Internet of Things monitoring method and device for rice field lobster growth status

Abstract

This invention belongs to the field of Internet of Things (IoT) technology and discloses an IoT monitoring method and device for the growth status of crayfish in rice paddies. The device includes a crayfish collection module, a solar charging module, and a telescopic image recognition module. The telescopic image recognition module acquires the original images of crayfish growth status collected by the crayfish collection module and transmits the acquired images to a cloud data server via a 4G channel to monitor crayfish growth changes. This invention uses IoT to monitor the growth status of crayfish in rice paddies, enabling yield and production capacity prediction during crayfish farming.

Description

Technical Field

[0001] This invention belongs to the field of Internet of Things (IoT) technology, specifically relating to an IoT monitoring method and device for the growth status of crayfish in rice paddies. Background Technology

[0002] Crayfish, an introduced species, was introduced to my country in the 1930s and has gradually developed into an industrialized product. The crayfish species farmed in my country is generally the red swamp crayfish (Procambarus clarkii), a highly valuable aquatic product. It is rich in protein and low in fat, making it a premium aquatic delicacy. Furthermore, crayfish have high added value in the industrial market. The carapace of the red swamp crayfish contains astaxanthin, astaxanthin, chitin, and other substances, which have wide applications in food, medicine, industry, printing and dyeing, daily chemical products, and agriculture.

[0003] In my country, crayfish farming primarily utilizes rice-crayfish hybridization, supplemented by pond farming, lotus root paddy field farming, and water chestnut paddy field farming. However, crayfish farming is currently still in an extensive farming model, requiring manual placement of cages to assess the crayfish's growth status. This manual assessment involves sending personnel to patrol and harvest the crayfish, and also risks cannibalism within the cages, leading to reduced yields. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides an Internet of Things (IoT) monitoring device and method for monitoring the growth status of crayfish in rice paddies. The IoT device system comprises a crayfish collection module, a solar charging module, a telescopic image recognition module, and a cloud data server. By periodically identifying the area of ​​crayfish heads and bodies within the collection device, the system uses mathematical statistics to monitor the growth status of crayfish in rice paddies, thereby enabling yield and production prediction, growth status monitoring, and feeding and medication decisions during the crayfish farming process.

[0005] To solve the above problems, the present invention is achieved through the following technical solution:

[0006] This invention relates to an IoT-based monitoring method for the growth status of crayfish in rice paddies. The IoT monitoring method is implemented through an IoT monitoring device and specifically includes the following steps:

[0007] Step 1: Acquire lobster images using a camera and perform statistical learning on the lobster pixel features;

[0008] Step 2: Collect the original images of lobster growth monitoring using the lobster collection module, and remove the background after collection;

[0009] Step 3: Perform feature identification on the original image of lobster growth status monitoring obtained in Step 2 to realize the monitoring of lobster growth changes.

[0010] A further improvement of the present invention is that step 1, lobster image acquisition and processing, specifically includes the following steps:

[0011] Step 1.1: Select samples evenly according to the size of lobsters ranging from 1 to 10 qian (approximately 5 grams). Use a camera to capture photos of lobsters ranging from green to dark red. Manually process the captured photos by replacing the background pixels R, G, and B with (0,0,0). Count the RGB pixels of the lobster foreground according to the pixel (x,y) sequence. Use the sum of the distances of the R, G, and B pixels as the partition distance. The total distance D of the foreground pixels of the lobster sample is then calculated.

[0012]

[0013] Where (x,y) are the horizontal and vertical indices of the pixels;

[0014] Step 1.2: Perform Gaussian interval statistics on the total distance of the foreground pixels of the lobster sample;

[0015] Step 1.3: Statistically analyze the foreground pixels of the lobster sample, sort them from largest to smallest according to the proportion of total pixels in each pixel interval, and categorize them as Q1, Q2, Q3, Q4, and Q5 respectively;

[0016] Step 1.4: Raise the shrimp collection head to the water surface and count the background pixels of the shrimp cage and the water surface. If the total distance D of the foreground pixels of the lobster sample cannot be distinguished from Q1, Q2, Q3, Q4, and Q5, change the color of the net plate of the shrimp collection head until it is significantly distinguishable from Q1, Q2, Q3, Q4, and Q5.

