Method and device for selecting X-ray exposure parameters of single trees of different tree species

Abstract

The invention discloses a method and a device for selecting X-ray exposure parameters of single trees of different tree species, and belongs to the technical field of forestry detection. Comprising the following steps: acquiring corresponding multi-frame X-ray images of a target tree under a plurality of different punching depths acquired by an image sensor under a plurality of groups of different parameter combinations; determining a target parameter combination corresponding to the same punching depth of the target tree based on imaging effects of multiple frames of X-ray images collected by the image sensor corresponding to the same punching depth under multiple groups of different parameter combinations; constructing an association relationship between the target parameter combination corresponding to each different target tree and the target thickness; and determining X-ray exposure parameters of the image sensor based on the incidence relation, the initial trunk diameter of the to-be-measured single tree and the tree species category of the to-be-measured single tree. According to the method provided by the invention, the internal structure information of the tree is accurately, clearly and efficiently collected on the premise that the complete area of the trunk is reserved to the maximum extent.

Description

Technical Field

[0001] The present application belongs to the field of forestry detection technology, and in particular relates to a method and device for selecting X-ray exposure parameters for single trees of different tree species. Background Art

[0002] With the continuous advancement of research in forestry resource monitoring, tree growth assessment, and timber quality prediction, obtaining information on the internal structure of trees has become a critical requirement in both forestry research and practical production management. Traditional testing methods often rely on destructive sampling, which not only affects the normal growth of trees but also suffers from cumbersome operations, low efficiency, and insufficient data representation. In recent years, X-ray nondestructive imaging technology has gradually gained application in timber and tree internal testing due to its advantages such as speed, intuitiveness, and high resolution.

[0003] However, when X-ray imaging methods are applied to tree detection, related technologies require multiple shots of different trees of the same tree species, and then the images with the best imaging effects are selected through subjective comparison by the human eye. This consumes a lot of energy and time, and the final exposure parameters are less accurate. In particular, its practicality in field non-destructive testing and large-scale forest censuses still needs to be improved. There is an urgent need to develop an adaptive, high-resolution and efficient tree internal imaging solution to meet the needs of modern forestry informatization and refined management. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application proposes a method and device for selecting X-ray exposure parameters for individual trees of different tree species. This method enables accurate, clear, and efficient collection of tree internal structural information while maximizing the preservation of the intact trunk area during tree research. The method has a wide range of application scenarios, high universality, and stability.

[0005] In a first aspect, the present application provides a method for selecting X-ray exposure parameters for individual trees of different tree species, the method comprising: Acquire multiple frames of X-ray images corresponding to a target tree at multiple different drilling depths, acquired by an image sensor under multiple different parameter combinations; the center of the image sensor lens and the marking point of the target tree are on the same horizontal line, and the drilling depth is obtained by drilling the target tree along the diameter direction of the marking point; Determining a target parameter combination corresponding to the same drilling depth for the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations at the same drilling depth; Establishing a correlation between target parameter combinations and target thicknesses corresponding to different target trees, wherein the target thickness is the difference between the initial trunk diameter of each target tree and the drilling depth; Based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured, the X-ray exposure parameters of the image sensor are determined to acquire an X-ray image of the single tree to be measured.

[0006] According to the method for selecting X-ray exposure parameters for single trees of different tree species of the present application, holes are punched in the target trees to obtain multiple frames of X-ray images corresponding to the target trees at multiple different punching depths, which are collected by the image sensor under multiple groups of different parameter combinations. The critical exposure parameters corresponding to each punching depth are determined based on the imaging effect of the X-ray images, and then the punching depth is converted into the trunk thickness under the same tree species category to obtain the critical exposure parameters corresponding to each trunk thickness. The operation is simple, easy to implement and low in cost. Without affecting the tree body, the sampling error can be effectively reduced, and the precision and accuracy of the determined target parameter combination can be improved, thereby effectively avoiding the problems caused by underexposure or overexposure while maintaining the imaging quality, so that in the process of tree research, the internal structure of the tree can be accurately, clearly and efficiently collected while maximizing the retention of the intact area of the trunk. It has a wide range of application scenarios, high universality and stability.

[0007] According to one embodiment of the present application, the acquisition of multiple frames of X-ray images corresponding to target trees at multiple different drilling depths, acquired by the image sensor under multiple sets of different parameter combinations, includes: Acquire an X-ray image of the target tree at the same drilling depth, acquired by the image sensor under the initial parameter combination; Adjust the parameters of the target category in the initial parameter combination along the target adjustment direction and target adjustment step size, while keeping the parameters of other categories unchanged, and reacquire the X-ray image corresponding to the target tree at the same drilling depth, acquired by the image sensor under the adjusted initial parameter combination. 3. The method for selecting X-ray exposure parameters for individual trees of different tree species according to claim 1, characterized in that acquiring multiple frames of X-ray images corresponding to the target tree at multiple different drilling depths, acquired by the image sensor under multiple different parameter combinations, comprises: Acquiring multiple frames of X-ray images corresponding to the target tree at the initial drilling depth, which are collected by the image sensor under multiple sets of different parameter combinations; The initial drilling depth is adjusted, and multiple frames of X-ray images corresponding to the target tree at the adjusted initial drilling depth are acquired by the image sensor under multiple groups of different parameter combinations.

[0008] According to one embodiment of the present application, determining the target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations at the same drilling depth includes: Performing image recognition on multiple frames of X-ray images corresponding to the same drilling depth based on an adjustment sequence; the adjustment sequence is the sequence for adjusting the parameters of the target category in the parameter combination during the image acquisition process; When it is recognized for the first time that the marking point is not displayed in the X-ray image, the parameter combination corresponding to the previous frame of the X-ray image is determined as the target parameter combination corresponding to the same drilling depth.

[0009] According to one embodiment of the present application, determining the target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations at the same drilling depth includes: Acquire multiple frames of X-ray images corresponding to multiple other trees of the same species as the target tree at multiple drilling depths and multiple sets of different parameter combinations; Determining target parameter combinations corresponding to the trees at the same target thickness based on imaging effects of multiple frames of X-ray images corresponding to the trees at the same target thickness; The target parameter combination corresponding to the target tree at the same target thickness is determined based on an average value of the target parameter combination corresponding to each of the trees at the same target thickness.

[0010] According to one embodiment of the present application, determining the target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations at the same drilling depth includes: While adjusting the parameters of the target category in the initial parameter combination along the target adjustment direction and the target adjustment step size, and maintaining the first values of the parameters of the other categories unchanged, determining, based on imaging effects of multiple frames of acquired X-ray images, the optimal values of the parameters of the target category corresponding to the first values of the parameters of the other categories, and determining the first values corresponding to the parameters of the other categories and the optimal values corresponding to the parameters of the target category as a set of target parameter combinations; Adjust the values of the parameters of the first category among the parameters of other categories to the second values, keep the values of the parameters of the remaining categories among the parameters of other categories unchanged at the first values, adjust the parameters of the target category along the target adjustment direction and the target adjustment step, and determine, based on the imaging effect of the collected multiple frames of X-ray images, the optimal values of the parameters of the target category corresponding to the first values when the parameters of the first category are the second values and the values of the parameters of the remaining categories are the first values, and determine the optimal values corresponding to the parameters of the target category when the parameters of the first category are the second values, the values of the parameters of the remaining categories are the first values, and the parameters of the target category as a set of target parameter combinations.

