CN111240200A - Fish swarm feeding control method, fish swarm feeding control device and feeding boat - Google Patents
Fish swarm feeding control method, fish swarm feeding control device and feeding boat Download PDFInfo
- Publication number
- CN111240200A CN111240200A CN202010049388.XA CN202010049388A CN111240200A CN 111240200 A CN111240200 A CN 111240200A CN 202010049388 A CN202010049388 A CN 202010049388A CN 111240200 A CN111240200 A CN 111240200A
- Authority
- CN
- China
- Prior art keywords
- feeding
- fish school
- image
- fish
- bait
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 79
- 235000003642 hunger Nutrition 0.000 claims abstract description 103
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 59
- 230000037406 food intake Effects 0.000 claims abstract description 52
- 238000005266 casting Methods 0.000 claims abstract description 39
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 33
- 235000012631 food intake Nutrition 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 28
- 238000003860 storage Methods 0.000 claims description 18
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 229910052760 oxygen Inorganic materials 0.000 claims description 6
- 239000001301 oxygen Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013519 translation Methods 0.000 claims description 5
- 235000002566 Capsicum Nutrition 0.000 claims description 4
- 239000006002 Pepper Substances 0.000 claims description 4
- 235000016761 Piper aduncum Nutrition 0.000 claims description 4
- 235000017804 Piper guineense Nutrition 0.000 claims description 4
- 235000008184 Piper nigrum Nutrition 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 150000003839 salts Chemical class 0.000 claims description 4
- 230000003416 augmentation Effects 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 230000002411 adverse Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 9
- 210000004027 cell Anatomy 0.000 description 7
- 238000005070 sampling Methods 0.000 description 6
- 210000003128 head Anatomy 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 241000722363 Piper Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009360 aquaculture Methods 0.000 description 2
- 244000144974 aquaculture Species 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- 230000001965 increasing effect Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005518 electrochemistry Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 244000144980 herd Species 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 230000037351 starvation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/80—Feeding devices
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Marine Sciences & Fisheries (AREA)
- Zoology (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Artificial Intelligence (AREA)
- Farming Of Fish And Shellfish (AREA)
Abstract
The embodiment of the invention provides a fish school feeding control method, a fish school feeding control device and a feeding boat, wherein the method comprises the following steps: acquiring a food intake image in a fish school food intake process; inputting the ingestion image into a preset convolutional neural network model, and outputting the hunger degree of the fish school; controlling the bait feeding amount according to the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label. The method inputs the ingestion image into a preset convolutional neural network model, outputs the hunger degree of the fish school, and is beneficial to obtaining the hunger degree of the fish school in the bait casting process. On the basis of acquiring the hunger degree of the fish school, the bait feeding amount is controlled according to the hunger degree of the fish school, so that targeted bait feeding is realized, individual balance among the fish schools is guaranteed, and the integral growth of the fish schools is facilitated. Meanwhile, not only is the bait consumption saved, but also the adverse effect of excessive feeding on the water area environment is avoided.
Description
Technical Field
The invention relates to the field of aquaculture, in particular to a fish school feeding control method, a fish school feeding control device and a feeding boat.
Background
In aquaculture, the feeding level of the fish determines the efficiency and production cost of the culture. The unreasonable feeding can lead to low bait utilization rate, uneven fish shoal growth and even environmental pollution.
However, most of the conventional bait casting machines are fixed type bait casting machines which feed regularly, quantitatively and in fixed positions. Although there are feeding devices that can achieve autonomous cruise feeding, targeted feeding according to fish distribution or bait demand during feeding is still not possible. In the feeding process of large water level, the current method can cause the phenomenon of uneven feeding, thereby increasing the individual difference among fish groups and influencing the growth of fish. At the same time, too much bait not ingested by the fish shoal can also have an adverse effect on the environment.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a fish school feeding control method, a fish school feeding control device, and a feeding boat.
In a first aspect, an embodiment of the present invention provides a fish school bait casting control method, including: acquiring a food intake image in a fish school food intake process; inputting the ingestion image into a preset convolutional neural network model, and outputting the hunger degree of the fish school; controlling the bait feeding amount according to the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
Further, the acquiring of the food intake image in the fish school food intake process comprises: acquiring a feeding image in the feeding process of the fish school in each water area; correspondingly, the bait feeding amount is controlled according to the hunger degree of the fish school, and the method specifically comprises the following steps: on a preset running path, controlling the bait casting amount to perform bait casting according to the hungry degree of fish school passing through the water area; and calculating the preset running path according to the fish shoal hunger degree of each water area.
Further, according to the hunger degree of the fish, before controlling the bait feeding amount: further comprising: acquiring water quality parameters of a region to be fed; correspondingly, according to the hunger degree of the fish school, the bait feeding amount is controlled, and the method specifically comprises the following steps: and controlling the bait feeding amount according to the hunger degree of the fish school and the water quality parameter.
Further, before acquiring the food intake image in the fish school food intake process, the method further comprises the following steps: acquiring images of ingestion of a plurality of fish schools, and marking the hunger degree of each image to obtain a plurality of image samples; and training the established convolutional neural network model by using the plurality of image samples to obtain the preset convolutional neural network model.