[0017] A further improvement of the present invention is that step 2 specifically includes the following steps:

[0018] Step 2.1: When the shrimp collection module is timed, the telescopic motor (301) reverses, and the RS485 laser rangefinder (302) measures the distance to the camera height;

[0019] Step 2.2: Turn on the camera and acquire the original image of the lobsters in the lobster collection module to monitor their growth status;

[0020] Step 2.3: Transmit the original image of lobster growth monitoring obtained in Step 2.2 to the cloud server via a 4G module, and perform pixel filtering on the image, keeping only pixels within the Q1, Q2, Q3, Q4, and Q5 pixel range.

[0021] A further improvement of the present invention is that step 3 specifically includes the following steps:

[0022] Step 3.1: Binarize the original image of lobster growth status monitoring after background removal to obtain the binarized image of lobster growth status monitoring.

[0023] Step 3.2: Rotate the collected binarized lobster growth status monitoring images by 5°-90°, with a unit interval of 5°. Label the rotated images as G1, G2, ..., G18, and label one of the rotated images as Gi, where i = 1-18.

[0024] Step 3.3: Using 10×10 pixels as intervals, perform horizontal pixel block statistics on Gi. When the proportion of black pixels in a pixel block is 30%, the pixel block is counted as a lobster foreground pixel. Count the number of lobster background blocks in each row and mark it as Wij, where i is the image number and j is the row number.

[0025] Step 3.4: The sum of the number of background pixels in each binarized lobster growth status monitoring image is labeled as the lobster area Si.

[0026]

[0027] Where i is the image number of the rotation, and the pixel value is 1920×1080;

[0028] Step 3.5: Count the number of foreground pixel blocks of lobsters in each column using 10×10 pixels, and label them as Nik, where i is the image number and k is the column number;

[0029] Step 3.6: Calculate the maximum values ​​of the number of lobster foreground pixels (Nik) in each column and the number of lobster background pixels (Wij) in each row of the rotated image Gi. Label these values ​​as the lobster length (Li) and width (Wi) of the rotated image, respectively, and label the aspect ratio (Yi).

[0030] Li = (Nik)max

[0031] Wi = (Wij)max

[0032] Yi = Li / Wi;

[0033] Where i = 1-18

[0034] Step 3.7: Sort the aspect ratios Yi, take the maximum value as the image for calculating the lobster's width and height, and label it with the sequence number n. Then, the characteristic values ​​of the lobster obtained are area S, width W, and length L:

[0035] S = Sn

[0036] L = Ln

[0037] W = Wn

[0038] Step 3.8: Statistically analyze the lobster feature values ​​obtained in Step 3.7 within one day and label them as Sm, Lm, and Wm, where m is the serial number. Control the raising and lowering time of the lobster trap to 15 minutes to obtain 0 or 1 lobster with a high probability. Calculate the mean of the width-to-height ratio Ym and remove sample data that deviate from the mean by 50%.

[0039] Step 3.9: Calculate the mean values ​​Su, Wu, and Lu for the area, width, and length of the lobster samples collected within one day, after removing those that deviate from the mean, and record the breeding time;

[0040] Step 3.10: Compare Su, Wu, and Lu longitudinally according to the breeding time to monitor the growth changes of lobsters.

[0041] This invention provides an IoT monitoring device for monitoring the growth status of crayfish in rice paddies. The IoT monitoring device includes a crayfish collection module placed on a crayfish feeding platform to collect original images of crayfish growth status. A solar charging module is installed above the crayfish collection module. A telescopic motor from a telescopic image recognition module is installed on the mounting platform of the solar charging module. The telescopic image recognition module acquires the original images of crayfish growth status collected by the crayfish collection module and transmits the acquired original images of crayfish growth status to a cloud data server via a 4G channel to monitor the growth changes of the crayfish.

[0042] A further improvement of this invention is that the shrimp collecting module is a shrimp cage structure, including a net cage placed in the lobster feeding area, a shrimp collecting head, an escape plate, an escape spring, a lifting screw hole, and an escape post hole. The net cage is a structure that allows entry but not exit. The shrimp collecting head and the net cage are softly connected by a channel composed of an elastic connecting net, and both the shrimp collecting head and the net cage are provided with corresponding inlets and outlets, allowing the lobster to enter the shrimp collecting head from the net cage. After the shrimp collecting head rises, it extends and retracts through the elastic connecting net without causing damage to the channel. The escape plate is connected to the bottom of the shrimp collecting head by an escape spring. When the escape rod in the telescopic image recognition module descends to the escape post hole, it opens the escape plate, and the lobster falls into the water to escape. The lifting screw hole is located at the top of the shrimp collecting module and is connected to the lifting rod of the telescopic image recognition module by a thread, allowing the shrimp collecting module to leave the water surface. The telescopic image recognition module identifies the size and number of lobsters. The escape post hole is located at the top of the shrimp collecting module and is opened by the escape rod.

