Method and device for adjusting shooting position of blade

Abstract

The invention provides a blade shooting position adjusting method and device. After respective target feature positions of a plurality of morphological feature points in a target leaf image are obtained at a first shooting position, selecting a plurality of preset target transformation models taking the first shooting position as a preset shooting starting position from a plurality of preset transformation models; obtaining each target position difference value of the corresponding morphological feature points through the respective target feature positions of the plurality of morphological feature points, performing similarity matching on each target position difference value of the plurality of morphological feature points and each predicted position difference value in a plurality of preset target transformation models, and determining a matched first preset target transformation model, and adjusting the camera through a position adjustment instruction stored in the first preset target transformation model. The matching data volume is reduced, the data processing efficiency is improved, automatic identification and camera position adjustment through the leaf image are realized, and manual errors and static measurement errors are avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing, and in particular to a method, device, medium and electronic device for adjusting a blade shooting position. Background Art

[0002] Leaves are where plants carry out photosynthesis, and their size and shape have a direct impact on plant growth. When screening fruit and vegetable varieties, leaf phenotypic parameter values ​​can be used to identify the number and area of ​​lesions on the leaves, and then the health of the plants can be evaluated. At present, the leaf phenotypic parameter values ​​are basically collected by manual measurement during the breeding process.

[0003] However, due to the different sizes, shapes, and complex edges of leaves, the measurement methods are diverse. Manually measuring the values ​​of leaf phenotypic parameters is not only laborious, but also prone to human errors. Handheld leaf area meters can only complete static monitoring, and static monitoring has a misalignment problem, resulting in a large error between static photo data and actual data.

[0004] Therefore, the present disclosure provides a method for adjusting the shooting position of a blade to solve one of the above technical problems. Summary of the invention

[0005] The purpose of the present disclosure is to provide a method, device, medium and electronic device for adjusting the blade shooting position, which can solve at least one of the above-mentioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of the present disclosure, in a first aspect, the present disclosure provides a method for adjusting a blade shooting position, comprising:

[0007] Obtaining target feature positions of respective multiple morphological feature points in the target leaf image captured by the camera at the first camera position;

[0008] Taking the first camera position as a preset starting camera position, acquiring a plurality of preset target transformation models from a plurality of preset transformation models;

[0009] Calculate the difference between the target feature position of each morphological feature point and the preset reference feature position of the corresponding morphological feature point at the first camera position on each coordinate axis to obtain the target position difference of the corresponding morphological feature point on the corresponding coordinate axis;

[0010] Performing similarity matching on the target position differences of the plurality of morphological feature points on all coordinate axes and the predicted position differences of the plurality of morphological feature points on all coordinate axes in each preset target transformation model, respectively, to determine a matched first preset target transformation model;

[0011] Based on the position adjustment instruction saved in the first preset target transformation model, the camera is adjusted from the first shooting position to the preset end shooting position saved in the first preset target transformation model.

[0012] Optionally, the similarity matching of the target position differences of the multiple morphological feature points on all coordinate axes with the predicted position differences of the multiple morphological feature points on all coordinate axes in each preset target transformation model to determine the matched first preset target transformation model includes:

[0013] The target position difference of each morphological feature point on each coordinate axis is calculated respectively with the predicted position difference of the corresponding morphological feature point on the corresponding coordinate axis in each preset target transformation model to obtain the target difference of the corresponding morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model;

[0014] At least based on the target difference values ​​of the plurality of morphological feature points in each preset target transformation model on all coordinate axes, respectively obtain the target and value of the corresponding preset target transformation model;

[0015] Determine the minimum target and value among the targets and values ​​of the plurality of preset target transformation models;

[0016] When the minimum target sum value is less than a preset similarity threshold, the preset target transformation model corresponding to the minimum target sum value is determined to be a matched first preset target transformation model.

[0017] Optionally, obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0018] The sum of the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value corresponding to the preset target transformation model.

[0019] Optionally, the multiple morphological feature points include at least one primary morphological feature point and multiple secondary morphological feature points;

[0020] Correspondingly, the step of obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0021] Calculate the product of the target difference of each primary morphological feature point on each coordinate axis in each preset target transformation model and the preset core weight value, and obtain the weighted target difference of the corresponding primary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model, and

[0022] Calculate the product of the target difference value of each secondary morphological feature point on each coordinate axis in each preset target transformation model and the preset area weight value, and obtain the weighted target difference value of the corresponding secondary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model;

[0023] The sum of the weighted target difference value of at least one primary morphological feature point on all coordinate axes and the weighted target difference value of each of the multiple secondary morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value of the corresponding preset target transformation model.

[0024] Optionally, the preset core weight value is greater than the preset area weight value, and the sum of the core weight value of each of the at least one primary morphological feature points and the preset area weight values ​​of each of the multiple secondary morphological feature points is equal to 1.

[0025] Optionally, one of the preset starting camera position and the preset ending camera position saved in each of the multiple preset target transformation models is a preset central camera position, and the other saved camera position is one of multiple preset peripheral camera positions; wherein the multiple preset peripheral camera positions surround the preset central camera position.

[0026] Optionally, the first camera position refers to a preset central camera position;

[0027] Correspondingly, the step of obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position includes:

[0028] The target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position are obtained.

