A silkworm mature state detection system based on improved YOLOv8

Abstract

The application relates to the technical field of silkworm breeding, and discloses a silkworm mature state detection system based on an improved YOLOv8. An image data of silkworms is collected by a collection unit, an image recognition model of instance segmentation is used by a model unit to recognize silkworms in the image data, an iteration unit is used to update and iterate the image recognition model before image recognition, an algorithm unit gives algorithm support to the model unit, a processing unit cuts the silkworm images recognized by the model unit and calculates a volume change rate TJ and a color change rate YS, a central unit receives the volume change rate TJ and the color change rate YS sent by the processing unit and calculates a judgment value P. The application recognizes silkworms in the image data through the improved YOLOv8 image recognition model of instance segmentation, induces the characteristics of mature silkworms and immature silkworms, and quickly and accurately classifies and counts the number of various silkworms.

Description

Technical Field

[0001] This invention relates to the field of silkworm breeding technology, and more specifically to a silkworm maturity status detection system based on an improved YOLOv8. Background Technology

[0002] Silkworms are insects belonging to the genus Bombyx moth in the family Bombycidae of the order Lepidoptera. The silk they spin is an important textile raw material. Mulberry silkworms spin cocoons to produce mulberry silk, which is mostly white and soft to the touch, and can be used to weave high-grade silk fabrics. Silkworm skin and dead silkworms are valuable traditional Chinese medicines. Silkworm excrement and silkworm excrement are also high-quality feed for livestock and can be used to extract industrial raw materials such as chlorophyll and copper sodium salts. Silkworm pupae can be fried for consumption, and pupal protein and pupal oil can also be extracted for medicinal purposes.

[0003] Automated silkworm rearing methods are a popular research direction at present. Currently, the determination of the maturity status of silkworms still mainly relies on the subjective judgment of the rearers, which has problems such as strong subjectivity, low efficiency, low accuracy, and easy visual fatigue.

[0004] When raising silkworms, they will stop eating once they reach maturity. Determining the maturity of silkworms can help silkworm farmers reduce feeding pressure and reduce the amount of mulberry leaves picked in time. Good quality mulberry leaves and sufficient feeding are essential. If the silkworms are prematurely ripened and placed on the cocoon, the quality of the cocoons will inevitably decline. If they are placed on the cocoon too late, the silk will be wasted, directly affecting the cocoon yield. To promote uniform placement of mature silkworms on the cocoon, molting hormone is added when the number of mature silkworms reaches about 5%. At this time, the use of molting hormone not only has no adverse effect on the quality of the cocoon product, but on the contrary, it can increase the rate of cocoon entry into the square grid, reduce the number of loose cocoons, improve the quality of the cocoons, and facilitate the cocooning operation. However, it is currently impossible to accurately determine the maturity of silkworms. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a silkworm maturity status detection system based on improved YOLOv8 to solve the technical problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a silkworm maturity status detection system based on an improved YOLOv8, comprising a data acquisition unit, a model unit, an iteration unit, an algorithm unit, a processing unit, a central unit, a display unit, an inspection unit, and a feeding unit. The data acquisition unit acquires silkworm image data. The model unit uses an instance segmentation image recognition model to identify silkworms within the image data. Before image recognition, the iteration unit updates and iterates the image recognition model. The algorithm unit provides algorithmic support to the model unit. The processing unit segments the silkworm image identified by the model unit and calculates the volume change rate TJ and the color change rate YS. The central unit receives the volume change rate TJ and the color change rate YS sent by the processing unit and calculates the judgment value P. The display unit receives and displays the maturity command and feeding command sent by the central unit. The inspection unit calculates the real-time correction value T within the judgment value P. The feeding unit performs the feeding of the silkworms.

[0007] The iterative unit includes a training module, a testing module, and a verification module. The training module receives images acquired by the image acquisition unit and annotates them using instance segmentation. The training module inputs the annotated images into the verification module for verification. Once the verification result of the training module meets the requirements, the testing module receives images from the image acquisition unit for testing. Once the test result of the testing module meets the requirements, the iterative unit sends the latest parameters to the model unit, which uses the latest parameters to identify silkworms.