[0043] A further improvement of the present invention is that the release of the lobster is achieved by the following specific steps: the telescopic motor reverses, the RS485 laser rangefinder measures the release height, the escape board opens, the lobster enters the water, the telescopic motor rotates forward, the RS485 laser rangefinder measures the water height, and the lobster head enters the water.

[0044] A further improvement of this invention is that the solar charging module includes a solar panel, an IoT module with an RS485 interface, an installation platform, a controller, and a column. The solar panel, which is 100W, is installed on top of the column. The installation platform is fixed to the upper part of the column and close to the solar panel. The installation platform is used to install a camera, a controller, a telescopic motor, and the IoT module. The controller controls the charging and discharging of the solar panel and has an RS485 communication interface and four DI / DO interfaces, used for transmitting remote control commands, acquiring lithium battery status, and controlling the lifting and lowering of the telescopic motor, respectively. The controller uses a 7-inch MCGS PRO from Kunlun Tongtai equipped with a 4G IoT card as the main control unit, and includes an external RS485 voltage acquisition module, a solar charging and discharging management module, and an RS485... The DI / DO acquisition module has a voltage acquisition range of 0V-36V. The main control unit has a built-in 4G data card and features RS485 and RJ45 interfaces. The solar charge / discharge management module operates independently and has a voltage monitoring output port that connects to the voltage acquisition module. The RS485 interface uses the MODBUSRTU protocol to acquire lithium battery voltage. The RS485 DI / DO acquisition module acquires four channels of DI information and controls four channels of DO output. The RJ45 interface uses the TCP / IP protocol to transmit camera image signals. There are two image acquisition modes: video mode and photo transmission mode, implemented through the MCGS PRO video acquisition interface program. The photo transmission mode saves data on the data card.

[0045] A further improvement of the present invention is that the telescopic image recognition module includes a telescopic motor, an RS485 laser rangefinder, a camera with an RJ45 interface, a lifting rod, and an escape rod. The telescopic motor is mounted on the installation platform, and the lifting rod is connected to the telescopic motor via a coupling. The escape rod is mounted below the installation platform, and the escape rod and the lifting rod are aligned with the escape column hole and the lifting screw hole in the shrimp collection module. The controller controls the forward and reverse rotation and power supply of the motor by controlling two DO channels respectively, thereby realizing the forward and reverse rotation control of the motor. The camera is mounted below the installation platform, and the RS485 laser rangefinder is mounted on the top of the installation platform through a drilled hole, exposing the laser probe. The RS485 communication interface of the RS485 laser rangefinder and the controller is connected to the RS485 interface of the IoT module, and the RJ45 interface of the camera is connected to the RJ45 interface of the IoT module.

[0046] A further improvement of the present invention is that: the cloud data server includes an IoT terminal and a cloud data server; the photos taken by the camera in the solar charging module interact with the IoT terminal and the cloud data server through a 4G channel; at the same time, the IoT terminal publishes control via the MQTT protocol, which can be accessed by a mobile phone to realize mobile phone control and viewing.

[0047] The beneficial effects of this invention are:

[0048] The IoT monitoring device of this invention uses a telescopic structure to lift the shrimp trap out of the water, enabling the shrimp collection module to capture and image lobsters. Lobster images are acquired every 15 minutes, ensuring that only one lobster is present in the collection module for most of the time. By statistically analyzing the foreground pixels of the lobster and setting a black background, a mixed background removal algorithm is implemented to remove the lobster background, leaving only the lobster image. The binarized foreground image of the lobster largely retains its shape. However, due to the uncertain imaging angle, this invention employs a fixed rotation method. When the ratio of the acquired length to width is maximized, the image represents a standard image. At this point, the number of horizontal and vertical black pixel blocks can essentially represent the length and width of the lobster, and the number of black pixel blocks can also represent the size of the individual lobster.

[0049] The image processing method of this invention is simple and the principle is clear. It monitors the growth status proportionally according to the growth period, without the need for data calibration, and is easy to use. At the same time, the frequency of lobster collection within a certain range also expresses the lobster yield in the aquaculture area. Since the entire device collects data outside the water, the cost is much lower than that of collecting data inside the water, which is suitable for large-scale promotion.

[0050] In summary, the method of this invention uses the Internet of Things to monitor the growth status of crayfish in rice paddies, thereby enabling the prediction of yield and production capacity during the crayfish farming process. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the overall structure of the IoT monitoring device of the present invention.