[0029] Optionally, before obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position, the method further includes:

[0030] Obtaining a second camera position where the camera is located;

[0031] When it is determined that the second camera position does not match the preset center camera position, determining a preset zeroing transformation model from the plurality of preset transformation models with the second camera position as the preset starting camera position and the preset center camera position as the preset ending camera position;

[0032] Based on the position adjustment instruction stored in the preset zeroing transformation model, the camera is adjusted from the second camera position to the preset center camera position.

[0033] Optionally, the at least one primary morphological feature point includes a leaf core feature point; and the multiple secondary morphological feature points include multiple leaf rectangular area feature points.

[0034] According to a specific embodiment of the present disclosure, in a second aspect, the present disclosure provides a device for adjusting a blade shooting position, comprising:

[0035] A position acquisition unit, used to acquire the target feature position of each of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position;

[0036] A model acquisition unit, configured to acquire a plurality of preset target transformation models from a plurality of preset transformation models by taking the first photographing position as a preset starting photographing position;

[0037] A difference calculation unit is used to perform difference calculation on each coordinate axis between the target feature position of each morphological feature point and the preset reference feature position of the corresponding morphological feature point at the first camera position, so as to obtain the target position difference of the corresponding morphological feature point on the corresponding coordinate axis;

[0038] A matching unit, configured to perform similarity matching on the target position differences of the plurality of morphological feature points on all coordinate axes and on the predicted position differences of the plurality of morphological feature points on all coordinate axes in each preset target transformation model, and determine a matched first preset target transformation model;

[0039] An adjustment unit is used to adjust the camera from the first shooting position to a preset end shooting position saved in the first preset target transformation model based on the position adjustment instruction saved in the first preset target transformation model.

[0040] Optionally, the similarity matching of the target position differences of the multiple morphological feature points on all coordinate axes with the predicted position differences of the multiple morphological feature points on all coordinate axes in each preset target transformation model to determine the matched first preset target transformation model includes:

[0041] The target position difference of each morphological feature point on each coordinate axis is calculated respectively with the predicted position difference of the corresponding morphological feature point on the corresponding coordinate axis in each preset target transformation model to obtain the target difference of the corresponding morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model;

[0042] At least based on the target difference values ​​of the plurality of morphological feature points in each preset target transformation model on all coordinate axes, respectively obtain the target and value of the corresponding preset target transformation model;

[0043] Determine the minimum target and value among the targets and values ​​of the plurality of preset target transformation models;

[0044] When the minimum target sum value is less than a preset similarity threshold, the preset target transformation model corresponding to the minimum target sum value is determined to be a matched first preset target transformation model.

[0045] Optionally, obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0046] The sum of the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value corresponding to the preset target transformation model.

[0047] Optionally, the multiple morphological feature points include at least one primary morphological feature point and multiple secondary morphological feature points;

[0048] Correspondingly, the step of obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0049] Calculate the product of the target difference of each primary morphological feature point on each coordinate axis in each preset target transformation model and the preset core weight value, and obtain the weighted target difference of the corresponding primary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model, and

[0050] Calculate the product of the target difference value of each secondary morphological feature point on each coordinate axis in each preset target transformation model and the preset area weight value, and obtain the weighted target difference value of the corresponding secondary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model;

[0051] The sum of the weighted target difference value of at least one primary morphological feature point on all coordinate axes and the weighted target difference value of each of the multiple secondary morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value of the corresponding preset target transformation model.

[0052] Optionally, the preset core weight value is greater than the preset area weight value, and the sum of the core weight value of each of the at least one primary morphological feature points and the preset area weight values ​​of each of the multiple secondary morphological feature points is equal to 1.

[0053] Optionally, one of the preset starting camera position and the preset ending camera position saved in each of the multiple preset target transformation models is a preset central camera position, and the other saved camera position is one of multiple preset peripheral camera positions; wherein the multiple preset peripheral camera positions surround the preset central camera position.

[0054] Optionally, the first camera position refers to a preset central camera position;

[0055] Correspondingly, the step of obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position includes:

[0056] The target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position are obtained.

[0057] Optionally, before obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position, the method further includes:

[0058] Obtaining a second camera position where the camera is located;

[0059] When it is determined that the second camera position does not match the preset center camera position, determining a preset zeroing transformation model from the plurality of preset transformation models with the second camera position as the preset starting camera position and the preset center camera position as the preset ending camera position;

[0060] Based on the position adjustment instruction stored in the preset zeroing transformation model, the camera is adjusted from the second camera position to the preset center camera position.

[0061] Optionally, the at least one primary morphological feature point includes a leaf core feature point; and the multiple secondary morphological feature points include multiple leaf rectangular area feature points.

[0062] According to a specific embodiment of the present disclosure, in a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for adjusting the blade shooting position as described in any one of the above items is implemented.

[0063] According to the specific implementation of the present disclosure, in a fourth aspect, the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for adjusting the blade shooting position as described in any one of the above items.

