the feature points, their feature information needs to be described as follows:

[0075] Step 1: First, extract the distribution features of the gradient m(x,y) and orientation θ(x,y) of each pixel within a 3×3 neighborhood of the Gaussian pyramid image containing the feature point. The formula is as follows:

[0076] ,

[0077] Step 2: After the data acquisition is completed, a histogram is used to count the gradient and orientation of all pixels. The histogram divides the 0-360° direction into 8 bars, each bar being 45°. In the histogram, the peak direction is considered as the main direction of the feature point. To improve robustness, directions that are 80% higher than the main direction are retained as auxiliary directions.

[0078] Step 3: After the above process, each feature point has three pieces of information: location, scale, and orientation. To complete feature point matching between two images, a descriptor needs to be constructed for each feature point, that is, the feature point information is vectorized. First, the image region required for calculating the descriptor is determined based on the Gaussian image of the feature point's scale. The radius calculation formula is as follows:

[0079] ,

[0080] Where d=4 means that the image region is divided into 4×4 sub-blocks.

[0081] Step 4: Next, rotate the coordinate axis where the feature point is located to the direction of the feature point. It is necessary to perform histogram statistics in 8 directions for each of the 4×4 sub-blocks to obtain the gradient magnitude in each direction. In this way, a 128-dimensional feature point description vector is formed for each feature point.

[0082] The Euclidean distance between feature points in two images is calculated using eigenvectors, using the following formula:

[0083] ,

[0084] Among them, a(i) is the feature vector of the feature points in a specific area of the image of the corn ear and corn stalk captured by the left camera, and b(i) is the feature vector of the feature points in a specific area of the image of the corn ear and corn stalk captured by the right camera. A threshold T is set, and when d < T, the feature point matching is successful. Through the above feature point matching, the first feature point set corresponding to the first image and the second feature point set corresponding to the second image can be aligned for subsequent calculations.

[0085] In some embodiments of the present application, determining the depth information of the several feature points according to the position parameters and optical parameters of the first camera and the second camera includes: for one of the several feature points, selecting several points from the optical center of the first camera, the optical center of the second camera, the feature point, the imaging point of the feature point on the first camera, and the imaging point of the feature point on the second camera to construct at least one set of similar triangles; based on the similar triangles, using several line lengths among the distance between the optical centers, the focal length of the first camera, the focal length of the second camera, and the distance from the imaging point to the end of the imaging plane, calculating the distance between the feature point and the line connecting the camera optical center or the distance between the feature point and the imaging plane; using the distance between the feature point and the line connecting the camera optical center or the distance between the feature point and the imaging plane as the depth information of the feature point.

[0086] Figure 5 Schematically shows a schematic diagram of a binocular vision ranging model according to an embodiment of the present application. As Figure 5 shown, in an ideal binocular vision ranging model diagram, the left and right cameras installed under the cab should have the same camera parameters. O L and O R respectively represent the optical centers of the left and right cameras. The optical axes of the two cameras are parallel to each other and are located on the same horizontal plane. The horizontal distance between the two optical centers is b. The feature point P is imaged as point P L and point P R on the left and right camera image planes respectively. The line where points P L and P R are located is parallel to the line connecting the camera optical center O R O L . The distance from point P L to the leftmost end of its imaging plane is X L , and the distance from point P R to the leftmost end of its imaging plane is X R .

[0087] According to the principle of similar triangles, it can be deduced that:

[0088] ,

[0089] ,

[0090] Adding the two equations together gives:

[0091] ,

[0092] Further derivation yields:

[0093] ,

[0094] Based on the position difference of the feature point at the bottom of the rice stalk on the X-axis of the image plane of the left and right cameras, the distance Z from this feature point to the optical center plane of the camera can be calculated according to the horizontal distance between the two cameras and the focal length f of the camera. Similarly, the depth information of the feature point at the bottom of the corn cob can also be obtained.

[0095] from Figure 5 It can also be seen that the figure contains multiple sets of similar triangles, and those skilled in the art can calculate the above method by using different similar triangles as needed. This application does not list them all here.