[0052] Figure 2 This is a schematic diagram of the shrimp collection module of the present invention.

[0053] Figure 3 This is a schematic diagram of the structure of the solar charging module of the present invention.

[0054] Figure 4 This is a schematic diagram of the controller of the present invention.

[0055] Figure 5 This is a schematic diagram of the structure of the stretchable image recognition module of the present invention.

[0056] Figure 6 This is a schematic diagram of the cloud data server structure of the present invention.

[0057] Figure 7 This is a binary rotational schematic diagram of the mature state of lobster in an embodiment of the present invention.

[0058] Figure 8 This is a schematic diagram of the binarized rotation of lobster larvae in an embodiment of the present invention.

[0059] Figure 9 This is a schematic diagram illustrating the principle of extracting the length, width, area, and morphological parameters of lobsters in an embodiment of the present invention.

[0060] Figure 10 This is a flowchart of the monitoring method of the present invention. Detailed Implementation

[0061] The embodiments of the present invention will be disclosed below with reference to the drawings. For clarity, many practical details will be described in the following description. However, it should be understood that these practical details are not intended to limit the present invention. That is, in some embodiments of the present invention, these practical details are not essential. In addition, for the sake of simplicity, some conventional structures and components will be shown in the drawings in a simple schematic manner.

[0062] like Figure 1 As shown, this invention is an IoT monitoring device for the growth status of crayfish in rice paddies. The device includes a crayfish collection module 4 placed on a crayfish feeding platform to collect original images of crayfish growth status. A solar charging module 1 is installed above the crayfish collection module 4. A telescopic motor 301 from a telescopic image recognition module 3 is installed on a mounting platform 103 in the solar charging module 1. The telescopic image recognition module 3 acquires the original images of crayfish growth status collected by the crayfish collection module 4 and transmits the acquired original images of crayfish growth status to a cloud data server 2 via a 4G channel to monitor the growth changes of the crayfish.

[0063] Specifically, such as Figure 2As shown, the shrimp collection module 4 is a shrimp cage structure, including a net cage 401 placed in the lobster foraging area, a shrimp collection head 404, an escape plate 402, an escape spring 403, a lifting screw hole 405, and an escape column hole 406. The net cage 401 is a structure that allows entry but not exit. The release is achieved through the structure of the net cage 401: the telescopic motor 301 reverses, the RS485 laser rangefinder 302 measures the release height, the escape plate 402 opens, and the lobster enters the water; the telescopic motor 301 rotates forward, the RS485 laser rangefinder 302 measures the height to be placed in the water, and the shrimp collection head 404 enters the water. The shrimp collecting head 404 and the net cage 401 are flexibly connected by a channel composed of an elastic connecting net. Both the shrimp collecting head 404 and the net cage 401 are provided with corresponding inlets and outlets, allowing the lobsters to enter the shrimp collecting head 404 from the net cage 401. After the shrimp collecting head 404 rises, it extends and retracts through the elastic connecting net without causing damage to the channel. The escape plate 402 is connected to the bottom of the shrimp collecting head 404 by an escape spring 403. When the escape rod 305 in the telescopic image recognition module 3 descends to the escape post hole 406, it opens the escape plate 402, and the lobsters fall into the water to escape. The lifting screw hole 405 is on the top of the shrimp collecting module 4 and is connected to the lifting rod 304 of the telescopic image recognition module 3 by a thread, so that the shrimp collecting module 4 leaves the water surface. The telescopic image recognition module 3 identifies the size and number of lobsters. The escape post hole 406 is on the top of the shrimp collecting module 4 and opens the escape plate 402 by the escape rod (305).

[0064] like Figure 3-4As shown, the solar charging module 1 includes a solar panel 101, an IoT module 102 with an RS485 interface, a mounting platform 103, a controller 104, and a column 105. The solar panel 101 is mounted on top of the column 105 and is 100W. The mounting platform 103 is fixed to the upper part of the column 105 and close to the solar panel 101, which provides some rain protection. This allows for a lower level of waterproofing and dustproofing when installing the camera, controller, telescopic motor, and IoT module. The mounting platform 103 is used to mount a camera 303, a controller 104, a telescopic motor, and an IoT module 102. The controller 104 controls the charging and discharging of the solar panel and has an RS485 communication interface and four DI / DO interfaces, used for transmitting remote control commands, acquiring lithium battery status, and controlling the lifting and lowering of the telescopic motor, respectively. The controller 104 uses a 7-inch MCGS PRO from Kunlun Tongtai equipped with a 4G IoT card as the main control unit, and has an external RS485 voltage acquisition module, a solar charging and discharging management module, and an RS485 DI / DO acquisition module. The voltage acquisition module has a voltage acquisition range of 0V-36V. The main control unit has a built-in 4G data card and has RS485 and RJ45 interfaces. The solar charging and discharging management module works independently and has a voltage monitoring output port connected to the voltage acquisition module. The RS485 interface uses MODBUS. The RTU protocol is used to acquire the lithium battery voltage through the RS485 voltage acquisition module and to acquire 4 DI information channels through the RS485 DI / DO acquisition module to control 4 DO output channels. The RJ45 interface uses the TCP / IP protocol to transmit camera image signals. There are two image acquisition modes: video mode and photo transmission mode. The video acquisition interface program of MCGS PRO is used to implement the video acquisition mode. The photo transmission mode can save data on the data card.

