A method for understory tree instance segmentation based on improved YOLOv8 model

Abstract

A method for instance segmentation of understory trees based on an improved YOLOv8 model belongs to the field of image recognition and deep learning. The present invention solves the problem that existing methods for instance segmentation of understory trees are high in cost and unsuitable for large-scale segmentation tasks. The method of the present invention specifically comprises the following steps: Step 1, creating a training dataset for instance segmentation of understory trees; Step 2, improving the original YOLOv8 model, i.e. replacing the C2f module of the original YOLOv8 model with the ParC module, replacing the SPPF module in the original YOLOv8 model with the SPPF‑LSKA module, and adding a DAT module at the end of the backbone network of the original YOLOv8 model to obtain an improved YOLOv8 model; Step 3, training the improved YOLOv8 model using the training dataset; Step 4, using the trained improved YOLOv8 model to perform instance segmentation of understory trees on the image to be segmented. The method of the present invention can be applied to instance segmentation of understory trees.

Description

Technical Field

[0001] The present invention belongs to the field of image recognition and deep learning, and specifically relates to a method for segmenting understory trees based on an improved YOLOv8 model. Background Art

[0002] Forests cover most of the Earth's land area and are a vital component of the ecosystem. my country boasts vast territories and abundant forest resources. As of 2021, the country's forest area reached 220 million hectares, with a forest coverage rate of 23.04% and a forest stock of 17.56 billion cubic meters. Surveying the growth and density of standing trees in forests is one of the top priorities of forestry management. Forests are subject to numerous threats, including forest fires, illegal logging, and climate change. Due to the vastness and sparse population of forest areas, there is an urgent need to intelligently and efficiently manage forest resources and improve the accuracy and convenience of forest resource surveys to meet the management requirements of digital forestry and precision forestry. Therefore, effective monitoring and management are necessary, and standing tree segmentation, as a key step, helps understand the health and dynamics of forests.

[0003] Traditional standing tree segmentation methods generally involve manually extracting tree features, and then using algorithms to separate the segmentation target from other irrelevant backgrounds. However, the segmentation accuracy of traditional image segmentation methods depends largely on the quality of the manually extracted target features, and good results are only achieved when the target features are more prominent. In recent years, with the continuous advancement of deep learning, it has been widely used in image processing, target detection, instance segmentation and other fields. In order to improve image processing and learning capabilities, a variety of image processing models and methods have emerged. Some methods focus on image preprocessing to highlight the characteristics of the tree trunk itself and thus improve the accuracy of model training. Some methods focus on the performance of the model itself, and improve the accuracy of tree trunk segmentation by improving the model's feature extraction capabilities. However, some related studies, such as the paper "SHI L, WANG G, MO L, et al. Automatic Segmentation of Standing Trees from Forest Images Based on Deep Learning [J]. Sensors, 2022, 22 (17).", proposed a lightweight network segmentation model SEMD based on neural networks to segment the entire tree. However, the segmented images contained fewer trees and no environmental interference, and the tree features were more prominent. The paper "GRONDIN V, FORTIN JM, POMERLEAU F, et al. Tree detection and diameter estimation based on deep learning [J]. Forestry, 2023, 96 (2): 264-76." proposed a simulated dataset containing 43K data. The computer simulated the real forest environment and then output a large amount of labeled forest data for training. However, the data output by this method did not take into account complex environmental interference factors, and the trained model did not perform well for tree species that did not exist in the dataset. The paper "LI R, SUN GD, WANG S, et al. Tree trunk detection in urban scenes using a multiscale attention-based deep learning method [J]. Ecological Informatics, 2023, 77." proposed an end-to-end tree trunk detection deep model TrunkNet, which is specifically used to segment complex tree structures. The targets are all single trees and are not suitable for a large number of tree trunk targets in forest environments.

[0004] In recent years, most studies that can eliminate most environmental interference and accurately segment tree trunks are based on three-dimensional point cloud images generated by lidar. The paper "CHANG L, FAN H, ZHU N, et al. A Two-Stage Approach for Individual Tree Segmentation From TLS Point Clouds [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 8682-93." uses lidar to construct point cloud images, and then uses semantic segmentation to divide the point cloud into tree points and non-tree points. Then, by combining object detection and post-processing refinement, the instance segmentation module is used to roughly extract trees, filter out understory vegetation, and increase the probability of extracting small trees. The paper "ITAKURA K, HOSOI F. Automatic Tree Detection from Three-Dimensional Images Reconstructed from 360-degrees Spherical Camera Using YOLO v2 [J]. Remote Sensing, 2020, 12(6)" uses forest images captured by a 360-degree spherical camera and constructs a 3D point cloud image using SFM (Structure From Motion) technology, which greatly reduces the cost of constructing the 3D point cloud image. The YOLOv8 model is then used to segment the trees in the 3D image and extract information such as the tree's diameter at breast height and height. However, these methods are still expensive and are not suitable for tasks such as large-scale forest inventory. Summary of the Invention

[0005] The purpose of this invention is to solve the problem that the existing standing tree instance segmentation method is high in cost and not suitable for large-scale segmentation tasks, and proposes an understory standing tree instance segmentation method based on an improved YOLOv8 model.

[0006] The technical solution adopted by the present invention to solve the above technical problems is: a method for segmenting understory trees based on an improved YOLOv8 model, the method specifically comprising the following steps:

[0007] Step 1: Create a training dataset for segmentation of standing trees under the forest;

[0008] Step 2: Build an improved YOLOv8 model. The improved YOLOv8 model is obtained by improving the original YOLOv8 model. The improvement method is as follows:

[0009] (1) Replace the C2f module of the original YOLOv8 model with the ParC module;

[0010] (2) Replace the SPPF module in the original YOLOv8 model with the SPPF-LSKA module;

[0011] (3) Add the DAT module at the end of the backbone network of the original YOLOv8 model;

[0012] Step 3: Use the training dataset to train the improved YOLOv8 model;

[0013] Step 4: Use the trained improved YOLOv8 model to segment the understory trees in the image to be segmented.

[0014] Furthermore, the specific process of step one is:

[0015] Step 11: Obtain an image dataset containing standing trees under the forest;

[0016] Step 1 and 2: Use annotation tools to annotate the standing trees in the acquired image and generate labels for the image dataset;

[0017] Step 1: Use the image dataset and corresponding labels to form a training dataset.