[0096] In some embodiments of this application, the target to be measured is determined based on the agronomic parameters to be determined, and feature points of the target to be measured are selected from the plurality of feature points, including: if the agronomic parameters to be determined are the size information of the object to be harvested, the target to be measured is the object to be harvested, and the feature points of the target to be measured include the left end feature point, right end feature point, top end feature point, and bottom end feature point of the object to be harvested; if the agronomic parameters to be determined are the stem distribution information of the object to be harvested, the target to be measured is the stem of the object to be harvested, and the feature points of the target to be measured include the bottom end feature point of the stem of the object to be harvested; if the agronomic parameters to be determined are the relative position of the object to be harvested on its stem, the target to be measured is the object to be harvested and its stem, and the feature points of the target to be measured include the bottom end feature point of the object to be harvested and the bottom end feature point of the stem of the object to be harvested. For example, after feature point matching is completed, the parameters such as plant spacing, ear length, diameter, and ear height of corn are calculated. The plant spacing can be obtained based on the feature points at the bottom of the two corn stalks. The ear length can be obtained based on the feature points at the top and bottom of the ear. The ear diameter can be obtained based on the feature points at the left and right ends of the ear. The ear height can be obtained based on the feature points at the bottom of the corn stalk and the bottom of the ear.

[0097] In some embodiments of this application, the value of the agronomic parameter to be determined is obtained based on the depth information of the feature points of the target under test and the pixel size information of the image formed by the target under test, including: obtaining the pixel distance between feature points based on the pixel size information of the line segment formed by the feature points of the target under test in the image; obtaining the projection height of the line segment formed by the feature points of the target under test based on the pixel distance and the depth information, and obtaining the value of the agronomic parameter to be determined based on the projection height. Figure 6A schematic diagram illustrating the principle of pinhole imaging according to an embodiment of this application is shown. Figure 6 As shown, a method for measuring ear height is designed based on its depth information and the principle of pinhole imaging. First, the height of the corn ear projected onto a plane parallel to the phase plane is calculated based on the feature points at the bottom of the corn stalk and the bottom of the corn ear. This can be expressed as: In the formula, L is the projected height of the corn ear. l This represents the pixel length corresponding to the ear height in pixel coordinates after camera imaging. dx The size occupied by a single pixel in the camera. f For camera focal length, D This is the depth value from the horizontal plane containing the target line segment to the optical center of the camera.

[0098] Furthermore, when the depth information of different feature points of the target to be measured is inconsistent, the method further includes: calculating the depth difference between different feature points within the same line segment, correcting the projection height based on the depth difference, and obtaining the value of the agronomic parameter to be determined from the corrected projection height. Since the growth direction of corn during harvesting is not completely perpendicular to the camera's shooting direction, the entire corn stalk cannot be completely parallel to the camera's phase plane when the camera is shooting. Therefore, it is necessary to correct the projection height by combining the depth difference. An example of the correction method is as follows: the ear height can be calculated by combining the depth difference h between the feature point at the bottom of the corn stalk and the feature point at the bottom of the corn ear, and the projection height L. H 结穗 :

[0099] ;

[0100] Similarly, the plant spacing, ear length, and diameter of corn can be obtained using the above methods.

[0101] In some embodiments of this application, the processing speed of the cutter for harvesting is obtained based on the agronomic parameters and the travel speed of the cutter, including: obtaining the plant processing speed based on the travel speed and the stem distribution information of the harvested crops in the agronomic parameters; and converting the plant processing speed into the cutter processing speed for the harvested crops based on the number of harvested crops per unit area. For example, after obtaining the agronomic parameters of corn, the total number of ears Q harvested by the cutter in the next second can be calculated based on the plant spacing and the travel speed detected by the speed sensor, which is usually consistent with the travel speed of the harvesting machinery where the cutter is located, i.e., equal to the travel speed of the corn harvester. The calculation formula is as follows:

[0102] ;

[0103] Where n is the number of rows at harvest time; V车 The speed of travel is expressed in m / s. L 株距 , where is the corn plant spacing in mm; Q is the total number of ears harvested in the next second in ear / s.

[0104] In some embodiments of this application, the processing components of the header that perform the harvesting process include stem-pulling rollers; the operating speed of each processing component of the header used to perform the harvesting process is obtained based on the processing speed, including:

[0105] The first constraint is that the stem-pulling time should not exceed the vehicle travel time, i.e.: ;

[0106] in, V 拉 Let be the linear velocity of the stem-pulling roller, and s be the safety factor. H 结穗 The height of the ear, H 摘穗 t is the height of the harvesting platform for picking ears. 车 The time required for the cutting platform to travel one plant spacing;

[0107] in: L 株距 For corn plant spacing, V 车 This refers to the speed of travel.

[0108] The second constraint is that the processing speed of the stem-pulling roller is greater than the processing speed of the header on the stem-pulling roller.

