Multi-target sperm movement analysis and evaluation method and system based on YOLOv11 improvement
By improving the YOLOv11 model and multi-scale differential fusion module, combined with the ID correction mechanism, the automation and efficient identification of sperm motion analysis are achieved, and the simple problems of artificial subjective judgment and algorithms in the existing technology are solved, and the accuracy and efficiency of sperm motion analysis are improved.
Patent Information
- Application Number
- CN202510411154.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-02
- Publication Date
- 2025-08-01
AI Technical Summary
The existing sperm analysis methods mainly rely on artificial technology, and there are large differences in subjective judgments and insufficient algorithm analysis, which leads to inaccurate identification of sperm motor indicators.
The multi-objective sperm motor analysis method based on YOLOv11 is adopted. By adding a multi-scale differential fusion module to YOLOv11, sperm position prediction and kinematic parameter analysis are realized, multi-objective cross collision is handled in combination with the ID correction mechanism, and real-time display and evaluation are used for upper computer interface.
It realizes fully automatic identification and detection and analysis of sperm multi-objectives, reduces manual operation errors, improves detection efficiency, and updates in real time through the pyqt architecture's upper computer interface, reducing time costs.
Smart Images

Figure CN120411162A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of assisted reproductive technologies, and particularly to a multi-object sperm movement analysis and evaluation method and system improved based on YOLOv11. Background Art
[0002] The existing sperm analysis methods in hospitals mainly adopt manual techniques, which have a large number of subjective judgments and possible differential events caused by insufficient sampling quantity. In related technologies, the analysis of sperm movement and other related indicators through algorithms is also relatively simple. Usually, a simple network is used for recognition without specific analysis and evaluation.
[0003] Therefore, it is necessary to provide a new method to solve the above technical problems. Summary of the Invention
[0004] To achieve the above objects and other advantages of the present invention, the first object of the present invention is to provide a multi-object sperm movement analysis and evaluation method improved based on YOLOv11, including the following steps:
[0005] Decompose the video frame by frame into images;
[0006] Perform object recognition on sperm in the images based on the YOLOv11 improved model to predict the sperm positions; wherein, the YOLOv11 improved model is obtained by adding a multi-scale difference fusion module to YOLOv11;
[0007] Analyze the kinematic parameters of the sperm through the predicted sperm positions to predict the sperm positions in the next frame;
[0008] Evaluate the sperm by analyzing the sperm trajectories and related movement parameters.
[0009] Further, the step of analyzing the kinematic parameters of the sperm through the predicted sperm positions to predict the sperm positions in the next frame further includes:
[0010] Correct the assigned ID when multiple object cross-collisions occur.
[0011] Further, the step of correcting the assigned ID when multiple object cross-collisions occur includes:
[0012] Judge whether the coincidence degree between the predicted box and the ground truth box is less than the threshold;
[0013] If not, successfully match the same ID;
[0014] If so, judge whether a trajectory with a relatively close unassigned ID can be found;
[0015] If a trajectory with a relatively close unassigned ID can be found, then select the trajectory with the smallest number of lost frames to successfully match the same ID;
[0016] If a trajectory with a relatively close unassigned ID cannot be found, then generate a new ID trajectory to successfully match the same ID.
[0017] Further, the multi-scale difference fusion module processes the output of the convolutional block in the YOLOv11 backbone network through the first multi-scale feature fusion unit and then inputs it into the channel convolutional block through the first element-wise addition. The output of the upsampling in the YOLOv11 neck network is processed through the second multi-scale feature fusion unit and then input into the channel convolutional block through the second element-wise addition. The output of the convolutional block in the YOLOv11 backbone network and the output of the upsampling in the YOLOv11 neck network are successively subjected to element-wise subtraction, absolute value, convolutional layer, and activation function processing. The result of the activation function processing is subjected to the first element-wise multiplication and then processed through the first element-wise addition. The result of the activation function processing is subjected to the second element-wise multiplication and then processed through the second element-wise addition. After the result of the activation function processing and the output of the channel convolutional block are subjected to the third element-wise multiplication, they are further processed through a convolutional layer and output to the convolutional block in the YOLOv11 neck network.
[0018] Further, between the step of predicting the sperm position in the next frame by analyzing the kinematic parameters of the sperm based on the predicted sperm position and the step of evaluating the sperm by analyzing the sperm trajectory and related motion parameters, it further includes:
[0019] Perform real-time display of the ID and trajectory of the position information output by the model.
