CN114532273B - Non-invasive active feeding method and system for recirculating aquaculture fish - Google Patents

Non-invasive active feeding method and system for recirculating aquaculture fish Download PDF

Info

Publication number
CN114532273B
CN114532273B CN202210230904.8A CN202210230904A CN114532273B CN 114532273 B CN114532273 B CN 114532273B CN 202210230904 A CN202210230904 A CN 202210230904A CN 114532273 B CN114532273 B CN 114532273B
Authority
CN
China
Prior art keywords
community
individuals
level
fish
feeding
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.)
Active
Application number
CN202210230904.8A
Other languages
Chinese (zh)
Other versions
CN114532273A (en
Inventor
赵建
文彦慈
魏丹
朋泽群
叶章颖
刘鹰
朱松明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202210230904.8A priority Critical patent/CN114532273B/en
Publication of CN114532273A publication Critical patent/CN114532273A/en
Application granted granted Critical
Publication of CN114532273B publication Critical patent/CN114532273B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • A01K61/10—Culture of aquatic animals of fish
    • 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
    • A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
    • A01K63/06—Arrangements for heating or lighting in, or attached to, receptacles for live fish
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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)
  • Environmental Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Zoology (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Theoretical Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • Operations Research (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Farming Of Fish And Shellfish (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a non-invasive active feeding method and a system for recirculating aquaculture fishes. The system mainly utilizes machine vision and a deep learning algorithm to analyze the community level of the recirculating aquaculture fishes, then couples the community level of the fish and the characteristics of the swimming strategy among individuals, realizes the representation of the real-time ingestion desire of the fish, and further judges when to trigger feeding. The system disclosed by the invention is simple in structure, simple, convenient and effective in method, and capable of realizing real-time quantification of the ingestion desire of cultured fishes under a non-invasive condition, making up for the defects of a traditional timed feeding (passive feeding) mode, ensuring the ingestion welfare of cultured objects to the greatest extent, improving the feed efficiency and being beneficial to maximization of culture benefits.