[0018] Furthermore, the SPPF-LSKA module includes a first Conv layer, a first MaxPool2d layer, a second MaxPool2d layer, a third MaxPool2d layer, a second Conv layer, a first DW-Conv layer, a second DW-Conv layer, a first DW-D-Conv layer, a second DW-D-Conv layer and a third Conv layer.

[0019] Furthermore, the working process of the SPPF-LSKA module is as follows:

[0020] The input F of the SPPF module in the original YOLOv8 model C It serves as the input of the first Conv layer and the first DW-Conv layer;

[0021] The output of the first Conv layer then passes through the first MaxPool2d layer, the second MaxPool2d layer, and the third MaxPool2d layer in sequence;

[0022] The output of the first DW-Conv layer then passes through the second DW-Conv layer:

[0023]

[0024] in, is the convolution kernel of the first DW-Conv layer, is the convolution kernel of the second DW-Conv layer, d is the expansion rate, the subscript is the size of the convolution kernel, and * indicates the convolution operation. is the output of the second DW-Conv layer;

[0025] Then pass through the first DW-D-Conv layer and the second DW-D-Conv layer in sequence:

[0026]

[0027] in, is the convolution kernel of the first DW-D-Conv layer, is the convolution kernel of the second DW-D-Conv layer. The subscript is the size of the convolution kernel. * indicates the convolution operation. Z C is the output of the second DW-D-Conv layer;

[0028] Z C Then pass through the third Conv layer:

[0029] A C =W 1×1 *Z C

[0030] Among them, W 1×1 It is the convolution kernel of the third Conv layer. The subscript is the size of the convolution kernel. * indicates the convolution operation. A C is the output of the third Conv layer;

[0031] Calculate A again C and F C Hadamard product:

[0032]

[0033] in, represents the Hadamard product operation, Indicates A C and F C Hadamard product;

[0034] Will The output of the first Conv layer, the output of the first MaxPool2d layer, the output of the second MaxPool2d layer, and the output of the third MaxPool2d layer are concatenated, and then the concatenation result is passed through the second Conv layer. The output of the second Conv layer is used as the output of the SPPF-LSKA module.

[0035] Furthermore, the working process of the ParC module is:

[0036] Step 1: Embed the vertical basis Generate instance position embedding pe through bilinear interpolation function F(·) V :

[0037]

[0038] in, They are instance position embedding pe V The 0th, 1st, ..., H-1th elements in , the superscript T represents transpose;

[0039] For pe V Copy and pe V Expand to the same dimension as x, and record the expanded matrix as x represents the input feature map of the C2f module in the original YOLOv8 model, the height of x is H, the width of x is W, and the number of channels of x is C;

[0040]

[0041] Among them, W is pe V The number of replications, EV(·) is the horizontal expansion function;

[0042] Will Concatenate with input x: Among them, x p is the result of splicing;

[0043] The splicing result x p Perform convolution and get the convolution result y:

[0044]

[0045] Among them, y i,j is the element in row i and column j of the convolution result y, is the splicing result x p The element in the (i+t) mod H row and j column, (i+t) mod H means calculating the remainder when i+t is divided by H. represent The tth row in ;

[0046] Step 2: Embed the horizontal basis Generate instance position embedding pe through bilinear interpolation function F(·) U :

[0047]

[0048] in, They are instance position embedding peU The 0th, 1st, ..., W-1th elements in ;

[0049] For pe U Copy and pe U Expand to the same dimension as the input x, and record the expanded matrix as

[0050]

[0051] Among them, H is the value of pe U The number of replications, EU(·) is the vertical expansion function;

[0052] Will Concatenate with input x:

[0053] For the splicing result x′ p Perform convolution and obtain the convolution result y′:

[0054]

[0055] Among them, y i ' ,j is the element in row i and column j of the convolution result y′, is the splicing result x′ p The element in the i-th row and the (j+t)modW column, (j+t)modW means calculating the remainder when j+t is divided by W. represent The t-1th column in ;

[0056] Step 3: Concatenate the convolution result y and the convolution result y′, and use the concatenation result as the output of the ParC-Net module.

[0057] Furthermore, the working process of the DAT module is:

[0058] Step ①: record the feature image input by the DAT module as x′∈R H×W×C , downsample the feature image to generate a reference grid, and record the grid point in the reference grid as p. The coordinate value of the grid point p is (0,0),…,(H G -1,W G -1), and then normalize the coordinate values ​​of each grid point to between [-1, +1];

[0059] Among them, (-1,-1) represents the coordinate value of the lower left corner grid point after normalization, and (+1,+1) represents the coordinate value of the upper right corner grid point after normalization;

[0060] Step 2: Perform linear projection on the input feature image x′ to obtain the coordinates q of the feature points in the image:

[0061] q=x′W q

[0062] Among them, W q is the projection matrix;

[0063] Step 3: Input the coordinate q into the offset network and generate the offset Δp through the offset network;

[0064] Step 4: Apply the obtained offset to the grid point to obtain the position of the deformation point;

[0065] Step 5: Sample the deformation point to obtain the feature feature After multi-head attention calculation, the query, key and value output by each attention head are obtained respectively;

[0066]

[0067]

[0068] in, is the key of the mth attention output, is the value output by the mth attention head, and is the parameter matrix of the m-th attention head;

[0069] Then, based on the query, key, and value output by each attention head, we can obtain the features of each attention head’s output:

[0070]

[0071] Where σ(·) represents the softmax function, d = C / M is the size of each attention head, M is the total number of attention heads, and z (m) represents the embedding output of the mth attention head, q (m) represents the query output by the m-th attention head, Indicates the relative offset in the continuous table Interpolation in ;

[0072] Step 6: Express the output of the DAT module as Z = [z (1) ,z (2) ,…,z (M) ].

[0073] Furthermore, the downsampling coefficient is r, H G=H / r,W G =W / r.

[0074] Furthermore, the offset satisfies Δp←stanh(Δp), where s is a preset factor.