Further, after the acquiring the images of the plurality of fish school feeding, the method further comprises: zooming the acquired images to a preset size; the Retinex (retina cerebral cortex theory) algorithm is used for enhancing the image, so that the contrast is improved; correspondingly, labeling the hunger degree of each image specifically includes: and marking the hunger degree of each image after the enhancement processing.
Further, after the labeling of the hunger degree of each image, the method further includes: performing expansion processing on each marked image to enable each original image to obtain a plurality of expanded images; the augmentation process includes: rotation, translation, gaussian and salt and pepper noise.
In a second aspect, an embodiment of the present invention provides a fish feeding control device, including: the image acquisition module is used for acquiring a food intake image in a fish school food intake process; the processing module is used for inputting the ingestion image into a preset convolutional neural network model and outputting the hunger degree of the fish school; the control module is used for controlling the bait feeding amount according to the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the fish feeding control method according to the first aspect of the present invention.
In a fourth aspect, an embodiment of the present invention provides a bait casting boat, including: the device comprises a ship body, a propulsion motor, a propeller, a bin, a stepping motor, a storage battery, an underwater camera and the electronic equipment in the third aspect of the invention; the boat body is used for providing buoyancy to enable the bait casting boat to float on the water surface; the propulsion motor is connected with the propeller and used for driving the ship body to move; the feed bin is arranged on the ship body and used for containing bait, and a valve is arranged at a feed opening of the feed bin; the stepping motor is used for controlling the opening and closing of the valve or the opening and closing size of the valve so as to control the bait feeding amount; the storage battery is used for providing power supply; the underwater camera is used for acquiring a food intake image of a fish school and sending the food intake image to the electronic equipment; and the electronic equipment is used for acquiring the hunger degree of the fish school according to the ingestion image and controlling the bait feeding amount through the stepping motor according to the hunger degree.
Further, the feeding boat further comprises a water quality sensor for collecting water temperature and dissolved oxygen concentration.
According to the fish school feeding control method, the fish school feeding control device and the feeding boat provided by the embodiment of the invention, the ingestion image is input into the preset convolutional neural network model, and the hunger degree of the fish school is output, so that the hunger degree of the fish school can be obtained in the feeding process. On the basis of acquiring the hunger degree of the fish school, the bait feeding amount is controlled according to the hunger degree of the fish school, so that targeted bait feeding is realized, individual balance among the fish schools is guaranteed, and the integral growth of the fish schools is facilitated. Meanwhile, not only is the bait consumption saved, but also the adverse effect of excessive feeding on the water area environment is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a fish feeding control method according to an embodiment of the present invention;
FIG. 2 is a structural diagram of a fish feeding control device according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention;
FIG. 4 is a schematic structural view of a bait-controlled boat according to an embodiment of the present invention;
description of reference numerals: the device comprises a solar cell panel 1, a storage bin 2, a storage battery 3, an obstacle avoidance sensor 4, a support 5, a stepping motor 6, a propulsion motor 7, a floating body 8, a propeller 9, a feed opening 10, a valve 11, bait 12, an underwater camera 13, a cradle head 14 and a water quality sensor 15, wherein the solar cell panel is arranged on the support, the floating body 8 is arranged on the support, the underwater camera 13 is arranged on the underwater camera 13, and the cradle head 14 is arranged on the support; the processing unit is controlled by 16.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a fish school bait casting control method according to an embodiment of the present invention, and as shown in fig. 1, a fish school bait casting control method according to an embodiment of the present invention includes:
101. and acquiring a feeding image in the feeding process of the fish school.
The method of the embodiment of the invention can be applied to automatic or semi-automatic bait casting equipment, such as a bait casting ship. In the specific implementation process, a control processing unit can be arranged on the head feeding boat, and the control processing unit can be a PC (personal computer), an industrial personal computer or an industrial server. Firstly, the control processing unit can acquire an image of a fish feeding process through the camera device, for example, a small amount of bait is thrown firstly, and then an image of a fish school feeding process is acquired through the camera device, for example, an underwater camera arranged in front of a feeding area is used for acquiring a dynamic or static image of the fish school in the feeding process, namely, a feeding image.
When arranging the underwater camera, in order to ensure the best image acquisition visual angle, the underwater camera is arranged in front of the feeding area. Taking fish culture as an example, the underwater camera is arranged at the lower part in front of the ship body. Wherein, the preferred network camera that is preferred to the camera under water, image output: 1920(H) × 1080(V), 1080P high definition, underwater viewing angle: about 75 ° x50 °. The external light source can complete video shooting in a dark environment. And the control processing unit is connected with the RJ45 interface.
102. Inputting the ingestion image into a preset convolutional neural network model, and outputting the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
The control processing unit is internally preset with a trained convolutional neural network model, the network model is obtained after training according to the fish school feeding image sample with the hunger degree label, and the corresponding hunger degree can be analyzed on the input fish school feeding image. And after the image of the fish school feeding process acquired by the camera device is input into the convolution network model, the hunger degree of the fish school can be output.
For example, one setting manner for relieving the hunger degree may be three, which is very hungry, hungry and not hungry, and the following description is given by taking this as an example.
