TW202214099A - System and method for smart aquaculture - Google Patents

Abstract

A smart aquaculture system includes a breeding pool, a bait machine, a moving module, a camera, and a computing module. The moving module is disposed above the breeding pool. The bait machine is connected to the moving module. The computing module obtains an image by the camera, detects an aquatic organism in the image, and calculates at least one indicator corresponding to the aquatic organism. The computing module also calculates a bait amount according to the index, and controls the moving module to move the bait machine to the position of the aquatic organism to through feed that matches the bait amount.

Description

Smart farming system and method

The present disclosure is about a smart farming system, which can adaptively determine the feeding amount according to the state of aquatic organisms.

In shrimp farms, the weight and length of shrimp are a set of important reference indicators for aquaculture managers. Since shrimps live in water for a long time, in order to measure the weight of the shrimps in the conventional technology, the shrimps must be salvaged. This method requires a lot of manpower, and at the same time, it is easy to cause the shrimps to be uneasy and die. How to improve the above practice is a topic of concern to those skilled in the art.

The embodiment of the present invention provides a smart breeding system, which includes a breeding pond, a feeding machine, a moving module, a camera and a computing module. The mobile module is arranged on the breeding pond, and the feeder is connected to the mobile module. The camera is used to capture images corresponding to the breeding pond. The computing module is communicatively connected to the camera, the moving module and the bait-casting machine, and is used for acquiring images, detecting aquatic organisms in the images, and calculating at least one indicator corresponding to the aquatic organisms, and the indicator includes the amount of dung being dragged. The calculation module is also used to calculate the feeding amount according to the index, and control the moving module to make the feeding machine move to the position of the aquatic organisms and input the feed that meets the feeding amount.

In some embodiments, the calculation module is used to substitute the length of the aquatic organism into a regression function to calculate the weight of the aquatic organism, and calculate the feeding amount according to the weight of the aquatic organism.

In some embodiments, the calculation module is further configured to perform the following steps: detecting the head and tail of the aquatic creature in the image, calculating the central axis between the head and the tail; setting a preset range from the central axis to the tail , and determine whether there are feces pixels within the preset range; and if there are feces pixels within the preset range, calculate a dragging length as the dragging amount.

In some embodiments, the above-mentioned step of calculating the dragging manure length includes: performing a breadth-first search on the manure pixels to calculate the dragging manure length; and if the dragging manure length is greater than a preset value, outputting the dragging manure length as the dragging manure amount, Otherwise, it is judged that there is no dragging of feces.

In some embodiments, the smart farming system further includes a cleaning module for cleaning the farming pond. The calculation module is further configured to perform the following steps: dividing the culture pond into a plurality of areas; and judging the number of aquatic organisms in each area according to the image, and determining the frequency of cleaning the corresponding area by the cleaning module according to the number of aquatic organisms.

From another perspective, the embodiments of the present invention provide a smart farming method, which is suitable for a smart farming system. The smart breeding system includes a breeding pond, a feeding machine, a mobile module, and a camera, wherein the mobile module is arranged on the breeding pond, and the feeding machine is connected to the mobile module. The smart farming method includes: capturing an image corresponding to a breeding pond through a camera; detecting aquatic organisms in the image, calculating at least one index of the corresponding aquatic organism, the index including the amount of feces being dragged; and calculating a feeding amount according to the index, and controlling The moving module moves the bait machine to the position of the aquatic creatures and puts in the feed that matches the bait amount.

FIG. 1 is a schematic diagram illustrating a smart farming system according to an embodiment. Referring to FIG. 1 , the smart breeding system 100 includes a breeding tank 110 , a feeding machine 120 , a moving module 130 , a camera 140 , a computing module 150 , a cleaning module 160 and a sewage pipe 170 . In this embodiment, the shape of the cultivation pond 110 is circular when viewed from above, and the aquatic organisms raised in the cultivation pond 110 are shrimps, but in other embodiments, they may also be fish or other suitable aquatic organisms. The moving module 130 includes a motor 131 and a bracket 132 . The moving module 130 is disposed above the breeding tank 110 . The camera 140 , the bait caster 120 and the cleaning module 160 are all connected to the moving module 130 .