[0011] According to one embodiment of the present application, the step of establishing an association between target parameter combinations and target thicknesses corresponding to different target trees includes: Taking the tree species categories and the target thickness corresponding to the plurality of target trees as samples and the target parameter combination as sample labels, a training sample is constructed; Input a plurality of the training samples into the network model, train the network model with the output prediction parameter combination of the network model as a target, and learn the association relationship.

[0012] According to an embodiment of the present application, the parameter combination includes a tube voltage parameter, a tube current parameter, and an exposure time parameter, and the parameters of each category are independent of each other.

[0013] According to one embodiment of the present application, determining the X-ray exposure parameters of the image sensor to capture the X-ray image of the tree to be measured based on the association relationship, the initial trunk diameter of the tree to be measured, and the tree species category of the tree to be measured includes: Determining a first width based on the bark thickness of the single tree to be tested; Determining a prediction parameter combination corresponding to the single tree to be tested based on the first width, the tree species category of the single tree to be tested, and an association between the target parameter combination and the target thickness; The X-ray exposure parameters of the image sensor are adjusted based on the predicted parameter combination to acquire an X-ray image of the single tree to be tested.

[0014] In a second aspect, the present application provides a device for selecting X-ray exposure parameters for single trees of different tree species, the device comprising: A first processing module is configured to obtain multiple frames of X-ray images corresponding to a target tree at multiple different drilling depths, acquired by an image sensor under multiple different parameter combinations; the center of the image sensor lens and the marking point of the target tree are co-horizontally aligned, and the drilling depths are obtained by drilling the target tree along the diameter of the marking point; a second processing module configured to determine a target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations corresponding to the same drilling depth; A third processing module is configured to establish a correlation between target parameter combinations corresponding to different target trees and target thicknesses, wherein the target thickness is the difference between the initial trunk diameter of each target tree and the drilling depth; The fourth processing module is used to determine the X-ray exposure parameters of the image sensor to acquire the X-ray image of the single tree to be measured based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured.

[0015] According to the device for selecting X-ray exposure parameters for single trees of different tree species of the present application, holes are punched in target trees to obtain multiple frames of X-ray images corresponding to target trees at multiple different punching depths, which are collected by the image sensor under multiple groups of different parameter combinations. The critical exposure parameters corresponding to each punching depth are determined based on the imaging effect of the X-ray image, and then the punching depth is converted into the trunk thickness under the same tree species category to obtain the critical exposure parameters corresponding to each trunk thickness. The operation is simple, easy to implement and low in cost. Without affecting the tree body, the sampling error can be effectively reduced, and the precision and accuracy of the determined target parameter combination can be improved, thereby effectively avoiding the problems caused by underexposure or overexposure while maintaining the imaging quality, so that in the process of tree research, the internal structure of the tree can be accurately, clearly and efficiently collected while maximizing the retention of the intact area of the trunk. It has a wide range of application scenarios, high universality and stability.

[0016] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for selecting X-ray exposure parameters for single trees of different tree species as described in the first aspect above is implemented.

[0017] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for selecting X-ray exposure parameters for single trees of different tree species as described in the first aspect above.

[0018] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method for selecting X-ray exposure parameters for single trees of different tree species as described in the first aspect above.

[0019] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects: By drilling holes in target trees, multiple frames of X-ray images corresponding to target trees at multiple different drilling depths, which are collected by image sensors under multiple groups of different parameter combinations, are obtained. The critical exposure parameters corresponding to each drilling depth are determined based on the imaging effect of the X-ray images. The drilling depths are then converted into trunk thicknesses under the same tree species category to obtain the critical exposure parameters corresponding to each trunk thickness. The operation is simple, easy to implement, and low in cost. Without affecting the tree body, the sampling error can be effectively reduced, and the precision and accuracy of the determined target parameter combination can be improved, thereby effectively avoiding problems caused by underexposure or overexposure while maintaining imaging quality. In the process of tree research, the internal structure of the tree can be accurately, clearly, and efficiently collected while maximizing the preservation of the intact area of the trunk. The method has a wide range of application scenarios, high universality, and stability.

[0020] Furthermore, by setting each exposure parameter as a parameter that can be adjusted independently, the three variables of tube voltage, tube current and exposure time change simultaneously, the data dimension is higher and the relationship between variables is more complex, which can further improve the precision and accuracy of the critical exposure parameters determined subsequently.

[0021] Furthermore, the use of deep learning algorithms to learn the correlation between target parameter combinations and target thickness can learn more complex relationships between exposure parameters and tree characteristics in multiple dimensions, thereby improving the precision and accuracy of exposure parameters calculated based on tree species and trunk thickness, further improving imaging effects, and the operation is simple and convenient, with high computational efficiency.

[0022] Furthermore, by replacing the trunk thickness with the first width of the bark area thickness removed to calculate the prediction parameter combination, the influence of the bark thickness on the imaging result can be taken into account, so that the prediction parameter combination can lose the bark area features in the image and only retain the xylem area features, further improving the imaging effect. Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 1 is a flow chart of a method for selecting X-ray exposure parameters for single trees of different tree species provided in an embodiment of the present application; Figure 2 This is one of the principle schematic diagrams of the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiments of the present application; Figure 3This is the second schematic diagram of the principle of the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application; Figure 4 This is the third schematic diagram of the principle of the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiments of the present application; Figure 5 This is the fourth schematic diagram of the principle of the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application; Figure 6 This is a schematic diagram of the results of the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application. Figure 7 2 is a schematic diagram of the structure of a device for selecting X-ray exposure parameters for single trees of different tree species provided in an embodiment of the present application; Figure 8 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0025] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0026] Below, in combination with the accompanying drawings, the method for selecting X-ray exposure parameters for single trees of different tree species, the device for selecting X-ray exposure parameters for single trees of different tree species, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0027] The method for selecting X-ray exposure parameters for individual trees of different tree species can be applied to a terminal, and can be specifically executed by hardware or software in the terminal.

[0028] The embodiment of the present application provides a method for selecting X-ray exposure parameters for single trees of different tree species. The execution subject of the method for selecting X-ray exposure parameters for single trees of different tree species can be an electronic device or a functional module or functional entity in the electronic device that can implement the method for selecting X-ray exposure parameters for single trees of different tree species. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras and wearable devices, etc. The method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application is explained below using electronic devices as the execution subject as an example.