[0064] Compared with the prior art, the above solution of the embodiment of the present disclosure has at least the following beneficial effects:

[0065] The present disclosure provides a method, device, medium and electronic device for adjusting the shooting position of a blade. The present disclosure provides a preset transformation model for each adjustment path, and each preset transformation model stores the key information required for the adjustment. After obtaining the target feature positions of each of the multiple morphological feature points in the target blade image at the first camera position, multiple preset target transformation models with the first camera position as the preset starting camera position are selected from multiple preset transformation models, and the target position differences of the corresponding morphological feature points on the corresponding coordinate axis are obtained through the target feature positions of each of the multiple morphological feature points. The target position differences of the multiple morphological feature points on the corresponding coordinate axis are similarly matched with the predicted position differences of the multiple morphological feature points in the multiple preset target transformation models on the corresponding coordinate axis, and the matched first preset target transformation model is determined. The camera is adjusted to the preset end camera position stored in the first preset target transformation model through the position adjustment instruction stored in the first preset target transformation model. The amount of matching data is reduced, the data processing efficiency is improved, the automatic recognition and adjustment of the camera position through the blade image is realized, and manual errors and static measurement errors are avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A flow chart showing a method for adjusting a blade shooting position according to an embodiment of the present disclosure is shown;

[0067] Figure 2 A schematic diagram showing preset reference feature positions of morphological feature points on a standard front leaf image according to an embodiment of the present disclosure is shown;

[0068] Figure 3 A schematic diagram showing target feature positions of morphological feature points on a side leaf image according to an embodiment of the present disclosure;

[0069] Figure 4 A schematic diagram of a star path layout according to an embodiment of the present disclosure is shown;

[0070] Figure 5 A unit block diagram of a device for adjusting a blade photographing position according to an embodiment of the present disclosure is shown;

[0071] Figure 6 A schematic diagram of a connection structure of an electronic device provided according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0073] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0074] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0075] It should be understood that although the terms first, second, third, etc. may be used to describe in the disclosed embodiments, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the disclosed embodiments, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0076] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0077] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0078] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0079] The optional embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0080] Example 1

[0081] The present disclosure provides an embodiment, that is, an embodiment of a method for adjusting a blade shooting position.

[0082] Combine the following Figure 1 The embodiments of the present disclosure are described in detail.

[0083] Step S101, obtaining target feature positions of respective multiple morphological feature points in a target leaf image captured by a camera at a first camera position.

[0084] In order to collect the leaf phenotypic parameter values, it is necessary to capture the front image of the leaf. However, the angle of the front of the leaf will change as the environmental conditions change. To this end, the embodiment of the present disclosure sets a plurality of preset camera positions near the leaf, and no matter how the front of the leaf changes, the front image of the leaf can be captured at one of the plurality of preset camera positions. The first camera position can be one of the plurality of preset camera positions, or a position near one of the preset camera positions.

[0085] The morphological feature points refer to the feature points of the shape, appearance and structure of the leaf. For example, the morphological feature points include: feature points on the leaf contour, feature points on the leaf center, feature points on key veins and / or feature points at the four corners of the leaf rectangular area, but the embodiments of the present disclosure are not limited thereto.

[0086] In the embodiments of the present disclosure, the positions mentioned refer to three-dimensional coordinate positions in a preset three-dimensional coordinate system.

[0087] By using the segmentation technology in the SAM model, the data calculation of the leaf surface contour in the target leaf image can be realized to obtain a pts data set. The three-dimensional coordinate position of the leaf contour can be generated by the pts data set. The process of obtaining the three-dimensional coordinate position of the leaf contour by using the SAM model is not described in detail in this embodiment, and can be implemented with reference to various implementation methods in the prior art.

[0088] Step S102: taking the first camera position as a preset starting camera position, acquiring a plurality of preset target transformation models from a plurality of preset transformation models.

[0089] In order to adjust the position of the camera between multiple preset camera positions, the disclosed embodiment sets a preset target transformation model for each adjustment path. The multiple preset transformation models can ensure that the camera can be moved to a position suitable for capturing the blade image at any position.

[0090] The preset transformation model stores a preset starting camera position and a preset ending camera position, predicted position differences of a plurality of morphological feature points on each coordinate axis, and position adjustment instructions.

[0091] The preset reference feature position of any morphological feature point refers to the position of the corresponding morphological feature point on the standard front leaf image collected at the camera position. Figure 2 As shown, the multiple morphological feature points include a leaf core feature point and four leaf rectangular area feature points; at the camera position (x a ,y a , z a ) collected, the preset reference feature position (x a00 ,y a00 , z a00 ), the preset reference feature position (x a01 ,y a01 , z a01 ), the preset reference feature position (x a02 ,y a02 , z a02 ), the preset reference feature position (x a03 ,y a03 , z a03 ), the preset reference feature position (x a04 ,y a04 , z a04 ).

[0092] For any morphological feature point, the preset reference feature position of the corresponding morphological feature point at the preset end camera position is mapped to the leaf image at the preset start camera position to obtain the target feature position of the corresponding morphological feature point. The difference between the target feature position of the corresponding morphological feature point and the preset reference feature position of the corresponding morphological feature point at the preset start camera position on each coordinate axis is the predicted position difference of any morphological feature point on the corresponding coordinate axis. For example, continuing the above example, Figure 3 As shown, at the camera position (x b ,y b , z b ) collected from the side blade image, the preset reference feature position of the blade core feature point (x a00 ,y a00 , z a00 ), mapped to the target feature position (x) of the core feature point of the blade on the side blade image b10 ,y b10 , z b10); if at the camera position (x b ,y b , z b ) to collect the second standard front leaf image, and the preset reference feature position (x b00 ,y b00 , z b00 ), then the predicted position difference (Δx b1 , Δy b1 , Δz b1 ), Δx b1 =x b10 -x b00 , Δy b1 =y b10 -y b00 , Δz b1 =z b10 -z b00 , and so on, to obtain the predicted position differences of other morphological feature points on each coordinate axis.