[0020] Further, after the step of evaluating the sperm by analyzing the sperm trajectory and related motion parameters, it further includes the step of:
[0021] Perform real-time update display of the sperm image, sperm trajectory, and sperm evaluation parameters.
[0022] The second object of the present invention is to provide a multi-object sperm motion analysis and evaluation system improved based on YOLOv11, applying the above method, including a host computer interface, a YOLOv11 improved model, a tracker, and a host computer; wherein,
[0023] The host computer interface is used to select target video data, decompose the video data frame by frame into images and return them to the host computer and transmit them to the YOLOv11 improved model, and display the predicted positions of the corresponding sperm in a trajectory and output them to the host computer;
[0024] After preprocessing the image data, the improved YOLOv11 model passes the data through its backbone network, neck network, and head network in sequence, and transmits the predicted sperm positions to the host computer and the tracker.
[0025] The tracker analyzes the kinematic parameters based on the predicted sperm positions to predict the sperm positions in the next frame.
[0026] The host computer evaluates the sperm by analyzing the sperm trajectories and related kinematic parameters.
[0027] Furthermore, the improved YOLOv11 model is written in Python, and the host computer interface is constructed using PyQt.
[0028] The third object of the present invention is to provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.
[0029] The fourth object of the present invention is to provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.
[0030] Compared with the prior art, the beneficial effects of the present invention are:
[0031] The present invention provides a multi-object sperm motion analysis and evaluation method and system based on the improved YOLOv11, which can realize the full-automatic recognition, detection, analysis, and evaluation of multiple sperm targets, and display and update in real time through the host computer interface based on the PyQt architecture, improving the detection efficiency and greatly reducing the redundant time cost in the manual operation process. In addition, the system effectively reduces the errors caused by manual operation through accurate model recognition to achieve full-automatic detection, recognition, and analysis.
[0032] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly and implement it according to the content of the specification, the following takes the preferred embodiments of the present invention and describes them in detail in conjunction with the drawings. The specific implementation manners of the present invention are given in detail by the following embodiments and their accompanying drawings. Description of the Drawings
[0033] The drawings described herein are used to provide a further understanding of the present invention, and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0034] Figure 1 It is a schematic diagram of the multi-object sperm motion analysis and evaluation principle based on the improved YOLOv11;
[0035] Figure 2 It is a flow chart for multi-object sperm motility analysis and evaluation improved based on YOLOv11;
[0036] Figure 3 It is a schematic diagram of the improved YOLOv11 model;
[0037] Figure 4 It is a structural diagram of the multi-scale difference fusion module;
[0038] Figure 5 It is a schematic diagram of the training results of the improved YOLOv11 model;
[0039] Figure 6 It is a schematic diagram of the training confusion matrix of the improved YOLOv11 model;
[0040] Figure 7 It is a flow chart for correcting the tracker ID assignment logic;
[0041] Figure 8 It is the host computer display interface;
[0042] Figure 9 It is a schematic diagram of the computer device;
[0043] Figure 10 It is a schematic diagram of the computer-readable storage medium. Specific implementation manners
[0044] Next, in combination with the accompanying drawings and specific implementation manners, the present invention will be further described. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be noted that, on the premise of no conflict, any combination of the following-described embodiments or technical features can form a new embodiment.
[0045] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.
[0046] In this application, the accompanying drawing numbers are only used to distinguish each step in the solution and are not used to limit the execution order of each step. The specific execution order shall be subject to the description in the specification.
[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.
[0048] Embodiment 1
[0049] A multi-object sperm motility analysis and evaluation method improved based on YOLOv11, which realizes accurate and efficient kinematic analysis and evaluation during sperm detection, such as Figure 1 - Figure 2 shown, the method includes the following steps:
[0050] Video data loading: Decompose the video frame by frame into images and transmit them to the host computer and subsequent models;
[0051] YOLOv11 improved model: Based on the YOLOv11 improved model, perform object recognition on sperm in the image to predict the sperm position;
[0052] Among them, the YOLOv11 improved model is obtained by adding a multi-scale difference fusion module to YOLOv11. The training results of the YOLOv11 improved model are as Figure 5 shown, and the training confusion matrix of the YOLOv11 improved model is as Figure 6 shown; Adding a multi-scale difference fusion module to YOLOv11 improves its accuracy. As Figure 3 、 Figure 4 shown, YOLOv11 includes a backbone network, a neck network, and a head network. The input of the multi-scale difference fusion module is connected to the convolutional block of the backbone network and the upsampling of the neck network. The output of the multi-scale difference fusion module is connected to the convolutional block of the neck network. The multi-scale difference fusion module processes the output of the convolutional block in the YOLOv11 backbone network through the first multi-scale feature fusion unit and then inputs it into the channel convolutional block through the first element-wise addition. The output of the upsampling in the YOLOv11 neck network is processed through the second multi-scale feature fusion unit and then input into the channel convolutional block through the second element-wise addition. The output of the convolutional block in the YOLOv11 backbone network and the output of the upsampling in the YOLOv11 neck network are successively subjected to element-wise subtraction, absolute value, convolutional layer, and activation function processing. The result of the activation function processing is processed through the first element-wise multiplication through the first element-wise addition, and the result of the activation function processing is processed through the second element-wise multiplication through the second element-wise addition. The result of the activation function processing and the output of the channel convolutional block are processed through the third element-wise multiplication and then output to the convolutional block in the YOLOv11 neck network after passing through the convolutional layer.