103. Controlling the feeding amount according to the hunger degree of the fish school.
And after the control processing unit obtains the hunger degree of the fish school, controlling the feeding speed of the feeding device according to the hunger degree. For example, if the degree of hunger is "very hungry", the feeding amount is increased; if the hunger degree is 'not hungry', the feeding is closed; when the hunger degree is hungry, the feeding rate is reduced or the feeding amount is kept. The amount of bait cast may be a time-dependent amount, i.e. controlling the amount of bait cast also includes controlling the speed of bait cast.
In the specific implementation process, a driving path of a bait casting ship can be planned through clients such as a mobile phone APP, the bait casting ship obtains the hungry degree of a fish school at a passing point on the driving path to feed, and the bait casting ship drives to the next passing point until the solving degree of the fish school is fed to be not hungry until the whole driving path is completed.
According to the control method for fish school bait casting provided by the embodiment, the ingestion image is input into the preset convolutional neural network model, and the hunger degree of the fish school is output, so that the hunger degree of the fish school can be obtained in the bait casting process. On the basis of acquiring the hunger degree of the fish school, the bait feeding amount is controlled according to the hunger degree of the fish school, so that targeted bait feeding is realized, individual balance among the fish schools is guaranteed, and the integral growth of the fish schools is facilitated. Meanwhile, not only is the bait consumption saved, but also the adverse effect of excessive feeding on the water area environment is avoided.
Based on the content of the above embodiments, as an alternative embodiment, acquiring a food intake image during a fish school food intake process includes: acquiring a feeding image in the feeding process of the fish school in each water area; correspondingly, the bait feeding amount is controlled according to the hunger degree of the fish school, and the method specifically comprises the following steps: on a preset running path, controlling the bait casting amount to perform bait casting according to the hungry degree of fish school passing through the water area; and calculating the preset running path according to the fish shoal hunger degree of each water area.
In order to further realize the accurate feeding of bait, the whole area of waiting to feed can be divided into the multi-disc waters in this embodiment, and every water area can correspond to the region that the camera can catch. Taking the feeding boat as an example, the control processing unit is used for acquiring the hunger degree of the fish school in each water area, and then a preset driving path is planned and obtained according to the hunger degree of the fish school. For example, the bait casting boat may first pass through each water area, feed a small amount of bait to obtain the overall hungry degree of fish in all water areas, and then plan a bait casting route according to the hungry degree of each water area. In the embodiment of three hunger degrees, if the hunger degree of the fish school in the water area is judged to be "not hungry", the fish school is classified as not needing to be fed and is excluded from the preset running route, and then the route planning is carried out according to the water areas of "hungry" and "very hungry", so that one running route can pass through all the water areas needing to be fed. The motion trail of the bait casting boat can be set on the mobile phone APP, accordingly, the hunger degree of each passing water area of the running path is obtained, feeding can be carried out through the control processing unit based on the obtained hunger degree after the bait casting boat runs to the corresponding water area, and the feeding amount and the feeding speed are controlled.
Based on the content of the above embodiment, as an alternative embodiment, the controlling the bait feeding amount according to the hunger degree of the fish group comprises: further comprising: acquiring water quality parameters of a region to be fed; correspondingly, according to the hunger degree of the fish school, the bait feeding amount is controlled, and the method specifically comprises the following steps: and controlling the bait feeding amount according to the hunger degree of the fish school and the water quality parameter.
The water quality parameter includes dissolved oxygen volume and temperature, and the accessible is preset water quality sensor and is acquireed water quality parameter, and water quality sensor can be electrochemistry or optical sensor, uses electrochemical sensor in this embodiment, dissolved oxygen measuring range: 0-40 mg/L, precision: 0.2 mg/L; temperature measurement range: 0-40 ℃, precision: . + -. 0.1 ℃. And the control processing unit is connected with the RS485 interface.
Comprehensively considering the control of the bait feeding amount, such as little bait feeding or no bait feeding in water areas with poor water quality. The bait feeding amount is controlled by combining the water quality parameters, so that the phenomenon that fish swarms ingest in water areas with poor water quality, the growth of the fish swarms is influenced, and meanwhile, the water quality is further deteriorated due to the movement of the fish swarms and excrement can be avoided.
On the basis, the control processing unit performs feeding based on the obtained hunger degree, and one implementation way of controlling the feeding amount and feeding speed is shown in table 1:
TABLE 1
Based on the content of the foregoing embodiment, as an optional embodiment, before acquiring the food intake image in the fish school food intake process, the method further includes: acquiring images of ingestion of a plurality of fish schools, and marking the hunger degree of each image to obtain a plurality of image samples; and training the established convolutional neural network model by using the plurality of image samples to obtain the preset convolutional neural network model.
The preset convolutional network model also comprises a training process before use, namely setting training parameters and training the CNN. In this embodiment, the learning rate at the time of training is set to 0.05, n _ epochs is set to 200, nkerns (convolution kernel parameter) is set to [5,10], and batch _ size is set to 40. If the set termination condition is reached, the training is ended, and the termination condition is set to n _ epochs as 200 in this embodiment.
Images of the ingestion of a plurality of fish herds of known hunger levels are obtained, and 80% can be randomly selected as a training set, 10% can be used as a testing set, and 10% can be used as a check set.