[0109] ;

[0110] Among them, Q 拉 The processing speed of the stem-pulling roller for the harvested material, n Q represents the number of rows at harvest time, and Q is the processing speed of the cutter for the harvested material.

[0111] After transforming the above equation, we get:

[0112] ;

[0113] Based on the aforementioned formula, the minimum linear speed required for the stalk-pulling roller can be determined according to the current travel speed, header ear-picking height, corn ear-setting height, and corn plant spacing. V 拉 ,Should V 拉 It can satisfy the first constraint and the second constraint.

[0114] In some embodiments of this application, the processing component of the header performing the harvesting process includes a reeling chain; obtaining the operating speed of each processing component of the header for performing the harvesting process based on the processing speed includes: obtaining an expression for the processing speed of the reeling chain on the corn ear, wherein the parameters of the expression include the linear velocity of the reeling chain; this expression is constructed based on the processing capacity of the corn ear on the picking channel, and includes various factors affecting the processing capacity, such as the fullness coefficient, the capacity, the length of the corn ear, and the linear velocity of the reeling chain, resulting in:

[0115] ;

[0116] Among them, Q 拨 To improve the processing speed of the harvested materials in the reeling chain, n The number of rows at harvest time. Ψ 1 represents the fullness coefficient, taking into account that the fruit bunches in the picking lane are not completely filled, with the fullness ranging from 0.5 to 1. L 0 represents the length of the corn ear, V 拨 This represents the linear velocity of the reeling chain.

[0117] The ear-carrying capacity Q of the reeling chain 拨 The number of ears harvested by the header in the next second should be greater than Q to ensure that the plants are processed. Therefore, the constraint is that the processing speed of the reel chain is greater than the processing speed of the header, i.e.:

[0118] ;

[0119] Determine the range of values ​​for the linear velocity of the reeling chain, i.e.:

[0120] ;

[0121] The minimum linear velocity of the reeling chain is obtained based on the range of values ​​for the linear velocity of the reeling chain.

[0122] In some embodiments of this application, the processing component of the header performing the harvesting process includes an auger; obtaining the operating speed of each processing component of the header for performing the harvesting process based on the processing speed includes: obtaining an expression for the processing speed of the auger on the corn ears, the expression being constructed based on the auger's processing capacity for corn ears, which includes various factors affecting the processing capacity, such as the auger blade size, auger pitch, auger actual efficiency, and auger rotation speed, resulting in:

[0123] ;

[0124] Among them, Q 搅龙 To improve the speed of processing the harvested materials, η This represents the actual efficiency value of the auger.P The pitch of the auger. π Pi d 1 represents the outer diameter of the auger blade. d 2 represents the inner diameter of the auger blades. n 搅龙 For the rotation speed of the auger, V 1 represents the volume of the material to be harvested:

[0125] , D 0 represents the diameter of the corn ear. L 0 represents the length of the corn ear.

[0126] The auger needs to transport all the fruit ears within the model. The auger's transport capacity should be greater than the total number of fruit ears harvested by the header in the next second. Therefore, the constraint is that the auger's processing speed for the harvested fruit must be greater than the header's processing speed for the harvested fruit.

[0127] ;

[0128] Determine the range of values ​​for the auger rotation speed, i.e.:

[0129] ;

[0130] The minimum rotational speed of the auger is obtained based on the range of values ​​for the auger's rotational speed.

[0131] In some embodiments of this application, after obtaining the operating speed of each processing component used to perform the harvesting process, the method further includes: adjusting the output flow of the hydraulic pump through a control signal to control the hydraulic motor to drive each processing component to operate at the said operating speed; and obtaining the real-time rotational speed of each working component of the header based on the current engine speed and feedback signals. Specifically, the header execution unit achieves matching of the rotational speed of the header working components with the travel speed and corn agronomic parameters through control signals issued by the intelligent control unit. The engine outputs power to the hydraulic pump, which converts mechanical energy into hydraulic energy and adjusts the output flow according to the control signal to achieve precise control of the hydraulic motor speed, thereby achieving control of the header working components. The electro-proportional hydraulic variable pump can send feedback signals back to the intelligent control unit, and the real-time rotational speed of each working component of the header can be obtained based on the current engine speed and feedback signals.

[0132] Through the above implementation methods, the target detection model for corn stalks and ears, the corn agronomic calculation model based on binocular vision, and the calculation of the required rotational speeds for each component of the header are all integrated into the data processing module of the intelligent control unit, achieving end-to-end rotational speed matching. During the actual operation of the corn harvester, each time the binocular camera captures an image, the image data is transmitted to the intelligent control unit via the image acquisition card. The intelligent control unit then uses the target detection model to identify and label the corn ears and stalks in the image, performs corn agronomic calculations, determines the corresponding minimum rotational speeds for each component of the header under the current working state and conditions, and outputs control signals to the actuators through the execution control module, thereby achieving accurate control of the actuators' working state.