Description

Non-invasive active feeding method and system for recirculating aquaculture fish
Technical Field
The invention belongs to the field of circulating water intelligent culture, relates to an intelligent feeding technology suitable for a circulating water culture mode, and particularly relates to a non-invasive active feeding method and system for circulating water cultured fishes.
Background
The method is characterized in that efficient feeding is advocated in aquaculture, and the key is to feed a proper amount of feed in a specific time period so as to meet the requirements of nutrients required by specific growth rate of a cultured object. Most of the current research on efficient feeding is based on the theoretical feeding rhythm of a cultured object, namely, timed feeding (passive feeding); in fact, the rhythm of fish ingestion is influenced by multiple factors such as the culture environment, the size of the individual, and other individuals in the population. Therefore, active feeding according to the real-time ingestion desire degree of the fishes is the key for ensuring accurate and efficient feeding.
The existing research utilizes fish learning capacity to combine with a Demand-feeding system to realize self-Demand feeding of the cultured objects, or realizes real-time automatic feeding of the cultured objects by analyzing the active aggregation degree of the fishes in a specified feeding area, however, the method needs to train the cultured objects for a long time in advance and is mainly used for experimental research; and the Demand-feeding based on Demand-feeding can cause the continuous excitation and alertness of fishes due to frequent feeding stimulation, and then the cortisol content in the body is increased, thus influencing the welfare of the fishes. Research shows that decision-making compromise among animal community individuals can be achieved according to respective requirements, and the community grade richness influences the decision-making compromise. This phenomenon is also reflected in fish stocks: different individuals can adjust the positions and behaviors of the individuals in the fish school according to the self nutrition conditions, and the behaviors are influenced by the social level of the individuals; as such, individuals in different community classes in a fish population do not have the same characteristic behavioral characteristics at similar levels of desire to eat. Therefore, the representation of the integral ingestion desire degree of the fish school is theoretically feasible by utilizing the fish school grade and the inter-individual swimming strategy characteristics.
On the basis of the background, the invention provides a non-invasive active feeding system for recirculating aquaculture fishes, which analyzes the community level of the recirculating aquaculture fishes by using a machine vision and deep learning algorithm, then couples the community level of the fish and the characteristics of inter-individual swimming strategies, realizes the representation of real-time ingestion desire of the fish, and further judges when to trigger feeding. The system disclosed by the invention is simple in structure, simple, convenient and effective in method, and capable of realizing real-time quantification of the ingestion desire of cultured fishes under a non-invasive condition, making up for the defects of a traditional timed feeding (passive feeding) mode, ensuring the ingestion welfare of cultured objects to the greatest extent, improving the feed efficiency and being beneficial to maximization of culture benefits.
Disclosure of Invention
The invention aims to provide a non-invasive active feeding system for recirculating aquaculture fishes, which can realize accurate representation of real-time ingestion desire of fish schools according to the swimming strategy variation characteristics among individuals with different community levels of the fish schools and provide good technical support for intelligent feeding of recirculating aquaculture fishes.
The technical scheme adopted by the invention is as follows:
a non-invasive active feeding method and system for recirculating aquaculture fishes are disclosed.
The system can comprise a culture pond, a depth camera, a server, a light supplement lamp, a feeder and the like; the depth camera is arranged right above the culture pond and is connected with the server; meanwhile, the output end of the server is respectively connected with the light supplementing lamp and the feeder.
By applying the active feeding system, the characterization of the real-time ingestion desire of the fish school in the circulating water aquaculture can be realized by analyzing the swimming strategy variation characteristics among individuals with different community grades of the fish school, and then the time for feeding is judged. The method specifically comprises the following steps:
(1) The server triggers the depth camera to read the real-time picture, and calculates the individual length (L) and thickness (T) information of the fish school in the current culture pond by using a deep learning algorithm; then, normalizing the individual body length information of the fish school: (1) when T is i ≤0.08L i When the temperature of the water is higher than the set temperature,
Figure GDA0003602908600000021
(2) when T is i ＞0.08L i When, is greater or less>
Figure GDA0003602908600000022
Wherein i is more than or equal to 1 and less than or equal to N, N is the number of the objects cultured in the current culture pond, and L i And T i Body length and body thickness, L, for the ith subject max And L min Respectively represents the longest length and the longest length of the cultured objects in the current culture pondShort body length;
(2) Based on the normalized fish school individual length information, the fish school individual community grade is quantized: (1) high community-level individuals: l is more than or equal to 0.7 and less than or equal to 1; (2) middle community level individuals: l is more than 0.3 and less than 0.7; (3) low community-level individuals: l is more than 0 and less than or equal to 0.3;
(3) The steps (1) and (2) are performed every n days;
(4) The method comprises the following steps of (1) representing the real-time ingestion desire degree of a fish school by utilizing the swimming strategy variation characteristics among individuals of different community levels of the fish school:
the real-time feeding desire of the fish herd is expressed by the following formula:
Figure GDA0003602908600000031
wherein, A is the calculation of a multiplied by V in the time period of sampling t p +a×V s +b×D nnd Average value of (e.g., 5 minutes per 25 minute interval); within 5 minutes of sampling time period, taking 1 frame per second for calculation; a. The full Calculating a x V within a time period t after feeding for satiety p +a×V s +b×D nnd And has an average value of:
1) Parameter(s)
Figure GDA0003602908600000032
Wherein L is h And L l Average body length, V, of high and low community-level individuals, respectively flow The current average flow velocity of the water body in the culture pond;
2) Variables of
Figure GDA0003602908600000033
Wherein +>
Figure GDA0003602908600000034
Figure GDA0003602908600000035
D h 、D m And D l Respectively representing centroids of individuals with high community level, individuals with medium community level and individuals with low community level to throwEuclidean distance average value, L, of geometric central point of feed water surface coverage area m Average body length of individuals of middle-community level, N h 、N m And N l Respectively representing the number of high, medium and low community-level individuals, N = N h +N m +N l ；
3) Variables of