[0053] Tracker: Analyze the kinematic parameters based on the predicted sperm position to predict the sperm position in the next frame;
[0054] In some embodiments, the step of analyzing the kinematic parameters based on the predicted sperm position to predict the sperm position in the next frame further includes:
[0055] When multiple targets cross and collide, correct the assigned ID.
[0056] Furthermore, as Figure 7As shown, the step of correcting the assigned ID when multiple target intersections occur includes:
[0057] Determine whether the degree of overlap (IoU) between the predicted box and the ground truth box is less than the threshold;
[0058] If not, successfully match the same ID;
[0059] If so, determine whether a trajectory with a relatively close distance and unassigned ID can be found;
[0060] If a trajectory with a relatively close distance and unassigned ID can be found, select the trajectory with the smallest number of lost frames and successfully match the same ID;
[0061] If a trajectory with a relatively close distance and unassigned ID cannot be found, generate a new ID trajectory and successfully match the same ID.
[0062] Sperm trajectory display: Real-time display of the ID and trajectory of the position information output by the model;
[0063] Sperm motility evaluation: Evaluate sperm by analyzing sperm trajectories and related motility parameters.
[0064] Host computer interface: Real-time update and display of sperm images, sperm trajectories, sperm evaluation parameters, etc., as Figure 8 shown.
[0065] Repeat the steps of target recognition of sperm in the image based on the improved YOLOv11 model to predict the sperm position to the step of evaluating sperm by analyzing sperm trajectories and related motility parameters, and perform sperm detection and evaluation on the next frame of image.
[0066] The YOLO model is written in the Python language, and the host computer interface is built using PyQt to ensure language unity between the model and the interface.
[0067] The present invention provides a multi-target sperm motility analysis and evaluation method based on the improved YOLOv11, which can realize full-automatic recognition, detection, analysis and evaluation of multiple sperm targets, and real-time display and update through the host computer interface with a PyQt architecture, improving the detection efficiency and greatly reducing the redundant time cost in the manual operation process. In addition, the system effectively reduces the errors caused by manual operation through accurate model recognition to achieve full-automatic detection, recognition and analysis.
[0068] Example 2
[0069] A multi-object sperm motility analysis and evaluation system improved based on YOLOv11 realizes accurate and efficient kinematic analysis and evaluation during sperm detection. For the detailed description of the method, reference can be made to the corresponding description in the above method embodiments, which will not be elaborated here. As Figure 1 - Figure 2 shown, the system includes a host computer interface, an improved YOLOv11 model, a tracker, and a host computer; among them,
[0070] The host computer interface is used to select target video data, decompose the video data frame by frame into images and return them to the host computer and transmit them to the improved YOLOv11 model, and display the predicted positions of the corresponding spermatozoa in a trajectory and output them to the host computer;
[0071] Optionally, select the target video data through the host computer interface keys, split the video data frame by frame into picture data and return it to the host computer and transmit it to the model.
[0072] After the improved YOLOv11 model performs operations such as data preprocessing on the image, the data passes through the internal backbone network, neck network, and head network in sequence, and transmits the predicted positions of the spermatozoa output by it to the host computer and the tracker;
[0073] The tracker analyzes the kinematic parameters through the predicted sperm positions to predict the sperm positions in the next frame;
[0074] The host computer evaluates the spermatozoa by analyzing the sperm trajectories and related kinematic parameters.
[0075] Furthermore, the improved YOLOv11 model is written in the Python language, and the host computer interface is built using PyQt to ensure the language unity between the model and the interface.
[0076] Based on the technical solution of the above embodiment, optionally, the step of predicting the sperm positions in the next frame by analyzing the kinematic parameters through the predicted sperm positions further includes:
[0077] When multiple target intersections and collisions occur, correct the assigned ID.