[0065] like Figure 5As shown, the telescopic image recognition module 3 includes a telescopic motor 301, an RS485 laser rangefinder 302, a camera 303 with an RJ45 interface, a lifting rod 304, and an escape rod 305. The telescopic motor 301 is mounted on the installation platform 103. The lifting rod 304 is connected to the telescopic motor 301 via a coupling. The escape rod 305 is installed below the installation platform 103, and the escape rod 305 and the lifting rod 304 are aligned with the escape column hole 406 and the lifting screw hole 405 in the shrimp collection module 4. The controller 104 controls the forward and reverse rotation and power supply of the motor by controlling two DO channels respectively, thereby achieving forward and reverse rotation control of the motor. The camera 303 is installed below the mounting platform 103. The RS485 laser rangefinder 302 is installed on the top of the mounting platform 103 through drilling, exposing the laser probe. The RS485 communication interface of the RS485 laser rangefinder 302 and the controller 104 is connected to the RS485 interface of the IoT module 102. The RJ45 interface of the camera 303 is connected to the RJ45 interface of the IoT module 102.

[0066] like Figure 6 As shown, the cloud data server 2 includes an IoT terminal 201 and a cloud data server 2. The photos taken by the camera 303 in the solar charging module 1 interact with the IoT terminal 201 and the cloud data server 2 through the 4G channel. At the same time, the IoT terminal 201 publishes control through the MQTT protocol, which can be accessed by a mobile phone to realize mobile phone control and viewing.

[0067] like Figure 10 As shown, based on the above-mentioned IoT monitoring device, the present invention also provides an IoT monitoring method for the growth status of crayfish in rice paddies, specifically including the following steps:

[0068] Step 1: Capture lobster images using a camera and perform statistical learning on the pixel features of the lobsters.

[0069] Specifically, the steps include the following:

[0070] Step 1.1: Select 140 samples evenly from lobsters weighing 1 to 10 qian (approximately 50 grams). Take photos of the lobsters, ranging from green to dark red, using a camera. Manually process the photos by replacing the background pixels R, G, and B with (0,0,0). Count the RGB pixels of the lobster foreground according to the pixel (x,y) sequence. Use the sum of the distances of the R, G, and B pixels as the partition distance. The total distance D of the foreground pixels of the lobster samples is 443. The calculation formula is:

[0071]

[0072] Where (x,y) are the horizontal and vertical indices of the pixels;

[0073] Step 1.2: Perform Gaussian interval statistics on the total distance of the foreground pixels of 140 lobster samples, with each interval being 20 pixels, i.e., [0,20], (20,40], ... (420,443], for a total of 22 intervals;

[0074] Step 1.3: Statistically analyze the foreground pixels of 140 lobster samples. The top 5 pixel intervals account for 90% of the total pixels. Sort the pixels by the percentage of the total pixels in each interval from largest to smallest, and categorize them as Q1, Q2, Q3, Q4, and Q5.

[0075] Step 1.4: Raise the shrimp trap 300mm above the water surface and perform background pixel statistics on the shrimp trap and the water surface. If the total distance D of the foreground pixels of the shrimp sample cannot be distinguished from Q1, Q2, Q3, Q4, and Q5, change the color of the shrimp trap's mesh until it is significantly distinguishable from Q1, Q2, Q3, Q4, and Q5. A white 10-mesh top mesh and a black 100-mesh bottom mesh on the shrimp trap provide better background differentiation.

