Camellia oleifera fruit tree yield prediction system and method based on three-dimensional laser scanner, and storage medium

Abstract

The invention provides a camellia oleifera fruit tree yield prediction system and method based on a three-dimensional laser scanner and a storage medium, and relates to the technical field of camellia oleifera fruit tree yield prediction.The method comprises the steps that in the data acquisition stage, the three-dimensional laser scanner and a hyperspectral camera are utilized to obtain fruit volume, geometric feature data and internal component content data, and the data are stored in a database; a foundation is built for subsequent analysis, the calculation precision of the fruit quality is effectively improved by calculating the actual density of the fruit, generating a density correction index and fully considering multiple factors influencing the density of the fruit, a quality prediction model is built based on a deep learning network, and the model can capture the complex relation between the fruit quality and the factors. According to the method, the adaptability to different growth environments and fruit individuals is greatly enhanced, the generalization ability of the model is remarkably improved, multiple modules work cooperatively, a complete systematic yield prediction system is constructed, all links are closely connected, manual intervention and data errors are reduced, and the working efficiency of camellia oleifera fruit tree yield detection is greatly improved.

Description

Technical Field

[0001] The invention relates to the technical field of camellia oil tree yield prediction, and in particular to a camellia oil tree yield prediction system, method and storage medium based on a three-dimensional laser scanner. Background Art

[0002] In recent years, although deep learning has achieved good results in object detection, it often requires complex computing models and a large amount of data training. In addition, due to the lush branches and leaves of the canopy of fruit trees and severe occlusion, it is difficult to extract the number of fruits by taking digital images. The image contains all the fruits on the fruit tree, which will lead to a large error between the final calculated number of fruits and the actual number, and then cause a greater error in the calculation of fruit yield. With the rapid development of information technology, 3D laser scanning technology is becoming more and more mature. This technology can collect point cloud data from different angles through laser radar to comprehensively obtain 3D point cloud information of oil tea fruit trees. It is not affected by factors such as object color and ambient light, and has good robustness. By processing and analyzing these point cloud data, the fruit can be distinguished. Compared with manual measurement and image-based methods, the detection speed is faster and the accuracy is higher, which provides a new and effective way for the intelligent measurement of oil tea fruit tree yield.

[0003] In the prior art, a method for detecting the yield of tea trees based on a three-dimensional laser scanner is provided in announcement number CN112215184B, which comprises the following steps: acquiring three-dimensional point cloud data of the tea tree by means of a three-dimensional laser scanner, and preprocessing the collected three-dimensional point cloud data to obtain a three-dimensional point cloud data set of the tea tree; segmenting the three-dimensional point cloud data set of the tea tree to obtain a three-dimensional point cloud data set containing leaf and fruit information; performing density statistics on the three-dimensional point cloud data set of leaf and fruit information, setting a threshold, filtering out the leaves, and obtaining N subsets of fruit three-dimensional point cloud data, where N is a positive integer; calculating the corresponding fruit radius of each fruit according to the fruit three-dimensional point cloud data subset to obtain a fruit radius array; calculating the fruit mass corresponding to each fruit radius in the fruit radius array according to the basic parameters in the relationship model between the fruit radius and the fruit mass, and accumulating and calculating the yield of the entire fruit tree.

[0004] However, there are still the following deficiencies. From the above statements, it can be seen that the existing technology only relies on a three-dimensional laser scanner to obtain the fruit radius, fails to collect the geometric characteristic parameters and internal component parameters of the fruit, and cannot fully describe the fruit information. The quality is calculated based solely on the relationship model between the fruit radius and the quality, without calculating the actual density of the fruit, and without considering the influence of geometric characteristics and internal components on the density, resulting in inaccurate calculation of the fruit quality. The fixed relationship model used is difficult to adapt to the complex and changeable growth environment and individual differences of the fruit, and cannot accurately capture the complex relationship between the fruit quality and the influencing factors, thereby reducing the accuracy and reliability of yield detection.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a tea oil tree yield prediction system, method and storage medium based on a three-dimensional laser scanner to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A method for predicting the yield of oil-tea trees based on a three-dimensional laser scanner, comprising: The data acquisition module is used to obtain the three-dimensional point cloud data of the sample and the oil-tea tree to be predicted through a three-dimensional laser scanner, and pre-process the three-dimensional point cloud data, perform threshold segmentation on the pre-processed three-dimensional point cloud data, obtain the fruit point cloud area and the branch and leaf point cloud area, obtain the volume of each fruit and the geometric feature data affecting the fruit density from the fruit point cloud area, and collect the fruit spectral images of the sample and the oil-tea tree to be predicted through a hyperspectral camera, extract the fruit spectral data based on the fruit spectral image, select the fruit corresponding to the spectral image acquisition from the collected samples, use the chemical analysis method to determine the internal components of the fruit, and obtain the internal component content data of each fruit; A content prediction model building module is used to build a content prediction model based on a deep learning network, taking the fruit spectrum data of the sample as input and the internal component content data of the fruit as output labels to train the content prediction model; The content simulation module is used to input the fruit spectral data of the oil-tea tree to be predicted into the trained content prediction model to obtain the internal component content data of the fruit of the oil-tea tree to be predicted; A reference density calculation module is used to select a plurality of standard fruits from the sample as reference samples, calculate the average value of the fruit density of the reference samples according to the density formula, use the average value of the fruit density as the reference density of the fruit, calculate the average value of the geometric characteristic data and the internal component content data of the reference samples, and use the average value of the geometric characteristic data and the internal component content data as the reference value of the geometric characteristic data and the internal component content data; The first calculation module is used to process the geometric characteristic data and the internal component content data of the fruit to generate a density correction index of the fruit; The quality prediction model building module is used to build a fruit quality prediction model based on a deep learning network, taking the baseline density, density correction index and volume of the sample fruit as inputs and the corresponding actual weight of each fruit as the label output to train the fruit quality prediction model; The quality simulation module is used to input the reference density, the density correction index and the volume of the fruit of the oil-tea tree to be predicted into the trained fruit quality prediction model to obtain the actual quality of each fruit of the oil-tea tree to be predicted; The second calculation module is used to accumulate and calculate the actual mass of each fruit on the oil-tea tree to be predicted, so as to obtain the yield of the oil-tea tree.