[0078] Based on the technical solution of the above embodiment, optionally, the step of correcting the assigned ID when multiple target intersections and collisions occur includes:
[0079] Judge whether the coincidence degree between the predicted box and the real box is less than the threshold;
[0080] If not, successfully match the same ID;
[0081] If so, judge whether a trajectory with a relatively close unassigned ID can be found;
[0082] If a trajectory with a nearby unassigned ID can be found, then select the trajectory with the smallest number of lost frames to successfully match the same ID;
[0083] If a trajectory with a nearby unassigned ID cannot be found, then generate a new ID trajectory to successfully match the same ID.
[0084] Based on the technical solution of the above embodiment, optionally, the multi-scale difference fusion module processes the output of the convolutional block in the YOLOv11 backbone network through the first multi-scale feature fusion unit and then inputs it into the channel convolutional block through the first element-wise addition. The output of the upsampling in the YOLOv11 neck network is processed through the second multi-scale feature fusion unit and then input into the channel convolutional block through the second element-wise addition. The output of the convolutional block in the YOLOv11 backbone network and the output of the upsampling in the YOLOv11 neck network are successively subjected to element-wise subtraction, absolute value, convolutional layer, and activation function processing. The result of the activation function processing is subjected to the first element-wise multiplication and then the first element-wise addition processing. The result of the activation function processing is subjected to the second element-wise multiplication and then the second element-wise addition processing. The result of the activation function processing and the output of the channel convolutional block are subjected to the third element-wise multiplication processing and then passed through a convolutional layer for output to the convolutional block in the YOLOv11 neck network.
[0085] Based on the technical solution of the above embodiment, optionally, between the step of predicting the sperm position in the next frame by analyzing the kinematic parameters of the sperm based on the predicted sperm position and the step of evaluating the sperm by analyzing the sperm trajectory and related motion parameters, the following is further included:
[0086] Perform real-time display of the ID and trajectory of the position information output by the model.
[0087] Based on the technical solution of the above embodiment, optionally, after the step of evaluating the sperm by analyzing the sperm trajectory and related motion parameters, the following step is further included:
[0088] Perform real-time update display of the sperm image, sperm trajectory, and sperm evaluation parameters.
[0089] The present invention provides a multi-object sperm motion analysis and evaluation system improved based on YOLOv11, which can realize full-automatic recognition, detection, analysis, and evaluation of multiple sperm targets, and perform real-time display and update through the upper computer interface with the pyqt architecture, improve the detection efficiency, and greatly reduce the redundant time cost in the manual operation process. In addition, the system effectively reduces the error caused by manual operation through accurate model recognition to achieve full-automatic detection, recognition, and analysis.
[0090] Embodiment 3
[0091] A computer device 100, such as Figure 9As shown, it includes a memory 110, a processor 120, and a computer program 130 stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a multi-object sperm motility analysis and evaluation method improved based on YOLOv11. For a detailed description of the method, reference can be made to the corresponding description in the above method embodiments, which will not be elaborated here.
[0092] Embodiment 4
[0093] A computer-readable storage medium, as Figure 10 shown, stores a computer program thereon. When the computer program is executed by a processor, it implements the steps of a multi-object sperm motility analysis and evaluation method improved based on YOLOv11. For a detailed description of the method, reference can be made to the corresponding description in the above method embodiments, which will not be elaborated here.
[0094] The number of devices and the scale of processing described here are used to simplify the description of the present invention. Applications, modifications, and variations of the present invention will be apparent to those skilled in the art.
[0095] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. It can be fully applied to various fields suitable for the present invention. For those familiar with the field, additional modifications can be easily made. Therefore, without departing from the general concept defined by the claims and the equivalent scope, the present invention is not limited to specific details and the examples shown and described here.
[0096] The devices, computer devices, non-volatile computer storage media provided in the embodiments of this specification correspond to the methods. Therefore, the devices, computer devices, and non-volatile computer storage media also have beneficial technical effects similar to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding devices, computer devices, and non-volatile computer storage media will not be elaborated here.
[0097] Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, the method steps can be logically programmed to enable the controller to be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same functions. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software units for implementing the method and structures within the hardware component.
[0098] The systems, devices or units illustrated in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. For the convenience of description, when describing the above devices, they are divided into various units according to their functions and described separately. Of course, when implementing one or more embodiments of this specification, the functions of each unit may be implemented in the same or multiple software and / or hardware.
[0099] Those skilled in the art should understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0100] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0101] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0103] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.