[0093] The position adjustment instruction refers to an instruction to adjust the camera from a preset starting shooting position to a preset ending shooting position.

[0094] The preset starting camera position in each preset target transformation model is the first camera position, that is, each preset target transformation model retains information from the first camera position to another camera position.

[0095] A plurality of preset target transformation models are obtained from a plurality of preset transformation models, thereby reducing the amount of data processing and improving adjustment efficiency.

[0096] Step S103 , performing difference calculations on each coordinate axis between the target feature position of each morphological feature point and the preset reference feature position of the corresponding morphological feature point at the first camera position, to obtain the target position difference of the corresponding morphological feature point on the corresponding coordinate axis.

[0097] For example, Figure 3 As shown, if the first camera position (x b ,y b , z b ), then the target feature position of the core feature point of the blade (x b11 ,y b11 , z b11 ), the preset reference feature position of the core feature point of the blade (x b00 ,y b00 , z b00 ), then the target position difference (Δx b2 , Δy b2 , Δz b2), Δx b2 =x b11 -x b00 , Δy b2 =y b11 -y b00 , Δz b2 =z b11 -z b00 , and so on, to obtain the target position differences of other morphological feature points on each coordinate axis.

[0098] Step S104 , similarity matching is performed on the target position differences of the multiple morphological feature points on all coordinate axes and the predicted position differences of the multiple morphological feature points on all coordinate axes in each preset target transformation model to determine a matched first preset target transformation model.

[0099] The purpose of similarity matching is to find a matching first preset target transformation model from multiple preset target transformation models. The position adjustment instruction saved in the first preset target transformation model can adjust the camera to the preset end shooting position saved in the first preset target transformation model, so as to capture the front image of the blade at the preset end shooting position.

[0100] The disclosed embodiment performs similarity matching between target position difference and predicted position difference, and compared with coordinate matching, changes the coordinate-to-coordinate matching mode into numerical matching, thereby reducing the amount of matching data and improving data processing efficiency.

[0101] In some specific embodiments, the method of performing similarity matching on the target position differences of the multiple morphological feature points on all coordinate axes and the predicted position differences of the multiple morphological feature points on all coordinate axes in each preset target transformation model to determine the matched first preset target transformation model includes the following steps:

[0102] Step S104-1, calculate the difference between the target position difference of each morphological feature point on each coordinate axis and the predicted position difference of the corresponding morphological feature point on the corresponding coordinate axis in each preset target transformation model, and obtain the target difference of the corresponding morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model.

[0103] For example, continuing the above example, Figure 3 As shown, if the first camera position (x b ,y b , z b ), the target position difference of the blade core feature point on each coordinate axis (Δx b2 , Δy b2 , Δz b2), and the predicted position difference (Δx b1 , Δy b1 , Δz b1 ) to calculate the difference, and obtain the target difference (ΔD x0 , ΔD y0 , ΔD z0 ), where ΔD x0 =x b2 -x b1 , ΔD y0 =y b2 -y b1 , ΔD z0 =z b2 -z b1 , and so on, the target difference values ​​of other morphological feature points saved in the preset target transformation model M1 on each coordinate axis are obtained, and the target difference values ​​of multiple morphological feature points saved in other preset target transformation models on each coordinate axis are obtained.

[0104] Step S104-2, obtaining the target sum value of the corresponding preset target transformation model respectively based on at least the target difference values ​​of the plurality of morphological feature points in each preset target transformation model on all coordinate axes.

[0105] In this specific embodiment, the target and value of each preset target transformation model, that is, the target similarity value of the corresponding preset target transformation model, is used to measure the similarity between the predicted position difference and the target difference of multiple morphological feature points in the corresponding preset target transformation model on each coordinate axis.

[0106] In some specific embodiments, obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0107] Step S104 - 2a , calculating the sum of target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model, and obtaining a target sum value corresponding to the preset target transformation model.

[0108] For example, the target difference (ΔD x0 , ΔD y0 , ΔD z0 ), the target difference (ΔD) of the feature points of the leaf rectangular area in the upper left corner of the area on each coordinate axis x1 , ΔD y1 , ΔD z1), the target difference (ΔD) of the feature points of the leaf rectangular area in the upper right corner of the area on each coordinate axis x2 , ΔD y2 , ΔD z2 ), the target difference (ΔD) of the feature points of the blade rectangular area in the lower right corner of the area on each coordinate axis x3 , ΔD y3 , ΔD z3 ), the target difference (ΔD) of the feature points of the blade rectangular area in the lower left corner of the area on each coordinate axis x4 , ΔD y4 , ΔD z4 ); preset target conversion model M1 target and value A1 = ΔD x0 +ΔD y0 +ΔD z0 +ΔD x1 +ΔD y1 +ΔD z1 +ΔD x2 +ΔD y2 +ΔD z2 +ΔD x3 +ΔD y3 +ΔD z3 +ΔD x4 +ΔD y4 +ΔD z4 , and so on, to obtain the targets and values ​​of other preset target transformation models.

[0109] In some specific embodiments, the plurality of morphological feature points include at least one primary morphological feature point and a plurality of secondary morphological feature points. The primary morphological feature point is located in the leaf image, is a key feature point of the leaf image, and can determine the position of the leaf in the image. The secondary morphological feature point can determine the outline of the leaf in the image, thereby combining with the primary morphological feature point to ensure that the posture of the leaf in the leaf image can be accurately identified.