[0008] Furthermore, the geometric characteristic data include the surface area, diameter and sphericity of the fruit, and the internal component content data include the oil content, sugar content and water content of the fruit.

[0009] Furthermore, the 3D point cloud data of the oil tea tree is obtained by a 3D laser scanner, and the 3D point cloud data is preprocessed, and the preprocessed 3D point cloud data is threshold segmented to obtain the fruit point cloud area and the branch and leaf point cloud area. The specific process is as follows: Around the tea trees, multiple scanning stations were set up at different positions and angles. The stations were evenly distributed around the trees, and the 3D point cloud data was pre-processed, including noise removal and normalization. The three-dimensional space where the point cloud is located is divided into uniform voxels. The side length of the voxel is determined according to the point cloud density and segmentation accuracy. The number of point clouds in each voxel is counted, and the mean and standard deviation of the number of point clouds in all voxels are calculated. When the number of point clouds in a voxel is greater than the threshold, the threshold is the sum of the mean and the standard deviation, and the point cloud in the voxel belongs to the fruit point cloud area. When the number of point clouds in a voxel is less than the threshold, the threshold is the difference between the mean and the standard deviation, and it is judged to be the branch and leaf point cloud area.

[0010] Furthermore, the geometric characteristic data and internal component content data of the fruit are processed to generate the density correction index of the fruit, according to the following formula: ; in, is the density correction index of the fruit; In the formula, is the surface area of ​​the fruit, is the reference value of the surface area, is the diameter of the fruit, is the reference value of the diameter, is the sphericity of the fruit, is the reference value of sphericity, is the oil content of the fruit, is the base value of fat content. is the sugar content of the fruit, is the reference value of sugar content. is the moisture content of the fruit, is the base value of moisture content; In the formula, is the weight coefficient of the ratio of surface area to the reference value of surface area, is the weight coefficient of the ratio of diameter to the reference diameter value, is the weight coefficient of the ratio of sphericity to the sphericity reference value, is the weight coefficient of the ratio of fat content to the reference value of fat content, is the weight coefficient of the ratio of sugar content to the reference value of sugar content, is the weight coefficient of the ratio of moisture content to the reference value of moisture content. On the basis of .

[0011] Furthermore, the actual mass of each fruit on the oil-tea tree to be predicted is accumulated and calculated to obtain the yield of the oil-tea tree, according to the following formula: ; in, The yield of tea oil trees, For the The actual mass of the fruit, is the index of the fruit on the oil-tea tree to be predicted, , The number of fruits of the tea oil tree to be predicted.

[0012] To achieve the above object, the present invention also provides the following technical solutions: A method for predicting the yield of oil-tea fruit trees based on a three-dimensional laser scanner, the method is generated based on any of the above-mentioned systems for predicting the yield of oil-tea fruit trees based on a three-dimensional laser scanner, and the specific steps include: S1. Acquire the three-dimensional point cloud data of the sample and the oil-tea tree to be predicted by a three-dimensional laser scanner, pre-process the three-dimensional point cloud data, perform threshold segmentation on the pre-processed three-dimensional point cloud data, obtain the fruit point cloud area and the branch and leaf point cloud area, obtain the volume of each fruit and the geometric feature data affecting the fruit density from the fruit point cloud area, select the volume and corresponding mass of multiple fruits, calculate the average value of the fruit density, take the average value of the fruit density as the benchmark density of the fruit, and collect the fruit spectral images of the sample and the oil-tea tree to be predicted by a hyperspectral camera, extract the fruit spectral data based on the fruit spectral image, select the fruit corresponding to the spectral image acquisition from the collected samples, use the chemical analysis method to determine the internal components of the fruit, and obtain the internal component content data of each fruit; S2. Constructing a content prediction model based on a deep learning network, taking the fruit spectral data of the sample as input and the internal component content data of the fruit as output labels, and training the content prediction model; S3. The fruit spectral data of the oil-tea tree to be predicted is input into the trained content prediction model to obtain the internal component content data of the fruit of the oil-tea tree to be predicted; S4. Select multiple standard fruits from the sample as the reference sample, calculate the average value of the fruit density of the reference sample according to the density formula, use the average value of the fruit density as the reference density of the fruit, calculate the average value of the geometric characteristic data and the internal component content data of the reference sample, and use the average value of the geometric characteristic data and the internal component content data as the reference value of the geometric characteristic data and the internal component content data; S5. Processing the geometric characteristic data and the internal component content data to generate a density correction index; S6. construct a fruit quality prediction model based on a deep learning network, take the baseline density, density correction index and volume of the sample fruit as input, and the corresponding actual weight of each fruit as the label output, and train the fruit quality prediction model; S7. The baseline density, density correction index and volume of the oil-tea tree fruit to be predicted are input into the trained fruit quality prediction model to obtain the actual quality of each fruit of the oil-tea tree to be predicted; S8. Accumulate and calculate the actual mass of each fruit on the oil-tea tree to be predicted to obtain the yield of the oil-tea tree.