Figure GDA0003602908600000036
Wherein
Figure GDA0003602908600000037
D hm 、D mm And D lm Respectively representing the moving distances of the space geometric centers of the high-community-level individuals, the medium-community-level individuals and the low-community-level individuals in the current sampling time period, wherein the space geometric center refers to the geometric center of a small group formed by the specific community-level individuals;
4) Variables of
Figure GDA0003602908600000038
Wherein
Figure GDA0003602908600000039
Figure GDA0003602908600000041
D m-h Representing the closest distance, D, between the high and medium community-level individuals l-m Representing the closest distance, D, between the middle and low community-level individuals h '、D m ' and D l ' are the average values of the spatial distances between different individuals and the nearest same-level individuals in the high-community-level individuals, the medium-community-level individuals and the low-community-level individuals respectively;
5) Variable A full Is a x V p +a×V s +b×D nnd Calculating to obtain an average value in a time period of 25-30 minutes after the feeding;
6) Step 5) executing once every n days;
(5) When Appetite is more than or equal to 0.75, the server triggers the feeder to feed;
(6) After the feeding is finished, the operation is repeated from the step (4).
The invention has the advantages that;
the non-invasive active feeding system for the recirculating aquaculture fishes is simple in structure and accurate and effective in method, and the representation of the real-time ingestion desire degree of the fish school is calculated based on the swimming strategy variation characteristics among individuals of different community grades of the fish school. The system can realize real-time quantification of the ingestion desire of the cultured fishes under a non-invasive condition, makes up the defects of the traditional timing feeding (passive feeding) mode, ensures the ingestion welfare of cultured objects to the maximum extent, improves the feed efficiency, and is beneficial to the maximization of the culture benefit.
Drawings
FIG. 1 is a schematic diagram of a non-invasive active recirculating aquaculture fish feeding system.
In the figure: 1-a culture pond; 2-a depth camera; 3-a server; 4-a light supplement lamp; 5-a feeder.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
Referring to fig. 1, a concrete structure example of a non-invasive active feeding system for recirculating aquaculture fish of the invention comprises a culture pond 1, a depth camera 2, a server 3, a light supplement lamp 4 and a feeding machine 5; the depth camera 2 is arranged right above the culture pond 1 and is connected with the server 3; meanwhile, the output end of the server 3 is respectively connected with the light supplement lamp 4 and the feeder 5.
The device is applied to active feeding of the recirculating aquaculture, and one example of the decision method comprises the following steps:
(1) The server triggers the depth camera to read the real-time picture, and calculates the individual length (L) and thickness (T) information of the fish school in the current culture pond by using a deep learning algorithm; then, normalizing the individual body length information of the fish school: (1) when T is i ≤0.08L i When the utility model is used, the water is discharged,
Figure GDA0003602908600000051
(2) when T is i ＞0.08L i When, is greater or less>
Figure GDA0003602908600000052
Wherein i is more than or equal to 1 and less than or equal to N, N is the number of the objects cultured in the current culture pond, and L i And T i Body length and body thickness, L, of the ith subject max And L min Respectively representing the longest length and the shortest length of the cultured objects in the current culture pond;
(2) Based on the normalized fish population individual length information, quantifying the fish population individual community level: (1) high community-level individuals: l is more than or equal to 0.7 and less than or equal to 1; (2) middle community level individuals: l is more than 0.3 and less than 0.7; (3) low community-level individuals: l is more than 0 and less than or equal to 0.3;
(3) The steps (1) and (2) are performed every 3 days;
(4) The method comprises the following steps of (1) representing the real-time ingestion desire degree of a fish school by utilizing the swimming strategy variation characteristics among individuals of different community levels of the fish school:
Figure GDA0003602908600000053
wherein A is the calculation of a × V in the sampling time period p +a×V s +b×D nnd In this example, samples were taken at intervals of 25 minutes for 5 minutes; within 5 minutes of sampling time, taking 1 frame per second for calculation; a. The full Calculating AxV for the time period after feeding for satiety p +a×V s +b×D nnd Wherein:
1) Parameter(s)
Figure GDA0003602908600000054
Wherein L is h And L l Average body length, V, of high and low community-level individuals, respectively flow The current average flow velocity of the water body in the culture pond;
2) Variables of
Figure GDA0003602908600000055
Wherein->
Figure GDA0003602908600000056
Figure GDA0003602908600000057
D h 、D m And D l Respectively representing Euclidean distance average values L from the centroids of the individuals with high community level, the individuals with medium community level and the individuals with low community level to the geometric central point of the water surface coverage area of the feed m Average body length of individuals of middle-community level, N h 、N m And N l Respectively representing the number of high, medium and low community-level individuals, N = N h +N m +N l ；
3) Variables of
Figure GDA0003602908600000061
Wherein
Figure GDA0003602908600000062
D hm 、D mm And D lm Respectively representing the moving distances of the space geometric centers of the high-community-level individual, the medium-community-level individual and the low-community-level individual in the current sampling time period;
4) Variables of
Figure GDA0003602908600000063
Wherein
Figure GDA0003602908600000064
Figure GDA0003602908600000065
D m-h Represents the closest distance, D, between the high and medium community-level individuals l-m Representing the closest distance, D, between the middle and low community-level individuals h '、D m ' and D l ' are the average values of the spatial distances between different individuals and the nearest same-level individual in the high-community-level individual, the medium-community-level individual and the low-community-level individual respectively;
5) Variable A full Is a x V p +a×V s +b×D nnd Calculating the average value in the 25 th to 30 th minute time period after the full feeding;
6) Step 5) is executed once every 3 days;
(5) When Appetite is more than or equal to 0.75, the server triggers the feeder to feed;
(6) After the feeding is finished, the operation is repeated from the step (4).
The system disclosed by the invention is simple in structure, simple, convenient and effective in method, and capable of realizing real-time quantification of the ingestion desire of cultured fishes under a non-invasive condition, making up for the defects of a traditional timed feeding (passive feeding) mode, ensuring the ingestion welfare of cultured objects to the greatest extent, improving the feed efficiency and being beneficial to maximization of culture benefits.
The above disclosure is only for the specific embodiment of the present invention, but the present invention is not limited thereto, and it should be understood by those skilled in the art that the modifications made without departing from the present invention shall fall within the protection scope of the present invention.