[0110] In some specific embodiments, the at least one primary morphological feature point includes a leaf core feature point; the multiple secondary morphological feature points include multiple leaf rectangular area feature points. The leaf core feature point is located in the middle of the leaf, is a key feature point of the leaf image, and can determine the position of the leaf in the image. The leaf rectangular area feature point can determine the contour information of the width and height of the leaf in the image. For example, the multiple leaf rectangular area feature points include four leaf rectangular area feature points, which are the leaf rectangular area feature point at the upper left corner of the area, the leaf rectangular area feature point at the upper right corner of the area, the leaf rectangular area feature point at the lower right corner of the area, and the leaf rectangular area feature point at the lower left corner of the area. Thus, the orientation of the leaf in the leaf image can be determined in combination with the leaf core feature point. Compared with using the morphological feature points on the contour line as the secondary morphological feature points, the contour information of the width and height of the leaf in the image can be determined by using four leaf rectangular area feature points, which effectively reduces the data volume of multiple secondary morphological feature points, not only ensuring that the posture of the leaf can be effectively identified, but also improving the data efficiency, and ensuring that the camera can accurately adjust the position.

[0111] Accordingly, obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model comprises the following steps:

[0112] Step S104-2b-1, calculate the product of the target difference value of each first-level morphological feature point in each preset target transformation model on each coordinate axis and the preset core weight value, and obtain the weighted target difference value of the corresponding first-level morphological feature point in the corresponding preset target transformation model on the corresponding coordinate axis, and calculate the product of the target difference value of each second-level morphological feature point in each preset target transformation model on each coordinate axis and the preset area weight value, and obtain the weighted target difference value of the corresponding second-level morphological feature point in the corresponding preset target transformation model on the corresponding coordinate axis.

[0113] For example, continuing the above example, the target difference (ΔD x0 , ΔD y0 , ΔD z0 ), the preset core weight value is Q1, then the weighted target difference (ΔD x0 ⅹQ1, ΔD y0 ⅹQ1, ΔD z0 ⅹQ1); the preset area weight value is Q2, the weighted target difference (ΔD) of the feature point of the leaf rectangular area in the upper left corner of the area on each coordinate axis x1 ⅹQ2, ΔD y1 ⅹQ2, ΔD z1ⅹQ2), the weighted target difference (ΔD) of the feature points of the leaf rectangular area in the upper right corner of the area on each coordinate axis x2 ⅹQ2, ΔD y2 ⅹQ2, ΔD z2 ⅹQ2), the weighted target difference (ΔD) of the feature points of the leaf rectangular area in the lower right corner of the area on each coordinate axis x3 ⅹQ2, ΔD y3 ⅹQ2, ΔD z3 ⅹQ2), the weighted target difference (ΔD) of the feature points of the leaf rectangular area in the lower left corner of the area on each coordinate axis x4 ⅹQ2, ΔD y4 ⅹQ2, ΔD z4 ⅹQ2).

[0114] Step S104-2b-2, calculate the sum of the weighted target difference value of at least one first-level morphological feature point in each preset target transformation model on all coordinate axes and the weighted target difference value of each of the multiple second-level morphological feature points on all coordinate axes, and obtain the target sum value of the corresponding preset target transformation model.

[0115] For example, continuing the above example, the target sum value A2 of the preset target transformation model M1 is (ΔD x0 +ΔD y0 +ΔD z0 )ⅹQ1+(ΔD x1 +ΔD y1 +ΔD z1 +ΔD x2 +ΔD y2 +ΔD z2 +ΔD x3 +ΔD y3 +ΔD z3 +ΔD x4 +ΔD y4 +ΔD z4 )ⅹQ2, and so on, to obtain the targets and values ​​of other preset target transformation models.

[0116] In this specific embodiment, a weight value is set for the target difference of each morphological feature point on each coordinate axis, which reflects the importance of the target difference of each morphological feature point on each coordinate axis in the target and value, respectively, and highlights the key role of key morphological feature points in the target and value, thereby improving the reliability of judging the blade posture and ensuring that the camera can accurately adjust its position.

[0117] In some specific embodiments, the preset core weight value is greater than the preset area weight value, and the sum of the core weight value of each of the at least one primary morphological feature points and the preset area weight values ​​of each of the multiple secondary morphological feature points is equal to 1.

[0118] For example, continuing the above example, the preset core weight value is 0.4, and the preset area weight value of each of the four leaf rectangular area feature points is 0.15; the preset core weight value is several times the preset area weight value, highlighting the importance and key role of the primary morphological feature points in the target and value, thereby improving the reliability of judging the leaf posture.

[0119] Step S104 - 3 , determining the minimum target sum value among the respective targets and values ​​of the plurality of preset target transformation models.

[0120] The target sum value of each preset target transformation model is used to measure the similarity between the predicted position difference value and the target difference value of each of the multiple morphological feature points on each coordinate axis in the corresponding preset target transformation model. The smaller the target sum value, the higher the similarity.

[0121] Step S104 - 4 : when the minimum target sum value is less than a preset similarity threshold, determining the preset target transformation model corresponding to the minimum target sum value as a matching preset target transformation model.