[0008] In a preferred embodiment, the model unit introduces a CARAFE sampling operator. The CARAFE sampling operator upsamples the low-resolution feature map and generates a feature map of the same size as the high-resolution feature map. The CARAFE sampling operator divides the low-resolution feature map into several small blocks, and then interacts with each small block with the high-resolution feature map to obtain the context information required for reconstruction. The CARAFE operator performs a convolution operation on the interacted feature map to obtain the sampling result for silkworm boundary recognition.

[0009] In a preferred embodiment, the algorithm unit employs a YOLOv8 backbone network, and the algorithm unit incorporates a DAT attention mechanism into the YOLOv8 backbone network. The last two C2F modules in the YOLOv8 backbone network within the algorithm unit are replaced with C2f_DCNv2 modules. The C2f_DCNv2 module combines the C2f module and the DCNv2 module. The Conv operation in the Bottleneck of the C2f module is replaced with DCNv2, forming a new DBottleneck. Each C2f-DCNv2 module consists of two DCNv2 modules and n DBottleneck modules.

[0010] In a preferred embodiment, the processing unit receives the image recognized by the model unit, and the processing unit uses a bitmap cutting method to cut the silkworm image recognized by the model unit. The processing unit performs bitmap cutting once every ten minutes, and the processing unit compares the latest bitmap-cut image with the first bitmap-cut image of the day. The processing unit compares the silkworm's own volume change rate TJ and color change rate YS, and sends the calculated results to the central unit.

[0011] In a preferred embodiment, when the processing unit calculates the volume change rate, it outputs the latest volume ZT after the latest bitmap cut for each silkworm and the previous volume ST after the bitmap cut on the previous side. The formula for calculating the volume change rate TJ is as follows: The processing unit performs grayscale processing on each silkworm image. The grayscale processing calculation formula is W = 0.3R + 0.58G + 0.12B, where W is the processed grayscale value, R is the red image, G is the green image, and B is the blue image, and R, G, and B are all within the grayscale value range of 0-255. The processing unit outputs the grayscale value of the latest bitmap after cropping as WZ, and the processing unit outputs the grayscale value of the previous bitmap after cropping as WS. The color change rate YS is calculated using the following formula:

[0012]

[0013] In a preferred embodiment, the central unit receives the volume change rate TJ and the color change rate YS and calculates a judgment value P. The formula for calculating the judgment value P is as follows: In the formula, k1 and k2 are both weights, and 0≤k1≤1, 0≤k2≤1, TS is the current number of days the silkworm is fed, BZ is the standard number of days required for the silkworm to reach maturity, and T is the real-time correction value.

[0014] In a preferred embodiment, the central unit compares the calculated judgment value P with its internal judgment threshold Y. When the judgment value P ≥ threshold Y, the central unit sends a ripening command to the display unit. When the judgment value P < threshold Y, the central unit sends a feeding command to the display unit. The display unit displays the ripening command and the feeding command. When the feeding command in the display unit changes to a ripening command, the display unit issues an alarm sound as a reminder.

[0015] In a preferred embodiment, the inspection unit goes to the location of the silkworms to conduct inspection after the central unit issues the maturity command. The inspection unit inspects the number of mature silkworms (CS) at the site. The real-time correction value T of the inspection unit is calculated by the formula T = [1 + (CS - 5%)]. When the inspection unit conducts the inspection, it inputs the number of mature silkworms (CS). If the number of mature silkworms (CS) is not input during the inspection, the real-time correction value T does not change.

[0016] In a preferred embodiment, the feeding unit feeds silkworms. When the central unit does not send a maturity command, the feeding unit adds mulberry leaves. When the central unit sends a maturity command, the feeding unit adds molting hormone to the mulberry leaves added by the feeding unit, and the feeding unit reduces the amount of mulberry leaves added after adding molting hormone.

