Image positioning recognition model and tea tender stem segmentation positioning method

Abstract

The application provides an image positioning recognition model and a tea tender stem segmentation positioning method.The image positioning recognition model comprises a backbone network, a neck network and a head network, wherein the backbone network is used for acquiring initial feature information of an input picture, the backbone network comprises a multi-path hollow space pyramid pooling module, the multi-path hollow space pyramid pooling module is arranged at an output end of the initial feature information of the backbone network, after feature information of an efficient aggregation layer network (ELAN) is acquired, different receptive field convolution kernels are constructed through different hollow rates, multi-scale object information is acquired, a fixed block pooling operation is adopted to extract significant feature information, then the multi-scale object information and the significant feature information are fused to obtain initial feature information with enhanced significant feature information, and the initial feature information with enhanced significant feature information is output to the neck network, and the application further provides a tea tender stem segmentation positioning method, which can more accurately segment and position tea tender stems.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, in particular to an image positioning and recognition model based on YOLOv7, and also to a method for segmenting and positioning young tea stems implemented by adopting the image positioning and recognition model based on YOLOv7. Background Art

[0002] As the total output value of dry tea continues to rise nationwide, tea planting areas are expanding to meet market demand. However, tea picking requires high standards, and manual picking suffers from low efficiency, high costs, and labor shortages. A new method has emerged on the market, using image recognition to locate picking points and combining it with mechanical equipment for tea picking.

[0003] In a complex natural environment, the region of interest containing young buds may contain interfering information such as old leaves, field ridges, and tea tree branches. In addition, the young tea stems are thin and have unclear texture features. Traditional image processing methods often perform feature extraction based on a specific color space.

[0004] The Zhejiang Sci-Tech University team used tea images in RGB color space as their research subjects. They first segmented the tea leaves using a watershed function, then binarized them to obtain the lowest point of the skeleton outline. Finally, they used the Shi-Tomasi algorithm to determine the picking point for the tea buds. The existing literature, "Research on Identification and Positioning Methods for Tea Buds with a Tea Picking Robot," extracts the GB component from the bud image, performs grayscale processing, and then uses an improved watershed algorithm for segmentation. Finally, the intersection of the minimum matrix and the bud is used as the picking point. The article "Research on Visual Recognition and Picking Point Positioning Methods of Tea Buds" designed super green features (2*Gbr) for segmentation and used edge detection and skeleton processing methods to locate picking points. The article "Research on Recognition and Bionic Picking Finger of High-end Famous Green Tea Buds" segmented based on the two rules of (RB)>80 and (GB)>80 and -1.01*G+0.8*B+0.19*R>99. The article "Research on Recognition of Tea Buds Based on k-means Clustering" used the k-means clustering method to select a and b categories in the Lab color model to segment the bud part. The article "Research on Tea Bud Image Segmentation Method Based on SLIC Superpixels" synthesized a color image with super red, cg, and gb components, and used the SLIC superpixel segmentation method to segment the image.

[0005] However, most traditional image processing methods are not very robust and often need to be performed in a stable experimental environment, with relatively high requirements on the stability of the external environment. In the actual picking process, traditional image processing methods have high limitations.

[0006] In order to more accurately locate the picking points of young shoots in a natural environment, various image recognition deep learning models have emerged on the market, such as the Mask R-CNN (Mask Region-based Convolutional Neural Network) deep learning algorithm, Deeplabv3+, Yolov5m, Yolov7, Yolov8l, etc. The Yolov7 model is one of the commonly used image recognition deep learning models. It is mainly divided into three parts: the backbone network Backbone, the neck network Neck, and the head network Head. After processing by the three major network structures, the final segmentation and positioning results are output.

[0007] However, in the natural environment, tea trees have lush branches and leaves, which are stacked layer upon layer. The young buds often block each other. In addition, the old buds and young buds have similar colors and textures, which makes the segmentation and positioning tasks difficult. As a result, the existing Yolov7 model has a high missed detection rate and false detection rate when segmenting and positioning tea buds. Therefore, it is necessary to improve the Yolov7 model to achieve more accurate segmentation and positioning of tea buds. Summary of the Invention

[0008] In order to solve the problems of thin stalks of young shoots, unclear texture features and difficult positioning in the intelligent tea picking process under complex background in the existing technology, the present invention provides an image positioning and recognition model based on YOLOv7, and also provides a tea shoot segmentation and positioning method implemented by the image positioning and recognition model based on YOLOv7. The YOLOv7-SEG model's ability to learn big data is utilized and optimized to more accurately segment the young shoots.