[0075] Furthermore, the improved YOLOv8 model replaces the FPN unit in the original YOLOv8 model with a feature fusion unit based on a collection and distribution mechanism, that is, the improved YOLOv8 model includes a Backbone unit, a feature fusion unit based on a collection and distribution mechanism, and a Segment unit;

[0076] The Backbone unit includes a first ConvModule module, a second ConvModule module, a first CSPLayer2Conv-Parc module, a third ConvModule module, a second CSPLayer2Conv-Parc module, a fourth ConvModule module, a third CSPLayer2Conv-Parc module, a fifth ConvModule module, a fourth CSPLayer2Conv-Parc module, an SPPF-LSKA module and a DAT module;

[0077] The feature fusion unit based on the collection and distribution mechanism includes a first SimFusion_4in module, a first FIM module, a sixth ConvModule module, a second SimFusion_4in module, a first InjectionMultiSum module, a first CSPLayer2Conv module, a seventh ConvModule module, a third SimFusion_4in module, a second InjectionMultiSum module, a second CSPLayer2Conv module, a first PyramidPoolAgg module, a first TopBasicLayer module, a first AdvPoolFusion module, a third InjectionMultiSum module, a third CSPLayer2Conv module, a second AdvPoolFusion module, a fourth InjectionMultiSum module and a fourth CSPLayer2Conv module;

[0078] And the working process of the improved YOLOv8 model is:

[0079] The input of the improved YOLOv8 model is used as the input of the first ConvModule module. The output of the first ConvModule module then passes through the second ConvModule module, the first CSPLayer2Conv-Parc module, the third ConvModule module, the second CSPLayer2Conv-Parc module, the fourth ConvModule module, the third CSPLayer2Conv-Parc module, the fifth ConvModule module, the fourth CSPLayer2Conv-Parc module, the SPPF-LSKA module and the DAT module in sequence;

[0080] Use the outputs of the first CSPLayer2Conv-Parc module, the second CSPLayer2Conv-Parc module, the third CSPLayer2Conv-Parc module, and the DAT module as the input of the first SimFusion_4in module;

[0081] Use the output of the first SimFusion_4in module as the input of the first FIM module;

[0082] Use the output of the DAT module as the input of the sixth ConvModule module;

[0083] Use the output of the sixth ConvModule module, the output of the second CSPLayer2Conv-Parc module, and the output of the third CSPLayer2Conv-Parc module as the input of the second SimFusion_4in module;

[0084] Use the output of the second SimFusion_4in module and the output of the first FIM module as the input of the first InjectionMultiSum module;

[0085] Use the output of the first InjectionMultiSum module as the input of the first CSPLayer2Conv module;

[0086] Use the output of the third CSPLayer2Conv-Parc module as the input of the seventh ConvModule module;

[0087] Use the output of the seventh ConvModule module, the first CSPLayer2Conv-Parc module, and the second CSPLayer2Conv-Parc module as the input of the third SimFusion_4in module;

[0088] Use the output of the third SimFusion_4in module and the output of the first FIM module as the input of the second InjectionMultiSum module;

[0089] Use the output of the second InjectionMultiSum module as the input of the second CSPLayer2Conv module;

[0090] Take the output of the DAT module, the output of the first CSPLayer2Conv module, and the output of the second CSPLayer2Conv module as the input of the first PyramidPoolAgg module;

[0091] Use the output of the first PyramidPoolAgg module as the input of the first TopBasicLayer module;

[0092] The output of the seventh ConvModule module and the output of the second CSPLayer2Conv module are used as the input of the first AdvPoolFusion module;

[0093] Take the output of the first TopBasicLayer module and the output of the first AdvPoolFusion module as the input of the third InjectionMultiSum module;

[0094] Use the output of the third InjectionMultiSum module as the input of the third CSPLayer2Conv module;

[0095] Use the output of the third CSPLayer2Conv module and the output of the sixth ConvModule module as the input of the second AdvPoolFusion module;

[0096] Take the output of the first TopBasicLayer module and the output of the second AdvPoolFusion module as the input of the fourth InjectionMultiSum module;

[0097] Use the output of the fourth InjectionMultiSum module as the input of the fourth CSPLayer2Conv module;

[0098] The output of the second CSPLayer2Conv module, the output of the third CSPLayer2Conv module, and the output of the fourth CSPLayer2Conv module are used as the input of the Segment unit, and the output of the Segment unit is used as the output of the improved YOLOv8 model.

[0099] Furthermore, the first InjectionMultiSum module includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a Sigmoid activation function layer, a first avgpool layer, a second avgpool layer and a RepConv-blocks layer;

[0100] And the working process of the first InjectionMultiSum module is:

[0101] The input of the first InjectionMultiSum module is used as the input of the first convolutional layer, the second convolutional layer, and the third convolutional layer respectively;

[0102] The output of the second convolutional layer is used as the input of the Sigmoid activation function layer. The output of the Sigmoid activation function layer passes through the first avgpool layer, and then the Hadamard product of the output of the first convolutional layer and the first avgpool layer is calculated to obtain a;

[0103] The output of the third convolutional layer is used as the input of the second avgpool layer, and the Hadamard product of the output of the second avgpool layer and a is calculated to obtain b;

[0104] Finally, b is passed through the RepConv-blocks layer, and the output of the RepConv-blocks layer is used as the output of the first InjectionMultiSum module.

[0105] The beneficial effects of the present invention are:

[0106] This paper combines improved YOLOv8 deep learning with digital image processing technology to extract the trunk features of standing trees in forest images. This allows for accurate and rapid detection and segmentation of standing tree trunks in complex forest environments, providing a technical approach for studying trunk segmentation in forest environments. By employing digital image processing technology, it achieves precise segmentation of multiple trunk targets simultaneously under complex environmental interference. The targets to be segmented include trunks obscured by branches and bushes, trunks that are far away in the image, and trunk targets of varying sizes. This effectively addresses the problems of low segmentation accuracy and efficiency caused by forest environmental interference, while meeting the practical needs of low-cost and accurate segmentation of a large number of tree trunks in the forest.

[0107] The detection and segmentation accuracy of the improved YOLOv8 model of the present invention reached 88.6% and 87.7%, respectively, which are 9.8% and 8.8% higher than the original YOLOv8 model. In addition, the computational complexity of the method of the present invention is 14GFLOPs, which is much lower than that of existing methods. The frame rate can reach 86.8 frames / s, which is much higher than the frame rate of the comparison model. At the same time, the average detection and segmentation accuracy are 1.8% and 3.6% higher than the best results in the traditional two-stage model. The improved YOLOv8 model is less affected by occlusion between trees and between trees and bushes. It can identify and segment tree trunks of different distances and sizes, and can accurately detect and segment dense tree trunk targets in complex forest environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0108] Figure 1 This is a flowchart of a method for segmenting understory trees based on an improved YOLOv8 model of the present invention;

[0109] Figure 2 This is a comparison chart of the effects of the present invention and the other six algorithms;

[0110] Figure 3 This is a structural diagram of the SPPF module in the YOLOv8 model improved by the SPPF-LSKA module in the present invention;

[0111] Figure 4 This is the workflow diagram of the ParC-Net module;