[0017] The technical effects and advantages of this invention are as follows:

[0018] 1. This invention uses an image recognition model based on improved YOLOv8 instance segmentation to identify silkworms within image data, summarizes and learns the characteristics of mature and immature silkworms, quickly and accurately classifies and counts the number of silkworms of each type, and performs annotation operations on the collected silkworm images during the actual breeding process and iterative training to make the model unit more accurate when identifying silkworms.

[0019] 2. This invention improves the model's ability to capture details and silkworm body boundaries by introducing the CARAFE upsampling operator into the model unit, which is beneficial for distinguishing individual silkworms and making the model prediction more reliable. This enables more accurate identification of silkworms. The DAT attention mechanism is added to the backbone network of YOLOv8 to help the network better capture the detailed features of silkworms, making feature fusion more accurate and targeted.

[0020] 3. Based on ensuring the accuracy of the volume change rate TJ and color change rate YS, this invention, combined with the number of feeding days TS, calculates a judgment value P that can accurately express the changes in silkworms. When the judgment value P ≥ the threshold Y, the number of mature silkworms reaches 5%. Therefore, when the feeding process needs to be adjusted, adding molting hormone can increase the grid cluster entry rate, reduce hairy cocoons, improve cocoon quality, and facilitate the cocooning operation. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the overall system composition of the present invention.

[0022] Figure 2 This is a schematic diagram of the C2f_DCNv2 module of the present invention.

[0023] Figure 3 This is a schematic diagram of the annotation operation before the model unit of the present invention is identified.

[0024] Figure 4 This is a schematic diagram of the results after identification according to the present invention. Detailed Implementation

[0025] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The silkworm maturity status detection system based on the improved YOLOv8 involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] This invention provides a silkworm maturity detection system based on an improved YOLOv8, comprising a data acquisition unit, a model unit, an iteration unit, an algorithm unit, a processing unit, a central unit, a display unit, a verification unit, and a feeding unit. The data acquisition unit acquires silkworm image data. The model unit uses an instance segmentation image recognition model to identify silkworms within the image data. The iteration unit updates the image recognition model before image recognition. The algorithm unit provides algorithmic support to the model unit. The processing unit segments the silkworm images identified by the model unit and calculates the volume change rate TJ and color change rate YS. The central unit receives the volume change rate TJ and color change rate YS sent by the processing unit and calculates a judgment value P. The display unit receives and displays maturity and feeding instructions sent by the central unit. The verification unit calculates a real-time correction value T within the judgment value P. The feeding unit performs the silkworm feeding operation.

[0027] In this embodiment, an image recognition model based on improved YOLOv8 instance segmentation is used to identify silkworms within image data. The characteristics of mature and immature silkworms are summarized and learned, and the number of silkworms of each type is quickly and accurately classified and counted. This helps silkworm farmers to add molting hormones in a timely manner, put the silkworms on the cocoons on time, and reduce silk waste. At the same time, if immature silkworms are put on the cocoons in advance, their behavior and excrement will cause contamination of the cocoons and cocooning equipment, thereby increasing the cocoon yield.

[0028] Referring to the figure, the iterative unit includes a training module, a testing module, and a verification module. The training module receives images acquired by the image acquisition unit and performs image annotation. The training module uses instance segmentation to annotate the images. The training module inputs the annotated images into the verification module for verification. After the verification result of the training module meets the requirements, the testing module receives images from the image acquisition unit for testing. After the usage result of the testing module meets the requirements, the iterative unit sends the latest parameters to the model unit.

[0029] In this embodiment, based on the instance segmentation method, the collected silkworm images from the actual breeding process are labeled to create a dataset, which is then divided into a training module, a testing module, and a verification module for iterative training. This keeps the model unit constantly updated and corrects any problems in a timely manner, ultimately making the model unit more accurate in identifying silkworms.

[0030] Referring to the figure, the model unit introduces a CARAFE sampling operator. The CARAFE sampling operator upsamples the low-resolution feature map and generates a feature map of the same size as the high-resolution feature map. The CARAFE sampling operator divides the low-resolution feature map into several small blocks, and then interacts with the high-resolution feature map to obtain the context information required for reconstruction. The CARAFE operator performs a convolution operation on the interacted feature map to obtain the sampling result and perform silkworm boundary recognition.