[0009] The present invention provides an image positioning and recognition model based on yolov7, including a backbone network, a neck network and a head network, wherein:

[0010] Backbone network: used to obtain the initial feature information of the input image. The backbone network includes a multi-path void space pyramid pooling module. The multi-path void space pyramid pooling module is set at the output end of the initial feature information of the backbone network. After obtaining the feature information of the efficient aggregation layer network ELAN, it constructs convolution kernels with different receptive fields through different void rates to obtain multi-scale object information. At the same time, it adopts a fixed block pooling operation to extract significant feature information. Then, the multi-scale object information and the significant feature information are fused to obtain the initial feature information with enhanced significant feature information, which is output to the neck network;

[0011] Neck network: set at the output end of the backbone network, used to establish connections between feature maps at different levels to achieve multi-level feature fusion;

[0012] Head network: It is set at the output end of the neck network and is used to output different results in a cascade manner. It also selects the target area with the highest accuracy through the non-maximum suppression algorithm and outputs the final segmentation and positioning result.

[0013] Furthermore, the backbone network also includes an attention mechanism module. The backbone network is provided with an N-level efficient aggregation layer network ELAN compressed by maximum pooling, where N is a positive integer greater than 1. The multi-path void space pyramid pooling module is provided at the output end of the N-level efficient aggregation layer network ELAN. The output ends of the 1st to N-1-level efficient aggregation layer networks ELAN are respectively provided with N-1 output channels corresponding to the neck network step-by-step upsampling features. The attention mechanism module is provided on the output channel to adjust the parameter weights of the segmentation target and perform channel feature enhancement operations on the feature maps output by the output channels.

[0014] Furthermore, the processing method of the attention mechanism module is:

[0015] (1) For the input feature In∈R H*W*C , the output feature is O out ∈R H*W*C , where H is the number of pixels in the vertical direction of the feature map R, W is the number of pixels in the horizontal direction of the feature map R, and C is the number of channels. The input feature In is regarded as a channel combination In={in0,in1,in2,......,in C-1}, use the global maximum pooling function to converge the feature map to one point, compress the spatial information, and generate a vector q∈R 1*1*C ;

[0016] q=MAX(in k (i,j))(0<k<C,0<i<H,0<j<W)

[0017] Among them, k (i, j) is the spatial feature in the input feature, k is the channel variable, i is the variable of the vertical pixel, and j is the variable of the horizontal pixel;

[0018] (2) compress the vector q and perform ReLU activation function mapping operation, and then restore it to its original length;

[0019] (3) Obtaining the adjusted feature weights limited to the interval [0, 1], the calculation formula of the feature weights is:

[0020] α=δ(F(q))

[0021] Among them, F(·) represents the compression and expansion and ReLU function activation operations, δ(·) represents the activation process of the sigmoid function, and α represents the spatial feature weight vector;

[0022] (4) Take the spatial feature weight vector α as the excitation, act on the input feature In, and calculate the new output feature O out =α*In,(In∈R H*W*C ,α∈R 1*1*C )

[0023] Furthermore, the multi-path dilated spatial pyramid pooling module includes a first 1*1 convolution component, one or more dilated convolution components with different expansion rates, and several pooling pyramid components. The dilated convolution component is used to obtain feature information of different receptive fields. The pooling pyramid component is used to filter out a large number of invalid repeated features in the convolutional neural network and extract feature information with more obvious distinguishing effect.

[0024] The multi-path void space pyramid pooling module also includes a feature splicing component and a second 1*1 convolution component, wherein the first 1*1 convolution component, one or more void convolution components with different expansion rates, and several pooling pyramid components are set in parallel, and their input ends respectively receive the same initial feature information, and their output ends are connected to the input end of the feature splicing component. The output end of the feature splicing component is connected to the input end of the second 1*1 convolution component, and after being processed by the second 1*1 convolution component, it is output to the neck network.