[0133] Based on the same inventive concept, this application also provides an automatic speed matching device for cutting table components. Figure 7 A schematic diagram of the automatic speed matching device for the cutter head component according to an embodiment of this application is shown. Figure 7 As shown, an automatic matching device for the rotation speed of a header component is disclosed. The device includes: a parameter acquisition module for acquiring agronomic parameters of the harvesting area in front of the header; the agronomic parameters include at least one of the following: the size information of the harvested material, the stem distribution information of the harvested material, and the relative position of the harvested material on its stem; a processing speed module for obtaining the processing speed of the header for the harvested material based on the agronomic parameters and the traveling speed of the header; and a speed output module for obtaining the operating speed of each processing component of the header used to perform the harvesting process based on the processing speed of the header for the harvested material.

[0134] In some alternative implementations, the processing speed of the cutter for the harvested material is obtained based on the agronomic parameters and the travel speed of the cutter, including: obtaining the plant processing speed based on the travel speed and the stem distribution information of the harvested material in the agronomic parameters; and converting the plant processing speed into the cutter processing speed for the harvested material based on the number of harvested material per unit area.

[0135] In some alternative embodiments, the processing component of the cutter for performing the harvesting process includes a stem-pulling roller; the operating speed of each processing component of the cutter for performing the harvesting process is obtained based on the processing speed, including: a first constraint condition that the stem-pulling time is not greater than the travel time; a second constraint condition that the processing speed of the stem-pulling roller on the harvested material is greater than the processing speed of the cutter on the harvested material; and the linear speed of the stem-pulling roller that satisfies the first and second constraint conditions is taken as the minimum linear speed of the stem-pulling roller.

[0136] In some alternative implementations, the first constraint condition is expressed as: ;

[0137] in, V 拉 Let be the linear velocity of the stem-pulling roller, and s be the safety factor. H 结穗 The height of the ear, H 摘穗 t is the height of the harvesting platform for picking ears. 车 The time required for the cutting platform to travel one plant spacing; the second constraint is expressed as:

[0138] ;

[0139] Among them, Q 拉 The processing speed of the stem-pulling roller for the harvested material, n Q represents the number of rows at harvest time, and Q is the processing speed of the cutter for the harvested material.

[0140] In some alternative embodiments, the processing component of the header performing the harvesting process includes a reeling chain; obtaining the operating speed of each processing component of the header for performing the harvesting process based on the processing speed includes: obtaining an expression for the processing speed of the reeling chain on the material to be harvested, the parameters of the expression including the linear velocity of the reeling chain; determining the range of values ​​for the linear velocity of the reeling chain with the constraint that the processing speed of the reeling chain on the material to be harvested is greater than the processing speed of the header on the material to be harvested; and obtaining the minimum linear velocity of the reeling chain based on the range of values ​​for the linear velocity of the reeling chain.

[0141] In some alternative implementations, the expression for the processing speed of the reeling chain on the harvested material includes:

[0142] ;

[0143] Among them, Q 拨 To improve the processing speed of the harvested materials in the reeling chain, n The number of rows at harvest time. Ψ 1 represents the fullness coefficient, taking into account that the fruit bunches in the picking lane are not completely filled, with the fullness ranging from 0.5 to 1. L 0 represents the length of the corn ear, V 拨 This represents the linear velocity of the reeling chain.

[0144] In some alternative embodiments, the processing component of the cutter for performing the harvesting process includes an auger; obtaining the operating speed of each processing component of the cutter for performing the harvesting process based on the processing speed includes: obtaining an expression for the processing speed of the auger on the material to be harvested, the parameters of the expression including the auger rotation speed; determining the range of values ​​for the auger rotation speed with the constraint that the processing speed of the auger on the material to be harvested is greater than the processing speed of the cutter on the material to be harvested; and obtaining the minimum rotation speed of the auger based on the range of values ​​for the auger rotation speed.

[0145] In some alternative implementations, the expression for the processing speed of the auger for the harvested material includes:

[0146] ;

[0147] Among them, Q 搅龙 To improve the speed of processing the harvested materials, η This represents the actual efficiency value of the auger. P The pitch of the auger. π Pi d 1 represents the outer diameter of the auger blade. d 2 represents the inner diameter of the auger blades. V 1 represents the volume of the item to be harvested. n 搅龙 This refers to the rotational speed of the auger.