[0076] Step 2: Collect raw images of lobster growth monitoring using the lobster collection module, and remove the background after collection. This includes the following steps:

[0077] Step 2.1: The shrimp collection module is timed for 15 minutes, the telescopic motor 301 reverses, and the RS485 laser rangefinder 302 measures the distance to the camera height;

[0078] Step 2.2: Turn on the camera and acquire the original image of the lobsters in the lobster collection module to monitor their growth status;

[0079] Step 2.3: Transmit the original image of lobster growth monitoring obtained in Step 2.2 to the cloud server via a 4G module. Filter the image by pixels in the ranges [0,20], (20,40], ... (420,443], keeping only pixels within the ranges Q1, Q2, Q3, Q4, and Q5.

[0080] Step 3: Perform feature identification on the original images of lobster growth monitoring obtained in Step 2 to monitor changes in lobster growth, such as... Figure 7-8 As shown. Specifically, it includes the following steps:

[0081] Step 3.1: Binarize the original image of lobster growth status monitoring after background removal to obtain the binarized image of lobster growth status monitoring.

[0082] Step 3.2: Rotate the collected binarized lobster growth status monitoring images by 5°-90°, with a unit interval of 5°. Label the rotated images as G1, G2, ..., G18, and label one of the rotated images as Gi, where i = 1-18.

[0083] Step 3.3: Using 10×10 pixels as intervals, perform horizontal pixel block statistics on Gi. When the proportion of black pixels in a pixel block is 30%, the pixel block is counted as a lobster foreground pixel. Count the number of lobster background blocks in each row and label them as Wij, where i is the image sequence number and j is the row sequence number. For example... Figure 9 As shown.

[0084] Step 3.4: The sum of the number of background pixels in each binarized lobster growth status monitoring image is labeled as the lobster area Si.

[0085]

[0086] Where i is the image number of the rotation, and the pixel value is 1920×1080;

[0087] Step 3.5: Count the number of foreground pixel blocks of lobsters in each column using 10×10 pixels, and label them as Nik, where i is the image number and k is the column number;

[0088] Step 3.6: Calculate the maximum values ​​of the number of lobster foreground pixels (Nik) in each column and the number of lobster background pixels (Wij) in each row of the rotated image Gi. Label these values ​​as the lobster length (Li) and width (Wi) of the rotated image, respectively, and label the aspect ratio (Yi).

[0089] Li = (Nik)max

[0090] Wi = (Wij)max

[0091] Yi = Li / Wi;

[0092] Where i = 1-18

[0093] Step 3.7: Sort the aspect ratios Yi, take the maximum value as the image for calculating the lobster's width and height, and label it with the sequence number n. Then, the characteristic values ​​of the lobster obtained are area S, width W, and length L:

[0094] S = Sn

[0095] L = Ln

[0096] W = Wn

[0097] Step 3.8: Statistically analyze the lobster feature values ​​obtained in Step 3.7 within one day and label them as Sm, Lm, and Wm, where m is the serial number. Control the raising and lowering time of the lobster trap to 15 minutes to obtain 0 or 1 lobster with a high probability. Calculate the mean of the width-to-height ratio Ym and remove sample data that deviate from the mean by 50%.

[0098] Step 3.9: Calculate the mean values ​​Su, Wu, and Lu for the area, width, and length of the lobster samples collected within one day, after removing those that deviate from the mean, and record the breeding time;

[0099] Step 3.10: Compare Su, Wu, and Lu longitudinally according to the breeding time to monitor the growth changes of lobsters.

[0100] This invention identifies the shrimp head and body area in the shrimp collector at regular intervals and uses mathematical statistics to monitor the growth status of crayfish in rice paddies, thereby enabling yield and production prediction, growth status monitoring, and feeding and medication decisions during the crayfish farming process.