The convolutional neural network model may be a Lenet5 network structure, and includes 7 layers (without input layer): c1 (convolutional layer), S2 (sub-sampling layer), C3 (convolutional layer), S4 (sub-sampling layer), C5 (convolutional layer or first fully-connected layer), and F6 (fully-connected layer). The input is a 50 x 80 pixel image. C1 contains 5 46 × 76 feature maps, and C1 contains 130 trainable parameters and 454,480 connections. The sub-sampling layer S2 has 5 23 × 38 feature maps, and each cell in each feature map is connected to a 2 × 2 neighborhood of the corresponding feature map in C1. S2 has 10 trainable parameters and 21,850 connections. Convolutional layer C3 is a layer having 10 feature maps, and each cell in the feature map is connected to several 5 x5 neighborhoods at the same position in the subset of the feature map in S2. C3 contains 1260 trainable parameters and 813,960 connections. The sub-sampling layer S4 has 10 5 × 5 feature maps, 20 trainable parameters, and 7650 connections. Convolutional layer C5 has 120 feature maps. The sub-sampling layer S4 has 30,120 trainable parameters and 1,957,800 connections. The fully connected layer F6 contains 84 cells, and the sub-sampling layer S4 has 10,164 trainable parameters and 660,660 connections. The output layer contains 3 neurons representing 3 levels of starvation during fish feeding. The output layer classification function uses the "softmax" function.
Based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner in which each image is labeled with the hunger degree, and the method includes, but is not limited to: when the fish school is taken badly and all the fed baits are consumed, the corresponding image is marked as 'very hungry'; when the fish school eats only the bait beside the mouth and a small amount of the bait remains (at the moment, the fish actively eats poor desire and only eats the bait beside the mouth), the image is marked as hungry; when the fish school swims around, has no response to the bait and a large amount of the bait remains, the image is marked as 'not hungry'.
In the process, each image is marked as 3 labels of being hungry, hungry and not hungry, and the specific small amount of residue can be determined according to the area of the bait suspended in the water area. The marking method analyzes according to the ingestion habit of the fish school, can realize accurate label marking, and is favorable for the accuracy of obtaining the hunger degree.
Based on the content of the foregoing embodiment, as an alternative embodiment, after the acquiring the images of the plurality of fish school feeding, the method further includes: zooming the acquired images to a preset size; enhancing the image by utilizing a Retinex algorithm to improve the contrast; correspondingly, labeling the hunger degree of each image specifically includes: and marking the hunger degree of each image after the enhancement processing.
Specifically, the collected images may be uniformly scaled to 80 × 50 pixels by image regularization, so as to increase the rate of subsequent training or processing. Then, the image is enhanced by utilizing a Retinex method, and the contrast is improved. The scale parameters of Retinex in this embodiment are 15, 80 and 250, respectively, the number of gaussian central-surround functions is 3, and the weighting factor is 1/3.
According to the fish school bait casting control method provided by the embodiment of the invention, after the preprocessing of zooming the acquired images to the preset size, the sizes of the images are unified, and the images are compressed, so that the workload of an algorithm is reduced. The Retinex algorithm is used for enhancing the image, the influence of low contrast, turbidity and the like on the imaging quality is reduced or eliminated after the image is enhanced, and the image processing effect in the later period is facilitated, so that the accuracy of image identification is improved, and the accuracy of hunger degree identification is further improved.
Based on the content of the foregoing embodiment, as an optional embodiment, after the labeling the hunger degree of each image, the method further includes: performing expansion processing on each marked image to enable each original image to obtain a plurality of expanded images; the augmentation process includes: rotation, translation, gaussian and salt and pepper noise.
To enhance the performance of the method, it is necessary to use rotation (5 ° left-right rotation), translation (5 pixels up-down left-right translation), Gauss addition (density: 0.01 and 0.04), and salt and pepper noise (variance: 10) for each original image and its mirror image respectively2/2552And 0.01) expanding the number of data sets; after data expansion, each original image is expanded into 22 images. By expanding each marked image, an ideal training effect can be achieved only by acquiring a small number of image samples.