[0031] In the embodiments of this application, the actual silkworm breeding environment is characterized by densely packed silkworm bodies with unclear boundaries. Therefore, the introduction of the CARAFE upsampling operator in the model unit can improve the model's ability to capture details and silkworm body boundaries, which is beneficial for distinguishing individual silkworms, making the model prediction more reliable, and thus enabling more accurate identification of silkworms.

[0032] Referring to the figure, the algorithm unit adopts a YOLOv8 backbone network, and the algorithm unit adds a DAT attention mechanism to the YOLOv8 backbone network. The last two C2F modules in the YOLOv8 backbone network of the algorithm unit are replaced with C2f_DCNv2 modules. The C2f_DCNv2 module combines the C2f module and the DCNv2 module. The Conv operation in the C2f module Bottleneck is replaced with DCNv2 to form a new DBottleneck. Each C2f-DCNv2 module consists of two DCNv2 modules and n DBottleneck modules.

[0033] In this embodiment, the attention mechanism is a computational model that mimics human attention allocation. It can adjust the allocation of attention based on the relevance and importance of the input, enabling the model to process information more effectively. Addressing issues such as dense silkworm populations, mutual occlusion, and similar characteristics between immature and mature fifth instar silkworms in actual silkworm rearing environments, this application incorporates the DAT attention mechanism into the YOLOv8 backbone network. This helps the network better capture detailed features of silkworms, making feature fusion more accurate and targeted, thereby improving detection accuracy and the network's representational capabilities. A C2f_DCNv2 module is designed by combining the C2f and DCNv2 modules, replacing the last two C2F modules in the backbone network with C2f_DCNv2 modules. The Conv operation in the C2f module's Bottleneck is replaced with DCNv2, forming a new DBottleneck. Each C2f-DCNv2 module consists of two DCNv2 modules and n DBottleneck modules, allowing for better feature extraction from different silkworm populations.

[0034] Referring to the figure, the processing unit receives the image recognized by the model unit, and the processing unit uses a bitmap segmentation method to segment the silkworm image recognized by the model unit. The processing unit performs bitmap segmentation every ten minutes, and compares the latest segmented image with the first bitmap segmented image of the day. The processing unit compares the silkworm's own volume change rate TJ and color change rate YS, and sends the calculated values ​​to the central unit. When calculating the volume change rate, the processing unit outputs the latest volume ZT after the latest bitmap segmentation and the previous volume ST after the previous bitmap segmentation for each silkworm. The formula for calculating the volume change rate TJ is as follows: The processing unit performs grayscale processing on each silkworm image. The grayscale processing calculation formula is W = 0.3R + 0.58G + 0.12B, where W is the processed grayscale value, R is the red image, G is the green image, and B is the blue image, and R, G, and B are all within the grayscale value range of 0-255. The processing unit outputs the grayscale value of the latest bitmap after cropping as WZ, and the processing unit outputs the grayscale value of the previous bitmap after cropping as WS. The color change rate YS is calculated using the following formula:

[0035] In this embodiment, after the silkworm is accurately identified by the model unit, the silkworm image identified by the model unit is segmented every five minutes using a bitmap segmentation method. By comparing the images before and after, the changes in the silkworm's state can be understood. The silkworm undergoes two changes as it matures: first, its body shortens after maturity; second, its thorax gradually becomes translucent, followed by its abdomen, resulting in a color change. This application calculates the volume change rate TJ and the color change rate YS to quickly determine whether the silkworm is mature. The use of the bitmap segmentation method ensures the accuracy of the volume change rate TJ and the color change rate YS calculations. After the first bitmap segmentation of the day, subsequent changes are based on this. Since the silkworm's maturation is a constantly changing process, the first collection of the day is used as a basis to observe subsequent changes and ensure the accuracy of the detection.