[0112] Figure 5 This is the flowchart of the variability attention mechanism module;

[0113] Figure 6 This is the structural diagram of the improved YOLOv8 model;

[0114] In the figure, CSPLayer2Conv-Parc represents the addition of Parc after CSPLayer2Conv, that is, the C2f module is replaced by Parc, and then the module composed of CSPLayer2Conv and Parc is used;

[0115] Figure 7 This is the structure diagram of the InjectionMultiSum module. DETAILED DESCRIPTION

[0116] Specific implementation method 1: Combination Figure 1 This embodiment describes a method for segmenting standing trees under a forest based on an improved YOLOv8 model, and the method specifically includes the following steps:

[0117] Step 1: Create a training dataset for segmentation of standing trees under the forest;

[0118] Step 2: Build an improved YOLOv8 model. The improved YOLOv8 model is obtained by improving the original YOLOv8 model. The improvement method is as follows:

[0119] (1) Replace the C2f module of the original YOLOv8 model with the ParC (Position aware circular convolution) module;

[0120] (2) Replace the SPPF module in the original YOLOv8 model with the SPPF-LSKA module;

[0121] (3) Adding a DAT module (Vision Transformer with Deformable Attention) to the end of the backbone network of the original YOLOv8 model;

[0122] Other parts that have not been improved are the same as the original YOLOv8 model;

[0123] Step 3: Use the training dataset to train the improved YOLOv8 model;

[0124] Step 4: Use the trained improved YOLOv8 model to segment the understory trees in the image to be segmented.

[0125] Specific embodiment 2: This embodiment differs from specific embodiment 1 in that the specific process of step 1 is as follows:

[0126] Step 11: Obtain an image dataset containing standing trees under the forest;

[0127] Step 1 and 2: Use annotation tools to annotate the standing trees in the acquired image and generate labels for the image dataset;

[0128] Step 1: Use the image dataset and corresponding labels to form a training dataset.

[0129] Other steps and parameters are the same as those in the first embodiment.

[0130] The labeling tools that can be used in the present invention include but are not limited to the labelme tool. Similarly, the verification dataset can be obtained by using the method for obtaining the training dataset, and the verification dataset can be used to verify the trained model.

[0131] Specific implementation method three: Combination Figure 3This embodiment differs from the first or second embodiment in that the SPPF-LSKA module includes a first Conv layer, a first MaxPool2d layer, a second MaxPool2d layer, a third MaxPool2d layer, a second Conv layer, a first DW-Conv layer, a second DW-Conv layer, a first DW-D-Conv layer, a second DW-D-Conv layer, and a third Conv layer.

[0132] Other steps and parameters are the same as those in the first or second embodiment.

[0133] Specific embodiment 4: This embodiment differs from any one of specific embodiments 1 to 3 in that the working process of the SPPF-LSKA module is as follows:

[0134] The input F of the SPPF module in the original YOLOv8 model C It serves as the input of the first Conv layer and the first DW-Conv layer;

[0135] The output of the first Conv layer then passes through the first MaxPool2d layer, the second MaxPool2d layer, and the third MaxPool2d layer in sequence;

[0136] The output of the first DW-Conv layer then passes through the second DW-Conv layer:

[0137]

[0138] in, is the convolution kernel of the first DW-Conv layer, is the convolution kernel of the second DW-Conv layer, d is the expansion rate, the subscript is the size of the convolution kernel, and * indicates the convolution operation. is the output of the second DW-Conv layer;

[0139] It captures local spatial information and compensates for the kernel size of subsequent depth-expanded convolutions. The grid effect;

[0140] Then pass through the first DW-D-Conv layer and the second DW-D-Conv layer in sequence:

[0141]

[0142] in, is the convolution kernel of the first DW-D-Conv layer, is the convolution kernel of the second DW-D-Conv layer. The subscript is the size of the convolution kernel. * indicates the convolution operation. Z Cis the output of the second DW-D-Conv layer;

[0143] Z C Then pass through the third Conv layer:

[0144] A C =W 1×1 *Z C

[0145] Among them, W 1×1 It is the convolution kernel of the third Conv layer. The subscript is the size of the convolution kernel. * indicates the convolution operation. A C is the output of the third Conv layer;

[0146] Calculate A again C and F C Hadamard product:

[0147]

[0148] in, represents the Hadamard product operation, Indicates A C and F C Hadamard product;

[0149] Will The output of the first Conv layer, the output of the first MaxPool2d layer, the output of the second MaxPool2d layer, and the output of the third MaxPool2d layer are concatenated, and then the concatenation result is passed through the second Conv layer. The output of the second Conv layer is used as the output of the SPPF-LSKA module.

[0150] The other steps and parameters are the same as those in the first to third embodiments.

[0151] like Figure 3 As shown, the LSKA in this embodiment decomposes the two-dimensional convolution kernel of the depth convolution into cascaded horizontal and vertical one-dimensional convolution kernels, so that the depth convolution layer does not cause a quadratic increase in computation and memory usage as the size of the convolution kernel increases, thereby improving the feature extraction capability of the model.

[0152] Specific implementation method five: Combination Figure 4 The difference between this embodiment and the first to fourth embodiments is that the working process of the ParC module is as follows:

[0153] Step 1: Embed the vertical basis Generate instance position embedding pe through bilinear interpolation function F(·) V :

[0154]

[0155] in, They are instance position embedding pe V The 0th, 1st, ..., H-1th elements in , the superscript T represents transpose; The dimensions are C×B×1;

[0156] For pe V Make a copy (that is, the copied vectors are sequentially used as the 2nd column, the 3rd column, ..., the Wth column), and pe V Expand to the same dimension as x, and record the expanded matrix as x represents the input feature map of the C2f module in the original YOLOv8 model, the height of x is H, the width of x is W, and the number of channels of x is C;

[0157]

[0158] Among them, W is pe V The number of replications, EV(·) is the horizontal expansion function;

[0159] Will Concatenate with input x (the concatenation is done by vertical stacking, i.e. Spliced ​​below the input x): Among them, x p is the result of splicing;

[0160] The splicing result x p Perform convolution and get the convolution result y:

[0161]

[0162] Among them, y i,j is the element in row i and column j of the convolution result y, is the splicing result x p The element in the (i+t) mod H row and j column, (i+t) mod H means calculating the remainder when i+t is divided by H. represent The tth row in ;

[0163] Step 2: Embed the horizontal basis Generate instance position embedding pe through bilinear interpolation function F(·) U :

[0164]

[0165] in, They are instance position embedding pe U The 0th, 1st, ..., W-1th elements in ; The dimensions are C×1×B;

[0166] For pe U Make a copy (that is, the copied vectors are sequentially used as the 2nd row, the 3rd row, ..., the Hth row), and pe U Expand to the same dimension as the input x, and record the expanded matrix as

[0167]

[0168] Among them, H is the value of pe U The number of replications, EU(·) is the vertical expansion function;

[0169] Will Concatenate with input x:

[0170] For the splicing result x′ p Perform convolution and obtain the convolution result y′:

[0171]

[0172] Among them, y i ' ,j is the element in row i and column j of the convolution result y′, is the splicing result x′ p The element in the i-th row and the (j+t) mod W column, (j+t) mod W means calculating the remainder when j+t is divided by W. represent The t-1th column in ;

[0173] Step 3: Concatenate the convolution result y and the convolution result y′, and use the concatenation result as the output of the ParC-Net module.