[0148] In some optional embodiments, obtaining agronomic parameters of the harvesting area in front of the harvesting platform includes: acquiring a first image and a second image of the harvesting area using a first camera and a second camera, respectively; identifying several feature points of the harvested material and its stem from the first image and the second image; determining the depth information of the several feature points based on the position and optical parameters of the first and second cameras; determining the target to be tested based on the agronomic parameters to be determined, and selecting feature points of the target to be tested from the several feature points; and obtaining the value of the agronomic parameters to be determined based on the depth information of the feature points of the target to be tested and the pixel size information of the image of the target to be tested.

[0149] In some optional implementations, identifying several feature points of the object to be picked and its stem from the first image and the second image includes: using a trained real-time target detection algorithm to identify the object to be picked and its stem from the first image and the second image respectively; using a scale-invariant feature transformation algorithm to identify a set of feature points from the object to be picked and its stem, obtaining a first set of feature points corresponding to the first image and a second set of feature points corresponding to the second image; and matching the first set of feature points and the second set of feature points to obtain several feature points of the object to be picked and its stem.

[0150] In some alternative implementations, the real-time object detection algorithm is obtained by modifying the YOLO algorithm as follows: introducing a channel-priority convolutional attention module into the backbone layer of the YOLO algorithm; and introducing a multi-scale convolutional module into the connection layer of the YOLO algorithm.

[0151] In some optional embodiments, determining the depth information of the plurality of feature points based on the position parameters and optical parameters of the first camera and the second camera includes: for each of the plurality of feature points, constructing at least one set of similar triangles by selecting several points from the feature point, the optical center of the first camera, the optical center of the second camera, the imaging point of the feature point on the first camera, and the imaging point of the feature point on the second camera; based on the similar triangles, calculating the distance between the feature point and the optical center of the camera or the distance between the feature point and the imaging surface using several line lengths from the distance between the optical centers, the focal length of the first camera, the focal length of the second camera, and the distance from the imaging point to the end of the imaging surface; and using the distance between the feature point and the optical center of the camera or the distance between the feature point and the imaging surface as the depth information of the feature point.

[0152] In some optional implementations, the target to be measured is determined based on the agronomic parameters to be determined, and feature points of the target to be measured are selected from the plurality of feature points, including: if the agronomic parameters to be determined are the size information of the object to be harvested, the target to be measured is the object to be harvested, and the feature points of the target to be measured include the left end feature point, right end feature point, top end feature point, and bottom end feature point of the object to be harvested; if the agronomic parameters to be determined are the stem distribution information of the object to be harvested, the target to be measured is the stem of the object to be harvested, and the feature points of the target to be measured include the bottom end feature point of the stem of the object to be harvested; if the agronomic parameters to be determined are the relative position of the object to be harvested on its stem, the target to be measured is the object to be harvested and its stem, and the feature points of the target to be measured include the bottom end feature point of the object to be harvested and the bottom end feature point of the stem of the object to be harvested.

[0153] In some optional implementations, the value of the agronomic parameter to be determined is obtained based on the depth information of the feature points of the target under test and the pixel size information of the image formed by the target under test, including: obtaining the pixel distance between feature points based on the pixel size information of the line segment formed by the feature points of the target under test in the image; obtaining the projection height of the line segment formed by the feature points of the target under test based on the pixel distance and the depth information, and obtaining the value of the agronomic parameter to be determined based on the projection height.

[0154] In some optional embodiments, when the depth information of different feature points of the target to be measured is inconsistent, the device further includes a projection correction module, which is used to: calculate the depth difference between different feature points within the same line segment, correct the projection height based on the depth difference, and obtain the value of the agronomic parameter to be determined from the corrected projection height.

[0155] In some alternative embodiments, after obtaining the operating speed of each processing component for performing the harvesting process, the device further includes a control and monitoring module for: adjusting the output flow of the hydraulic pump through control signals, controlling the hydraulic motor to drive each processing component to operate at the operating speed; and obtaining the real-time rotational speed of each working component of the header based on the current engine speed and feedback signals.

[0156] The specific limitations of each functional module in the aforementioned automatic header component speed matching device can be found in the limitations of the automatic header component speed matching method described above, and will not be repeated here. Each module in the above system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independently of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module. It also achieves the advantage of automated control based on adaptive agronomic parameters.