[0013] A storage medium is used to store a computer program, which, when executed by a processor, implements any of the above-mentioned tea oil tree yield prediction systems based on a three-dimensional laser scanner.

[0014] Compared with the prior art, the present invention has the following beneficial effects: In the data collection stage, the present invention uses a three-dimensional laser scanner and a hyperspectral camera to comprehensively obtain fruit volume, geometric feature data, and internal component content data. The collection of multi-dimensional information can more comprehensively and accurately characterize fruit characteristics, laying a foundation for subsequent analysis. A content prediction model is constructed based on a deep learning network to obtain the internal component content data of the oil-tea tree to be predicted. By calculating the density correction index of the fruit, the influence of various factors on the fruit density is fully considered, and the calculation accuracy of the fruit quality is effectively improved. A quality prediction model is constructed based on a deep learning network. The model can accurately capture the complex relationship between fruit quality and various factors, greatly enhancing the adaptability to different growth environments and individual fruits. Compared with the simple fixed relationship model in the prior art, the model can better adapt to the complex and changeable growth environment and individual differences of fruits, greatly improving the generalization ability of the model. Through the collaborative work of multiple modules, a complete and systematic yield prediction system is formed. From data collection, calculation and analysis to model construction and prediction, each link is closely connected. This optimized workflow reduces manual intervention and data errors, and greatly improves the work efficiency of oil-tea tree yield detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a block diagram of the module composition of the present invention; Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0016] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0017] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0018] Embodiment 1: See also Figure 1 , the present invention provides a technical solution: A tea tree yield prediction system based on a three-dimensional laser scanner, comprising: The data acquisition module is used to obtain the three-dimensional point cloud data of the sample and the oil-tea tree to be predicted through a three-dimensional laser scanner, and pre-process the three-dimensional point cloud data, perform threshold segmentation on the pre-processed three-dimensional point cloud data, obtain the fruit point cloud area and the branch and leaf point cloud area, obtain the volume of each fruit and the geometric feature data affecting the fruit density from the fruit point cloud area, and collect the fruit spectral images of the sample and the oil-tea tree to be predicted through a hyperspectral camera, extract the fruit spectral data based on the fruit spectral image, select the fruit corresponding to the spectral image acquisition from the collected samples, use the chemical analysis method to determine the internal components of the fruit, and obtain the internal component content data of each fruit; Based on the above embodiment, the geometric feature data include the surface area, diameter and sphericity of the fruit, and the internal component content data include the oil content, sugar content and water content of the fruit.

[0019] On the basis of the above-mentioned embodiment, the collected oil-tea tree is a mature oil-tea tree, so the three-dimensional point cloud image and the fruit spectrum image are both images of the mature oil-tea tree.

[0020] On the basis of the above embodiment, the 3D point cloud data of the oil tea fruit tree is obtained by a 3D laser scanner, and the 3D point cloud data is preprocessed, and the preprocessed 3D point cloud data is threshold segmented to obtain the fruit point cloud area and the branch and leaf point cloud area. The specific process is as follows: Around the tea trees, multiple scanning stations were set up at different positions and angles. The stations were evenly distributed around the trees, and the 3D point cloud data was pre-processed, including noise removal and normalization. The three-dimensional space where the point cloud is located is divided into uniform voxels. The side length of the voxel is determined by the point cloud density and segmentation accuracy. When the point cloud density is high, it is 0.05 meters, and when it is low, it is 0.1 meters. The number of point clouds in each voxel is counted, and the mean and standard deviation of the number of point clouds in all voxels are calculated. When the number of point clouds in a voxel is greater than the threshold, the threshold is the sum of the mean and the standard deviation. The point cloud in the voxel is likely to belong to the fruit point cloud area. When the number of point clouds in a voxel is less than the threshold, the threshold is the difference between the mean and the standard deviation, and it tends to be judged as the branch and leaf point cloud area.

[0021] Based on the above embodiment, the method for obtaining the volume, surface area, diameter and sphericity of each fruit from the fruit point cloud region is as follows: First, the fruit point cloud is triangulated to construct a three-dimensional mesh composed of multiple triangular patches. Then, based on the geometric characteristics of the mesh, the integral formula is used to calculate the volume. Suppose the mesh model is triangular patches, The area of ​​a triangular patch is , is the index of the triangle patch, , No. The normal vector of a triangle patch is , No. The distance from the triangle patch to the coordinate origin is , then the volume of each fruit for: ; The fruit point cloud is converted into a triangular mesh through a triangulation algorithm. triangular patches, calculate the The area of ​​the triangle patch, The area of ​​a triangle is calculated using Heron's formula. The lengths of the three sides of the triangle are , , , half circumference , then The area of ​​the triangle patch ,Will The surface area is obtained by adding the areas of the triangles ; Traverse each pair of points in the fruit point cloud and calculate the Euclidean distance between them. If the coordinates of the two points are and ; The Euclidean distance is , record the maximum distance as the diameter ; According to the formula Calculate sphericity , is the area of ​​the triangle patch, For each fruit volume, sphericity The closer the value is to 1, the closer the fruit is to a sphere.