[0029] like Figure 1 As shown, the method for selecting X-ray exposure parameters for single trees of different tree species includes: step 110, step 120, step 130 and step 140.

[0030] Step 110: Acquire multiple frames of X-ray images corresponding to the target tree at multiple different drilling depths, collected by the image sensor under multiple sets of different parameter combinations; In this step, the target tree may be any tree of any tree species. In some embodiments, a tree with a larger trunk diameter may be selected from any tree species.

[0031] The marking point is used to indicate the location of the drilling point later, and can be marked with a marker in the direction of the trunk diameter at breast height.

[0032] The center of the image sensor lens is on the same horizontal line as the marking point of the target tree, and the drilling depth is obtained by drilling the target tree along the diameter direction where the marking point is located.

[0033] The drilling depth can be between 0 and the diameter of the target tree. A drilling depth of 0 means no drilling is performed, which can be used as the initial state for image acquisition, such as Figure 5 shown.

[0034] Continue to refer Figure 5 In some embodiments, the image sensor may be a digital radiography (DR) device, which includes an X-ray generator and a detector. During the shooting process, the X-ray generator, the trunk diameter at breast height, and the detector should be in a straight line. The X-ray generator is set in front of the trunk of the target tree, and the detector is close to the other side of the trunk.

[0035] The shooting distance is the distance between the X-ray generator and the detector. The shooting distance can be customized by the user. You only need to keep the shooting distance corresponding to the same target tree the same.

[0036] In some embodiments, the shooting distance can be set to 1.5m or 2m, etc.

[0037] A parameter combination includes multiple exposure parameters.

[0038] In the actual implementation process, continue to refer to Figure 5 , we can first define the target tree and measure the diameter of its trunk at a certain height, such as the initial trunk diameter D at 1.3m from the ground, and mark a mark point at this height; then set up the portable DR device at 1.3m from the ground, with the center point of the lens facing the direction of the breast diameter, which is also the subsequent drilling direction, and shoot the target tree under a certain parameter combination to obtain a frame of X-ray image; then adjust the parameter value in the parameter combination, re-shoot the target tree to obtain a frame of X-ray image, and so on, until all parameter combinations are traversed and multiple frames of X-ray images corresponding to the current drilling depth are obtained.

[0039] Then, the drilling depth is changed, and the above steps are repeated to obtain multiple frames of X-ray images corresponding to the next drilling depth, and so on, until multiple frames of X-ray images corresponding to multiple different drilling depths are obtained.

[0040] Among them, the imaging effect of the X-ray image is affected by the exposure parameters of the image sensor. The obtained X-ray image may include the texture features of the tree trunk or may not include the texture features. The width of the included texture features may also be different. The X-ray images obtained under different exposure parameters are as follows: Figure 4 shown.

[0041] It is understandable that in the case of underexposure, although the image area is complete, it may cause image blur and loss of details, thereby affecting the clarity of the X-ray image and failing to meet the needs of image differentiation; and in the case of overexposure, although it has higher clarity, it may cause the thinner edge parts of the tree to be missing in the image, that is, it may cause the loss of part of the target area, thereby affecting the integrity of the X-ray image.

[0042] Under optimal exposure conditions, the acquired X-ray images have high clarity and high detail integrity, which can be approximately considered to meet the requirements of image differentiation.

[0043] In some embodiments, the X-ray image may also include features corresponding to the marker points.

[0044] In some embodiments, the parameter combination may include: tube voltage parameter (unit: kilovolts), tube current parameter (unit: milliamperes), and exposure time parameter (unit: seconds). Parameters of each category are independent of each other and can be adjusted individually.

[0045] According to the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application, by setting each exposure parameter as a parameter that can be adjusted independently, the situation involving the simultaneous changes of three variables: tube voltage, tube current and exposure time, the data dimension is higher and the relationship between variables is more complex, which can further improve the precision and accuracy of the critical exposure parameters determined subsequently.

[0046] Step 120: Determine a target parameter combination corresponding to the same drilling depth for the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations at the same drilling depth; In this step, the effectiveness can be judged based on the completeness of the target tree in the X-ray image and whether the marking points can be identified. It is understandable that in the case of underexposure or overexposure, the marking points cannot be displayed in the X-ray image.

[0047] During the actual implementation process, the X-ray image can be identified based on the image recognition algorithm to determine the imaging effect.

[0048] The target parameter combination is a critical exposure parameter. When the image sensor acquires images based on the target parameter combination, it can minimize exposure loss and improve the integrity of the X-ray image while maintaining image clarity. When the target parameter combination is exceeded, overexposure is considered to have occurred. The target parameter combination is one or more exposure parameter combinations that can maintain a balance between image clarity and image integrity.

[0049] In some embodiments, the target parameters corresponding to the same target number and the same drilling depth may be one or more.

[0050] The determination of the critical exposure parameters corresponding to each drilling depth can be achieved by using the method of steps 110 to 120, which will not be described in detail in this application.

[0051] Step 130: Constructing a correlation between target parameter combinations and target thicknesses corresponding to different target trees, where the target thickness is the difference between the initial trunk diameter and the drilling depth of each target tree; In this step, the target thickness is the length of the remaining hole after the trunk is drilled, that is, the target thickness is the difference between the initial trunk diameter and the drilling depth, such as Figure 2 shown.

[0052] It can be understood that when the target tree and the initial trunk thickness of the target tree remain unchanged, the drilling depth changes and the target thickness changes accordingly. The deeper the drilling depth, the thinner the corresponding target thickness. In the actual implementation process, the target thickness can be approximately regarded as the trunk thickness corresponding to the collected X-ray image. The X-ray images corresponding to different drilling depths can be approximately regarded as X-ray images of the same tree species as the target tree but with different trunk thicknesses.

[0053] The correlation relationship is used to characterize the correlation between tree species category (i.e., tree category), trunk diameter, and critical exposure parameter combination of the image sensor. Figure 6 An example of an association relationship is shown.

[0054] The association relationship is used for the image sensor to collect X-ray images of trees of the same category and target thickness as the target tree.

[0055] In the actual implementation process, for any tree species category, a single tree of the tree species category is selected as the target tree, and the method of steps 110 to 120 is executed to obtain the critical exposure parameters corresponding to the image sensor of the target tree at different drilling depths.

[0056] The drilling depth is converted, and the difference between the initial trunk diameter of the target tree and each drilling depth is approximated as the trunk thickness corresponding to different trees of the same tree species category as the target tree. This can obtain the critical exposure parameters of the image sensor corresponding to trees of the same tree species category with different trunk thicknesses.

[0057] The above method is used for each tree species category, so that the critical exposure parameters of the image sensor corresponding to trees with different trunk thicknesses in each tree species category can be obtained.

[0058] In some embodiments, a linear fitting algorithm may be used to fit the obtained tree species, different trunk thicknesses, and critical exposure parameters corresponding to the tree species and trunk thicknesses to obtain a correlation between the three.