[0036] Referring to the figure, the central unit receives the volume change rate TJ and the color change rate YS and calculates the judgment value P. The formula for calculating the judgment value P is as follows: In the formula, k1 and k2 are weights, and 0≤k1≤1, 0≤k2≤1. TS is the current number of feeding days for silkworms, BZ is the standard number of days required for silkworms to reach maturity, and T is the real-time correction value. The central unit compares the calculated judgment value P with its internal judgment threshold Y. When the judgment value P≥ threshold Y, the central unit sends a maturity command to the display unit. When the judgment value P< threshold Y, the central unit sends a feeding command to the display unit. The display unit displays the maturity command and the feeding command. When the feeding command in the display unit changes to the maturity command, the display unit issues an alarm sound to provide a prompt.

[0037] In this embodiment, based on the calculated volume change rate TJ and color change rate YS, and considering both and the number of days the silkworms have been fed, the calculated judgment value P can accurately express the changes in the silkworms. When the judgment value P ≥ the threshold Y, the number of mature silkworms reaches 5%, so the feeding process needs to be adjusted. This application can make timely adjustments, and when the display unit receives the maturity instruction, it will issue an alarm sound to remind the feeding personnel to make timely adjustments.

[0038] Referring to the figure, the inspection unit goes to the location of the silkworms to conduct inspections after the central unit issues a maturity command. The inspection unit inspects the number of mature silkworms (CS) at the site. The real-time correction value T of the inspection unit is calculated using the formula T = [1 + (CS - 5%)]. When the inspection unit conducts the inspection, it inputs the number of mature silkworms (CS). If the number of mature silkworms (CS) is not input during the inspection, the real-time correction value T does not change. The feeding unit feeds the silkworms. When the central unit does not send a maturity command, the feeding unit adds mulberry leaves. When the central unit sends a maturity command, the feeding unit adds molting hormone to the mulberry leaves added by the feeding unit. After adding molting hormone, the feeding unit reduces the amount of mulberry leaves added.

[0039] In this embodiment, after the system undergoes maturation changes, the inspection unit inspects the silkworm maturity level CS at the location of the silkworms to determine if the maturity level CS is within 5%. If it fluctuates around 5%, the real-time correction value T is adjusted, thereby adjusting the judgment value P, making the judgment value P continuously adjusted and more accurate. When the silkworm maturity level reaches 5%, molting hormone is added in time, which not only has no adverse effect on the quality of the silkworm cocoons, but also increases the grid cluster entry rate, reduces hairy cocoons, improves cocoon quality, and is also beneficial for the clustering operation.

[0040] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. The units and algorithm steps of the various examples described in the embodiments can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0041] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0042] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that cannot be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0043] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A silkworm maturity status detection system based on an improved YOLOv8, characterized in that: The system includes a data acquisition unit, a model unit, an iteration unit, an algorithm unit, a processing unit, a central unit, a display unit, a verification unit, and a feeding unit. The data acquisition unit acquires image data of silkworms. The model unit uses an instance segmentation image recognition model to identify silkworms within the image data. The iteration unit updates the image recognition model before performing image recognition. The algorithm unit provides algorithmic support to the model unit. The processing unit segments the silkworm images identified by the model unit and calculates the volume change rate TJ and color change rate YS. The central unit receives the volume change rate TJ and color change rate YS sent by the processing unit and calculates the judgment value P. The display unit receives and displays the maturity and feeding instructions sent by the central unit. The verification unit calculates the real-time correction value T within the judgment value P. The feeding unit performs the feeding of silkworms. The iterative unit includes a training module, a testing module, and a verification module. The training module receives images acquired by the image acquisition unit and annotates them using instance segmentation. The training module inputs the annotated images into the verification module for verification. Once the verification result of the training module meets the requirements, the testing module receives images from the image acquisition unit for testing. Once the test result of the testing module meets the requirements, the iterative unit sends the latest parameters to the model unit, which uses the latest parameters to identify silkworms.