Fig. 2 is a structural view of a fish school feeding control device according to an embodiment of the present invention, and as shown in fig. 2, the fish school feeding control device includes: an image acquisition module 201, a processing module 202 and a control module 203. The image acquisition module 201 is used for acquiring a food intake image in a fish school food intake process; the processing module 202 is configured to input the ingestion image into a preset convolutional neural network model, and output a hunger degree of a fish school; the control module 203 is used for controlling the bait feeding amount according to the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
The device embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
According to the fish school bait casting control device provided by the embodiment of the invention, the ingestion image is input into the preset convolutional neural network model, and the hunger degree of the fish school is output, so that the hunger degree of the fish school can be obtained in the bait casting process. On the basis of acquiring the hunger degree of the fish school, the bait feeding amount is controlled according to the hunger degree of the fish school, so that targeted bait feeding is realized, individual balance among the fish schools is guaranteed, and the integral growth of the fish schools is facilitated. Meanwhile, not only is the bait consumption saved, but also the adverse effect of excessive feeding on the water area environment is avoided.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the bus 304. The communication interface 302 may be used for information transfer of an electronic device. Processor 301 may call logic instructions in memory 303 to perform a method comprising: acquiring a food intake image in a fish school food intake process; inputting the ingestion image into a preset convolutional neural network model, and outputting the hunger degree of the fish school; controlling the bait feeding amount according to the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
In addition, the logic instructions in the memory 303 may be stored in a computer readable storage medium when the logic instructions are implemented by software functions and sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof, which essentially contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-described method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: acquiring a food intake image in a fish school food intake process; inputting the ingestion image into a preset convolutional neural network model, and outputting the hunger degree of the fish school; controlling the bait feeding amount according to the hunger degree of the fish school; the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
Fig. 4 is a schematic structural view of a bait boat according to an embodiment of the present invention, and as shown in fig. 4, the embodiment of the present invention provides a fish bait boat, including: the device comprises a ship body, a propulsion motor 7, a propeller 9, a bin 2, a stepping motor 6, a storage battery 3, an underwater camera 13 and a communication module 16; the boat body is used for providing buoyancy to enable the bait casting boat to float on the water surface; the propulsion motor 7 is connected with a propeller 9 and used for driving the ship body to move; the storage bin 2 is arranged in the middle of the ship body and used for containing bait 12, and a valve 11 is arranged at a feed opening 10 of the storage bin 2; the stepping motor 6 is used for controlling the opening and closing of the valve 11 or the opening and closing size of the valve 11 so as to control the bait casting speed; the storage battery 3 is used for providing power supply; and the electronic equipment is used for acquiring the hunger degree of the fish school according to the ingestion image and controlling the bait feeding amount through the stepping motor according to the hunger degree. The underwater camera 13 is used for acquiring a food intake image of the fish school and sending the food intake image to the electronic equipment.
Specifically, the electronic device is the control processing unit 16 in fig. 4, the hull may include a floating body 8 and a support 5, the floating body 8 is a material having a density less than that of water or is inflated to provide buoyancy. The floating body 8 is provided with a bracket 5, and other devices are respectively arranged on the bracket 5. The propulsion motor 7 and the propeller 9 are arranged at the lower part of the bracket 5, or at the upper part of the bracket 5, and the propeller 9 is contacted with the water surface to provide power through the propulsion motor 7.
The storage bin 2 is disposed on the hull, and in order to facilitate the balance of the hull, the storage bin 2 is disposed at the middle of the hull support 5 as a preferred embodiment. Feed bin 2 includes feed opening 10 and valve 11, and 2 openings of feed bin set up down, and feed opening 10 straight-through surface of water, after valve 11 opens, bait 12 can be put into the aquatic through gravity. The valve 11 is connected with the stepping motor 6, and the opening and closing of the valve 11 are controlled by the stepping motor 6.
The storage battery 3 respectively provides power for the propulsion motor 7, the stepping motor 6, the control processing unit 16 and the underwater camera 13.
After the underwater camera 13 acquires the image of the prey area of the fish school, the image of the prey area is analyzed through a convolutional neural network model preset in the control processing unit 16, and the corresponding hunger degree of the fish school is obtained. The control processing unit 16 controls the valve 11 by sending a control command to the stepping motor 6 according to the degree of hunger, thereby adjusting the amount of feeding.
According to the bait casting boat provided by the embodiment of the invention, the underwater camera is used for acquiring the image of the fish school predation area, the ingestion image is input into the convolutional neural network model preset in the control processing unit, the hunger degree of the fish school is output, and the acquisition of the hunger degree of the fish school in the bait casting process is facilitated. On the basis of acquiring the hunger degree of the fish school, the bait feeding amount is controlled according to the hunger degree of the fish school, so that the bait feeding amount is controlled, and the bait feeding amount can be adjusted according to the predation condition of the fish school. The feeding boat can control the feeding speed and the feeding amount according to the intensive degree and feeding speed of a fish school, thereby realizing targeted feeding, improving the low utilization rate of bait, ensuring the balanced growth of the fish school and avoiding causing environmental pollution.
Based on the above description of the embodiments, as an alternative embodiment, the bait casting boat further includes an obstacle avoidance sensor 4 for detecting an obstacle. If the obstacle avoidance sensor device comprises 4 obstacle avoidance sensors 4 which are respectively arranged in the front, back, left and right directions of a ship body and used for detecting obstacles. For example, upon detection of the obstacle information, a corresponding electrical signal is generated for changing the rotational speed of the propulsion motor 7, thereby bypassing the obstacle.
Based on the above-mentioned embodiment, as an alternative embodiment, the number of the propellers 9 and the propulsion motors 7 is 2, and they are located at the left and right ends of the rear part of the bait casting boat in the advancing direction.
The embodiment drives the corresponding propeller by 2 propelling motors, can control the advancing and steering of the boat body by the differential principle based on the content of the embodiment, and as an optional embodiment, the bait casting boat further comprises a solar cell panel 1 which is arranged above the boat body and is connected with the electrode of the storage battery 3 by a lead.