[0025] The present invention also provides a method for segmenting and locating young tea stems using the image positioning and recognition model based on YOLOv7, comprising the following steps:

[0026] S1: Take a certain number of tea bud images to obtain a tea bud image dataset;

[0027] S2: Divide the tea bud image dataset into a training set, a test set, and a validation set according to a certain ratio, for training the image positioning and recognition model based on yolov7 to form a tea bud image positioning and recognition model;

[0028] S3: Input a picture of young tea buds, call the trained tea bud picture positioning and recognition model to segment and locate the picture of young tea buds, and output the final segmentation and positioning result.

[0029] Furthermore, in step S3, the method of calling the trained tea bud image positioning and recognition model to segment and locate the tea bud image is:

[0030] S301: The backbone network processes the tea bud image using convolution operations of different kernel sizes and pooling functions to obtain feature information of the input tea bud image using an efficient aggregation layer network (ELAN).

[0031] S302: Input the acquired feature information to the multi-path dilated spatial pyramid pooling module;

[0032] S303: The multi-path dilated spatial pyramid pooling module constructs convolution kernels with different receptive fields through different dilation rates to obtain multi-scale object information. At the same time, a fixed-block pooling operation is used to extract salient feature information. The multi-scale object information and the salient feature information are then fused to obtain initial feature information with enhanced salient feature information, which is then output to the neck network.

[0033] S304: The neck network is used to establish connections between feature maps at different levels to achieve multi-level feature fusion, and then output the output results of several layers of efficient aggregation layer networks after multi-level feature fusion to the head network respectively;

[0034] S305: The head network outputs different results in a cascade manner, and uses a non-maximum suppression algorithm to screen out the target area with the highest accuracy, and outputs the final segmentation and positioning result.

[0035] Furthermore, an attention mechanism module is set in the backbone network. The backbone network is provided with N levels of efficient aggregation layer networks ELAN compressed by maximum pooling, where N is a positive integer greater than 1. The multi-path void space pyramid pooling module is set at the output end of the N-level efficient aggregation layer network ELAN. The output ends of the 1st to N-1-level efficient aggregation layer networks ELAN are respectively provided with N-1 output channels corresponding to the features of the neck network up-sampled step by step. The attention mechanism module is set on the output channel.

[0036] While steps S302 and S303 are being executed, the step of adjusting the parameter weights of the segmentation target using the attention mechanism module is also included, and a channel feature enhancement operation is performed on the feature map output by the output channel.

[0037] Furthermore, the maximum pooling compressed efficient aggregation layer network ELAN has three levels, and the attention mechanism module includes a first attention mechanism module and a second attention mechanism module. The first attention mechanism module is set at the output end of the first-level efficient aggregation layer network ELAN, and the second attention mechanism module is set at the output end of the second-level efficient aggregation layer network ELAN.

[0038] The neck network is provided with a two-stage upsampling feature splicing component. The first-stage upsampling unit samples the initial feature information output by the multi-path void space pyramid pooling module, and performs feature splicing with the information output by the second attention mechanism module through the feature splicing unit, and outputs it to the first-stage efficient aggregation layer network ELAN-H. The second-stage upsampling unit samples the feature information output by the first-stage efficient aggregation layer network ELAN-H, and performs feature splicing with the information output by the first attention mechanism module through the feature splicing unit, and outputs it to the second-stage efficient aggregation layer network ELAN-H.

[0039] The information output by the second-level efficient aggregation layer network ELAN-H is processed by the feature processing component of the neck network and then outputs multi-level feature information to the head network.

[0040] In step S1, when taking the picture of the tea buds, the camera is set above the tea tree, the height range between the camera and the top layer of the tea tree canopy is 20 to 40 centimeters, and the angle between the camera's shooting angle and the horizontal plane is between 45° and 60°.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: by replacing the MASPP in the YOLOv7 model backbone network with a multi-path void space pyramid pooling module, the observation field of the model can be broadened to obtain multi-scale tender shoot feature information, filter a large number of invalid repeated features in the convolutional neural network, extract feature information with more obvious distinguishing effect, and finally enhance the expression ability of the model by stacking and fusing these features, improve the accuracy of feature recognition, and thus improve the stability of the application.