[0022] Based on the above embodiment, the specific process of obtaining the number of fruits of the oil-tea tree is as follows: Use the connected body marking algorithm to mark the voxels that are determined to be fruit point cloud areas. The algorithm starts with an unlabeled fruit body voxel, marks it with a specific connected body number, and then recursively marks all other fruit body voxels connected to it until all voxels of the connected body are marked. Then, find the next unlabeled fruit body voxel and repeat the above process until all fruit body voxels are marked. Each connected body with a different number represents a potential fruit. The number of voxels contained in each connected body is calculated and converted into volume. According to the actual size range of Camellia oleifera fruits, a minimum volume threshold and a maximum volume threshold are set. Connected bodies with a volume smaller than the minimum volume threshold are likely to be noise point clouds or misjudged small areas, while connected bodies with a volume larger than the maximum volume threshold may be multiple fruits sticking together or other abnormal situations. Connected bodies that do not meet the volume threshold range are removed. The remaining connected bodies were morphologically analyzed and their sphericity was calculated. Camellia oleifera fruits are approximately spherical, so connected bodies with higher sphericity are more likely to be real fruits. A sphericity threshold was set to exclude connected bodies with sphericity lower than the threshold. The number of remaining connected bodies was the number of fruits preliminarily counted. Some overlapping fruits may be marked as a connected body. By analyzing the shape, volume and distribution characteristics of the internal point cloud of the connected body, a machine learning algorithm is used to determine whether the connected body is one fruit or multiple fruits. For example, if the volume of the connected body is significantly larger than the normal volume of the fruit and the internal point cloud distribution shows multiple clustering centers, it may contain multiple fruits. Based on these characteristics, it can be further split into multiple fruits for counting.

[0023] On the basis of the above embodiment, the fruit spectral image of the oil tea tree is collected by a hyperspectral camera, and the oil content, sugar content and water content of the fruit are extracted from the fruit spectral image. The specific process is as follows: For the fruit spectral image, the spectral reflectance intensity value of the pixel point in the image is , Represents the horizontal and vertical coordinates of the pixel point, dividing the image into foreground (fruit) and background. The binary image after segmentation Obtained by the following formula: ; When the spectral reflectance intensity value of the pixel point Greater than or equal to the spectral reflectance intensity value threshold , , at this time, the corresponding pixel point is considered to be the foreground image, that is, the fruit image; When the spectral reflectance intensity value of the pixel point Less than the spectral reflectance intensity value threshold , , the corresponding pixels are considered as the background image; For the fruit area segmented by image processing, the reflectance or absorbance data of the area at each wavelength are extracted, and these data are arranged in order of wavelength, so as to obtain the spectrum curve of the fruit; The Soxhlet extraction method is used. This method is based on specific chemical principles and experimental operation procedures to process fruit samples, so as to accurately determine the oil content in the fruit; Using high performance liquid chromatography, the sugar content of the fruit was measured separately, taking advantage of the method's ability to separate and detect components in a mixture; The loss on drying method is used to determine the moisture content of the fruit by drying the fruit sample under certain conditions and measuring the weight change before and after drying. While using chemical methods to measure the fruit components, the fruits are photographed again with a hyperspectral camera to obtain their spectral images, and then the spectral data corresponding to each fruit is extracted from these spectral images. Since the content of each fruit's internal components has been obtained through chemical analysis before, now there is the corresponding spectral data, and the content of each fruit's internal components (oil, sugar, water) and its corresponding spectral information (i.e., the reflectivity or absorbance data at each wavelength contained in the spectral curve) are successfully matched; A content prediction model building module is used to build a content prediction model based on a deep learning network, taking the fruit spectrum data of the sample as input and the internal component content data of the fruit as output labels to train the content prediction model; On the basis of the above embodiment, the content prediction model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU (rectified linear unit) as an activation function; In the content prediction model, the input features of the multi-layer perceptron deep learning network include: fruit spectral data of the sample, 1 feature.

[0024] The structure of the deep learning network of multi-layer perceptron is: Input layer: receives input of 1 feature; The first hidden layer has 128 neurons and uses ReLU as the activation function. The second hidden layer has 64 neurons and also uses the ReLU activation function. The third hidden layer has 32 neurons and uses the ReLU activation function. Output layer: has 1 neuron, which outputs the internal component content data of the fruit.

[0025] The process of training the content prediction model is as follows: The fruit spectral data of the sample is used as the input, and the internal component content data of the fruit is used as the output label for training. The mean square error is used as the loss function. When it is within the range, the training of the content prediction model is completed.

[0026] The content simulation module is used to input the fruit spectral data of the oil-tea tree to be predicted into the trained content prediction model to obtain the internal component content data of the fruit of the oil-tea tree to be predicted; The reference density calculation module is used to select multiple standard fruits from the sample as reference samples, calculate the average value of the fruit density of the reference samples according to the density formula, take the average value of the fruit density as the reference density of the fruit, calculate the average value of the geometric characteristic data and the internal component content data of the reference samples, take the average value of the geometric characteristic data and the internal component content data as the reference value of the geometric characteristic data and the internal component content data, the reference values ​​of the geometric characteristic data include the surface area reference value, the diameter reference value, and the sphericity reference value, and the reference values ​​of the internal component content data include the oil content reference value, the sugar content reference value, and the water content reference value.