Solar cell panel 1 can be the electric energy with solar energy conversion to save through battery 3 for propulsion motor 7, step motor 6, camera 13 and communication module 16's power supply, not only the energy saving can also reduce the number of times of charging of battery, thereby reduces the maintenance time of the ship of feeding, increases duration.
Based on the content of above-mentioned embodiment, as an optional embodiment, still include cloud platform 14, be connected with camera 13 under water for drive camera 13 under water upper and lower left and right sides rotation.
In order to adjust the angle of the camera according to the requirement, in this embodiment, the underwater camera 13 is connected through the cradle head 14, and the communication module 16 can receive the angle adjustment instruction, so that the cradle head 14 can rotate and adjust, thereby adjusting the angle of the camera.
Based on the content of the above embodiment, as an optional embodiment, the water quality sensor 15 is further included for collecting the water temperature and the dissolved oxygen concentration.
The water quality sensor 15 may be an electrochemical or optical sensor, such as an electrochemical sensor. The measurement range of dissolved oxygen can be measured: 0-40 mg/L, precision: 0.2 mg/L; temperature measurement range: 0-40 ℃, precision: . + -. 0.1 ℃. The amount of bait is controlled by the degree of hunger and the water quality, as described in the above method examples.
Based on the content of the above embodiment, as an optional embodiment, the system further comprises a light source for supplementing light when the underwater camera acquires an image. For example, the light source can be a general LED light source or a halogen lamp, and is used for light supplement when the underwater camera acquires an image, so that video shooting or image shooting can be completed in a dark environment.
Based on the content of the above embodiment, as an optional embodiment, the bait casting device further comprises a positioning module for acquiring the bait casting boat position information. For example, the positioning module is a GPS module or a BD module, and is connected to the communication module, and can send the acquired position information to the control terminal.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A fish school bait feeding control method is characterized by comprising the following steps:
acquiring a food intake image in a fish school food intake process;
inputting the ingestion image into a preset convolutional neural network model, and outputting the hunger degree of the fish school;
controlling the bait feeding amount according to the hunger degree of the fish school;
the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
2. The fish feeding control method according to claim 1, wherein the acquiring of the feeding image during the feeding of the fish comprises:
acquiring a feeding image in the feeding process of the fish school in each water area;
correspondingly, the bait feeding amount is controlled according to the hunger degree of the fish school, and the method specifically comprises the following steps:
on a preset running path, controlling the bait casting amount to perform bait casting according to the hungry degree of fish school passing through the water area;
and calculating the preset running path according to the fish shoal hunger degree of each water area.
3. The method for controlling feeding of a fish school according to claim 1 or 2, wherein the control of the feeding amount is performed before: further comprising:
acquiring water quality parameters of a region to be fed;
correspondingly, according to the hunger degree of the fish school, the bait feeding amount is controlled, and the method specifically comprises the following steps:
and controlling the bait feeding amount according to the hunger degree of the fish school and the water quality parameter.
4. The fish school feeding control method according to claim 1 or 2, wherein before the obtaining of the feeding image during the feeding of the fish school, the method further comprises:
acquiring images of ingestion of a plurality of fish schools, and marking the hunger degree of each image to obtain a plurality of image samples;
and training the established convolutional neural network model by using the plurality of image samples to obtain the preset convolutional neural network model.
5. The fish school feeding control method according to claim 4, further comprising, after the acquiring the images of the plurality of fish school feeding:
zooming the acquired images to a preset size;
enhancing the image by utilizing a Retinex algorithm to improve the contrast;
correspondingly, labeling the hunger degree of each image specifically includes:
and marking the hunger degree of each image after the enhancement processing.
6. The method of claim 4, wherein the labeling of the hunger level for each image further comprises:
performing expansion processing on each marked image to enable each original image to obtain a plurality of expanded images;
the augmentation process includes: rotation, translation, gaussian and salt and pepper noise.
7. A fish school feeding control device, comprising:
the image acquisition module is used for acquiring a food intake image in a fish school food intake process;
the processing module is used for inputting the ingestion image into a preset convolutional neural network model and outputting the hunger degree of the fish school;
the control module is used for controlling the bait feeding amount according to the hunger degree of the fish school;
the convolutional neural network model is obtained by training a fish school feeding image sample with a hunger degree label.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the fish farm feeding control method according to any one of claims 1 to 6.
9. A bait casting boat, comprising: a hull, a propulsion motor, a propeller, a bin, a stepper motor, a battery, an underwater camera, and the electronic device of claim 8;
the boat body is used for providing buoyancy to enable the bait casting boat to float on the water surface;
the propulsion motor is connected with the propeller and used for driving the ship body to move;
the feed bin is arranged on the ship body and used for containing bait, and a valve is arranged at a feed opening of the feed bin;
the stepping motor is used for controlling the opening and closing of the valve or the opening and closing size of the valve so as to control the bait feeding amount;
the storage battery is used for providing power supply;
the underwater camera is used for acquiring a food intake image of a fish school and sending the food intake image to the electronic equipment;
and the electronic equipment is used for acquiring the hunger degree of the fish school according to the ingestion image and controlling the bait feeding amount through the stepping motor according to the hunger degree.