[0042] By setting an attention mechanism module in the backbone network, the attention mechanism is used to automatically increase the parameter weight of the segmentation target, thereby increasing the model's attention to the segmentation target and improving the model's ability to extract detailed features.

[0043] By training the image positioning and recognition model of the present invention and applying it to the segmentation and positioning of tea leaves, compared with the existing image recognition model, the present invention has a stronger feature extraction capability, can adapt to more complex natural light environments, and more accurately segment and locate tea leaves. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1It is a structural diagram of the existing yolov7 model;

[0046] Figure 2 This is a structural diagram of the image positioning and recognition model based on yolov7 of the present invention;

[0047] Figure 3 This is a schematic diagram of the working principle of an embodiment of a multi-path void space pyramid pooling module of the present invention;

[0048] Figure 4 This is a schematic diagram of the working principle of the attention mechanism module of the present invention;

[0049] Figure 5 Schematic diagram showing the comparison of the accuracy indexes of the yolov7 model and the image positioning and recognition model of the present invention;

[0050] Figure 6 Schematic diagram comparing the recall rate indicators of the yolov7 model and the image positioning and recognition model of the present invention.

[0051] Figure 7 and Figure 8 They are respectively display diagrams of the segmentation and positioning results of tender tea stems according to the present invention. DETAILED DESCRIPTION

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0053] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0055] 1. Model Optimization

[0056] like Figure 1As shown in the figure, the yolov7-seg model is mainly divided into three parts: the backbone network, the neck network, and the head network. The backbone network intensively uses convolution operations with different kernel sizes and pooling functions to obtain the initial features of the input image. In addition, the efficient layer aggregation network (ELAN) is creatively proposed in the yolov7-seg model. This structure repeatedly uses residual structures, multi-path merging, and other methods to enhance the network's feature extraction capabilities without destroying the original network depth. The neck network uses a path aggregation feature pyramid (FPN) structure. The FPN structure combines the multi-resolution scale prediction of SSD and the multi-resolution feature fusion network structure of U-Net. It achieves multi-level feature fusion by establishing connections between feature maps at different levels. The head network outputs different results in a cascade manner, and after non-maximum suppression (NMS), the target area with the highest accuracy is selected to output the final segmentation and positioning results.

[0057] like Figure 2 As described above, the present invention optimizes the above-mentioned yolov7-seg model based on its poor performance in segmentation and positioning of tender tea stems and certain difficulties. The specific optimization points are:

[0058] (1) The multi-path atrous spatial pyramid pooling module MASPP is used to replace SPPCSPC to broaden the model's observation field of view, which is used to obtain multi-scale sprout stem feature information, filter out a large number of invalid repeated features in the convolutional neural network, and extract feature information with more obvious distinguishing effect. Finally, these features are stacked and fused to enhance the model's expressive power.

[0059] (2) The CBS module on the backbone network is replaced by the attention mechanism module SE, and the attention mechanism is used to automatically increase the parameter weight of the segmentation target, thereby increasing the model's attention to the segmentation target and improving the model's ability to extract detailed features.

[0060] Specifically, the image positioning and recognition model based on yolov7 of the present invention also includes a backbone network, a neck network and a head network, wherein:

[0061] Backbone network: used to obtain the initial feature information of the input image. The backbone network includes a multi-path void space pyramid pooling module. The multi-path void space pyramid pooling module is set at the output end of the initial feature information of the backbone network. After obtaining the feature information of the efficient aggregation layer network ELAN, it constructs convolution kernels with different receptive fields through different void rates to obtain multi-scale object information. At the same time, it adopts a fixed block pooling operation to extract significant feature information. Then, the multi-scale object information and the significant feature information are fused to obtain the initial feature information with enhanced significant feature information, which is output to the neck network;

[0062] Neck network: set at the output end of the backbone network, used to establish connections between feature maps at different levels to achieve multi-level feature fusion;

[0063] Head network: It is set at the output end of the neck network and is used to output different results in a cascade manner. It also selects the target area with the highest accuracy through the non-maximum suppression algorithm and outputs the final segmentation and positioning result.