[0157] In some embodiments of this application, an electronic device is also provided, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which executes the aforementioned automatic rotation speed matching method for the cutting table component. Its internal structure diagram can be shown as follows. Figure 8 As shown. Figure 8 The diagram schematically illustrates the internal structure of an electronic device according to an embodiment of this application. The electronic device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The network interface A02 is used for communication with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements an automatic speed matching method for cutting table components.

[0158] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0159] In one embodiment provided in this application, a harvesting machine is also provided. Figure 9 A schematic diagram illustrating the system structure of the harvesting machinery according to an embodiment of this application is shown. For example... Figure 9 As shown, the harvesting machinery includes: a vision recognition unit, a sensor unit, an intelligent control unit, a header execution unit, a human-machine interaction unit, and a connecting harness.

[0160] The visual recognition unit includes a camera and a deep learning target detection model. The camera uses two area array cameras to form a binocular camera for taking pictures. The target detection model is trained to accurately identify corn ears and corn stalks and is then embedded into the intelligent control unit.

[0161] The sensor unit includes a speed sensor and an infrared sensor, which are installed on the front axle and the header of the corn harvester, respectively, to monitor the corn harvester's speed and header height in real time during operation.

[0162] The header actuator unit consists of an electro-proportional hydraulic variable pump, an actuator motor, and various working components of the header. It can match the rotational speed of the header's working components with the travel speed and corn agronomic parameters via control signals from the intelligent control unit. The engine outputs power to the hydraulic pump, which converts mechanical energy into hydraulic energy and adjusts the output flow or oil inlet / outlet direction according to the control signals, achieving precise control of the hydraulic motor's rotational speed, thereby controlling the header's working components. The electro-proportional hydraulic variable pump can send feedback signals back to the intelligent control unit, allowing the real-time rotational speed of each header working component to be obtained based on the current engine speed and the feedback signals. The control panel can display the monitored travel speed and the rotational speed of each header component in real time.

[0163] The core processor of the intelligent control unit is a PLC, whose main function is to execute the aforementioned automatic speed matching method for the header components. It can include a data acquisition module, a data processing module, and an execution control module. The data acquisition module can receive images captured by the camera and can also read information such as travel speed and header height from sensors. The data processing module can recognize the captured images and perform calculations and analyses on various agronomic processes of corn through a built-in binocular vision algorithm, thereby calculating the required speed of each component of the header and issuing control signals. The execution control module outputs the control signals to the actuators, thereby matching and adjusting the speed of each component of the header.

[0164] A wiring harness is a type of wiring harness used to connect sensor units, intelligent control units, execution units, and human-machine interaction units. It includes communication lines, power lines, and signal lines. The intelligent control unit is connected to the human-machine interaction unit and the execution unit via communication lines, while the control unit is connected to the sensor unit via signal lines. All hardware needs to be directly or indirectly connected to a power source from the battery.

[0165] In summary, by acquiring real-time image information of the work scene through binocular cameras and using a deep learning object detection algorithm, corn ears and stalks in the current work scene are detected. Based on binocular vision technology, the current corn plant spacing, ear height, ear length and diameter are analyzed. The current travel speed and header height are monitored by speed and infrared sensors. The corn processing capacity per second of the header is calculated based on the travel speed and plant spacing. Based on the processing capacity, the number of rows harvested, the corn plant spacing, ear height, ear length and diameter, the required rotation speed of each component of the header is deduced and adjusted to achieve automatic matching of the rotation speed of each component of the header.

[0166] In one embodiment provided in this application, a machine-readable storage medium is provided, on which instructions are stored, which, when executed by a processor, cause the processor to be configured to perform the aforementioned automatic matching method for the rotational speed of the cutting table component.

[0167] In one embodiment provided in this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the aforementioned automatic rotation speed matching method for the cutting table component.

[0168] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0169] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0170] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0171] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0172] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0173] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0174] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0175] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0176] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for automatically matching the rotational speed of a header component, characterized by, The method comprises: Obtaining the agricultural parameters of the area to be picked in front of the header; the agricultural parameters include at least one of the size information of the objects to be picked, the stem distribution information of the objects to be picked, and the relative position of the objects to be picked on the stem; According to the agricultural parameters and the traveling speed of the header, the processing speed of the header on the objects to be picked is obtained; Based on the processing speed of the header on the objects to be picked, the running speed of each processing component of the header for performing the picking process is obtained; The processing component of the header for performing the picking process includes a stem pulling roller; based on the processing speed, the running speed of each processing component of the header for performing the picking process is obtained, which includes: Taking the stem pulling time not greater than the driving time as a first constraint condition; Taking the processing speed of the stem pulling roller on the objects to be picked greater than the processing speed of the header on the objects to be picked as a second constraint condition; Taking the linear speed of the stem pulling roller meeting the first constraint condition and the second constraint condition as the minimum linear speed of the stem pulling roller.