[0174] The other steps and parameters are the same as those in the first to fourth embodiments.

[0175] For input with dimension CHW, the position embedding with dimension CB1 is first adjusted to the dimension CH1 suitable for the input through the bilinear interpolation function F to adapt to the input of features of different sizes, and the pe VThe horizontal copy is expanded to the CHW dimension, and the expanded result is added to the input feature. In addition, the convolution kernel of the CH1 size that adapts to the input dimension is obtained by interpolation, and the convolution operation is performed on the feature addition result, that is, step 1 is equivalent to completing a global information exchange in the vertical direction. For the input of dimension CHW, the PositionEmbedding of dimension CB1 is first adjusted to the dimension CH1 suitable for the input through the bilinear interpolation function F to adapt to the input of features of different sizes, and the pe is copied. H The result is expanded to the CHW dimension and added to the input features. Similarly, a convolution kernel of the size CH1 that adapts to the input dimension is obtained by interpolation. The result of the feature addition is convolved. In other words, step 2 is equivalent to completing a horizontal global information exchange. The ParC-Net module integrates the advantages of visual transformers into convolutional neural networks, and has faster inference speed and better performance than models based on visual transformers.

[0176] Specific implementation method six: combination Figure 5 This embodiment differs from the first to fifth embodiments in that the working process of the DAT module is as follows:

[0177] Step ①: record the feature image input by the DAT module as x′∈R H×W×C , downsample the feature image to generate a reference grid, and record the grid point in the reference grid as p. The coordinate value of the grid point p is (0,0),…,(H G -1,W G -1), and then normalize the coordinate values ​​of each grid point to between [-1, +1];

[0178] Among them, (-1,-1) represents the coordinate value of the lower left corner grid point after normalization, and (+1,+1) represents the coordinate value of the upper right corner grid point after normalization;

[0179] Step 2: Perform linear projection on the input feature image x′ to obtain the coordinates q of the feature points in the image:

[0180] q=x′W q

[0181] Among them, W q is the projection matrix;

[0182] Step 3: Input the coordinate q into the offset network (lightweight subnetwork) and generate the offset Δp = θ through the offset network offset(q) ;

[0183] Step 4: Apply the obtained offset to the grid point to obtain the position of the deformation point;

[0184] Step 5: Perform feature sampling (bilinear interpolation) on the deformation point position to obtain the feature feature After multi-head attention calculation, the query, key and value output by each attention head are obtained respectively;

[0185]

[0186]

[0187] in, is the key of the mth attention output, is the value output by the mth attention head, and is the parameter matrix of the m-th attention head;

[0188] Then, based on the query, key, and value output by each attention head, we can obtain the features of each attention head’s output:

[0189]

[0190] Where σ(·) represents the softmax function, d = C / M is the size of each attention head, M is the total number of attention heads, and z (m) represents the embedding output of the mth attention head, q (m) represents the query output by the m-th attention head, Indicates the relative offset in the continuous table Interpolation in ;

[0191] Step 6: Express the output of the DAT module as Z = [z (1) ,z (2) ,…,z (M) ].

[0192] The other steps and parameters are the same as those in the first to fifth embodiments.

[0193] The addition of a deformable mechanism can narrow the range of the key corresponding to the query, reduce the interference of irrelevant information, enhance information capture, effectively reduce the interference of irrelevant factors in the environment, and improve the ability to detect dense targets.

[0194] Specific embodiment 7: This embodiment differs from any one of specific embodiments 1 to 6 in that the downsampling coefficient is r, H G =H / r,W G =W / r.

[0195] The other steps and parameters are the same as those in the first to sixth embodiments.

[0196] Specific embodiment eight: This embodiment differs from any one of specific embodiments one to seven in that the offset satisfies Δp←stanh(Δp), where “←” indicates that stanh(Δp) approaches Δp, and s is a preset factor (the specific value can be set according to actual conditions).

[0197] The other steps and parameters are the same as those in the first to seventh embodiments.

[0198] In order to stabilize the training process, this embodiment uses a predefined factor to measure the amplitude of Δp to prevent an excessively large offset.

[0199] Specific embodiment 9: This embodiment differs from any one of specific embodiments 1 to 8 in that the improved YOLOv8 model replaces the FPN unit in the original YOLOv8 model with a feature fusion unit based on a collection and distribution mechanism, that is, the improved YOLOv8 model includes a Backbone unit, a feature fusion unit based on a collection and distribution mechanism (i.e., a Neck part), and a Segment unit;

[0200] The Backbone unit includes a first ConvModule module (i.e., the module numbered 0 in the figure), a second ConvModule module (i.e., the module numbered 1 in the figure), a first CSPLayer2Conv-Parc module (i.e., the module numbered 2 in the figure), a third ConvModule module (i.e., the module numbered 3 in the figure), a second CSPLayer2Conv-Parc module (i.e., the module numbered 4 in the figure), a fourth ConvModule module (i.e., the module numbered 5 in the figure), a third CSPLayer2Conv-Parc module (i.e., the module numbered 6 in the figure), a fifth ConvModule module (i.e., the module numbered 7 in the figure), a fourth CSPLayer2Conv-Parc module (i.e., the module numbered 8 in the figure), an SPPF-LSKA module (i.e., the module numbered 9 in the figure), and a DAT module (i.e., the module numbered 10 in the figure);