[0064] Among them, Input is input, Output is output, CBS is convolution + normalization + activation function, ELAN is efficient aggregation layer network, MP is Maxpool (maximum pooling) + CBS, Cat is feature splicing module, Up is upsampling module, SE is attention mechanism module, REP is convolution + BN module, Conv is convolution module.

[0065] like Figure 3 As shown, the multi-path dilated spatial pyramid pooling module of the present invention has multiple parallel dilated convolutions with different sampling rates, and the features extracted for each sampling rate are further processed in a separate branch. This module constructs convolution kernels with different receptive fields through different dilation rates to obtain multi-scale object information. At the same time, in order to effectively avoid problems such as image distortion caused by cropping and scaling operations on the image area and solve the problem of repeated feature extraction in convolutional neural networks, multiple fixed-block pooling operations are used to extract relatively significant feature information for inputs of different sizes. In addition, the fusion of features of different sizes has a stronger ability to extract features such as the details and color of the shoot stem.

[0066] As an embodiment of the present invention, the multi-path void space pyramid pooling module of the present invention includes a first 1*1 convolution component, three void convolution components with different expansion rates (expansion rates are 5, 9, and 13, respectively), and four pooling pyramid components (pooling kernel sizes use global pooling functions of 1, 3, 9, and 19, respectively). The void convolution component is used to obtain feature information of different receptive fields, and the pooling pyramid component is used to filter a large number of invalid repeated features in the convolutional neural network and extract feature information with more obvious distinguishing effect.

[0067] The multi-path dilated spatial pyramid pooling module in this example also includes a feature splicing component and a second 1*1 convolution component. The first 1*1 convolution component, three dilated convolution components with different expansion rates, and four pooling pyramid components are set in parallel. Their input ends respectively receive the same initial feature information, and their output ends are connected to the input end of the feature splicing component. The output end of the feature splicing component is connected to the input end of the second 1*1 convolution component. By stacking and fusing these features, the expression ability of the model is enhanced, and then the features are output to the neck network of the subsequent stage.

[0068] like Figure 4 As shown, in the present invention, an attention mechanism module SE is set in the output channel of the backbone network, which can enhance the channel features of the input feature map, and the final SE module output does not change the size of the input feature map.

[0069] The backbone network is provided with N levels of efficient aggregation layer networks ELAN compressed by maximum pooling, where N is a positive integer greater than 1. The multi-path void space pyramid pooling module is arranged at the output end of the N-level efficient aggregation layer network ELAN. The output ends of the 1st to N-1-level efficient aggregation layer networks ELAN are respectively provided with N-1 output channels for feature splicing corresponding to the step-by-step upsampling of the neck network. The attention mechanism module is arranged on the output channel for adjusting the parameter weights of the segmentation target and performing channel feature enhancement operations on the feature maps output by the output channels.

[0070] The attention mechanism module and upsampling in this example are both two-level. The processing method of the attention mechanism module in this example is:

[0071] (1) For the input feature In∈R H*W*C , the output feature is O out ∈R H*W*C , where H is the number of pixels in the vertical direction of the feature map R, W is the number of pixels in the horizontal direction of the feature map R, and C is the number of channels. The input feature In is regarded as a channel combination In={in0,in1,in2,......,in C-1}, use the global maximum pooling function to converge the feature map to one point, compress the spatial information, and generate a vector q∈R 1*1*C ;

[0072] q=MAX(in k (i,j))(0<k<C,0<i<H,0<j<W)

[0073] Among them, k (i, j) is the spatial feature in the input feature, k is the channel variable, i is the variable of the vertical pixel, and j is the variable of the horizontal pixel;

[0074] (2) In order to obtain the recalibrated feature gain, the present invention compresses the vector q and performs a ReLU activation function mapping operation, and then restores it to its original length;

[0075] (3) The sigmoid function is used to obtain the adjusted feature weights limited to the interval [0, 1]. The calculation formula of the feature weights is:

[0076] α=δ(F(q))

[0077] Among them, F(·) represents the compression and expansion and ReLU function activation operations, δ(·) represents the activation process of the sigmoid function, and α represents the spatial feature weight vector;

[0078] (3) Take the spatial feature weight vector α as the excitation, act on the input feature In, and calculate the new output feature O out =α*In,(In∈R H*W*C ,α∈R 1*1*C ), Scale is the size of the output feature map.