2. The header component rotational speed automatic matching method of claim 1, wherein, According to the agricultural parameters and the traveling speed of the header, the processing speed of the header on the objects to be picked is obtained, which includes: According to the traveling speed and the stem distribution information of the objects to be picked in the agricultural parameters, the plant processing speed is obtained; The plant processing speed is converted into the processing speed of the header on the objects to be picked according to the number of the objects to be picked per unit area.

3. The header component rotational speed automatic matching method of claim 1, wherein, The first constraint condition is expressed as: ； wherein, V 拉 is the linear speed of the stalk pulling roller, s is the safety factor, H 结穗 is the ear height, H 摘穗 is the header ear picking height, t 车 is the time required for the header to travel one plant spacing; The second constraint condition is expressed as: ； where Q 拉 is the processing speed of the stalk pulling roller pair for the plants to be harvested, n is the number of rows at the time of harvesting, and Q is the processing speed of the header for the plants to be harvested.

4. The header component rotational speed automatic matching method of claim 1, wherein, The processing component of the header for performing the picking process includes a reed chain; based on the processing speed, the running speed of each processing component of the header for performing the picking process is obtained, which includes: An expression of the processing speed of the reed chain on the objects to be picked is obtained, and parameters of the expression include the linear speed of the reed chain; Taking the processing speed of the reed chain on the objects to be picked greater than the processing speed of the header on the objects to be picked as a constraint condition, the value range of the linear speed of the reed chain is determined; Based on the value range of the linear speed of the reed chain, the minimum linear speed of the reed chain is obtained.

5. The header component rotational speed automatic matching method of claim 4, wherein, The expression of the processing speed of the reed chain on the objects to be picked includes: ； where Q 拨 is the processing speed of the chain, n is the number of rows at the time of harvesting, Ψ 1 is the fullness coefficient, taking into account that the ears in the path of the picker are not completely full, the fullness being between 0.5 and 1, L 0 is the length of the corn ear, V 拨 is the linear speed of the chain.

6. The header component rotational speed automatic matching method of claim 1, wherein, The processing component of the header for performing the picking process includes a beater; based on the processing speed, the running speed of each processing component of the header for performing a picking process is obtained, which includes: An expression of the processing speed of the beater on the objects to be picked is obtained, and parameters of the expression include the rotating speed of the beater; Taking the processing speed of the beater on the objects to be picked greater than the processing speed of the header on the objects to bepicked as a constraint condition, the value range of the rotating speed of the beater is determined; Based on the value range of the rotating speed of the beater, the minimum rotating speed of the beater is obtained.

7. The header component rotational speed automatic matching method of claim 6, wherein, The expression of the processing speed of the beater on the objects to be picked includes: ； wherein Q 搅龙 is the processing speed of the harvester for the picked objects, η is the actual efficiency value of the harvester, P is the pitch of the harvester, π is the value of the circle constant, d 1 is the outer diameter of the harvester blade, d 2 is the inner diameter of the harvester blade, V 1 is the volume of the objects to be picked, n 搅龙 is the rotational speed of the harvester.

8. The header component rotational speed automatic matching method of claim 1, wherein, Obtaining the agricultural parameters of the area to be picked in front of the header includes: Obtaining a first image and a second image of the area to be picked through a first camera and a second camera respectively; Identifying a plurality of feature points of the objects to be picked and the stems thereof from the first image and the second image; Determining the depth information of the plurality of feature points according to the position parameters and optical parameters of the first camera and the second camera; Determining a target to be measured based on the agricultural parameters to be determined, and selecting a feature point of the target to be measured from the plurality of feature points; The value of the to-be-determined agronomic parameter is obtained based on depth information of feature points of the to-be-measured target and pixel size information of the to-be-measured target.

9. The header component rotational speed automatic matching method of claim 8, wherein, A plurality of feature points of the to-be-picked object and the stem thereof are identified from the first image and the second image, including: A trained real-time target detection algorithm is used to identify the to-be-picked object and the stem thereof from the first image and the second image, respectively; A scale-invariant feature transformation algorithm is used to identify a feature point set from the to-be-picked object and the stem thereof, to obtain a first feature point set corresponding to the first image and a second feature point set corresponding to the second image; The first feature point set and the second feature point set are matched to obtain a plurality of feature points of the to-be-picked object and the stem thereof.