[0027] The surface area, diameter, sphericity, oil content, sugar content, and water content of the collected fruits must be normalized. Through normalization, the data of different indicators are unified into the range of 0 to 1, eliminating the influence of dimension and value range, making these data comparable and consistent in subsequent analysis operations.

[0028] The first calculation module is used to process the geometric feature data and the internal component content data to generate a density correction index; On the basis of the above embodiment, the geometric characteristic data and the internal component content data of the fruit are processed to generate the density correction index of the fruit, and the formula based on it is as follows: ; in, It is the density correction index of the fruit. The density correction index is used to combine the surface area, diameter, sphericity, oil content, sugar content, and water content of the fruit to comprehensively evaluate the influence of each parameter on the density of each fruit. The larger the density correction index, the greater the influence. In the formula, is the surface area of ​​the fruit, is the reference value of the surface area, is the diameter of the fruit, is the reference value of the diameter, is the sphericity of the fruit, is the reference value of sphericity, is the oil content of the fruit, is the base value of fat content. is the sugar content of the fruit, is the reference value of sugar content. is the moisture content of the fruit, is the base value of moisture content; Select multiple fruits, calculate the average values ​​of surface area, diameter, sphericity, oil content, sugar content and water content, and use the average values ​​of surface area, diameter, sphericity, oil content, sugar content and water content as the benchmark value of surface area, the benchmark value of diameter, the benchmark value of sphericity, the benchmark value of oil content, the benchmark value of sugar content and the benchmark value of water content.

[0029] The reference density of the fruit corresponds to the reference value of the surface area, the reference value of the diameter, the reference value of the sphericity, the reference value of the oil content, the reference value of the sugar content, and the reference value of the water content.

[0030] On this basis, it should be noted that: Generally speaking, the higher the sphericity, the closer the fruit is to a sphere. Under the same volume, the surface area of ​​a sphere is the smallest, the compactness of the internal material is relatively high, and its density is relatively large when the mass is the same. Therefore, when the sphericity is Relative benchmark value When it increases, it means that the fruit is closer to a spherical shape and the density tends to increase, which makes the density correction index Increase.

[0031] Sugar and water are important components in fruits. or moisture content Relative to their respective benchmark values , When the density increases, it means that the sugar or water content inside the fruit increases. When the volume of the fruit does not change much, the mass will increase. According to the density formula, the density will increase, which will increase the density correction index. Increase.

[0032] Benchmark value Represents the surface area of ​​the fruit under a certain standard state. relatively Increase means that the shape of the fruit deviates from the standard state and tends to be flatter or irregular. For example, assuming that the surface area of ​​a standard spherical fruit is , when it is squeezed and deformed by external force, the surface area Increase, this change in shape will change the internal space layout of the fruit. When the mass remains unchanged, the volume will increase relatively. From a geometric point of view, for a given volume, a sphere is the shape with the smallest surface area. When the shape of the fruit becomes irregular or flat, its surface area increases. In order to accommodate the same mass of material, the volume will also increase accordingly. According to the density formula, if the mass remains unchanged and the volume increases, the density of the fruit will inevitably decrease. Since the density correction index is used to measure the change in fruit density relative to the standard state, when the surface area relatively When it increases, it affects the shape and volume of the fruit, thereby reducing the density, which ultimately leads to a decrease in the density correction index.

[0033] Benchmark value Indicates the standard diameter of the fruit. relatively Increased, indicating that the overall size of the fruit has increased compared to the standard state. For example, the diameter of a certain fruit that grows normally to a certain stage is , if grown under special conditions, the diameter becomes and greater than As the diameter of the fruit increases, the growth and distribution of its internal cells may change, causing the internal structure to become relatively loose. The cells inside the fruit may be stretched in the diameter direction, and the gaps between the cells increase, thereby forming more voids inside the fruit. In this case, if the increase in fruit mass is less than the increase in volume due to the increase in diameter, the density of the fruit will decrease according to the density formula, because the density correction index is a quantitative indicator of the relative standard state of fruit density. When the diameter relatively When it increases, it causes changes in the internal structure of the fruit and a decrease in density, which in turn causes a decrease in the density correction index.

[0034] Benchmark value Represents the normal level of oil content in the fruit. relatively Increase, indicating that the oil content in the fruit exceeds the normal state. For example, the oil content of the fruit of a certain oil crop under normal growth conditions is , but after special cultivation or environmental influences, the oil content becomes and greater than The oil in the fruit is mainly distributed in the intercellular spaces or in specific oil bodies. As the oil content increases, the oil will expand the intercellular spaces, increase the space inside the fruit, or change the microstructure inside the fruit, making it less compact. Since the density of oil is usually smaller than other components of the fruit, when the quality of the fruit does not change much, the increase in oil content leads to an increase in volume. According to the density formula, the density of the fruit will decrease. The density correction index is an indicator that reflects the relative standard state of fruit density. When the oil content is relatively When it increases, the density decreases by changing the internal structure and volume of the fruit, which in turn leads to a decrease in the density correction index.

[0035] In summary, the density correction index It is negatively correlated with surface area, diameter, and oil content. The density correction index It is positively correlated with sphericity, sugar content and moisture content.