[0059] Step 140 : Based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured, determine the X-ray exposure parameters of the image sensor to capture an X-ray image of the single tree to be measured.

[0060] In this step, the single tree to be tested can be any tree for which X-ray image acquisition is required during research or application.

[0061] It is understandable that in actual application, Figure 6As shown, a plurality of target trees of different categories can be pre-selected, and according to the method of steps 110 to 130, the target parameter combinations corresponding to the target trees at different drilling depths are respectively obtained, so as to fit the correlation between the target parameter combinations of the tree species, target thickness, and the tree species and target thickness, which can obtain a clear and complete X-ray image; in the subsequent application process, it is only necessary to substitute the initial trunk diameter of the single tree to be measured and the tree species category of the single tree to be measured into the fitted correlation relationship to obtain the target parameter combination required for collecting a complete and clear X-ray image of the single tree to be measured, and then adjust the parameters of the image sensor to the determined target parameter combination, collect the image of the single tree to be measured, and obtain an X-ray image. The X-ray image can relatively completely retain the contour features of the single tree to be measured, and can clearly present the structural details, with a high imaging effect.

[0062] In some embodiments, multiple sets of target parameter combinations may be obtained based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured.

[0063] In some embodiments, a target parameter combination may be selected from a plurality of target parameter combinations according to a first input from a user as an X-ray exposure parameter of the image sensor.

[0064] In some embodiments, based on the performance parameters of the image sensor, target parameter combinations that match the performance parameters can be screened and used as the X-ray exposure parameters of the image sensor. This can be flexibly selected according to actual needs.

[0065] During the research and development process, the inventors discovered that in the related art, there is also a method of determining the critical parameters by continuously shooting X-ray images with different exposure parameter combinations at the same angle, combining the conversion relationship between the pixel width of the exposure loss area and the physical width of the tree, and using a vernier caliper to measure the trunk width Wr corresponding to the position deep into the trunk Lr, thereby obtaining the critical overexposure depth under the exposure parameters. However, this method requires conversion between pixel values and physical values, and requires multiple measurements of the thickness of the trunk. The measurement error is large, which affects the accuracy of the final determined exposure parameters. The steps are relatively complicated and the measurement efficiency is low.

[0066] In the present application, holes are punched in target trees to obtain multiple frames of X-ray images corresponding to target trees at multiple different drilling depths, which are collected by an image sensor under multiple sets of different parameter combinations. The critical exposure parameters corresponding to each drilling depth are determined based on the imaging effect of the X-ray images, and then the drilling depths are converted into the trunk thickness of the same tree species category to obtain the critical exposure parameters corresponding to each trunk thickness. The accurate target parameter combination can be obtained without calibration and conversion of pixel coordinates and three-dimensional space coordinates, which simplifies the operation steps, is simple and easy to implement, and has higher processing efficiency.

[0067] In addition, for each tree species category, only one tree needs to be selected to measure its initial trunk diameter, without the need to collect the thickness of different trunks multiple times, which effectively reduces sampling errors and further improves the precision and accuracy of the determined target parameter combination; it is suitable for data collection and exposure parameter determination in large-scale, multi-tree species scenarios, reducing manpower and time costs, improving processing efficiency and detection efficiency, and is suitable for field non-destructive testing and large-scale forest censuses, with high practicality.

[0068] The holes drilled by the electric drill are small in diameter and have negligible impact on the tree. After completing the drilling and photographing of the target tree, the holes can be filled to protect the tree. This allows the target parameter combination to be determined efficiently, conveniently and at low cost without affecting the tree, and the determined target parameter combination has high precision and accuracy.

[0069] On this basis, according to the constructed association relationship, in the subsequent application process, the exposure parameters can be automatically obtained and adjusted based on the association relationship according to the characteristics of different tree species and their trunk diameters, so as to achieve efficient, clear and accurate image acquisition of the internal structure of the trunk, and intelligently obtain the best X-ray image for the single tree to be tested. It can comprehensively consider that different tree species have different wood structure density and moisture content, and their absorption capacity of X-rays varies significantly; and the trunk diameter varies widely, which directly affects the imaging penetration depth and image quality and other factors on the imaging effect. It has high accuracy and helps to improve the imaging effect. On the premise of preserving the complete and clear image area of the trunk as much as possible, it has both adaptability and imaging stability, providing reliable non-destructive testing means and data support for forestry resource surveys, tree health monitoring and related scientific research, and can meet the needs of modern forestry informatization and refined management.

[0070] According to the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application, holes are punched in the target trees to obtain multiple frames of X-ray images corresponding to the target trees at multiple different drilling depths, which are collected by the image sensor under multiple groups of different parameter combinations. The critical exposure parameters corresponding to each drilling depth are determined based on the imaging effect of the X-ray images, and then the drilling depth is converted into the trunk thickness under the same tree species category to obtain the critical exposure parameters corresponding to each trunk thickness. The operation is simple, easy to implement and low in cost. Without affecting the tree body, the sampling error can be effectively reduced, and the precision and accuracy of the determined target parameter combination can be improved, thereby effectively avoiding the problems caused by underexposure or overexposure while maintaining the imaging quality, so that in the process of tree research, the internal structure of the tree can be accurately, clearly and efficiently collected while maximizing the preservation of the intact area of the trunk. The method has a wide range of application scenarios, high universality, stability and practicality, and is suitable for field non-destructive testing and large-scale forest surveys.

[0071] In some embodiments, step 110 may include: Obtain the X-ray image of the target tree at the same drilling depth, which is collected by the image sensor under the initial parameter combination; The parameters of the target category in the initial parameter combination are adjusted along the target adjustment direction and the target adjustment step size, while the parameters of other categories remain unchanged. The X-ray images corresponding to the target trees at the same drilling depth, which are collected by the image sensor under the adjusted initial parameter combination, are reacquired.

[0072] In this embodiment, the target adjustment direction is an adjustment direction corresponding to the magnitude of the parameter, such as increasing or decreasing in sequence.

[0073] In some embodiments, the target adjustment direction can be determined based on the initial trunk diameter of the target tree. When the initial trunk diameter is larger than the preset diameter, the target adjustment direction is set to decrease successively; when the initial trunk diameter is less than or equal to the preset diameter, the target adjustment direction is set to increase successively.

[0074] The target adjustment step is the difference between the numerical value of the parameter of the target category and the numerical value of the parameter before adjustment. It can be customized by the user. The target adjustment step can be a fixed step or a variable step, which is not limited in this application.

[0075] The initial parameter combination includes the initial values of multiple types of parameters. The size of the initial value is set according to the target adjustment direction. For example, if the target adjustment direction is decreasing, the initial value can be set to a larger value; if the target adjustment direction is increasing, the initial value can be set to a smaller value.

[0076] The target category can be any of the included parameter categories.

[0077] Taking the initial parameter combination including tube voltage parameters, tube current parameters and exposure time parameters as an example, first fix the two types of parameters, change the third type of parameters to make it gradually increase, and at each value corresponding to the third type of parameters, use the image sensor to collect X-ray images until the preset conditions are met and then stop collecting.