10. The baiting vessel of claim 9, further comprising a water quality sensor for collecting water temperature and dissolved oxygen concentration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010049388.XA CN111240200A (en) | 2020-01-16 | 2020-01-16 | Fish swarm feeding control method, fish swarm feeding control device and feeding boat |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010049388.XA CN111240200A (en) | 2020-01-16 | 2020-01-16 | Fish swarm feeding control method, fish swarm feeding control device and feeding boat |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111240200A true CN111240200A (en) | 2020-06-05 |
Family
ID=70869661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010049388.XA Pending CN111240200A (en) | 2020-01-16 | 2020-01-16 | Fish swarm feeding control method, fish swarm feeding control device and feeding boat |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111240200A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112136741A (en) * | 2020-08-28 | 2020-12-29 | 盐城工学院 | Accurate feeding method for visual area |
| CN112352724A (en) * | 2020-11-13 | 2021-02-12 | 湖北海洋工程装备研究院有限公司 | Method and system for feeding feed in fishing ground |
| CN112766040A (en) * | 2020-12-23 | 2021-05-07 | 北京农业信息技术研究中心 | Method, device and apparatus for detecting residual bait and readable storage medium |
| CN113349111A (en) * | 2021-05-25 | 2021-09-07 | 中国农业大学 | Dynamic feeding method, system and storage medium for aquaculture |
| CN113749030A (en) * | 2021-09-09 | 2021-12-07 | 浙江大学 | Fish welfare self-adaptive feeding system suitable for recirculating aquaculture mode |
| CN113841650A (en) * | 2021-10-15 | 2021-12-28 | 天津科技大学 | Intelligent bait feeding system for outdoor aquaculture pond and control method thereof |
| CN114287377A (en) * | 2022-01-17 | 2022-04-08 | 大连海洋大学 | Feeding machine device and accurate feeding system |
| CN114451338A (en) * | 2021-12-29 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Fish swarm feeding intensity grading method and device and intelligent speed-regulating feeder |
| CN115486391A (en) * | 2022-09-13 | 2022-12-20 | 浙江大学 | Method for accurately feeding and culturing pearl, gentian and grouper |
| CN115578678A (en) * | 2022-11-08 | 2023-01-06 | 中国农业大学 | Fish feeding intensity classification method and system |
| CN115861906A (en) * | 2023-03-01 | 2023-03-28 | 北京市农林科学院信息技术研究中心 | Fish school feeding intensity identification method, device and system and feeding machine |
| CN116548345A (en) * | 2023-04-25 | 2023-08-08 | 广东环境保护工程职业学院 | Fish and shrimp feeding method, device, system and storage medium |
| CN116630080A (en) * | 2023-07-25 | 2023-08-22 | 广东省农业科学院动物科学研究所 | Method and system for determining capacity of aquatic product intensive culture feed based on image recognition |
| CN117456310A (en) * | 2023-12-22 | 2024-01-26 | 中国海洋大学 | Intelligent bait feeding method and training method of aquatic organism state recognition model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205813255U (en) * | 2016-07-26 | 2016-12-21 | 贾贤杰 | A kind of self-service fish-feeding device |
| CN108445746A (en) * | 2018-01-25 | 2018-08-24 | 北京农业信息技术研究中心 | A kind of intelligence feeds control method and device |
| CN108450386A (en) * | 2018-01-22 | 2018-08-28 | 中国农业大学 | A kind of regulating and controlling water quality System and method for of industrialized aquiculture |
| CN110298824A (en) * | 2019-06-17 | 2019-10-01 | 浙江省农业科学院 | Squid automatic classification method based on color image and convolutional neural networks technology |
| CN110583550A (en) * | 2019-09-20 | 2019-12-20 | 重庆工商大学 | Accurate feeding system and device are bred to fish shrimp sea cucumber based on target detection and tracking |
-
2020
- 2020-01-16 CN CN202010049388.XA patent/CN111240200A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205813255U (en) * | 2016-07-26 | 2016-12-21 | 贾贤杰 | A kind of self-service fish-feeding device |
| CN108450386A (en) * | 2018-01-22 | 2018-08-28 | 中国农业大学 | A kind of regulating and controlling water quality System and method for of industrialized aquiculture |
| CN108445746A (en) * | 2018-01-25 | 2018-08-24 | 北京农业信息技术研究中心 | A kind of intelligence feeds control method and device |
| CN110298824A (en) * | 2019-06-17 | 2019-10-01 | 浙江省农业科学院 | Squid automatic classification method based on color image and convolutional neural networks technology |
| CN110583550A (en) * | 2019-09-20 | 2019-12-20 | 重庆工商大学 | Accurate feeding system and device are bred to fish shrimp sea cucumber based on target detection and tracking |
Non-Patent Citations (1)
| Title |
|---|
| 编写组编著, 北京：农业出版社 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112136741A (en) * | 2020-08-28 | 2020-12-29 | 盐城工学院 | Accurate feeding method for visual area |
| CN112352724A (en) * | 2020-11-13 | 2021-02-12 | 湖北海洋工程装备研究院有限公司 | Method and system for feeding feed in fishing ground |
| CN112766040A (en) * | 2020-12-23 | 2021-05-07 | 北京农业信息技术研究中心 | Method, device and apparatus for detecting residual bait and readable storage medium |