[0036] The relative value is obtained by dividing the sugar content of the fruit by the reference value, which can reflect the degree of deviation of the index from the reference state. The reference value indicates the size of the fruit parameter under the set standard state, and is used to measure the size of other fruit parameters relative to the standard. Is the reference value 2 times, , the influence of oil content on the fruit density correction index can be significantly reflected in the formula calculation. Compared with simple numerical values, relative values ​​can better reflect the difference between the actual situation and the standard situation of the indicator. The original numerical values ​​of various indicators of fruits of different types and different growth environments are very different. The benchmark value can be selected according to the research object or application scenario. The formula constructed by dividing by the benchmark value can adapt to different fruit samples. Regardless of the size of the fruit or the content of its ingredients, it can be included in the formula calculation through relative values, making the formula more widely applicable and universal.

[0037] In summary, the above weighted summation formula is used to characterize the density correction index and surface area ,diameter , Sphericity , oil content , sugar content , moisture content The functional relationship between them.

[0038] In the formula, is the weight coefficient of the ratio of surface area to the reference value of surface area, is the weight coefficient of the ratio of diameter to the reference diameter value, is the weight coefficient of the ratio of sphericity to the sphericity reference value, is the weight coefficient of the ratio of fat content to the reference value of fat content, is the weight coefficient of the ratio of sugar content to the reference value of sugar content, is the weight coefficient of the ratio of moisture content to the reference value of moisture content; From the perspective of geometric morphology, sphericity fundamentally affects the arrangement and compactness of the internal material of the fruit. The higher the sphericity, the more efficient the internal space utilization of the fruit, the more compact the material distribution, and has a fundamental and structural impact on the density of the fruit. For example, in fruits with high sphericity, components such as cells can be arranged more orderly, reducing internal gaps and directly increasing density.

[0039] Sugar content mainly affects density from the perspective of component quality. Although increased sugar content will increase fruit quality and thus affect density, it is only one of the many components of the fruit, and the distribution of sugar in the fruit may be uneven. Its impact on density is more based on the increase in quality, unlike sphericity, which affects the overall structure. Therefore, in terms of the comprehensive impact weight on fruit density, sphericity corresponds to Greater than the sugar content .

[0040] Sugar is a key component in fruit with a clear contribution to quality. Changes in its content are closely related to fruit maturity and quality, and have a direct and quantifiable impact on fruit density. As the fruit grows, sugar continues to accumulate, and the fruit density will change significantly.

[0041] The surface area mainly reflects the appearance of the fruit. It has no direct causal relationship with the actual content and compactness of the internal substances of the fruit. Even if the surface area changes, the internal composition and structure of the fruit may not change accordingly, and the impact on density is relatively indirect. Higher than the surface area .

[0042] Changes in surface area can reflect the wrinkles, bumps and other conditions on the fruit surface to a certain extent. These characteristics may affect the interaction between the internal substances of the fruit and the external environment, and then have some effects on the distribution and accumulation of internal substances. For example, a large surface area may be conducive to the accumulation of photosynthetic products, indirectly affecting the internal composition and density of the fruit.

[0043] The diameter is only a linear measure of the size of the fruit. It focuses more on describing the external dimensions of the fruit, and has limited indication of the specific composition and distribution of the internal substances of the fruit. The increase in diameter may only be the expansion of the fruit as a whole, and does not mean that the density or composition of the internal substances has changed substantially. Therefore, the weight corresponding to the surface area is The diameter corresponds to To be high.

[0044] Diameter, as a basic measure of fruit size, is related to the growth stage and overall development of the fruit to a certain extent. The changing trend of fruit diameter can reflect its growth law and has a certain reference value for judging the maturity of the fruit, while maturity has a potential connection with fruit density.

[0045] Oil is usually dispersed in the fruit in the form of small oil droplets. Although the oil content will affect the density of the fruit, its proportion in the fruit composition is relatively unstable, and the distribution of oil is relatively random. In contrast, the diameter, a more macroscopic and stable morphological indicator, reflects the overall characteristics of the fruit more directly. Therefore, the weight corresponding to the diameter is Higher than the corresponding fat content .

[0046] Oil is a relatively stable component in fruit. Although changes in its content have limited effects on fruit density, it has a certain regularity and predictability. Oil also plays a specific role in the physiological processes and quality characteristics of fruit.

[0047] The water content in the fruit is easily affected by external environmental factors (such as air humidity, irrigation conditions, etc.), with a large fluctuation range and relatively random changes. Short-term changes in water content may not accurately reflect the physiological state and density characteristics of the fruit itself, and the impact on fruit density is more of a temporary and unstable factor. Therefore, the weight corresponding to the oil content is Higher than the moisture content .

[0048] In summary, On the basis of .

[0049] As an implementation method, The value range is 0.1-0.3, The value range is 0.05-0.2, The value range is 0.3-0.6, The value range is 0.05-0.2, The value range is 0.2-0.5. The value range is 0.05-0.2. The specific value is set by the technicians according to the actual situation and is not limited here.

[0050] The quality prediction model building module is used to build a fruit quality prediction model based on a deep learning network, taking the baseline density, density correction index and volume of the sample fruit as inputs and the corresponding actual weight of each fruit as the label output to train the fruit quality prediction model; On the basis of the above embodiment, the quality prediction model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function; In the quality prediction model, the input features of the multi-layer perceptron deep learning network include three features: baseline density, density correction index and volume.

[0051] The structure of the deep learning network of multi-layer perceptron is: Input layer: receives input of 3 features; The first hidden layer has 128 neurons and uses ReLU as the activation function. The second hidden layer has 64 neurons and also uses the ReLU activation function. The third hidden layer has 32 neurons and uses the ReLU activation function. Output layer: has 1 neuron, which outputs the actual weight of each fruit.