[0122] If the minimum target sum value is too large, greater than or equal to the preset similarity threshold, it is not worth adjusting the camera position. Therefore, this specific embodiment determines whether to move the camera position by the preset similarity threshold. When the minimum target sum value is less than the preset similarity threshold, it indicates that the preset end camera position stored in the preset target transformation model corresponding to the minimum target sum value is more suitable for the camera to collect effective leaf images. This ensures the effectiveness of adjusting the camera position.

[0123] Step S105 , based on the position adjustment instruction saved in the first preset target transformation model, adjusting the camera from the first shooting position to the preset end shooting position saved in the first preset target transformation model.

[0124] The disclosed embodiment provides a preset transformation model for each adjustment path, and each preset transformation model stores the key information required for adjustment. After obtaining the target feature positions of each of the multiple morphological feature points in the target blade image at the first camera position, multiple preset target transformation models with the first camera position as the preset starting camera position are selected from the multiple preset transformation models, and the target position differences of the corresponding morphological feature points on the corresponding coordinate axes are obtained through the target feature positions of each of the multiple morphological feature points. The target position differences of the multiple morphological feature points on the corresponding coordinate axes are similarly matched with the predicted position differences of the multiple morphological feature points in the multiple preset target transformation models on the corresponding coordinate axes, and the matched first preset target transformation model is determined. The camera is adjusted to the preset end camera position stored in the first preset target transformation model through the position adjustment instruction stored in the first preset target transformation model. The amount of matching data is reduced, the data processing efficiency is improved, the automatic recognition and adjustment of the camera position through the blade image is realized, and manual errors and static measurement errors are avoided.

[0125] In some other specific embodiments, one of the preset starting camera position and the preset ending camera position saved in each of the plurality of preset target transformation models is a preset central camera position, and the other saved camera position is one of a plurality of preset peripheral camera positions.

[0126] Wherein, the plurality of preset peripheral camera positions surround the preset central camera position.

[0127] For example, Figure 4 As shown in the figure, a circle is divided into 9 areas, including a central area and 8 surrounding fan-shaped areas. The center point of each area is set as a camera position, which are: F0, F1, F2, F3, F4, F5, F6, F7 and F8; F0 represents a preset central camera position, and F1 to F8 represent preset peripheral camera positions respectively; a star-shaped path layout is set, that is, an adjustment path is set from F0 to F1 to F8 respectively, and an adjustment path is set from F1 to F8 to F0 respectively, which are: F0—>F1, F0—>F2, F0 —>F3, F0—>F4, F0—>F5, F0—>F6, F0—>F7, F0—>F8, F1—>F0, F2—>F0, F3—>F0, F4—>F0, F5—>F0, F6—>F0, F7—>F0, F8—>F0, a total of 16 adjustment paths, each adjustment path corresponds to a preset transformation model, wherein the camera position at the tail of the arrow represents the preset starting camera position saved in the preset transformation model, and the camera position of the arrow represents the preset ending camera position saved in the preset transformation model.

[0128] The star-shaped path layout can not only fully cover various transformation angles of the blades, but also minimize the adjustment path, greatly reduce the number of preset transformation models, control the data processing volume within a very small range, ensure data processing efficiency, and improve the response speed of the mobile camera.

[0129] In some other specific embodiments, the first camera position refers to a preset central camera position.

[0130] Correspondingly, the step of obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position includes:

[0131] Step S101a, obtaining the target feature positions of each of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position.

[0132] For example, if the first camera position is at F0, the preset starting camera positions stored in the multiple preset target transformation models are all F0, and the preset ending camera positions are one of F1 to F8.

[0133] When the preset central camera position is the origin of the preset coordinate system, the camera directly reaches each preset peripheral camera position from the origin of the preset coordinate system, which can reduce the cumulative error in the camera movement process and improve the accuracy of the camera movement.

[0134] In some other specific embodiments, before obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position, the following steps are also included:

[0135] Step S100-1, obtaining a second camera position where the camera is located.

[0136] Step S100-2: when it is determined that the second camera position does not match the preset center camera position, a preset zeroing transformation model is determined from the plurality of preset transformation models using the second camera position as the preset starting camera position and the preset center camera position as the preset ending camera position.

[0137] Step S100 - 3 , based on the position adjustment instruction stored in the preset zeroing transformation model, adjusting the camera from the second camera position to the preset center camera position.

[0138] In this specific embodiment, if the position of the camera is not at the preset center camera position, the camera is adjusted back to the preset center camera position, that is, the position of the camera is reset to zero, back to the origin position, and then it is identified whether it is necessary to adjust from the preset center camera position to other preset peripheral camera positions. The last step of adjusting the camera is to start from the preset center camera position, thereby reducing the cumulative error in the process of camera movement and improving the accuracy of camera movement.

[0139] Example 2

[0140] The present disclosure also provides an apparatus embodiment that is consistent with the above-mentioned embodiment, and is used to implement the method steps described in the above-mentioned embodiment. The explanation based on the same name meaning is the same as that of the above-mentioned embodiment, and has the same technical effect as that of the above-mentioned embodiment, and will not be repeated here.