The feeder 120 can be used to put feed into the breeding tank 110 , and the amount of feed (also referred to as feeding amount) can be controlled by the calculation module 150 . The camera 140 is an underwater camera, which includes a Charge-coupled Device (CCD) sensor, a Complementary Metal-Oxide Semiconductor (Complementary Metal-Oxide Semiconductor) sensor, or other suitable photosensitive elements, in some embodiments The middle camera 140 can also sense infrared or other invisible light. The computing module 150 can be various electronic devices or circuits with computing capabilities. For example, the computing module 150 can be a personal computer, a notebook computer, a server or an industrial computer. The computing module 150 can include a central processing unit, a graphics Processors, microprocessors, microcontrollers, image processing chips, special application integrated circuits, etc. The cleaning module 160 has an extraction capability to clean up excrement or remaining feed at the bottom of the pool.

The computing module 150 can be connected to the motor 131 , the camera 140 , the baitcaster 120 and the cleaning module 160 through wired or wireless communication, so as to control the positions of the camera 140 , the baitcaster 120 and the cleaning module 160 . Specifically, the bracket 132 is an inverted "T" shape, the motor 131 is controlled by the computing module 150 , and driven by the motor 131 , the bracket 132 can rotate 360 degrees. On the other hand, the moving module 130 further includes a plurality of rollers and motors (not shown), which are respectively connected to the camera 140 , the bait caster 120 and the cleaning module 160 . These motors can also be controlled by the computing module 150 , so that the camera 140. The bait casting machine 120 and the cleaning module 160 can move horizontally on the bracket 132. From another perspective, from the top of the breeding tank 110, the motor 131 can determine the angle of the polar coordinate, and the motor connected to the camera 140, the feeder 120 and the cleaning module 160 can determine the radius of the polar coordinate, so that the camera 140 , the feeding machine 120 and the cleaning module 160 can be moved to any position of the breeding tank 110 .

The camera 140 is used for capturing an image corresponding to the breeding tank 110 , and the image is sent to the computing module 150 . The calculation module 150 detects aquatic organisms in the image, and calculates one or more indicators corresponding to the aquatic organisms, and these indicators may include the length, width, weight, and fecal volume of the aquatic organisms. According to these indicators, the feeding amount can be calculated, and then the calculation module 150 will control the moving module 130 to make the feeding machine 120 move to the position of the aquatic organisms and feed the feed that meets the above-mentioned feeding amount. In this way, the feeding amount can be adaptively determined according to the conditions of the aquatic organisms, the feed will not be wasted, and the feed will not be left to pollute the water in the breeding tank 110, and the aquatic organisms can also eat enough feed to grow smoothly. .

FIG. 2 is a schematic diagram illustrating a captured image according to an embodiment. Referring to FIG. 2 , first, the computing module 150 can detect aquatic organisms (shrimp in this embodiment) in the image through a machine learning algorithm. The machine learning algorithm is, for example, a convolutional neural network, which can be TensorFlow, VOLO, or any suitable tool to perform object detection. In some embodiments, a bounding box, such as a bounding box 210, can be obtained after the object detection is performed. The length of the bounding box 210 can be set to the length of the aquatic creature 211, or the length of the bounding box 210 can be set. Multiply by a ratio to get the length of the aquatic creature 211. In some embodiments, after the object detection is performed, each pixel can be divided into shrimp and non-shrimp, and the length of the aquatic creature 211 can be calculated according to the pixels belonging to the shrimp. Here, the length of the aquatic creature 211 can be substituted into the pre-trained regression function to calculate the weight of the aquatic creature 211 . Specifically, the length of multiple aquatic organisms can be collected in advance, and the weight of aquatic organisms can be obtained by weighing, and the regression function between length and weight can be calculated through regression analysis. The regression function can be A linear function, a polynomial function, an exponential function or a combination thereof, the present invention is not limited thereto. By the above method, the weight of the aquatic organism 211 can be directly calculated without salvaging the aquatic organism 211 . In some embodiments, the amount of bait can be determined according to the weight. Generally speaking, the larger the weight, the larger the amount of bait. The amount of bait can be obtained, for example, by looking up a table.

In some embodiments, the feeding amount can be determined according to the amount of manure dragged, and the amount of dragged manure refers to the length of the dragged manure. Specifically, FIG. 3 is a flowchart illustrating the calculation of the dragging length according to an embodiment. Referring to FIG. 2 and FIG. 3 , in step 301 , the head 221 and the tail 222 of the aquatic creature in the image are detected according to a machine learning algorithm. In this embodiment, both the head 221 and the tail 222 are surrounded by a bounding box.