[0078] Among them, the preset conditions can be based on user customization, such as setting a maximum number of adjustments, and the preset conditions are considered to be met when the number of adjustments reaches the maximum number of adjustments; or the target range corresponding to each parameter can be set, and the preset conditions are considered to be met when the parameter value after adjustment exceeds the target range.

[0079] In some embodiments, step 110 may include: Acquire multiple frames of X-ray images corresponding to the target tree at the initial drilling depth, which are collected by the image sensor under multiple sets of different parameter combinations; The initial drilling depth is adjusted, and multiple frames of X-ray images corresponding to the target tree at the adjusted initial drilling depth are acquired by the image sensor under multiple sets of different parameter combinations.

[0080] In this embodiment, the initial punching depth can be customized based on the user, such as setting the initial punching depth to 0, that is, adjusting the exposure parameters of the image sensor without punching, and obtaining multiple frames of X-ray images under multiple sets of different parameter combinations. The specific method of adjusting the parameter combination has been described in the above embodiment and will not be repeated here.

[0081] After collecting all X-ray images at the initial drilling depth, adjust the initial drilling depth. For example, starting from the marked point, drill a certain depth of the trunk of the target tree along the diameter direction of the marked point, keep the position of the image sensor fixed, and shoot the target tree at the current drilling depth in sequence according to each set of parameter combinations at the initial drilling depth, and obtain multiple frames of X-ray images corresponding to multiple sets of different parameter combinations at the current drilling depth.

[0082] In some embodiments, adjusting the initial drilling depth may include drilling holes in the target tree along a diameter direction where the marking point is located based on the first step length.

[0083] In this embodiment, each punch should maintain the same orientation.

[0084] The first step length is the distance advanced by the current drilling depth relative to the previous drilling depth. It can be customized based on the user and can be set to a smaller length, such as 0.1 times or 0.2 times the initial trunk diameter of the target tree, etc. This application is not limited here.

[0085] In some embodiments, step 120 may include: Image recognition is performed on multiple frames of X-ray images corresponding to the same drilling depth based on an adjustment sequence; the adjustment sequence is the order in which parameters of the target category in the parameter combination are adjusted during the image acquisition process; When it is recognized for the first time that the marking point in the X-ray image is not displayed, the parameter combination corresponding to the previous frame of the X-ray image is determined as the target parameter combination corresponding to the same drilling depth.

[0086] In this embodiment, the adjustment order is the order of adjusting the parameters of the target category in the parameter combination, such as increasing in sequence.

[0087] Continuing with the example of a parameter combination including tube voltage, tube current, and exposure time, in actual implementation, two exposure parameters are first fixed, such as the tube current and exposure time. The third exposure parameter is then changed, so that the tube voltage is gradually increased from 0 with a target adjustment step size. At each tube voltage, an X-ray image captured by the image sensor is acquired, and a marker point in the X-ray image is identified using an image recognition algorithm. If the marker point in the X-ray image is detected to have disappeared, the previous parameter combination can be determined as the target parameter combination corresponding to the drilling depth, i.e., the critical exposure parameter combination for the target thickness corresponding to the drilling depth.

[0088] By gradually deepening the hole depth according to the depth gradient of the first step and repeating the above steps, the target parameter combination corresponding to each drilling depth can be obtained, thereby obtaining the critical exposure parameters corresponding to different trunk thicknesses.

[0089] In some embodiments, step 120 may include: While adjusting the parameters of the target category in the initial parameter combination along the target adjustment direction and the target adjustment step size, and maintaining the first values of the parameters of the other categories unchanged, determining, based on imaging effects of multiple frames of acquired X-ray images, the optimal values of the parameters of the target category corresponding to the first values of the parameters of the other categories, and determining the first values corresponding to the parameters of the other categories and the optimal values corresponding to the parameters of the target category as a set of target parameter combinations; Adjust the values of the parameters of the first category among the parameters of other categories to the second values, keep the values of the parameters of the remaining categories among the parameters of other categories unchanged at the first values, adjust the parameters of the target category along the target adjustment direction and the target adjustment step, and determine, based on the imaging effect of the collected multi-frame X-ray images, the optimal values of the parameters of the target category corresponding to the second values of the parameters of the first category and the first values of the parameters of the remaining categories, and determine the optimal values corresponding to the parameters of the target category with the second values of the parameters of the first category, the first values of the parameters of the remaining categories, and the first values as a set of target parameter combinations.

[0090] In this embodiment, continuing to take the initial parameter combination including the tube voltage parameter, the tube current parameter, and the exposure time parameter as an example, the exposure time parameter can be first determined as a parameter of the target category, and the tube voltage parameter and the tube current parameter can be determined as parameters of other categories. During the adjustment process, the tube voltage parameter and the tube current parameter are first set to fixed values, such as setting the tube voltage parameter to a1 and the tube current parameter to b1. Then, the exposure time parameter is adjusted along the target adjustment direction and target adjustment step size, and multiple parameter combinations are obtained: (a1, b1, c1), (a1, b1, c2), ..., (a1, b1, cn), where c1, c2 ..., cn are the values of the exposure time parameters, and n is a positive integer corresponding to the number of adjustments.

[0091] Obtain the X-ray images collected by the image sensor under the above parameter combinations, and select a set of target parameter combinations based on the imaging effect, such as (a1, b1, c1). This target parameter combination is the critical exposure parameter corresponding to the exposure time parameter when the tube voltage parameter is a1 and the tube current parameter is set to b1.

[0092] Keeping the drilling depth unchanged, the tube voltage parameter is determined as the parameter of the first category, and the tube current parameter is the parameter of the remaining categories. Based on the previous round, the values of the parameters of the first category are adjusted and fixed. For example, the tube voltage parameter is adjusted from a1 to a2, and the value of the tube current parameter is kept unchanged from the previous round. Then, the exposure time parameter is adjusted along the target adjustment direction and target adjustment step size, and multiple parameter combinations are obtained: (a2, b1, c1), (a2, b1, c2), ..., (a2, b1, cn).

[0093] Obtain the X-ray images collected by the image sensor under the above parameter combinations, and select a set of target parameter combinations based on the imaging effect, such as (a2, b1, c3). This target parameter combination is the critical exposure parameter corresponding to the exposure time parameter when the tube voltage parameter is a2 and the tube current parameter is set to b1.

[0094] Continue to adjust the tube voltage parameter and repeat the above process until the tube voltage parameter can no longer be adjusted, thereby obtaining multiple sets of target parameter combinations corresponding to the tube current parameter b1.

[0095] Then adjust the values of the parameters of the remaining categories and fix them. For example, adjust the tube current parameter from b1 to b2. Repeat the above steps to obtain multiple sets of target parameter combinations corresponding to the tube current parameter b2.