[0079] 2. Model Training

[0080] The image positioning and recognition model of the present invention is trained and applied to the segmentation and positioning of tea leaves. The method for segmenting and positioning tea leaves using the image positioning and recognition model based on yolov7 comprises the following steps:

[0081] S1: Take a certain number of tea bud images to obtain a tea bud image dataset;

[0082] S2: Divide the tea bud image dataset into a training set, a test set, and a validation set according to a certain ratio, for training the image positioning and recognition model based on yolov7 to form a tea bud image positioning and recognition model;

[0083] S3: Input a picture of young tea buds, call the trained tea bud picture positioning and recognition model to segment and locate the picture of young tea buds, and output the final segmentation and positioning result.

[0084] The following are examples to illustrate each step.

[0085] In this example, a Nikon D5300 camera was used under natural light conditions. It was placed above the tea tree, and the height from the top of the tea tree canopy was maintained at 20 to 40 cm. The angle between the camera and the horizontal plane was maintained at approximately 45° to 60°.

[0086] Images of Meitan 601 Mingqian tea buds were taken, and 1217 images were obtained after screening and cropping. A tea bud image dataset was established. The dataset was divided into training, test, and validation sets in a ratio of 6:2:2. The training set was then used to train the image positioning and recognition model of the present invention. After training, the test set and validation set were used for testing and verification, respectively.

[0087] 3. Experimental Verification

[0088] 1. Comparison between the yolov7 model and the model of the present invention

[0089] During the testing and verification process, the model evaluation indicators used include precision (P), mean average precision (mAP), and recall (R). The calculation method of each indicator is as follows:

[0090]

[0091] Among them, TP represents the number of positive samples recognized by the model, FP represents the number of negative samples recognized, FN represents the number of positive samples misidentified, AP is the area under the PR curve, and the PR curve consists of the P vertical axis and the R horizontal axis. The larger the PR area, the higher the AP value, which means the detection model is more accurate. AP(n) is the AP value of each category, mAP is the mean AP of all categories, and m represents the number of categories.

[0092] The existing YOLOv7 model (experiment number 1) is compared with the improved YOLOv7 model (experiment numbers 2-4). The test results of various indicators are shown in Table 1.

[0093] Experiment number SE MASPP P R MAP@0.5 1 0.871 0.895 0.916 2 √ 0.920 0.901 0.909 3 √ 0.923 0.900 0.924 4 √ √ 0.932 0.909 0.935

[0094] Table 1 Comparison table of various indicators tested in experiment numbers 1-4

[0095] The comparison of indicators in the training process between Experiment No. 1 (Yolov7 model) and Experiment No. 4 (model of the present invention) is as follows: Figure 5 and Figure 6 As shown, the blue curve represents the training process of the model of the present invention, and the red curve represents the training process of the YOLOv7 model. It can be clearly observed that as the number of training times increases and the model tends to stabilize, the improved YOLOv7-SEG model containing the SE and MASPP modules has higher precision and recall values ​​than the original YOLOv7-SEG model, indicating that the improved YOLOv7-SEG model is better than the original YOLOv7-SEG model in extracting features such as bud stem details and texture.

[0096] 2. Comparison between the model of the present invention and other models

[0097] The model of the present invention is compared with the mainstream image visual recognition models on the market, and the test results of various indicators are shown in Table 2.

[0098] Model P R MAP@0.5 maskRcnn - - 0.498 Deeplabv3+ 0.8825 0.857 - Yolov5m-seg 0.889 0.868 0.914 Yolov7-seg 0.871 0.895 0.916 Yolov8l-seg 0.886 0.884 0.896 Model of the present invention 0.932 0.909 0.935

[0099] Table 2 Comparison table of various model index tests

[0100] As can be observed in Table 2, the proposed model outperforms existing models such as Yolov8l-seg, Yolov5m-seg, Deeplabv3+, maskRcnn, and Yolov7-seg in terms of evaluation indicators such as P, R, and MAP@0.5. This shows that the improved model has stronger feature extraction capabilities, can adapt to more complex natural light environments, and can more accurately segment and locate tea bud stems.