| CN112766040B (en) * | 2020-12-23 | 2024-02-06 | 北京农业信息技术研究中心 | Method, device, apparatus and readable storage medium for detecting residual bait |
| CN113349111A (en) * | 2021-05-25 | 2021-09-07 | 中国农业大学 | Dynamic feeding method, system and storage medium for aquaculture |
| CN113749030B (en) * | 2021-09-09 | 2022-07-15 | 浙江大学 | Fish welfare self-adaptive feeding system suitable for circulating water aquaculture mode |
| CN113749030A (en) * | 2021-09-09 | 2021-12-07 | 浙江大学 | Fish welfare self-adaptive feeding system suitable for recirculating aquaculture mode |
| CN113841650A (en) * | 2021-10-15 | 2021-12-28 | 天津科技大学 | Intelligent bait feeding system for outdoor aquaculture pond and control method thereof |
| CN114451338A (en) * | 2021-12-29 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Fish swarm feeding intensity grading method and device and intelligent speed-regulating feeder |
| CN114287377A (en) * | 2022-01-17 | 2022-04-08 | 大连海洋大学 | Feeding machine device and accurate feeding system |
| CN115486391B (en) * | 2022-09-13 | 2024-02-06 | 浙江大学 | Precise feeding and breeding method for pearl gentian garrupa |
| CN115486391A (en) * | 2022-09-13 | 2022-12-20 | 浙江大学 | Method for accurately feeding and culturing pearl, gentian and grouper |
| CN115578678A (en) * | 2022-11-08 | 2023-01-06 | 中国农业大学 | Fish feeding intensity classification method and system |
| CN115861906A (en) * | 2023-03-01 | 2023-03-28 | 北京市农林科学院信息技术研究中心 | Fish school feeding intensity identification method, device and system and feeding machine |
| CN116548345A (en) * | 2023-04-25 | 2023-08-08 | 广东环境保护工程职业学院 | Fish and shrimp feeding method, device, system and storage medium |
| CN116548345B (en) * | 2023-04-25 | 2024-01-09 | 广东环境保护工程职业学院 | Fish and shrimp feeding method, device, system and storage medium |
| CN116630080B (en) * | 2023-07-25 | 2024-01-26 | 广东省农业科学院动物科学研究所 | Method and system for determining capacity of aquatic product intensive culture feed based on image recognition |
| CN116630080A (en) * | 2023-07-25 | 2023-08-22 | 广东省农业科学院动物科学研究所 | Method and system for determining capacity of aquatic product intensive culture feed based on image recognition |
| CN117456310A (en) * | 2023-12-22 | 2024-01-26 | 中国海洋大学 | Intelligent bait feeding method and training method of aquatic organism state recognition model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111240200A (en) | Fish swarm feeding control method, fish swarm feeding control device and feeding boat | |
| EP3843542B1 (en) | Optimal feeding based on signals in an aquaculture environment | |
| CN109591982B (en) | Unmanned monitoring underwater aquaculture robot | |
| CN107094683B (en) | Automatic feeding and water quality monitoring control system for aquaculture | |
| WO2019232247A1 (en) | Biomass estimation in an aquaculture environment | |
| Wu et al. | Application of intelligent and unmanned equipment in aquaculture: A review | |
| CN113040081B (en) | Recirculating aquaculture fish feeding decision-making system based on fish shoal swimming energy consumption analysis | |
| CN114467824B (en) | Intelligent bait casting boat | |
| CN110108704A (en) | A kind of automatic monitoring and pre-alarming method of cyanobacteria and its automatic monitoring and alarming system | |
| CN110692548B (en) | Wide-area breeding robot device with terahertz sensing and communication functions and method | |
| CN112400773B (en) | Greenhouse fry intelligent feeding device and method based on machine vision technology | |
| CN111838027A (en) | Pure oxygen supply aquaculture system and method | |
| CN113170758B (en) | Variable-speed flow intelligent control system based on fish shoal behaviors and bottom pollution discharge characteristics | |
| CN111610733A (en) | Fishing ground culture monitoring system and method based on machine fish | |
| CN208746199U (en) | A kind of intelligence fishery cultivating unmanned boat | |
| CN109466725B (en) | Intelligent water surface floater fishing system based on neural network and image recognition | |
| CN214748140U (en) | Deep sea culture monitoring system | |
| Kuroki et al. | Development of simulator for efficient aquaculture of Sillago japonica using reinforcement learning | |
| JP7227179B2 (en) | AQUACULTURE MANAGEMENT DEVICE, AQUACULTURE MANAGEMENT METHOD, AND FEEDING ROBOT | |
| CN117063868A (en) | Intelligent feeding method for fish pond | |
| CN113277034B (en) | Underwater robot for marine product fishing | |
| CN212279457U (en) | Fish ship of feeding | |
| Kobayashi et al. | Aqua colony for fully automated aquaculture | |
| CN109625218B (en) | Unmanned monitoring underwater aquaculture robot system based on solar charging | |
| CN114532276A (en) | Be used for unmanned material ship of throwing of aquaculture intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |
|
| RJ01 | Rejection of invention patent application after publication |