[0096] This process is repeated until the tube current parameter cannot be adjusted any further, thereby obtaining multiple target parameter combinations corresponding to the same target tree at the same drilling depth.

[0097] Then, the drilling depth is changed and the above steps are repeated, so that multiple sets of target parameter combinations corresponding to the same target tree at multiple drilling depths can be obtained, wherein each drilling depth corresponds to at least one set of target parameter combinations. In some embodiments, step 120 may include: Acquire multiple X-ray images of other trees of the same species as the target tree at multiple drilling depths and multiple sets of different parameter combinations; Based on the imaging effects of multiple frames of X-ray images corresponding to each tree at the same target thickness, the target parameter combination corresponding to each tree at the same target thickness is determined; Based on the average value of the target parameter combination corresponding to each tree at the same target thickness, the target parameter combination corresponding to the target tree at the same target thickness is determined.

[0098] In this embodiment, in each tree species category, multiple trees can be selected for testing to obtain critical exposure parameters under different trunk thicknesses (i.e., target thicknesses), so that the trunk thickness range can cover the same tree species category in the entire forest stand.

[0099] At the same time, the critical exposure parameters obtained under the same tree species and the same trunk thickness are added and averaged, and the average value is used as the critical overexposure parameter corresponding to each tree species at the corresponding trunk thickness, providing the exposure dose characteristics under tree species and different part thickness conditions.

[0100] According to the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application, the target parameter combination is calculated by taking the average of multiple samplings, thereby further improving the accuracy of the determined critical exposure parameters.

[0101] In some embodiments, step 130 may include: The tree species and target thicknesses corresponding to multiple target trees are used as samples, and the target parameter combinations are used as sample labels to construct training samples. Multiple training samples are input into the network model, and the network model is trained with the network model output prediction parameter combination as the goal to learn the association relationship.

[0102] In this embodiment, the network model may be a deep learning model or a neural network model, such as a CNN model or a Transformer model, etc., which is not limited in this application.

[0103] During training, continue to refer to Figure 6 The input data of the network model include tree species category (S), target thickness (T), tube voltage (TV), tube current (TC) and exposure time (ET), and the output data is the critical exposure parameter combination corresponding to the predicted tree species category and target thickness.

[0104] By training the network model, it learns the complex relationship between different exposure parameters and tree characteristics, and then provides the most suitable exposure parameter combination (TV, TC, ET) under the conditions of tree species and target thickness (T). In subsequent applications, it is only necessary to input the tree species category and the trunk thickness corresponding to the tree species to be tested (such as trunk diameter) to obtain the critical exposure parameter combination predicted by the network model.

[0105] During the actual implementation process, the target parameter combinations corresponding to multiple trees under multiple different tree species categories at different target thicknesses can be obtained through steps 110 to 120, and these data can be paired to obtain multiple training samples. The multiple training samples are divided into a training set, a validation set, and a test set in a ratio of 7:1:2 or 8:1:1. The network model is trained with the training set, and the network model is validated and tested with the validation set and the test set until the difference between the predicted parameter combination predicted by the network model and the input target parameter combination is not less than the target threshold, such as not less than 85% or 90%.

[0106] According to the method for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application, a deep learning algorithm is used to learn the correlation between the target parameter combination and the target thickness. It is capable of learning more complex relationships between exposure parameters and tree characteristics in multiple different dimensions, thereby improving the precision and accuracy of the exposure parameters calculated based on the tree species category and trunk thickness, further improving the imaging effect, and the operation is simple and convenient, and the calculation efficiency is high.

[0107] In some embodiments, step 140 may include: determining a first width based on the bark thickness of the single tree to be measured; Determining a prediction parameter combination corresponding to the single tree to be tested based on the first width, the tree species category of the single tree to be tested, and the correlation between the target parameter combination and the target thickness; Based on the predicted parameter combination, the X-ray exposure parameters of the image sensor are adjusted to acquire an X-ray image of the single tree to be tested.

[0108] In this embodiment, Figure 3 As shown, the trunk includes a bark region and a xylem region. In the actual shooting process, the main purpose is to obtain an X-ray image of the xylem region.

[0109] The first width is the distance between the intersection of the outer tangent line of the xylem area and the outer periphery of the trunk after removing the bark thickness L of the bark area from the trunk diameter, such as Figure 3 WL in the middle can be approximately considered as the thickness of the xylem region.

[0110] The predicted parameter combination calculated based on the correlation between the first width, the tree species category of the single tree to be tested, and the target parameter combination and the target thickness can be approximately used as the optimal exposure parameter combination under the tree species category and trunk thickness.

[0111] The prediction parameter combination may be one or more combinations, and any one of them may be selected as the optimal exposure parameter according to actual conditions.

[0112] Taking the network model as an example, after the network model training is completed, the tree species category (S) and the first width (WL) corresponding to the bark thickness are passed as input to the network model M. The output of the network model M is the corresponding optimal exposure parameter combination (TV, TC, ET).

[0113] It's understandable that the thicker the tree, the thicker the bark. However, the bark isn't the target for inspection and can be removed. Generally, a clear image can be captured after the exposure dose is adjusted to sufficiently remove the bark area. By replacing the trunk thickness with the first width to calculate the prediction parameter combination, the effect of bark thickness on X-ray imaging quality can be taken into account. The bark area is removed from the image, reducing irrelevant features in the image. The inventors have verified through multiple experiments that X-ray images captured after the exposure dose is adjusted to sufficiently remove the bark area are clear and complete, thereby further improving the imaging quality of the captured X-ray images.

[0114] During the research and development process, the inventors discovered that in the relevant technology, there is also a method that uses the tree width at a depth of 5% and 1% of the trunk diameter as the upper and lower limits of the optimal X-ray exposure depth, which correspond to the upper and lower limits of the X-ray exposure dose respectively. However, this method is not universal and affects accuracy.

[0115] In this application, by losing the bark area in the image (due to certain density differences between the phloem and xylem, the lost area may be slightly larger than the bark area, but this loss is acceptable), the degradation of imaging quality can be effectively avoided; in addition, by predicting the critical parameter combination based on the tree species category and the width of the xylem area, the optimal exposure parameter value that can reduce the influence of the bark area can be adaptively predicted based on the bark thickness corresponding to different trees, thereby further improving the accuracy of the obtained parameter combination, thereby improving the imaging effect, and having universal applicability.

[0116] According to the method for selecting X-ray exposure parameters for single trees of different tree species provided in an embodiment of the present application, the prediction parameter combination is calculated by replacing the trunk thickness with the first width after removing the thickness of the bark area. This can take into account the influence of the bark thickness on the imaging results, so that the prediction parameter combination can lose the bark area features in the image and only retain the xylem area features, thereby further improving the imaging effect.

[0117] The method for selecting X-ray exposure parameters for individual trees of different tree species provided in the embodiments of the present application can be executed by a device for selecting X-ray exposure parameters for individual trees of different tree species. In the embodiments of the present application, the device for selecting X-ray exposure parameters for individual trees of different tree species performing the method for selecting X-ray exposure parameters for individual trees of different tree species is used as an example to illustrate the device for selecting X-ray exposure parameters for individual trees of different tree species provided in the embodiments of the present application.