[0101] 3. Positioning and segmentation effect display

[0102] The present invention inputs a picture of young tea buds, calls the trained image positioning and recognition model to segment and locate the picture of young tea buds, and the output effect diagram is as follows: Figure 7 and Figure 8 As shown, the red marked part represents the segmentation and positioning result of the model for the tender shoot rod, d is the identified category, the present invention represents the tender shoot rod category, and the number after d represents the confidence rate of the correct segmentation. It can be seen from the effect diagram that the present invention can accurately identify the tender shoot rod.

[0103] The specific implementation manner described above is a preferred implementation manner of the present invention, and is not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation manner. All equivalent changes made in accordance with the present invention are within the protection scope of the present invention.

Claims

1. An image positioning and recognition model system based on yolov7, characterized in that: It includes backbone network, neck network and head network, among which, Backbone network: used to obtain the initial feature information of the input image. The backbone network includes a multi-path void space pyramid pooling module. The multi-path void space pyramid pooling module is set at the output end of the initial feature information of the backbone network. After obtaining the feature information of the efficient aggregation layer network ELAN, it constructs convolution kernels with different receptive fields through different void rates to obtain multi-scale object information. At the same time, it adopts a fixed block pooling operation to extract significant feature information. Then, the multi-scale object information and the significant feature information are fused to obtain the initial feature information with enhanced significant feature information, which is output to the neck network; Neck network: set at the output end of the backbone network, used to establish connections between feature maps at different levels to achieve multi-level feature fusion; Head network: It is set at the output end of the neck network and is used to output different results in a cascade manner. It also selects the target area with the highest accuracy through the non-maximum suppression algorithm and outputs the final segmentation and positioning results. The backbone network also includes an SE attention mechanism module. The backbone network is provided with N levels of efficient aggregation layer networks ELAN compressed by maximum pooling, where N is a positive integer greater than 1. The multi-path void space pyramid pooling module is arranged at the output end of the N-level efficient aggregation layer network ELAN. The output ends of the 1st to N-1-level efficient aggregation layer networks ELAN are respectively provided with N-1 output channels for feature splicing corresponding to the step-by-step upsampling of the neck network. The SE attention mechanism module is arranged on the output channel to adjust the parameter weights of the segmentation target and perform channel feature enhancement operations on the feature maps output by the output channels.

2. The image positioning and recognition model system based on yolov7 according to claim 1 is characterized in that: The processing method of the SE attention mechanism module is: (1) For input features , the output features are The feature map of R, where H is the number of pixels in the vertical direction of the feature map R, W is the number of pixels in the horizontal direction of the feature map R, and C is the number of channels. Considered as a channel combination , use the global maximum pooling function to converge the feature map to one point, compress the spatial information, and generate a vector ; ， in, is the spatial feature in the input feature, k is the channel variable, i is the vertical pixel variable, and j is the horizontal pixel variable; (2) Vector Perform compression and Relu activation function mapping operations, and then restore to the original length; (3) Obtain the adjusted feature weights limited to the interval [0, 1]. The calculation formula of the feature weights is: Among them, F(•) represents the compression and expansion and ReLU function activation operations, δ(•) represents the activation process of the sigmoid function, and α represents the spatial feature weight vector; (4) Take the spatial feature weight vector α as the excitation, act on the input feature In, and calculate the new output feature , .

3. The image positioning recognition model system based on yolov7 according to claim 1 or 2, characterized in that: The multi-path dilated spatial pyramid pooling module includes a first 1*1 convolution component, one or more dilated convolution components with different expansion rates, and a plurality of pooling pyramid components. The dilated convolution component is used to obtain feature information of different receptive fields. The pooling pyramid component is used to filter a large number of invalid repeated features in the convolutional neural network and extract feature information with more obvious distinguishing effect. The multi-path void space pyramid pooling module also includes a feature splicing component and a second 1*1 convolution component, wherein the first 1*1 convolution component, one or more void convolution components with different expansion rates, and several pooling pyramid components are set in parallel, and their input ends respectively receive the same initial feature information, and their output ends are connected to the input end of the feature splicing component. The output end of the feature splicing component is connected to the input end of the second 1*1 convolution component, and after being processed by the second 1*1 convolution component, it is output to the neck network.