10. The header component rotational speed automatic matching method of claim 9, wherein, The real-time target detection algorithm is obtained by improving the YOLO algorithm as follows: A channel-first convolution attention module is introduced into the backbone layer of the YOLO algorithm; and A multi-scale convolution module is introduced into the connection layer of the YOLO algorithm.

11. The header component rotational speed automatic matching method of claim 8, wherein, Depth information of the plurality of feature points is determined according to position parameters and optical parameters of the first camera and the second camera, including: For each feature point in the plurality of feature points, at least one group of similar triangles is constructed by selecting a plurality of points from the feature point, the optical center of the first camera, the optical center of the second camera, the imaging point of the feature point in the first camera, and the imaging point of the feature point in the second camera; Based on the similar triangles, the distance between the optical centers, the focal length of the first camera, the focal length of the second camera, and the distance between the imaging point and the end of the imaging surface are used to calculate the distance between the feature point and the optical center of the camera or the distance between the feature point and the imaging surface; The distance between the feature point and the optical center of the camera or the distance between the feature point and the imaging surface is used as the depth information of the feature point.

12. The header component rotational speed automatic matching method of claim 8, wherein, A to-be-measured target is determined based on the to-be-determined agronomic parameter, and a feature point of the to-be-measured target is selected from the plurality of feature points, including: If the to-be-determined agronomic parameter is to-be-picked object size information, the to-be-measured target is the to-be-picked object, and the feature point of the to-be-measured target includes the left end feature point, the right end feature point, the top end feature point, and the bottom end feature point of the to-be-picked object; If the to-be-determined agronomic parameter is to-be-picked object stem distribution information, the to-be-measured target is the to-be-picked object stem, and the feature point of the to-be-measured target includes the bottom end feature point of the to-be-picked object stem; If the to-be-determined agronomic parameter is the relative position of the to-be-picked object on the stem thereof, the to-be-measured target is the to-be-picked object and the stem thereof, and the feature point of the to-be-measured target includes the bottom end feature point of to-be-picked object and the bottom end feature point of the to-be-picked object stem.

13. The header component rotational speed automatic matching method of claim 8, wherein, The value of the to-be-determined agronomic parameter is obtained based on depth information of feature point of the to-be-measured target and pixel size information of the to-be-measured target, including: Pixel distance between feature points is obtained based on pixel size information of a line segment formed by the feature points of the to-be-measured target in the imaging; A projection height of the line segment formed by the feature points of the to-be-measured target is obtained based on the pixel distance and the depth information, and the value of the to-be-determined agronomic parameter is obtained based on the projection height.

14. The header component rotational speed automatic matching method of claim 13, wherein, When the depth information of different feature points of the target to be measured is inconsistent, the method further comprises: calculating the depth difference between different feature points in the same line segment, correcting the projection height based on the depth difference, and obtaining the value of the agronomic parameter to be determined with the corrected projection height.

15. The header component rotational speed automatic matching method of claim 1, wherein, After obtaining the running speed of each processing component for performing the picking process respectively, the method further comprises: adjusting the output flow of the hydraulic pump through the control signal, and controlling the hydraulic motor to drive each processing component to operate at the running speed; and obtaining the real-time speed of each working component of the header according to the current engine speed and the feedback signal.

16. An automatic header component speed matching device, characterized by, The device for implementing the header component speed automatic matching method in any one of claims 1 to 15 comprises: a parameter acquisition module configured to acquire agronomic parameters of a picking area in front of the header, wherein the agronomic parameters comprise at least one of size information of the objects to be picked, stem distribution information of the objects to be picked, and relative position of the objects to be picked on the stem; a processing speed module configured to obtain a processing speed of the header to the objects to be picked according to the agronomic parameters and a traveling speed of the header; and a speed output module configured to obtain a running speed of each processing component of the header for performing the picking process respectively based on the processing speed of the header to the objects to be picked. comprises: at least one processor; 17. An electronic device, comprising: a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the steps of the header component speed automatic matching method in any one of claims 1 to 15 by executing the instructions stored in the memory. The computer program / instructions, when executed by the processor, implement the steps of the header component speed automatic matching method in any one of claims 1 to 15. The PLC in the harvesting machine is configured to execute the header component speed automatic matching method in any one of claims 1 to 15.

18. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, ​ 19. A harvesting machine characterized in that, ​

Images