[0201] The feature fusion unit based on the collection and distribution mechanism includes the first SimFusion_4in module (i.e., the module numbered 11 in the figure), the first FIM module (i.e., the module numbered 12 in the figure), the sixth ConvModule module (i.e., the module numbered 13 in the figure), the second SimFusion_4in module (i.e., the module numbered 14 in the figure), the first InjectionMultiSum module (i.e., the module numbered 15 in the figure), the first CSPLayer2Conv module (i.e., the module numbered 16 in the figure), the seventh ConvModule module (i.e., the module numbered 17 in the figure), the third SimFusion_4in module (i.e., the module numbered 18 in the figure), and the second InjectionMultiSum module (i.e., the module numbered 19 in the figure) , the second CSPLayer2Conv module (i.e., the module numbered 20 in the figure), the first PyramidPoolAgg module (i.e., the module numbered 21 in the figure), the first TopBasicLayer module (i.e., the module numbered 22 in the figure), the first AdvPoolFusion module (i.e., the module numbered 23 in the figure), the third InjectionMultiSum module (i.e., the module numbered 24 in the figure), the third CSPLayer2Conv module (i.e., the module numbered 25 in the figure), the second AdvPoolFusion module (i.e., the module numbered 26 in the figure), the fourth InjectionMultiSum module (i.e., the module numbered 27 in the figure), and the fourth CSPLayer2Conv module (i.e., the module numbered 28 in the figure);

[0202] And the working process of the improved YOLOv8 model is:

[0203] The input of the improved YOLOv8 model is used as the input of the first ConvModule module. The output of the first ConvModule module then passes through the second ConvModule module, the first CSPLayer2Conv-Parc module, the third ConvModule module, the second CSPLayer2Conv-Parc module, the fourth ConvModule module, the third CSPLayer2Conv-Parc module, the fifth ConvModule module, the fourth CSPLayer2Conv-Parc module, the SPPF-LSKA module and the DAT module in sequence;

[0204] Use the outputs of the first CSPLayer2Conv-Parc module, the second CSPLayer2Conv-Parc module, the third CSPLayer2Conv-Parc module, and the DAT module as the input of the first SimFusion_4in module;

[0205] Use the output of the first SimFusion_4in module as the input of the first FIM module;

[0206] Use the output of the DAT module as the input of the sixth ConvModule module;

[0207] Use the output of the sixth ConvModule module, the output of the second CSPLayer2Conv-Parc module, and the output of the third CSPLayer2Conv-Parc module as the input of the second SimFusion_4in module;

[0208] Use the output of the second SimFusion_4in module and the output of the first FIM module as the input of the first InjectionMultiSum module;

[0209] Use the output of the first InjectionMultiSum module as the input of the first CSPLayer2Conv module;

[0210] Use the output of the third CSPLayer2Conv-Parc module as the input of the seventh ConvModule module;

[0211] Use the output of the seventh ConvModule module, the first CSPLayer2Conv-Parc module, and the second CSPLayer2Conv-Parc module as the input of the third SimFusion_4in module;

[0212] Use the output of the third SimFusion_4in module and the output of the first FIM module as the input of the second InjectionMultiSum module;

[0213] Use the output of the second InjectionMultiSum module as the input of the second CSPLayer2Conv module;

[0214] Take the output of the DAT module, the output of the first CSPLayer2Conv module, and the output of the second CSPLayer2Conv module as the input of the first PyramidPoolAgg module;

[0215] Use the output of the first PyramidPoolAgg module as the input of the first TopBasicLayer module;

[0216] The output of the seventh ConvModule module and the output of the second CSPLayer2Conv module are used as the input of the first AdvPoolFusion module;

[0217] Take the output of the first TopBasicLayer module and the output of the first AdvPoolFusion module as the input of the third InjectionMultiSum module;

[0218] Use the output of the third InjectionMultiSum module as the input of the third CSPLayer2Conv module;

[0219] Use the output of the third CSPLayer2Conv module and the output of the sixth ConvModule module as the input of the second AdvPoolFusion module;

[0220] Take the output of the first TopBasicLayer module and the output of the second AdvPoolFusion module as the input of the fourth InjectionMultiSum module;

[0221] Use the output of the fourth InjectionMultiSum module as the input of the fourth CSPLayer2Conv module;

[0222] The output of the second CSPLayer2Conv module, the output of the third CSPLayer2Conv module, and the output of the fourth CSPLayer2Conv module are used as the input of the Segment unit, and the output of the Segment unit is used as the output of the improved YOLOv8 model.

[0223] The other steps and parameters are the same as those in Specific Embodiments 1 to 8.

[0224] By globally fusing multi-level features and injecting global information into higher levels to achieve effective information exchange in YOLO, this significantly enhances the information fusion capability of the neck without significantly increasing the delay, thereby improving the performance of the model on different object sizes. Figure 5 and Figure 6As shown, the collection and distribution process corresponds to three modules. The collection process consists of two steps: first, the FAM collects and aligns features from various levels; second, the IFM fuses the aligned features to generate global information. After obtaining the fused global information from the collection process, the injection module (Inject) distributes this information to various levels and injects it using a simple attention operation, thereby enhancing the detection ability of branches.

[0225] Specific implementation method ten: Combination Figure 7 This embodiment is different from any one of the first to ninth embodiments in that the first InjectionMultiSum module includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a Sigmoid activation function layer, a first avgpool layer, a second avgpool layer, and a RepConv-blocks layer.

[0226] And the working process of the first InjectionMultiSum module is:

[0227] The input of the first InjectionMultiSum module is used as the input of the first convolutional layer, the second convolutional layer, and the third convolutional layer respectively;

[0228] The output of the second convolutional layer is used as the input of the Sigmoid activation function layer. The output of the Sigmoid activation function layer passes through the first avgpool layer, and then the Hadamard product of the output of the first convolutional layer and the first avgpool layer is calculated to obtain a;

[0229] The output of the third convolutional layer is used as the input of the second avgpool layer, and the Hadamard product of the output of the second avgpool layer and a is calculated to obtain b;

[0230] Finally, b is passed through the RepConv-blocks layer, and the output of the RepConv-blocks layer is used as the output of the first InjectionMultiSum module.

[0231] The other steps and parameters are the same as those in Specific Embodiments 1 to 9.

[0232] The working processes of the first InjectionMultiSum module, the second InjectionMultiSum module, and the third InjectionMultiSum module are the same as the working process of the first InjectionMultiSum module.

[0233] It should be noted that the convolutional layers in the SPPF-LSKA module and the InjectionMultiSum module are numbered separately, that is, the first convolutional layer in the SPPF-LSKA module is not the first convolutional layer in the first InjectionMultiSum module, but only represents the first convolutional layer in its own module.