Claims (5)

1. A non-invasive active feeding method for fish cultured by circulating water is characterized in that,
firstly, analyzing the community grade of the recirculating aquaculture fishes by using a machine vision and deep learning algorithm; the method specifically comprises the following steps:
(1) The depth camera reads the real-time picture, and calculates the individual body length L and body thickness T information of the fish school in the current culture pond by using a deep learning algorithm; then, carrying out normalization on the individual body length information of the fish school: (1) when T is i ≤0.08L i When the utility model is used, the water is discharged,
Figure FDA0004067846940000011
(2) when T is i ＞0.08L i When, is greater or less>
Figure FDA0004067846940000012
Wherein i is more than or equal to 1 and less than or equal to N, N is the number of the objects cultured in the current culture pond, and L i And T i Body length divided into ith subjectAnd body thickness, L max And L min Respectively representing the longest length and the shortest length of the cultured objects in the current culture pond;
(2) Based on the normalized fish population individual length information, quantifying the fish population individual community level: (1) high community-level individuals: l is more than or equal to 0.7 and less than or equal to 1; (2) middle community level individuals: l is more than 0.3 and less than 0.7; (3) low community-level individuals: l is more than 0 and less than or equal to 0.3;
then, coupling the fish community grade and the inter-individual swimming strategy characteristics, and representing the real-time ingestion desire of the fish;
and judging whether to trigger feeding according to the characterization result.
2. The active feeding method of non-invasive recirculating aquaculture fish as claimed in claim 1, wherein the real-time feeding desire of the fish is characterized by coupling the community level of the fish and the inter-individual swimming strategy characteristics, specifically:
the real-time fish feeding desire is expressed as follows:
Figure FDA0004067846940000013
wherein, A is the calculation of a × V in the sampling t time period p +a×V s +b×D nnd Average value of (A) full Calculating a x V within a time period t after feeding for satiety p +a×V s +b×D nnd And has an average value of:
1) Parameter(s)
Figure FDA0004067846940000021
Wherein L is h And L l Average body length, V, of high and low community-level individuals, respectively flow The current average flow velocity of the water body of the culture pond;
2) Variables of
Figure FDA0004067846940000022
Wherein +>
Figure FDA0004067846940000023
Figure FDA0004067846940000024
D h 、D m And D l Respectively representing the mean value L of Euclidean distances from the centroids of individuals with high community level, individuals with medium community level and individuals with low community level to the geometric central point of the water surface coverage area of the feed m Average body length of individuals of middle-community level, N h 、N m And N l Respectively representing the number of individuals with high community level, individuals with medium community level and individuals with low community level;
3) Variables of
Figure FDA0004067846940000025
Wherein
Figure FDA0004067846940000026
D hm 、D mm And D lm Respectively representing the moving distances of the space geometric centers of the high-community-level individual, the medium-community-level individual and the low-community-level individual in the current sampling time period;
Figure FDA0004067846940000027
wherein->
Figure FDA0004067846940000028
Figure FDA0004067846940000029
D m-h Represents the closest distance, D, between the high and medium community-level individuals l-m Representing the closest distance, D, between the middle and low community-level individuals h '、D m ' and D l ' different individuals among high, medium and low community-level individuals and the mostSpatial distance averages of neighboring peer individuals.
3. The active non-invasive method for feeding recirculating aquaculture fish of claim 2 wherein the recirculating aquaculture fish are ranked every n days and a is given a full An update is performed.
4. The active feeding method for the non-invasive recirculating aquaculture fish as claimed in claim 2, wherein the feeding is triggered when Appetite is greater than or equal to 0.75.
5. A non-invasive active feeding system for recirculating aquaculture fish is characterized by comprising a depth camera, a server and a feeding machine; the depth camera is arranged above the culture pond and is connected with the server; with the output of the server connected to a feeder, the system operating according to the method of any one of claims 1 to 4.
CN202210230904.8A 2022-03-10 2022-03-10 Non-invasive active feeding method and system for recirculating aquaculture fish Active CN114532273B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210230904.8A CN114532273B (en) 2022-03-10 2022-03-10 Non-invasive active feeding method and system for recirculating aquaculture fish