[0141] like Figure 5 As shown, the present disclosure provides a blade shooting position adjustment device 500, comprising:

[0142] A position acquisition unit 501 is used to acquire the target feature position of each of a plurality of morphological feature points in the target leaf image captured by the camera at the first camera position;

[0143] A model acquisition unit 502 is used to acquire a plurality of preset target transformation models from a plurality of preset transformation models by taking the first photographing position as a preset starting photographing position;

[0144] The difference calculation unit 503 is used to calculate the difference between the target feature position of each morphological feature point and the preset reference feature position of the corresponding morphological feature point at the first camera position on each coordinate axis, so as to obtain the target position difference of the corresponding morphological feature point on the corresponding coordinate axis;

[0145] A matching unit 504 is used to perform similarity matching on the target position differences of the plurality of morphological feature points on all coordinate axes and the predicted position differences of the plurality of morphological feature points on all coordinate axes in each preset target transformation model, and determine a matched first preset target transformation model;

[0146] The adjusting unit 505 is configured to adjust the camera from the first shooting position to a preset end shooting position saved in the first preset target transformation model based on the position adjustment instruction saved in the first preset target transformation model.

[0147] Optionally, the similarity matching of the target position differences of the multiple morphological feature points on all coordinate axes with the predicted position differences of the multiple morphological feature points on all coordinate axes in each preset target transformation model to determine the matched first preset target transformation model includes:

[0148] The target position difference of each morphological feature point on each coordinate axis is calculated respectively with the predicted position difference of the corresponding morphological feature point on the corresponding coordinate axis in each preset target transformation model to obtain the target difference of the corresponding morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model;

[0149] At least based on the target difference values ​​of the plurality of morphological feature points in each preset target transformation model on all coordinate axes, respectively obtain the target and value of the corresponding preset target transformation model;

[0150] Determine the minimum target and value among the targets and values ​​of the plurality of preset target transformation models;

[0151] When the minimum target sum value is less than a preset similarity threshold, the preset target transformation model corresponding to the minimum target sum value is determined to be a matched first preset target transformation model.

[0152] Optionally, obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0153] The sum of the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value corresponding to the preset target transformation model.

[0154] Optionally, the multiple morphological feature points include at least one primary morphological feature point and multiple secondary morphological feature points;

[0155] Correspondingly, the step of obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes:

[0156] Calculate the product of the target difference of each primary morphological feature point on each coordinate axis in each preset target transformation model and the preset core weight value, and obtain the weighted target difference of the corresponding primary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model, and

[0157] Calculate the product of the target difference value of each secondary morphological feature point on each coordinate axis in each preset target transformation model and the preset area weight value, and obtain the weighted target difference value of the corresponding secondary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model;

[0158] The sum of the weighted target difference value of at least one primary morphological feature point on all coordinate axes and the weighted target difference values ​​of the multiple secondary morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value of the corresponding preset target transformation model.

[0159] Optionally, the preset core weight value is greater than the preset area weight value, and the sum of the core weight value of each of the at least one primary morphological feature points and the preset area weight values ​​of each of the multiple secondary morphological feature points is equal to 1.

[0160] Optionally, one of the preset starting camera position and the preset ending camera position saved in each of the multiple preset target transformation models is a preset central camera position, and the other saved camera position is one of multiple preset peripheral camera positions; wherein the multiple preset peripheral camera positions surround the preset central camera position.

[0161] Optionally, the first camera position refers to a preset central camera position;

[0162] Correspondingly, the step of obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position includes:

[0163] The target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position are obtained.

[0164] Optionally, before obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position, the method further includes:

[0165] Obtaining a second camera position where the camera is located;

[0166] When it is determined that the second camera position does not match the preset center camera position, determining a preset zeroing transformation model from the plurality of preset transformation models with the second camera position as the preset starting camera position and the preset center camera position as the preset ending camera position;

[0167] Based on the position adjustment instruction stored in the preset zeroing transformation model, the camera is adjusted from the second camera position to the preset center camera position.

[0168] Optionally, the at least one primary morphological feature point includes a leaf core feature point; and the multiple secondary morphological feature points include multiple leaf rectangular area feature points.

[0169] The disclosed embodiment provides a preset transformation model for each adjustment path, and each preset transformation model stores the key information required for adjustment. After obtaining the target feature positions of each of the multiple morphological feature points in the target blade image at the first camera position, multiple preset target transformation models with the first camera position as the preset starting camera position are selected from the multiple preset transformation models, and the target position differences of the corresponding morphological feature points on the corresponding coordinate axes are obtained through the target feature positions of each of the multiple morphological feature points. The target position differences of the multiple morphological feature points on the corresponding coordinate axes are similarly matched with the predicted position differences of the multiple morphological feature points in the multiple preset target transformation models on the corresponding coordinate axes, and the matched first preset target transformation model is determined. The camera is adjusted to the preset end camera position stored in the first preset target transformation model through the position adjustment instruction stored in the first preset target transformation model. The amount of matching data is reduced, the data processing efficiency is improved, the automatic recognition and adjustment of the camera position through the blade image is realized, and manual errors and static measurement errors are avoided.

[0170] Example 3

[0171] like Figure 6 As shown, this embodiment provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method steps described in the above embodiment.

[0172] Example 3

[0173] An embodiment of the present disclosure provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the method steps described in the above embodiment.

[0174] Example 4

[0175] Reference below Figure 6 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0176] like Figure 6As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In RAM 603, various programs and data required for the operation of the electronic device are also stored. The processing device 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0177] Typically, the following devices may be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 605 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication devices 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0178] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0179] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0180] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0181] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0182] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0183] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0184] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0185] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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 disclosure.