In step 302, the central axis 223 between the head 221 and the tail 222 is calculated. For example, the center axis 223 is formed from the center point of the bounding box of the head 221 to the center point of the bounding box of the tail 222 .

In some embodiments, in step 301, each pixel in the image is classified into head pixels, tail pixels, and other categories. In step 302 , a central axis 223 may be formed by extending from the centroid of the head pixel to the centroid of the tail pixel.

In step 303 , a predetermined range 230 is set in the direction from the central axis 223 to the tail 222 . The predetermined range 230 can be determined by experiment to determine its width and length, and the invention is not limited thereto.

In step 304, a machine learning algorithm is executed to classify each pixel within the predetermined range 230 as a fecal pixel and a non-fecal pixel. In this example, the shrimp has a situation of dragging feces, so there are a plurality of feces pixels 231 within the preset range 230 .

In step 305, it is judged whether there is a feces pixel within the preset range 230, if not (that is, the dragging length is 0), then step 306 is performed to judge that there is no dragging.

If the determination result in step 305 is yes, in step 307, a breadth-first search (BFS) is performed for the fecal pixels. Next, in step 308, the drag length is calculated according to the result of the breadth-first search. For example, a breadth-first search is performed starting from the feces pixel closest to the center point of the tail 222, and adjacent pixels are treated as pixels of depth 1, and then spread out to find pixels of depth 2, until there are no adjacent feces pixels, The largest depth is the length of the dung, which should be understood by those with ordinary knowledge in the field, and will not be described in detail here.

In step 309, it is judged whether the dragging manure length is greater than the preset value, if so, the dragging manure length is output in step 310 as the dragging manure amount, if not, returning to step 306 to judge that there is no dragging manure situation. Generally speaking, the longer the dung length is, the more full the shrimp will be, so the amount of bait can be reduced. On the contrary, when there is no dung or the length of the dung is relatively small, the amount of bait can be increased.

Referring back to FIG. 1 , in some embodiments, the frequency of cleaning may also be determined according to the number of aquatic organisms. Specifically, the bottom of the culture pond 110 can be drawn into multiple areas, and the number of aquatic organisms in each area can be determined according to the image captured by the camera 140, and the frequency of cleaning the corresponding area by the cleaning module 160 can be determined according to this number. . For example, if the number of aquatic organisms in a certain area exceeds a critical value, the cleaning module 160 will be frequently controlled to perform cleaning in this area, otherwise, the cleaning will be performed according to an existing schedule. In some embodiments, the above-mentioned critical value is to multiply the number of all aquatic organisms in the culture pond 110 by x%, where x is an integer between 0 and 100, and the present invention does not limit the value of x.

In some embodiments, the smart farming system 100 can also set the light source 180 at any appropriate position, for example, on the horizontal sides of the farming pond 110, the light source 180 can emit red light, and when the red light shines on the shrimp, it can appear The gonads of shrimp can be detected through image processing technology. When it is judged that the gonads are mature, a warning can be issued to remind the breeders to perform artificial mating.

FIG. 4 is a flowchart illustrating a smart farming method according to an embodiment, and the method can be applied to the smart farming system 100 of FIG. 1 . Referring to FIG. 4, in step 401, an image corresponding to the breeding pond is captured through a camera. In step 402, aquatic organisms in the image are detected, and at least one indicator of aquatic organisms is calculated, including the amount of feces dragged. In step 403, the feeding amount is calculated according to the index, and the moving module is controlled to make the feeding machine move to the position of the aquatic creatures and feed the feed that meets the feeding amount. However, each step in FIG. 4 has been described in detail as above, and will not be repeated here. It should be noted that each step in FIG. 4 can be implemented as a plurality of codes or circuits, and the present invention is not limited thereto. In addition, the method of FIG. 4 may be used in conjunction with the above embodiments, or may be used alone. In other words, other steps may be added between the steps in FIG. 4 .

In the above-mentioned smart farming system and method, the amount of feed can be adaptively determined by the weight of the shrimp and the amount of manure dragged, so that the feed will not be wasted, and the aquatic organisms can also eat enough feed. Experiments have found that such a mechanism The weight of shrimp can be increased under the same breeding time.

Although the present invention has been disclosed above by the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, The protection scope of the present invention shall be determined by the scope of the appended patent application.