[0234] This paper selected six models for comparative testing, including two classic segmentation models, Mask-R-CNN and Cascade-R-CNN, and four models that were improved on the basis of Mask-R-CNN and Cascade-R-CNN and are specifically designed for standing tree trunk segmentation: Mask-Swin-T, Mask-DB-Swin-T, Cascade-Swin-S, and Cascade-DB-Swin-S. DB refers to the dual backbone (DB) feature extraction method using CBNetV2, and Swin refers to the self-attention moving window strategy of the Swin transformer to improve the efficiency of feature extraction for different objects. To ensure the fairness of the experiment, these models were trained and tested using the default hyperparameters in the same environment.

[0235] Figure 2 The sample results of the improved model of the present invention and other CNN models are shown in Figure 1. It can be seen that the model of the present invention is superior to other models in the segmentation accuracy of densely packed tree trunks, distant tree trunks, heavily occluded tree trunks, and tree trunks of different sizes.

[0236] The above examples are merely illustrative of the calculation model and process of the present invention and are not intended to limit the embodiments of the present invention. Persons skilled in the art will readily appreciate that other variations or modifications based on the above description are possible. This list of embodiments is not exhaustive; however, any obvious variations or modifications derived from the technical solution of the present invention remain within the scope of protection of the present invention.

Claims

1. A method for segmenting standing trees under forests based on an improved YOLOv8 model, characterized in that: The method specifically comprises the following steps: Step 1: Create a training dataset for segmentation of standing trees under the forest; Step 2: Build an improved YOLOv8 model. The improved YOLOv8 model is obtained by improving the original YOLOv8 model. The improvement method is as follows: (1) The ParC module is added after CSPLayer2Conv of the original YOLOv8 model, and then CSPLayer2Conv and Parc are used to form the CSPLayer2Conv-Parc module; (2) Replace the SPPF module in the original YOLOv8 model with the SPPF-LSKA module; (3) Add the DAT module at the end of the backbone network of the original YOLOv8 model; Step 3: Use the training dataset to train the improved YOLOv8 model; Step 4: Use the trained improved YOLOv8 model to segment the understory trees in the image to be segmented.

2. The method for segmenting standing trees under forests based on the improved YOLOv8 model according to claim 1, characterized in that: The specific process of step one is: Step 11: Obtain an image dataset containing standing trees under the forest; Step 1 and 2: Use annotation tools to annotate the standing trees in the acquired image and generate labels for the image dataset; Step 1: Use the image dataset and corresponding labels to form a training dataset.

3. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 2, characterized in that: The SPPF-LSKA module includes a first Conv layer, a first MaxPool2d layer, a second MaxPool2d layer, a third MaxPool2d layer, a second Conv layer, a first DW-Conv layer, a second DW-Conv layer, a first DW-D-Conv layer, a second DW-D-Conv layer and a third Conv layer.

4. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 3, characterized in that: The working process of the SPPF-LSKA module is as follows: The input F of the SPPF module in the original YOLOv8 model C It serves as the input of the first Conv layer and the first DW-Conv layer; The output of the first Conv layer then passes through the first MaxPool2d layer, the second MaxPool2d layer, and the third MaxPool2d layer in sequence; The output of the first DW-Conv layer then passes through the second DW-Conv layer: in, is the convolution kernel of the first DW-Conv layer, is the convolution kernel of the second DW-Conv layer, d is the expansion rate, the subscript is the size of the convolution kernel, and * indicates the convolution operation. is the output of the second DW-Conv layer; Then pass through the first DW-D-Conv layer and the second DW-D-Conv layer in sequence: in, is the convolution kernel of the first DW-D-Conv layer, is the convolution kernel of the second DW-D-Conv layer. The subscript is the size of the convolution kernel. * indicates the convolution operation. Z C is the output of the second DW-D-Conv layer; Z C Then pass through the third Conv layer: AND C =In 1×1 *WITH C Among them, W 1×1 It is the convolution kernel of the third Conv layer. The subscript is the size of the convolution kernel. * indicates the convolution operation. A C is the output of the third Conv layer; Calculate A again C and F C Hadamard product: in, represents the Hadamard product operation, Indicates A C and F C Hadamard product; Will The output of the first Conv layer, the output of the first MaxPool2d layer, the output of the second MaxPool2d layer, and the output of the third MaxPool2d layer are concatenated, and then the concatenation result is passed through the second Conv layer. The output of the second Conv layer is used as the output of the SPPF-LSKA module.

5. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 4, characterized in that: The working process of the ParC module is: Step 1: Embed the vertical basis Generate instance position embedding pe through bilinear interpolation function F(·) V : in, They are instance position embedding pe V The 0th, 1st, ..., H-1th elements in , the superscript T represents transpose; For pe V Copy and pe V Expand to the same dimension as x, and record the expanded matrix as x represents the input feature map of the C2f module in the original YOLOv8 model, the height of x is H, the width of x is W, and the number of channels of x is C; Among them, W is pe V The number of replications, EV(·) is the horizontal expansion function; Will Concatenate with input x: Among them, x p is the result of splicing; The splicing result x p Perform convolution and get the convolution result y: Among them, y i,j is the element in row i and column j of the convolution result y, is the splicing result x p The element in the (i+t) mod H row and j column, (i+t) mod H means calculating the remainder when i+t is divided by H. represent The tth row in ; Step 2: Embed the horizontal basis Generate instance position embedding pe through bilinear interpolation function F(·) U : in, They are instance position embedding pe U The 0th, 1st, ..., W-1th elements in ; For pe U Copy and pe U Expand to the same dimension as the input x, and record the expanded matrix as Among them, H is the value of pe U The number of replications, EU(·) is the vertical expansion function; Will Concatenate with input x: For the splicing result x′ p Perform convolution and obtain the convolution result y′: Among them, y′ i,j is the element in row i and column j of the convolution result y′, is the splicing result x′ p The element in the i-th row and the (j+t)modW column, (j+t)modW means calculating the remainder when j+t is divided by W. represent The t-1th column in ; Step 3: Concatenate the convolution result y and the convolution result y′, and use the concatenation result as the output of the ParC-Net module.

6. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 5, characterized in that: The working process of the DAT module is: Step ①: record the feature image input by the DAT module as x′∈R H×W×C , downsample the feature image to generate a reference grid, and record the grid point in the reference grid as p. The coordinate value of the grid point p is (0,0),…,(H G -1,W G -1), and then normalize the coordinate values ​​of each grid point to between [-1, +1]; Among them, (-1,-1) represents the coordinate value of the lower left corner grid point after normalization, and (+1,+1) represents the coordinate value of the upper right corner grid point after normalization; Step 2: Perform linear projection on the input feature image x′ to obtain the coordinates q of the feature points in the image: q=x′W q Among them, W q is the projection matrix; Step 3: Input the coordinate q into the offsetnetwork and generate the offset Δp through the offsetnetwork; Step 4: Apply the obtained offset to the grid point to obtain the position of the deformation point; Step 5: Sample the deformation point to obtain the feature feature After multi-head attention calculation, the query, key and value output by each attention head are obtained respectively; in, is the key of the mth attention output, is the value output by the mth attention head, and is the parameter matrix of the m-th attention head; Then, based on the query, key, and value output by each attention head, we can obtain the features of each attention head’s output: Where σ(·) represents the softmax function, d = C / M is the size of each attention head, M is the total number of attention heads, and z (m) represents the embedding output of the mth attention head, q (m) represents the query output by the m-th attention head, Indicates the relative offset in the continuous table Interpolation in ; Step 6: Express the output of the DAT module as Z = [z (1) ,z (2) ,…,z (M) ].

7. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 6, characterized in that: The downsampling coefficient of the downsampling process is r, H G =H / r,W G =W / r.

8. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 7, characterized in that: The offset satisfies Δp←stanh(Δp), where s is a preset factor.

9. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 8, characterized in that: The improved YOLOv8 model replaces the FPN unit in the original YOLOv8 model with a feature fusion unit based on a collection and distribution mechanism, that is, the improved YOLOv8 model includes a Backbone unit, a feature fusion unit based on a collection and distribution mechanism, and a Segment unit; The Backbone unit includes a first ConvModule module, a second ConvModule module, a first CSPLayer2Conv-Parc module, a third ConvModule module, a second CSPLayer2Conv-Parc module, a fourth ConvModule module, a third CSPLayer2Conv-Parc module, a fifth ConvModule module, a fourth CSPLayer2Conv-Parc module, an SPPF-LSKA module and a DAT module; The feature fusion unit based on the collection and distribution mechanism includes a first SimFusion_4in module, a first FIM module, a sixth ConvModule module, a second SimFusion_4in module, a first InjectionMultiSum module, a first CSPLayer2Conv module, a seventh ConvModule module, a third SimFusion_4in module, a second InjectionMultiSum module, a second CSPLayer2Conv module, a first PyramidPoolAgg module, a first TopBasicLayer module, a first AdvPoolFusion module, a third InjectionMultiSum module, a third CSPLayer2Conv module, a second AdvPoolFusion module, a fourth InjectionMultiSum module and a fourth CSPLayer2Conv module; And the working process of the improved YOLOv8 model is: The input of the improved YOLOv8 model is used as the input of the first ConvModule module. The output of the first ConvModule module then passes through the second ConvModule module, the first CSPLayer2Conv-Parc module, the third ConvModule module, the second CSPLayer2Conv-Parc module, the fourth ConvModule module, the third CSPLayer2Conv-Parc module, the fifth ConvModule module, the fourth CSPLayer2Conv-Parc module, the SPPF-LSKA module and the DAT module in sequence; Use the outputs of the first CSPLayer2Conv-Parc module, the second CSPLayer2Conv-Parc module, the third CSPLayer2Conv-Parc module, and the DAT module as the input of the first SimFusion_4in module; Use the output of the first SimFusion_4in module as the input of the first FIM module; Use the output of the DAT module as the input of the sixth ConvModule module; Use the output of the sixth ConvModule module, the output of the second CSPLayer2Conv-Parc module, and the output of the third CSPLayer2Conv-Parc module as the input of the second SimFusion_4in module; Use the output of the second SimFusion_4in module and the output of the first FIM module as the input of the first InjectionMultiSum module; Use the output of the first InjectionMultiSum module as the input of the first CSPLayer2Conv module; Use the output of the third CSPLayer2Conv-Parc module as the input of the seventh ConvModule module; Use the output of the seventh ConvModule module, the first CSPLayer2Conv-Parc module, and the second CSPLayer2Conv-Parc module as the input of the third SimFusion_4in module; Use the output of the third SimFusion_4in module and the output of the first FIM module as the input of the second InjectionMultiSum module; Use the output of the second InjectionMultiSum module as the input of the second CSPLayer2Conv module; Take the output of the DAT module, the output of the first CSPLayer2Conv module, and the output of the second CSPLayer2Conv module as the input of the first PyramidPoolAgg module; Use the output of the first PyramidPoolAgg module as the input of the first TopBasicLayer module; The output of the seventh ConvModule module and the output of the second CSPLayer2Conv module are used as the input of the first AdvPoolFusion module; Take the output of the first TopBasicLayer module and the output of the first AdvPoolFusion module as the input of the third InjectionMultiSum module; Use the output of the third InjectionMultiSum module as the input of the third CSPLayer2Conv module; Use the output of the third CSPLayer2Conv module and the output of the sixth ConvModule module as the input of the second AdvPoolFusion module; Take the output of the first TopBasicLayer module and the output of the second AdvPoolFusion module as the input of the fourth InjectionMultiSum module; Use the output of the fourth InjectionMultiSum module as the input of the fourth CSPLayer2Conv module; The output of the second CSPLayer2Conv module, the output of the third CSPLayer2Conv module, and the output of the fourth CSPLayer2Conv module are used as the input of the Segment unit, and the output of the Segment unit is used as the output of the improved YOLOv8 model.

10. The method for segmenting understory trees based on the improved YOLOv8 model according to claim 9, characterized in that: The first InjectionMultiSum module includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a Sigmoid activation function layer, a first avgpool layer, a second avgpool layer and a RepConv-blocks layer; And the working process of the first InjectionMultiSum module is: The input of the first InjectionMultiSum module is used as the input of the first convolutional layer, the second convolutional layer, and the third convolutional layer respectively; The output of the second convolutional layer is used as the input of the Sigmoid activation function layer. The output of the Sigmoid activation function layer passes through the first avgpool layer, and then the Hadamard product of the output of the first convolutional layer and the first avgpool layer is calculated to obtain a; The output of the third convolutional layer is used as the input of the second avgpool layer, and the Hadamard product of the output of the second avgpool layer and a is calculated to obtain b; Finally, b is passed through the RepConv-blocks layer, and the output of the RepConv-blocks layer is used as the output of the first InjectionMultiSum module.

Images