[0052] The process of training the quality prediction model is as follows: The reference density, density correction index and volume of the sample are used as input, and the actual weight of each fruit is used as the label for training. The mean square error is used as the loss function. When it is within the range, the training of the quality prediction model is completed.

[0053] The quality simulation module is used to input the baseline density, density correction index and volume of the fruits of the oil-tea tree to be predicted into the trained fruit quality prediction model to obtain the actual quality of each fruit of the oil-tea tree to be predicted; the second calculation module is used to accumulate the actual quality of each fruit on the oil-tea tree to be predicted to obtain the yield of the oil-tea tree.

[0054] On the basis of the above embodiment, the actual mass of each fruit on the oil-tea tree to be predicted is accumulated and calculated to obtain the yield of the oil-tea tree, according to the following formula: ; in, The yield of tea oil trees, For the The actual mass of the fruit, is the index of the fruit on the oil-tea tree to be predicted, , The number of fruits of the tea oil tree to be predicted.

[0055] See also Figure 2 , the present invention also provides a technical solution: A method for predicting the yield of oil-tea fruit trees based on a three-dimensional laser scanner, the method is generated based on any of the above-mentioned systems for predicting the yield of oil-tea fruit trees based on a three-dimensional laser scanner, and the specific steps include: S1. Acquire the three-dimensional point cloud data of the sample and the oil-tea tree to be predicted by a three-dimensional laser scanner, pre-process the three-dimensional point cloud data, perform threshold segmentation on the pre-processed three-dimensional point cloud data, obtain the fruit point cloud area and the branch and leaf point cloud area, obtain the volume of each fruit and the geometric feature data affecting the fruit density from the fruit point cloud area, and collect the fruit spectral images of the sample and the oil-tea tree to be predicted by a hyperspectral camera, extract the fruit spectral data based on the fruit spectral image, select the fruit corresponding to the spectral image acquisition from the collected samples, use the chemical analysis method to determine the internal components of the fruit, and obtain the internal component content data of each fruit; S2. Constructing a content prediction model based on a deep learning network, taking the fruit spectral data of the sample as input and the internal component content data as output labels, and training the content prediction model; S3. The fruit spectral data of the oil-tea tree to be predicted is input into the trained content prediction model to obtain the internal component content data of the oil-tea tree to be predicted; S4. Select multiple standard fruits from the sample as the reference sample, calculate the average value of the fruit density of the reference sample according to the density formula, use the average value of the fruit density as the reference density of the fruit, calculate the average value of the geometric characteristic data and the internal component content data of the reference sample, and use the average value of the geometric characteristic data and the internal component content data as the reference value of the geometric characteristic data and the internal component content data; S5. Processing the geometric characteristic data and the internal component content data to generate a density correction index; S6. construct a fruit quality prediction model based on a deep learning network, take the baseline density, density correction index and volume of the sample as input, and the corresponding actual weight of each fruit as the label output, and train the fruit quality prediction model; S7. The baseline density, density correction index and volume of the oil-tea tree to be predicted are input into the trained fruit quality prediction model to obtain the actual quality of each fruit of the oil-tea tree to be predicted; S8. Accumulate and calculate the actual mass of each fruit on the oil-tea tree to be predicted to obtain the yield of the oil-tea tree.

[0056] A storage medium is used to store a computer program, which, when executed by a processor, implements any of the above-mentioned tea oil tree yield prediction systems based on a three-dimensional laser scanner.

[0057] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0058] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0059] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A tea tree yield prediction system based on a three-dimensional laser scanner, characterized in that: include: The data acquisition module is used to obtain the three-dimensional point cloud data of the sample and the oil-tea tree to be predicted through a three-dimensional laser scanner, and pre-process the three-dimensional point cloud data, perform threshold segmentation on the pre-processed three-dimensional point cloud data, obtain the fruit point cloud area and the branch and leaf point cloud area, obtain the volume of each fruit and the geometric feature data affecting the fruit density from the fruit point cloud area, and collect the fruit spectral images of the sample and the oil-tea tree to be predicted through a hyperspectral camera, extract the fruit spectral data based on the fruit spectral image, select the fruit corresponding to the spectral image acquisition from the collected samples, use the chemical analysis method to determine the internal components of the fruit, and obtain the internal component content data of each fruit; A content prediction model building module is used to build a content prediction model based on a deep learning network, taking the fruit spectrum data of the sample as input and the internal component content data of the fruit as output labels to train the content prediction model; The content simulation module is used to input the fruit spectral data of the oil-tea tree to be predicted into the trained content prediction model to obtain the internal component content data of the fruit of the oil-tea tree to be predicted; A reference density calculation module is used to select a plurality of standard fruits from the sample as reference samples, calculate the average value of the fruit density of the reference samples according to the density formula, use the average value of the fruit density as the reference density of the fruit, calculate the average value of the geometric characteristic data and the internal component content data of the reference samples, and use the average value of the geometric characteristic data and the internal component content data as the reference value of the geometric characteristic data and the internal component content data; The first calculation module is used to process the geometric characteristic data and the internal component content data of the fruit to generate a density correction index of the fruit; The quality prediction model building module is used to build a fruit quality prediction model based on a deep learning network, taking the reference density, density correction index and volume of the sample fruit as input and the corresponding actual mass as the label output to train the fruit quality prediction model; The quality simulation module is used to input the reference density, the density correction index and the volume of the fruit of the oil-tea tree to be predicted into the trained fruit quality prediction model to obtain the actual quality of each fruit of the oil-tea tree to be predicted; The second calculation module is used to accumulate and calculate the actual mass of each fruit on the oil-tea tree to be predicted, so as to obtain the yield of the oil-tea tree.