100: Smart Breeding System 110: Breeding pond 120: Bait Caster 130: Mobile Mods 131: Motor 132: Bracket 140: Camera 150: Computing Module 160: Cleanup mods 170: Sewage pipe 180: light source 210: Bounding Box 211: Aquatic Creatures 221: Head 222: tail 223: Central axis 230: Preset range 231: Stool Pixel 301~310, 401~403: Steps

In order to make the above-mentioned features and advantages of the present invention more obvious and easy to understand, the following embodiments are given and described in detail with the accompanying drawings as follows. [FIG. 1] is a schematic diagram illustrating a smart farming system according to an embodiment. [ FIG. 2 ] is a schematic diagram illustrating a captured image according to an embodiment. [ FIG. 3 ] is a flow chart illustrating the calculation of the dragging length according to an embodiment. [FIG. 4] is a flowchart illustrating a smart farming method according to an embodiment.

210: Bounding Box

211: Aquatic Creatures

221: Head

222: tail

223: Central axis

230: Preset range

231: Stool Pixel

Claims (10)

A smart farming system, comprising: a breeding pond; a bait-casting machine; a mobile module, arranged on the breeding pond, wherein the bait caster is connected to the mobile module; a camera for capturing images corresponding to the pond; and a computing module, communicatively connected to the camera, the moving module and the bait-casting machine, for acquiring the image, detecting aquatic creatures in the image, and calculating at least one index corresponding to the aquatic creature, the at least one index Including the amount of manure dragged, a bait amount is calculated according to the at least one index, and the moving module is controlled to make the bait dispenser move to the position of the aquatic organism to put in the feed that meets the bait amount. The smart farming system according to claim 1, wherein the at least one indicator further includes the length of the aquatic organism, and the calculation module is used for substituting the length of the aquatic organism into a regression function to calculate the weight of the aquatic organism, and The feeding amount is calculated according to the weight of the aquatic organism. The smart farming system according to claim 1, wherein the computing module is further configured to perform the following steps: detecting the head and tail of the aquatic creature in the image, and calculating the central axis between the head and the tail; Setting a predetermined range from the central axis to the tail, and determining whether there are feces pixels within the predetermined range; and If there are feces pixels within the preset range, a feces dragging length is calculated as the feces dragging amount. The intelligent breeding system as claimed in claim 3, wherein the step of calculating the length of the dragged manure comprises: performing a breadth-first search on the feces pixels to calculate the drag length; and If the dragging manure length is greater than a preset value, output the dragging manure length as the dragging manure amount, otherwise it is judged that there is no dragging manure condition. The smart farming system as described in claim 1 further includes: a cleaning module for cleaning the breeding pond, The computing module is also used to perform the following steps: dividing the pond into zones; and The number of the aquatic organisms in each of the areas is determined according to the image, and the frequency of cleaning the corresponding area by the cleaning module is determined according to the number of the aquatic organisms. A smart breeding method is applicable to a smart breeding system. The smart breeding system includes a breeding pond, a feeding machine, a mobile module, and a camera, the mobile module is arranged on the breeding pond, and the feeding machine is connected to The mobile module and the smart farming method include: Capture images corresponding to the breeding pond through the camera; Detecting aquatic organisms in the image, and calculating at least one index corresponding to the aquatic organisms, the at least one index includes the amount of dragged feces; and Calculate a feeding amount according to the at least one index, and control the moving module to move the feeding machine to the position of the aquatic creature to throw the feed that matches the feeding amount. The smart farming method according to claim 6, wherein the at least one indicator further includes the length of the aquatic organism, and the smart farming method further includes: The length of the aquatic organism is substituted into a regression function to calculate the weight of the aquatic organism, and the feeding amount is calculated according to the weight of the aquatic organism. The smart farming method according to claim 6, further comprising: detecting the head and tail of the aquatic creature in the image, and calculating the central axis between the head and the tail; Setting a predetermined range from the central axis to the tail, and determining whether there are feces pixels within the predetermined range; and If there are feces pixels within the preset range, a feces dragging length is calculated as the feces dragging amount. The intelligent breeding method as claimed in claim 8, wherein the step of calculating the length of the dragged manure comprises: performing a breadth-first search on the feces pixels to calculate the drag length; and If the dragging manure length is greater than a preset value, output the dragging manure length as the dragging manure amount, otherwise it is judged that there is no dragging manure condition. The smart farming method according to claim 6, wherein the smart farming system further includes a cleaning module, and the smart farming method further includes: dividing the pond into zones; and The number of the aquatic organisms in each of the areas is determined according to the image, and the frequency of cleaning the corresponding area by the cleaning module is determined according to the number of the aquatic organisms.

Images