4. A method for segmenting and locating young tea stems, implemented using the image positioning and recognition model system based on YOLOv7 according to any one of claims 1 to 3, characterized in that: The steps include: S1: Take a certain number of tea bud images to obtain a tea bud image dataset; S2: Divide the tea bud image dataset into a training set, a test set, and a validation set according to a certain ratio, for training the image positioning and recognition model based on yolov7 to form a tea bud image positioning and recognition model; S3: Input a picture of young tea buds, call the trained tea bud picture positioning and recognition model to segment and locate the picture of young tea buds, and output the final segmentation and positioning result.

5. The method for segmenting and positioning young tea stems according to claim 4, characterized in that: In step S3, the method of calling the trained tea bud image positioning and recognition model to segment and locate the tea bud image is as follows: S301: The backbone network processes the tea bud image using convolution operations of different kernel sizes and pooling functions to obtain feature information of the input tea bud image using an efficient aggregation layer network (ELAN). S302: Input the acquired feature information to the multi-path dilated spatial pyramid pooling module; S303: The multi-path dilated spatial pyramid pooling module constructs convolution kernels with different receptive fields through different dilation rates to obtain multi-scale object information. At the same time, a fixed-block pooling operation is used to extract salient feature information. The multi-scale object information and the salient feature information are then fused to obtain initial feature information with enhanced salient feature information, which is then output to the neck network. S304: The neck network is used to establish connections between feature maps at different levels to achieve multi-level feature fusion, and then output the output results of several layers of efficient aggregation layer networks after multi-level feature fusion to the head network respectively; S305: The head network outputs different results in a cascade manner, and uses a non-maximum suppression algorithm to screen out the target area with the highest accuracy, and outputs the final segmentation and positioning result.

6. The method for segmenting and positioning young tea stems according to claim 5, characterized in that: An SE attention mechanism module is set in the backbone network. The backbone network is provided with an N-level efficient aggregation layer network ELAN compressed by maximum pooling, where N is a positive integer greater than 1. The multi-path void space pyramid pooling module is set at the output end of the N-level efficient aggregation layer network ELAN. The output ends of the 1st to N-1-level efficient aggregation layer networks ELAN are respectively provided with N-1 output channels corresponding to the features of the neck network up-sampled step by step. The SE attention mechanism module is set on the output channel. While steps S302 and S303 are being executed, the SE attention mechanism module is also used to adjust the parameter weights of the segmentation target, and a channel feature enhancement operation is performed on the feature map output by the output channel.

7. The method for segmenting and positioning young tea stems according to claim 6, characterized in that: The maximum pooling compressed efficient aggregation layer network ELAN has three levels, and the SE attention mechanism module includes a first SE attention mechanism module and a second SE attention mechanism module. The first SE attention mechanism module is set at the output end of the first-level efficient aggregation layer network ELAN, and the second SE attention mechanism module is set at the output end of the second-level efficient aggregation layer network ELAN. The neck network is provided with a two-stage upsampling feature splicing component. The first-stage upsampling unit samples the initial feature information output by the multi-path void space pyramid pooling module, and performs feature splicing with the information output by the second SE attention mechanism module through the feature splicing unit, and outputs it to the first-stage efficient aggregation layer network ELAN-H. The second-stage upsampling unit samples the feature information output by the first-stage efficient aggregation layer network ELAN-H, and performs feature splicing with the information output by the first SE attention mechanism module through the feature splicing unit, and outputs it to the second-stage efficient aggregation layer network ELAN-H. The information output by the second-level efficient aggregation layer network ELAN-H is processed by the feature processing component of the neck network and then outputs multi-level feature information to the head network.

8. The method for segmenting and positioning young tea stems according to any one of claims 5 to 7, characterized in that: In step S1, when taking the picture of the tea buds, the camera is set above the tea tree, the height range between the camera and the top layer of the tea tree canopy is 20~40 cm, and the angle between the camera's shooting angle and the horizontal plane is between 45°~60°.

Images