2. The oil-tea tree yield prediction system based on three-dimensional laser scanner according to claim 1 is characterized in that: The geometric characteristic data include the surface area, diameter and sphericity of the fruit, and the internal component content data include the oil content, sugar content and water content of the fruit.

3. The oil-tea tree yield prediction system based on three-dimensional laser scanner according to claim 1 is characterized in that: The 3D point cloud data of the oil tea tree is obtained by a 3D laser scanner, and the 3D point cloud data is preprocessed. The preprocessed 3D point cloud data is threshold segmented to obtain the fruit point cloud area and the branch and leaf point cloud area. The specific process is as follows: Around the oil-tea tree, multiple scanning stations were set up at different positions and angles. The stations were evenly distributed around the tree, and the 3D point cloud data was pre-processed, including noise removal and normalization. The three-dimensional space where the point cloud is located is divided into uniform voxels. The side length of the voxel is determined according to the point cloud density and segmentation accuracy. The number of point clouds in each voxel is counted, and the mean and standard deviation of the number of point clouds in all voxels are calculated. When the number of point clouds in a voxel is greater than the threshold, the threshold is the sum of the mean and the standard deviation, and the point cloud in the voxel belongs to the fruit point cloud area. When the number of point clouds in a voxel is less than the threshold, the threshold is the difference between the mean and the standard deviation, and it is judged to be the branch and leaf point cloud area.

4. The oil-tea tree yield prediction system based on three-dimensional laser scanner according to claim 2 is characterized in that: The geometric characteristic data of the fruit and the content data of the components are processed to generate the density correction index, based on the following formula: ； in, is the density correction index of the fruit; In the formula, is the surface area of ​​the fruit, is the reference value of the surface area, is the diameter of the fruit, is the reference value of the diameter, is the sphericity of the fruit, is the reference value of sphericity, is the oil content of the fruit, is the base value of fat content. is the sugar content of the fruit, is the reference value of sugar content. is the moisture content of the fruit, is the base value of moisture content; In the formula, is the weight coefficient of the ratio of surface area to the reference value of surface area, is the weight coefficient of the ratio of diameter to the reference diameter value, is the weight coefficient of the ratio of sphericity to the sphericity reference value, is the weight coefficient of the ratio of fat content to the reference value of fat content, is the weight coefficient of the ratio of sugar content to the reference value of sugar content, is the weight coefficient of the ratio of moisture content to the reference value of moisture content. On the basis of .

5. The oil-tea tree yield prediction system based on three-dimensional laser scanner according to claim 1 is characterized in that: The actual weight of each fruit on the oil-tea tree to be predicted is accumulated and calculated to obtain the yield of the oil-tea tree, based on the following formula: ； in, The yield of tea oil trees, For the The actual mass of the fruit, is the index of the fruit on the oil-tea tree to be predicted, , The number of fruits of the tea oil tree to be predicted.

6. A method for predicting the yield of oil-tea camellia fruit trees based on a three-dimensional laser scanner, the method being generated based on a system for predicting the yield of oil-tea camellia fruit trees based on a three-dimensional laser scanner as claimed in any one of claims 1 to 5, characterized in that: The specific steps include: S1. Acquire the three-dimensional point cloud data of the sample and the oil-tea tree to be predicted by a three-dimensional laser scanner, pre-process the three-dimensional point cloud data, perform threshold segmentation on the pre-processed three-dimensional point cloud data, obtain the fruit point cloud area and the branch and leaf point cloud area, obtain the volume of each fruit and the geometric feature data affecting the fruit density from the fruit point cloud area, and collect the fruit spectral images of the sample and the oil-tea tree to be predicted by a hyperspectral camera, extract the fruit spectral data based on the fruit spectral image, select the fruit corresponding to the spectral image acquisition from the collected samples, use the chemical analysis method to determine the internal components of the fruit, and obtain the internal component content data of each fruit; S2. Constructing a content prediction model based on a deep learning network, taking the fruit spectral data of the sample as input and the internal component content data of the fruit as output labels, and training the content prediction model; S3. The fruit spectral data of the oil-tea tree to be predicted is input into the trained content prediction model to obtain the internal component content data of the fruit of the oil-tea tree to be predicted; S4. Select multiple standard fruits from the sample as the reference sample, calculate the average value of the fruit density of the reference sample according to the density formula, use the average value of the fruit density as the reference density of the fruit, calculate the average value of the geometric characteristic data and the internal component content data of the reference sample, and use the average value of the geometric characteristic data and the internal component content data as the reference value of the geometric characteristic data and the internal component content data; S5. Processing the geometric characteristic data and the internal component content data to generate a density correction index; S6. construct a fruit quality prediction model based on a deep learning network, take the baseline density, density correction index and volume of the sample fruit as input, and the corresponding actual weight of each fruit as the label output, and train the fruit quality prediction model; S7. The baseline density, density correction index and volume of the oil-tea tree fruit to be predicted are input into the trained fruit quality prediction model to obtain the actual quality of each fruit of the oil-tea tree to be predicted; S8. Accumulate and calculate the actual mass of each fruit on the oil-tea tree to be predicted to obtain the yield of the oil-tea tree.

7. A storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements a tea oil tree yield prediction system based on a three-dimensional laser scanner as described in any one of claims 1-5.

Images