2. The silkworm maturity status detection system based on improved YOLOv8 according to claim 1, characterized in that: The model unit introduces the CARAFE sampling operator, which upsamples the low-resolution feature map and generates a feature map of the same size as the high-resolution feature map. The CARAFE sampling operator divides the low-resolution feature map into several small blocks, and then interacts with the high-resolution feature map to obtain the context information required for reconstruction. The CARAFE operator performs a convolution operation on the interacted feature map to obtain the sampling result for silkworm boundary recognition.

3. The silkworm maturity status detection system based on improved YOLOv8 according to claim 1, characterized in that: The algorithm unit uses a YOLOv8 backbone network, and the algorithm unit adds a DAT attention mechanism to the YOLOv8 backbone network. The last two C2F modules in the YOLOv8 backbone network within the algorithm unit are replaced with C2f_DCNv2 modules. The C2f_DCNv2 module combines the C2f module and the DCNv2 module. The Conv operation in the C2f module's Bottleneck is replaced with DCNv2 to form a new DBottleneck. Each C2f-DCNv2 module consists of two DCNv2 modules and n DBottleneck modules.

4. The silkworm maturity status detection system based on improved YOLOv8 according to claim 1, characterized in that: The processing unit receives the image recognized by the model unit, and the processing unit uses a bitmap cutting method to cut the silkworm image recognized by the model unit. The processing unit performs bitmap cutting once every ten minutes, and the processing unit compares the latest bitmap-cut image with the first bitmap-cut image of the day. The processing unit compares the silkworm's own volume change rate TJ and color change rate YS, and sends the calculated results to the central unit.

5. The silkworm maturity status detection system based on improved YOLOv8 according to claim 4, characterized in that: When the processing unit calculates the volume change rate, it outputs the latest volume ZT after the latest bitmap cut for each silkworm and the previous volume ST after the bitmap cut on the previous side. The formula for calculating the volume change rate TJ is as follows: The processing unit performs grayscale processing on each silkworm image. The grayscale processing calculation formula is W = 0.3R + 0.58G + 0.12B, where W is the processed grayscale value, R is the red image, G is the green image, and B is the blue image, and R, G, and B are all within the grayscale value range of 0-255. The processing unit outputs the grayscale value of the latest bitmap after cropping as WZ, and the processing unit outputs the grayscale value of the previous bitmap after cropping as WS. The color change rate YS is calculated using the following formula:

6. The silkworm maturity status detection system based on improved YOLOv8 according to claim 5, characterized in that: The central unit receives the volume change rate TJ and the color change rate YS and calculates the judgment value P. The formula for calculating the judgment value P is as follows: In the formula, k1 and k2 are both weights, and 0≤k1≤1, 0≤k2≤1, TS is the current number of days the silkworm is fed, BZ is the standard number of days required for the silkworm to reach maturity, and T is the real-time correction value.

7. The silkworm maturity status detection system based on improved YOLOv8 according to claim 6, characterized in that: The central unit compares the calculated judgment value P with its internal judgment threshold Y. When the judgment value P ≥ threshold Y, the central unit sends a ripening command to the display unit. When the judgment value P < threshold Y, the central unit sends a feeding command to the display unit. The display unit displays the ripening command and the feeding command. When the feeding command in the display unit changes to a ripening command, the display unit emits an alarm sound to provide a prompt.

8. The silkworm maturity status detection system based on improved YOLOv8 according to claim 1, characterized in that: The inspection unit goes to the location of the silkworms to conduct inspections after the central unit issues the maturity command. The inspection unit inspects the number of mature silkworms (CS) at the site. The real-time correction value T of the inspection unit is calculated using the formula T = [1 + (CS - 5%)]. When the inspection unit conducts the inspection, it inputs the number of mature silkworms (CS). If the number of mature silkworms (CS) is not input during the inspection, the real-time correction value T does not change.

9. A silkworm maturity status detection system based on an improved YOLOv8 according to claim 1, characterized in that: The feeding unit feeds silkworms. When the central unit does not send a maturity command, the feeding unit adds mulberry leaves. When the central unit sends a maturity command, the feeding unit adds molting hormone to the mulberry leaves added by the feeding unit, and the feeding unit reduces the amount of mulberry leaves added after adding molting hormone.

Images