[0118] The embodiment of the present application also provides a device for selecting X-ray exposure parameters for single trees of different tree species.

[0119] like Figure 7 As shown, the device for selecting X-ray exposure parameters for single trees of different tree species includes: a first processing module 710 , a second processing module 720 , a third processing module 730 and a fourth processing module 740 .

[0120] The first processing module 710 is configured to obtain multiple frames of X-ray images corresponding to a target tree at multiple different drilling depths, acquired by an image sensor under multiple different parameter combinations; the center of the image sensor lens and the target tree's marking point are co-level, and the drilling depth is obtained by drilling the target tree along the diameter of the marking point; The second processing module 720 is configured to determine a target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations corresponding to the same drilling depth; The third processing module 730 is used to establish a correlation between the target parameter combination corresponding to each target tree and the target thickness, where the target thickness is the difference between the initial trunk diameter of each target tree and the drilling depth; The fourth processing module 740 is configured to determine X-ray exposure parameters of the image sensor to acquire an X-ray image of the tree to be measured based on the association relationship, the initial trunk diameter of the tree to be measured, and the tree species of the tree to be measured.

[0121] According to the device for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application, a target tree is drilled to obtain multiple frames of X-ray images corresponding to the target tree at multiple different drilling depths, which are collected by the image sensor under multiple groups of different parameter combinations. The critical exposure parameters corresponding to each drilling depth are determined based on the imaging effect of the X-ray image, and then the drilling depth is converted into the trunk thickness under the same tree species category to obtain the critical exposure parameters corresponding to each trunk thickness. The operation is simple, easy to implement and low in cost. Without affecting the tree body, the sampling error can be effectively reduced, and the precision and accuracy of the determined target parameter combination can be improved, thereby effectively avoiding the problems caused by underexposure or overexposure while maintaining the imaging quality, so that in the process of tree research, the internal structure of the tree can be accurately, clearly and efficiently collected while maximizing the retention of the intact area of the trunk. It has a wide range of application scenarios, high universality and stability.

[0122] In some embodiments, the first processing module 710 may also be used to: Obtain the X-ray image of the target tree at the same drilling depth, which is collected by the image sensor under the initial parameter combination; The parameters of the target category in the initial parameter combination are adjusted along the target adjustment direction and the target adjustment step size, while the parameters of other categories remain unchanged. The X-ray images corresponding to the target trees at the same drilling depth, which are collected by the image sensor under the adjusted initial parameter combination, are reacquired.

[0123] In some embodiments, the first processing module 710 may also be used to: Acquire multiple frames of X-ray images corresponding to the target tree at the initial drilling depth, which are collected by the image sensor under multiple sets of different parameter combinations; The initial drilling depth is adjusted, and multiple frames of X-ray images corresponding to the target tree at the adjusted initial drilling depth are acquired by the image sensor under multiple sets of different parameter combinations.

[0124] In some embodiments, the second processing module 720 may also be used to: Image recognition is performed on multiple frames of X-ray images corresponding to the same drilling depth based on an adjustment sequence; the adjustment sequence is the order in which parameters of the target category in the parameter combination are adjusted during the image acquisition process; When it is recognized for the first time that the marking point in the X-ray image is not displayed, the parameter combination corresponding to the previous frame of the X-ray image is determined as the target parameter combination corresponding to the same drilling depth.

[0125] In some embodiments, the second processing module 720 may also be used to: While adjusting the parameters of the target category in the initial parameter combination along the target adjustment direction and the target adjustment step size, and maintaining the first values of the parameters of the other categories unchanged, determining, based on imaging effects of multiple frames of acquired X-ray images, the optimal values of the parameters of the target category corresponding to the first values of the parameters of the other categories, and determining the first values corresponding to the parameters of the other categories and the optimal values corresponding to the parameters of the target category as a set of target parameter combinations; Adjust the values of the parameters of the first category among the parameters of other categories to the second values, keep the values of the parameters of the remaining categories among the parameters of other categories unchanged at the first values, adjust the parameters of the target category along the target adjustment direction and the target adjustment step, and determine, based on the imaging effect of the collected multi-frame X-ray images, the optimal values of the parameters of the target category corresponding to the second values of the parameters of the first category and the first values of the parameters of the remaining categories, and determine the optimal values corresponding to the parameters of the target category with the second values of the parameters of the first category, the first values of the parameters of the remaining categories, and the first values as a set of target parameter combinations.

[0126] In some embodiments, the second processing module 720 may also be used to: Acquire multiple X-ray images of other trees of the same species as the target tree at multiple drilling depths and multiple sets of different parameter combinations; Based on the imaging effects of multiple frames of X-ray images corresponding to each tree at the same target thickness, the target parameter combination corresponding to each tree at the same target thickness is determined; Based on the average value of the target parameter combination corresponding to each tree at the same target thickness, the target parameter combination corresponding to the target tree at the same target thickness is determined.

[0127] In some embodiments, the third processing module 730 may also be used to: The tree species and target thicknesses corresponding to multiple target trees are used as samples, and the target parameter combinations are used as sample labels to construct training samples. Multiple training samples are input into the network model, and the network model is trained with the network model output prediction parameter combination as the goal to learn the association relationship.

[0128] In some embodiments, the fourth processing module may further be configured to: determining a first width based on the bark thickness of the single tree to be measured; Determining a prediction parameter combination corresponding to the single tree to be tested based on the first width, the tree species category of the single tree to be tested, and the correlation between the target parameter combination and the target thickness; Based on the predicted parameter combination, the X-ray exposure parameters of the image sensor are adjusted to acquire an X-ray image of the single tree to be tested.

[0129] The device for selecting X-ray exposure parameters for individual trees of different tree species in the embodiments of the present application can be an electronic device or a component of an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or other device other than a terminal. For example, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. It can also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc., and the embodiments of the present application are not specifically limited.

[0130] The device for selecting X-ray exposure parameters for individual trees of different tree species in the embodiments of the present application can be a device having an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0131] The device for selecting X-ray exposure parameters for single trees of different tree species provided in the embodiment of the present application can achieve Figures 1 to 6 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0132] In some embodiments, as Figure 8 As shown, an embodiment of the present application further provides an electronic device 800, including a processor 801, a memory 802, and a computer program stored in the memory 802 and executable on the processor 801. When the program is executed by the processor 801, each process of the above-mentioned embodiment of the method for selecting X-ray exposure parameters for single trees of different tree species is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0133] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0134] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the various processes of the above-mentioned embodiment of the method for selecting X-ray exposure parameters for single trees of different tree species, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0135] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0136] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for selecting X-ray exposure parameters for single trees of different tree species.