Claims

1. A method for adjusting a blade shooting position, characterized in that: include: Obtaining target feature positions of respective multiple morphological feature points in the target leaf image captured by the camera at the first camera position; Taking the first camera position as a preset starting camera position, acquiring a plurality of preset target transformation models from a plurality of preset transformation models; Calculate the difference between the target feature position of each morphological feature point and the preset reference feature position of the corresponding morphological feature point at the first camera position on each coordinate axis to obtain the target position difference of the corresponding morphological feature point on the corresponding coordinate axis; Performing similarity matching on the target position differences of the plurality of morphological feature points on all coordinate axes and the predicted position differences of the plurality of morphological feature points on all coordinate axes in each preset target transformation model, respectively, to determine a matched first preset target transformation model; Based on the position adjustment instruction saved in the first preset target transformation model, the camera is adjusted from the first shooting position to the preset end shooting position saved in the first preset target transformation model.

2. The method according to claim 1, characterized in that: The method of performing similarity matching on the target position differences of the plurality of morphological feature points on all coordinate axes and on the predicted position differences of the plurality of morphological feature points on all coordinate axes in each preset target transformation model to determine a matched first preset target transformation model includes: The target position difference of each morphological feature point on each coordinate axis is calculated respectively with the predicted position difference of the corresponding morphological feature point on the corresponding coordinate axis in each preset target transformation model to obtain the target difference of the corresponding morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model; At least based on the target difference values ​​of the plurality of morphological feature points in each preset target transformation model on all coordinate axes, respectively obtain the target and value of the corresponding preset target transformation model; Determine the minimum target and value among the targets and values ​​of the plurality of preset target transformation models; When the minimum target sum value is less than a preset similarity threshold, the preset target transformation model corresponding to the minimum target sum value is determined to be a matched first preset target transformation model.

3. The method according to claim 2, characterized in that The step of obtaining the target and value of the corresponding preset target transformation model based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model comprises: The sum of the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value corresponding to the preset target transformation model.

4. The method according to claim 2, characterized in that: The multiple morphological feature points include at least one primary morphological feature point and multiple secondary morphological feature points; Correspondingly, the step of obtaining the target and value of the corresponding preset target transformation model respectively based on the target difference values ​​of the plurality of morphological feature points on all coordinate axes in each preset target transformation model includes: Calculate the product of the target difference of each primary morphological feature point on each coordinate axis in each preset target transformation model and the preset core weight value, and obtain the weighted target difference of the corresponding primary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model, and Calculate the product of the target difference value of each secondary morphological feature point on each coordinate axis in each preset target transformation model and the preset area weight value, and obtain the weighted target difference value of the corresponding secondary morphological feature point on the corresponding coordinate axis in the corresponding preset target transformation model; The sum of the weighted target difference value of at least one primary morphological feature point on all coordinate axes and the weighted target difference value of each of the multiple secondary morphological feature points on all coordinate axes in each preset target transformation model is calculated to obtain the target sum value of the corresponding preset target transformation model.

5. The method according to claim 4, characterized in that The preset core weight value is greater than the preset area weight value, and the sum of the core weight value of each of the at least one primary morphological feature points and the preset area weight values ​​of each of the plurality of secondary morphological feature points is equal to 1.

6. The method according to claim 1, characterized in that One of the preset starting camera position and the preset ending camera position saved in each of the multiple preset target transformation models is a preset central camera position, and the other saved camera position is one of multiple preset peripheral camera positions; wherein the multiple preset peripheral camera positions surround the preset central camera position.

7. The method according to claim 6, characterized in that The first camera position refers to a preset central camera position; Correspondingly, the step of obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position includes: The target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position are obtained.

8. The method according to claim 7, characterized in that Before obtaining the target feature positions of the plurality of morphological feature points in the target leaf image captured by the camera at the preset central camera position, the method further includes: Obtaining a second camera position where the camera is located; When it is determined that the second camera position does not match the preset center camera position, determining a preset zeroing transformation model from the plurality of preset transformation models with the second camera position as the preset starting camera position and the preset center camera position as the preset ending camera position; Based on the position adjustment instruction stored in the preset zeroing transformation model, the camera is adjusted from the second camera position to the preset center camera position.

9. The method according to claim 4, characterized in that The at least one primary morphological feature point includes a leaf core feature point; the multiple secondary morphological feature points include multiple leaf rectangular area feature points.

10. A device for adjusting the shooting position of a blade, characterized in that: include: A position acquisition unit, used to acquire the target feature position of each of the plurality of morphological feature points in the target leaf image captured by the camera at the first camera position; A model acquisition unit, configured to acquire a plurality of preset target transformation models from a plurality of preset transformation models by taking the first photographing position as a preset starting photographing position; A difference calculation unit is used to perform difference calculation on each coordinate axis between the target feature position of each morphological feature point and the preset reference feature position of the corresponding morphological feature point at the first camera position, so as to obtain the target position difference of the corresponding morphological feature point on the corresponding coordinate axis; A matching unit, configured to perform similarity matching on the target position differences of the plurality of morphological feature points on all coordinate axes and on the predicted position differences of the plurality of morphological feature points on all coordinate axes in each preset target transformation model, and determine a matched first preset target transformation model; An adjustment unit is used to adjust the camera from the first shooting position to a preset end shooting position saved in the first preset target transformation model based on the position adjustment instruction saved in the first preset target transformation model.

Images