[0104] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program units. Generally, program units include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program units may be located in local and remote computer storage media including storage devices.
[0105] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the relevant parts of the method embodiments for the related content.
[0106] The above is only for the embodiments of this specification and is not used to limit one or more embodiments of this specification. For those skilled in the art, various changes and modifications can be made to one or more embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of one or more embodiments of this specification.
Claims
1. A multi-object sperm motility analysis and evaluation method improved based on YOLOv11, characterized in that It includes the following steps: Decompose the video frame by frame into images; Perform object recognition on sperm in the images based on the improved YOLOv11 model to predict the sperm positions; wherein, the improved YOLOv11 model is obtained by adding a multi-scale difference fusion module to YOLOv11; Analyze the kinematic parameters based on the predicted sperm positions to predict the sperm positions in the next frame; Evaluate the sperm by analyzing the sperm trajectories and related kinematic parameters.
2. The multi-object sperm motility analysis and evaluation method improved based on YOLOv11 according to claim 1, wherein The step of analyzing the kinematic parameters based on the predicted sperm positions to predict the sperm positions in the next frame further includes: Correct the assigned ID when multiple object cross-collisions occur.
3. The multi-object sperm motility analysis and evaluation method improved based on YOLOv11 according to claim 2, characterized in that, The step of correcting the assigned ID when multiple object cross-collisions occur includes: Judge whether the overlap degree between the predicted box and the ground truth box is less than the threshold; If not, successfully match the same ID; If so, judge whether a trajectory with a relatively close distance and an unassigned ID can be found; If a trajectory with a relatively close distance and an unassigned ID can be found, select the trajectory with the minimum number of lost frames and successfully match the same ID; If a trajectory with a relatively close distance and an unassigned ID cannot be found, generate a new ID trajectory and successfully match the same ID.
4. A multi-object sperm motility analysis and evaluation method improved based on YOLOv11 according to claim 1, characterized in that: The multi-scale difference fusion module processes the output of the convolutional block in the YOLOv11 backbone network through the first multi-scale feature fusion unit and then inputs it into the channel convolutional block through the first element-wise addition. The output of the upsampling in the YOLOv11 neck network is processed through the second multi-scale feature fusion unit and then input into the channel convolutional block through the second element-wise addition. The output of the convolutional block in the YOLOv11 backbone network and the output of the upsampling in the YOLOv11 neck network are successively subjected to element-wise subtraction, absolute value, convolutional layer, and activation function processing. The result of the activation function processing is subjected to the first element-wise multiplication and then the first element-wise addition processing, the result of the activation function processing is subjected to the second element-wise multiplication and then the second element-wise addition processing, and the result of the activation function processing and the output of the channel convolutional block are subjected to the third element-wise multiplication processing and then passed through the convolutional layer for output to the convolutional block in the YOLOv11 neck network.
5. The multi-object sperm motility analysis and evaluation method improved based on YOLOv11 according to claim 1, characterized in that Between the step of analyzing the kinematic parameters based on the predicted sperm positions to predict the sperm positions in the next frame and the step of evaluating the sperm by analyzing the sperm trajectories and related kinematic parameters, it further includes: Perform real-time display of the ID and trajectory of the position information output by the model.
6. The multi-object sperm motility analysis and evaluation method improved based on YOLOv11 according to claim 1, characterized in that After the step of evaluating the sperm by analyzing the sperm trajectories and related kinematic parameters, it further includes the step: Perform real-time update display of the sperm images, sperm trajectories, and sperm evaluation parameters.
7. A multi-object sperm motility analysis and evaluation system improved based on YOLOv11, applying the method according to any one of claims 1 to 6, characterized in that: It includes a host computer interface, an improved YOLOv11 model, a tracker, and a host computer; wherein, The host computer interface is used to select the target video data, decompose the video data frame by frame into images and return them to the host computer and transmit them to the improved YOLOv11 model, and display the predicted positions of the corresponding sperm in a trajectory and output them to the host computer; After preprocessing the image data, the improved YOLOv11 model passes the data through the backbone network, neck network, and head network inside it in sequence, and transmits the predicted sperm positions output by it to the host computer and the tracker; The tracker analyzes the kinematic parameters through the predicted sperm positions to predict the sperm positions in the next frame; The host computer evaluates the sperm by analyzing the sperm trajectories and related motion parameters.
8. A multi-object sperm motility analysis and evaluation system improved based on YOLOv11 as claimed in claim 7, characterized in that: The improved YOLOv11 model is written in the Python language, and the host computer interface is constructed using PyQt.
9. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.