[0137] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0138] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned embodiment of the method for selecting X-ray exposure parameters for single trees of different tree species, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0139] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0140] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0141] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of this application.

[0142] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0143] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0144] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for selecting X-ray exposure parameters for single trees of different tree species, characterized in that: include: Acquire multiple frames of X-ray images corresponding to target trees at multiple different drilling depths, collected by an image sensor under multiple sets of different parameter combinations; The center of the lens of the image sensor and the mark point of the target tree are on the same horizontal line, and the drilling depth is obtained by drilling the target tree along the diameter direction where the mark point is located; Determining a target parameter combination corresponding to the same drilling depth for the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations at the same drilling depth; Establishing a correlation between target parameter combinations and target thicknesses corresponding to different target trees, wherein the target thickness is the difference between the initial trunk diameter of each target tree and the drilling depth; Based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured, the X-ray exposure parameters of the image sensor are determined to acquire an X-ray image of the single tree to be measured.

2. The method for selecting X-ray exposure parameters for single trees of different tree species according to claim 1, characterized in that: The acquisition of multiple frames of X-ray images corresponding to target trees at multiple different drilling depths, acquired by the image sensor under multiple sets of different parameter combinations, includes: Acquire an X-ray image of the target tree at the same drilling depth, acquired by the image sensor under the initial parameter combination; The parameters of the target category in the initial parameter combination are adjusted along the target adjustment direction and the target adjustment step size, while the parameters of other categories remain unchanged, and the X-ray image corresponding to the target tree at the same drilling depth, which is collected by the image sensor under the adjusted initial parameter combination, is reacquired.

3. The method for selecting X-ray exposure parameters for single trees of different tree species according to claim 1, characterized in that: The acquisition of multiple frames of X-ray images corresponding to target trees at multiple different drilling depths, acquired by the image sensor under multiple sets of different parameter combinations, includes: Acquiring multiple frames of X-ray images corresponding to the target tree at the initial drilling depth, which are collected by the image sensor under multiple sets of different parameter combinations; The initial drilling depth is adjusted, and multiple frames of X-ray images corresponding to the target tree at the adjusted initial drilling depth are acquired by the image sensor under multiple groups of different parameter combinations.

4. The method for selecting X-ray exposure parameters for single trees of different tree species according to any one of claims 1 to 3, characterized in that: The determining of the target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple groups of different parameter combinations at the same drilling depth includes: Performing image recognition on multiple frames of X-ray images corresponding to the same drilling depth based on an adjustment sequence; the adjustment sequence is the sequence for adjusting the parameters of the target category in the parameter combination during the image acquisition process; When it is recognized for the first time that the marking point is not displayed in the X-ray image, the parameter combination corresponding to the previous frame of the X-ray image is determined as the target parameter combination corresponding to the same drilling depth.

5. The method for selecting X-ray exposure parameters for single trees of different tree species according to any one of claims 1 to 3, characterized in that: The determining of the target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple groups of different parameter combinations at the same drilling depth includes: Acquire multiple frames of X-ray images corresponding to multiple other trees of the same species as the target tree at multiple drilling depths and multiple sets of different parameter combinations; Determining target parameter combinations corresponding to the trees at the same target thickness based on imaging effects of multiple frames of X-ray images corresponding to the trees at the same target thickness; The target parameter combination corresponding to the target tree at the same target thickness is determined based on an average value of the target parameter combination corresponding to each of the trees at the same target thickness.

6. The method for selecting X-ray exposure parameters for single trees of different tree species according to any one of claims 1 to 3, characterized in that: The determining of the target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple groups of different parameter combinations at the same drilling depth includes: While adjusting the parameters of the target category in the initial parameter combination along the target adjustment direction and the target adjustment step size, and maintaining the first values of the parameters of the other categories unchanged, determining, based on imaging effects of multiple frames of acquired X-ray images, the optimal values of the parameters of the target category corresponding to the first values of the parameters of the other categories, and determining the first values corresponding to the parameters of the other categories and the optimal values corresponding to the parameters of the target category as a set of target parameter combinations; Adjust the values of the parameters of the first category among the parameters of other categories to the second values, keep the values of the parameters of the remaining categories among the parameters of other categories unchanged at the first values, adjust the parameters of the target category along the target adjustment direction and the target adjustment step, and determine, based on the imaging effect of the collected multiple frames of X-ray images, the optimal values of the parameters of the target category corresponding to the first values when the parameters of the first category are the second values and the values of the parameters of the remaining categories are the first values, and determine the optimal values corresponding to the parameters of the target category when the parameters of the first category are the second values, the values of the parameters of the remaining categories are the first values, and the parameters of the target category as a set of target parameter combinations.

7. The method for selecting X-ray exposure parameters for single trees of different tree species according to any one of claims 1 to 3, characterized in that: The construction of the correlation between the target parameter combination and the target thickness corresponding to each different target tree includes: Taking the tree species categories and the target thickness corresponding to the plurality of target trees as samples and the target parameter combination as sample labels, a training sample is constructed; Input a plurality of the training samples into the network model, train the network model with the output prediction parameter combination of the network model as a target, and learn the association relationship.

8. The method for selecting X-ray exposure parameters for single trees of different tree species according to any one of claims 1 to 3, characterized in that: The parameter combination includes tube voltage parameters, tube current parameters and exposure time parameters, and the parameters of each category are independent of each other.

9. The method for selecting X-ray exposure parameters for single trees of different tree species according to any one of claims 1 to 3, characterized in that: The determining, based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured, an X-ray exposure parameter of the image sensor to acquire an X-ray image of the single tree to be measured includes: Determining a first width based on the bark thickness of the single tree to be tested; Determining a prediction parameter combination corresponding to the single tree to be tested based on the first width, the tree species category of the single tree to be tested, and an association between the target parameter combination and the target thickness; The X-ray exposure parameters of the image sensor are adjusted based on the predicted parameter combination to acquire an X-ray image of the single tree to be tested.

10. A device for selecting X-ray exposure parameters for single trees of different tree species, characterized in that: include: A first processing module is configured to obtain multiple frames of X-ray images corresponding to a target tree at multiple different drilling depths, acquired by an image sensor under multiple different parameter combinations; the center of the image sensor lens and the marking point of the target tree are co-horizontally aligned, and the drilling depths are obtained by drilling the target tree along the diameter of the marking point; a second processing module configured to determine a target parameter combination corresponding to the same drilling depth of the target tree based on imaging effects of multiple frames of X-ray images acquired by the image sensor under multiple sets of different parameter combinations corresponding to the same drilling depth; A third processing module is configured to establish a correlation between target parameter combinations corresponding to different target trees and target thicknesses, wherein the target thickness is the difference between the initial trunk diameter of each target tree and the drilling depth; The fourth processing module is used to determine the X-ray exposure parameters of the image sensor to acquire the X-ray image of the single tree to be measured based on the association relationship, the initial trunk diameter of the single tree to be measured, and the tree species category of the single tree to be measured.

Images