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210230904.8A CN114532273B (en) 2022-03-10 2022-03-10 Non-invasive active feeding method and system for recirculating aquaculture fish

Publications (2)

Publication Number Publication Date
CN114532273A CN114532273A (en) 2022-05-27
CN114532273B true CN114532273B (en) 2023-03-31

Family

ID=81663545

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210230904.8A Active CN114532273B (en) 2022-03-10 2022-03-10 Non-invasive active feeding method and system for recirculating aquaculture fish

Country Status (1)

Country Link
CN (1) CN114532273B (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110089477B (en) * 2019-05-23 2020-08-28 浙江大学 Fish welfare intelligent culture system and method for circulating water culture mode
CN113749030B (en) * 2021-09-09 2022-07-15 浙江大学 Fish welfare self-adaptive feeding system suitable for circulating water aquaculture mode

Also Published As

Publication number Publication date
CN114532273A (en) 2022-05-27

Similar Documents

Publication Publication Date Title
JP3101938B2 (en) Automatic feeding device and method for aquatic organisms
Margulies et al. Spawning and early development of captive yellowfin tuna (Thunnus albacares)
CN113749030B (en) Fish welfare self-adaptive feeding system suitable for circulating water aquaculture mode
CN113040081B (en) Recirculating aquaculture fish feeding decision-making system based on fish shoal swimming energy consumption analysis
CN103814857B (en) A kind of fish crab culturing pool and cultural method thereof
CN107372267A (en) A kind of intelligent feeding system based on swimming type Fish behavior profile feedback
TWI736415B (en) A smart shrimp and/or crab feeding management system and the method thereof
CN114467824B (en) Intelligent bait casting boat
CN110637764B (en) Method for accurately determining feeding amount for river crab culture
CN108935243B (en) A kind of close hippocampus mating mating system according to production requirement regulation
CN111443744A (en) Recirculating aquaculture variable-speed flow intelligent control system based on fish shoal behavior and ammonia discharge law feedback
CN114532273B (en) Non-invasive active feeding method and system for recirculating aquaculture fish
CN115633654A (en) Intelligent adjusting method and device for breeding environment
CN114946711B (en) Deep-water cage culture method for tuna with yellow fins
CN116863322A (en) Self-adaptive illumination method, device and storage medium for fish breeding based on AI
CN111578990A (en) Aquaculture management system based on Internet of things
Luque et al. Fishing behaviour of Alaska brown bear
CN117063868A (en) Intelligent feeding method for fish pond
CN116228455A (en) Method for processing test data of flow culture of Notopterygium longituba in leaf
CN114419432B (en) Fish group ingestion intensity assessment method and device
CN114467825B (en) Intelligent classification system for recirculating aquaculture fishes
CN114241291A (en) Phagostimulant screening method based on inert element labeling method and computer vision
CN115049692A (en) Intelligent regulation method and system for marine aquaculture illumination simulating natural ecology
CN205596905U (en) Circulating rivers device of breeding fish
Yang et al. (Retracted) Dynamic scene images-assisted intelligent control method for industrialized feeding through deep vision learning

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
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Zhao Jian

Inventor after: Wen Yanci

Inventor after: Wei Dan

Inventor after: Peng Zequn

Inventor after: Ye Zhangying

Inventor after: Liu Ying

Inventor after: Zhu Songming

Inventor before: Zhao Jian

Inventor before: Wei Dan

Inventor before: Wen Yanci

Inventor before: Peng Zequn

Inventor before: Ye Zhangying

Inventor before: Liu Ying

Inventor before: Zhu Songming

GR01 Patent grant
GR01 Patent grant