[0101] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. An IoT monitoring method for the growth status of crayfish in rice paddies, characterized in that: The IoT monitoring method is implemented through IoT monitoring devices and specifically includes the following steps: Step 1: Acquire lobster images using a camera and perform statistical learning on the lobster pixel features; Step 2: Collect the original images of lobster growth monitoring using the lobster collection module, and remove the background after collection; Step 3: Perform feature identification on the original image of lobster growth status monitoring obtained in Step 2 to realize the monitoring of lobster growth changes; Specifically, step 1, lobster image acquisition and processing, includes the following steps: Step 1.1: Select samples of lobsters ranging from 1 to 10 qian (approximately 50 grams). Use a camera to capture photos of lobsters ranging from green to dark red. Manually process the captured photos by replacing the background pixels R, G, and B with (0,0,0). Count the RGB pixels of the lobster foreground according to the pixel (x,y) sequence. Use the sum of the distances of the R, G, and B pixels as the partition distance. The total distance of the foreground pixels of the lobster sample is then D: Where (x,y) are the horizontal and vertical indices of the pixels; Step 1.2: Perform Gaussian interval statistics on the total distance of the foreground pixels of the lobster sample; Step 1.3: Statistically analyze the foreground pixels of the lobster sample, sort them from largest to smallest according to the proportion of total pixels in each pixel interval, and categorize them as Q1, Q2, Q3, Q4, and Q5 respectively; Step 1.4: Raise the shrimp collection head to the water surface and count the background pixels of the shrimp cage and the water surface. If the total distance D of the foreground pixels of the lobster sample cannot be distinguished from Q1, Q2, Q3, Q4, Q5, then change the color of the net plate of the shrimp collection head until it can be distinguished from Q1, Q2, Q3, Q4, Q5. Step 2 specifically includes the following steps: Step 2.1: When the shrimp collection module is timed, the telescopic motor (301) reverses, and the RS485 laser rangefinder (302) measures the distance to the camera height; Step 2.2: Turn on the camera and acquire the original image of the lobsters in the lobster collection module to monitor their growth status; Step 2.3: Transmit the original image of lobster growth monitoring obtained in Step 2.2 to the cloud server via a 4G module, and perform pixel filtering on the image, keeping only pixels within the Q1, Q2, Q3, Q4, and Q5 pixel distances; Step 3 specifically includes the following steps: Step 3.1: Binarize the original image of lobster growth status monitoring after background removal to obtain the binarized image of lobster growth status monitoring. Step 3.2: Rotate the collected binarized lobster growth status monitoring images by 5°-90°, with a unit interval of 5°. Label the rotated images as G1, G2, ..., G18, and label one of the rotated images as Gi, where i = 1-18. Step 3.3: Using 10×10 pixels as intervals, perform horizontal pixel block statistics on Gi. When the proportion of black pixels in a pixel block is 30%, the pixel block is counted as a lobster foreground pixel. Count the number of lobster background blocks in each row and mark it as Wij, where i is the image number and j is the row number. Step 3.4: The sum of the number of background pixels in each binarized lobster growth status monitoring image is labeled as the lobster area Si. Where i is the image number of the rotation, and the pixel value is 1920×1080; Step 3.5: Count the number of foreground pixel blocks of lobsters in each column using 10×10 pixels, and label them as Nik, where i is the image number and k is the column number; Step 3.6: Calculate the maximum values ​​of the number of lobster foreground pixels (Nik) in each column and the number of lobster background pixels (Wij) in each row of the rotated image Gi. Label these values ​​as the lobster length (Li) and width (Wi) of the rotated image, respectively, and label the aspect ratio (Yi). Li = (Nik)max Wi = (Wij)max Yi = Li / Wi; Where i = 1-18 Step 3.7: Sort the aspect ratios Yi, take the maximum value as the image for calculating the lobster's width and height, and label it with the sequence number n. Then, the characteristic values ​​of the lobster obtained are area S, width W, and length L: S = Sn L = Ln W = Wn Step 3.8: Statistically analyze the lobster characteristic values ​​obtained in Step 3.7 within one day, and label them as Sm, Lm, and Wm, where m is the serial number. Control the raising and lowering time of the shrimp collection cage to 15 minutes, and obtain 0 or 1 shrimp. Calculate the mean of the width-to-height ratio Ym, and remove sample data that deviate from the mean by 50%. Step 3.9: Calculate the mean values ​​Su, Wu, and Lu for the area, width, and length of the lobster samples collected within one day, after removing those that deviate from the mean, and record the breeding time; Step 3.10: Compare Su, Wu, and Lu longitudinally according to the breeding time to monitor the growth changes of lobsters.

2. An IoT monitoring device for implementing the IoT monitoring method for the growth status of crayfish in rice paddies as described in claim 1, characterized in that: The IoT monitoring device includes a shrimp collection module (4) placed on a lobster feeding platform to collect original images of lobster growth. A solar charging module (1) is set above the shrimp collection module (4). The telescopic motor (301) in the telescopic image recognition module (3) is installed on the mounting platform (103) in the solar charging module (1). The telescopic image recognition module (3) acquires the original images of lobster growth collected by the shrimp collection module (4) and transmits the acquired original images of lobster growth to the cloud data server (2) through a 4G channel to monitor the growth changes of the lobster.

3. The IoT monitoring device for the growth status of rice paddy crayfish according to claim 2, characterized in that: The shrimp collecting module (4) is a shrimp cage structure, including a net cage (401) placed in the lobster foraging area, a shrimp collecting head (404), an escape plate (402), an escape spring (403), a lifting screw hole (405), and an escape column hole (406). The net cage (401) is a structure that allows entry but not exit. The shrimp collecting head (404) and the net cage (401) are softly connected by a channel composed of an elastic connecting net. Both the shrimp collecting head (404) and the net cage (401) are provided with corresponding inlets and outlets, allowing lobsters to enter the shrimp collecting head (404) from the net cage (401). After the shrimp collecting head (404) rises, it enters through the elastic connecting net. The escape plate (402) is connected to the bottom of the shrimp collecting head (404) via an escape spring (403). When the escape rod (305) in the telescopic image recognition module (3) descends to the escape column hole (406), the escape plate (402) is opened, and the lobster falls into the water to escape. The lifting screw hole (405) is on the top of the shrimp collecting module (4) and is connected to the lifting rod (304) of the telescopic image recognition module (3) via a thread, so that the shrimp collecting module (4) leaves the water surface. The telescopic image recognition module (3) identifies the size and number of lobsters. The escape column hole (406) is on the top of the shrimp collecting module (4) and the escape plate (402) is opened by the escape rod (305).

4. The IoT monitoring device for the growth status of rice paddy crayfish according to claim 3, characterized in that: The release of the lobster is achieved by the following mechanism: the telescopic motor (301) reverses, the RS485 laser rangefinder (302) measures the release height, the escape board (402) opens, the lobster enters the water, the telescopic motor (301) rotates forward, the RS485 laser rangefinder (302) measures the height to be placed in the water, and the lobster head (404) enters the water.

5. The IoT monitoring device for the growth status of crayfish in rice paddies according to claim 2, characterized in that: The solar charging module (1) includes a solar panel (101), an IoT module (102) with an RS485 interface, an installation platform (103), a controller (104), and a column (105). The solar panel (101) is installed on the top of the column (105). The installation platform (103) is fixed to the upper part of the column (105) and close to the solar panel (101). The installation platform (103) is used to install a camera (303), a controller (104), a telescopic motor, and the IoT module (102). The controller (104) is equipped with a 7-inch MCGS PRO with a 4G IoT card as the main control unit. It has an external RS485 voltage acquisition module, a solar charge and discharge management module, and an RS485 DI / DO acquisition module. The main control unit has a built-in 4G data card and has an RS485 interface and an RJ45 interface. The solar charge and discharge management module works independently and has a voltage monitoring output port connected to the voltage acquisition module. The RS485 interface uses MODBUS. The RTU protocol is used to acquire the lithium battery voltage through the RS485 voltage acquisition module and to acquire 4 DI information channels through the RS485 DI / DO acquisition module to control 4 DO output channels. The RJ45 interface uses the TCP / IP protocol to transmit camera image signals. There are two image acquisition modes: video mode and photo transmission mode. The video acquisition interface program of MCGS PRO is used to implement the video acquisition mode. The photo transmission mode can save data on the data card.

6. The IoT monitoring device for the growth status of rice paddy crayfish according to claim 5, characterized in that: The telescopic image recognition module (3) includes a telescopic motor (301), an RS485 laser rangefinder (302), a camera (303) with an RJ45 interface, a lifting rod (304), and an escape rod (305). The telescopic motor (301) is mounted on the installation platform (103). The lifting rod (304) is connected to the telescopic motor (301) via a coupling. The escape rod (305) is mounted below the installation platform (103), and the escape rod (305) and the lifting rod (304) are aligned with the escape column hole (406) and the lifting screw hole (404) in the shrimp collection module (4). 405), the controller (104) controls the forward and reverse rotation and power-on of the motor by controlling 2 DOs respectively, thereby realizing the forward and reverse rotation control of the motor. The camera (303) is installed below the mounting platform (103). The RS485 laser rangefinder (302) is installed on the top of the mounting platform (103) by drilling, exposing the laser probe. The RS485 communication interface of the RS485 laser rangefinder (302) and the controller (104) is connected to the RS485 interface of the Internet of Things module (102). The RJ45 interface of the camera (303) is connected to the RJ45 interface of the Internet of Things module (102).

7. The IoT monitoring device for the growth status of crayfish in rice paddies according to claim 2, characterized in that: The cloud data server (2) includes an IoT terminal (201) and a cloud data server (2). The photos taken by the camera (303) in the solar charging module (1) interact with the IoT terminal (201) and the cloud data server (2) through the 4G channel. At the same time, the IoT terminal (201) publishes control through the MQTT protocol, which can be accessed by mobile phones to realize mobile phone control and viewing.

Images