CN116863322B - Self-adaptive illumination method, device and storage medium for fish breeding based on AI - Google Patents
Self-adaptive illumination method, device and storage medium for fish breeding based on AI Download PDFInfo
- Publication number
- CN116863322B CN116863322B CN202310937596.7A CN202310937596A CN116863322B CN 116863322 B CN116863322 B CN 116863322B CN 202310937596 A CN202310937596 A CN 202310937596A CN 116863322 B CN116863322 B CN 116863322B
- Authority
- CN
- China
- Prior art keywords
- illumination
- fish
- target
- current
- shoal
- 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
Links
- 238000005286 illumination Methods 0.000 title claims abstract description 272
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 231
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000009395 breeding Methods 0.000 title description 3
- 230000001488 breeding effect Effects 0.000 title description 3
- 238000003062 neural network model Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000001172 regenerating effect Effects 0.000 claims abstract description 11
- 230000006399 behavior Effects 0.000 claims description 58
- 230000003044 adaptive effect Effects 0.000 claims description 31
- 230000015654 memory Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 13
- 235000013305 food Nutrition 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims 1
- 235000019688 fish Nutrition 0.000 description 162
- 241001125889 Micropterus salmoides Species 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000004083 survival effect Effects 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000000366 juvenile effect Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 241000252082 Anguilla anguilla Species 0.000 description 2
- 241001247197 Cephalocarida Species 0.000 description 2
- 241001014350 Cynoglossus semilaevis Species 0.000 description 2
- 238000009360 aquaculture Methods 0.000 description 2
- 244000144974 aquaculture Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000013601 eggs Nutrition 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003031 feeding effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000008188 pellet Substances 0.000 description 2
- 230000003134 recirculating effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000252229 Carassius auratus Species 0.000 description 1
- 241000723298 Dicentrarchus labrax Species 0.000 description 1
- 206010034972 Photosensitivity reaction Diseases 0.000 description 1
- 241000157468 Reinhardtius hippoglossoides Species 0.000 description 1
- 241000277263 Salmo Species 0.000 description 1
- 241000277289 Salmo salar Species 0.000 description 1
- 241000512310 Scophthalmus maximus Species 0.000 description 1
- 241001417495 Serranidae Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000005273 aeration Methods 0.000 description 1
- 239000003963 antioxidant agent Substances 0.000 description 1
- 230000003078 antioxidant effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000002060 circadian Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 235000013332 fish product Nutrition 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 210000002149 gonad Anatomy 0.000 description 1
- 230000026109 gonad development Effects 0.000 description 1
- 230000002710 gonadal effect Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000012447 hatching Effects 0.000 description 1
- 230000001418 larval effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000029052 metamorphosis Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000005868 ontogenesis Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 108091008695 photoreceptors Proteins 0.000 description 1
- 230000036211 photosensitivity Effects 0.000 description 1
- 230000029264 phototaxis Effects 0.000 description 1
- 238000009372 pisciculture Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000001954 sterilising effect Effects 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
- 210000001325 yolk sac Anatomy 0.000 description 1
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
- A01K61/10—Culture of aquatic animals of fish
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/05—Underwater scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Environmental Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Zoology (AREA)
- Animal Husbandry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Biodiversity & Conservation Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The application provides an AI-based self-adaptive illumination method, an AI-based self-adaptive illumination device and a storage medium for fish reproduction, wherein the method comprises the following steps: acquiring identification information and growth condition information of fish; according to the identification information and the growth condition information, matching a target illumination requirement and a target food-training requirement from a database, and generating an illumination strategy according to the target illumination requirement and the target food-training requirement; determining the acquisition requirement of fish-shoal sample information according to the current illumination strategy, and acquiring a fish-shoal sample image sequence in a target area; based on the image sequence of the fish school sample, identifying the current fish school density, the fish school growth condition and the fish school behavior in the target area through a trained neural network model; and comparing the current fish school density, the fish school growth condition and the fish school behavior in the target area with target expected fish school information, and regenerating an illumination strategy by combining with the current illumination strategy to perform self-adaptive illumination. According to the scheme, the illumination of the fish in the propagation scene can be adjusted in a self-adaptive and dynamic mode.
Description
Technical Field
The application relates to the technical field of lighting systems, in particular to an AI-based self-adaptive illumination method, an AI-based self-adaptive illumination device and a storage medium for fish reproduction.
Background
Fish farming refers to the production activity of controlling the processes of fish reproduction, cultivation and harvesting by manual means. The method can be divided into rough culture (such as a traditional pond culture mode), semi-rough culture (such as a deep-open sea net cage culture mode) and intensive culture (such as a factory circulating water culture mode) according to the utilization rate of resources in the production process. The recirculating aquaculture system (Recirculating aquaculture systems, RAS) is a typical paradigm for human comprehensive modern technological means to reform nature and service society. The defects of multiple uncontrollable factors, low production efficiency and high environmental pollution degree in the rough/semi-rough cultivation process are abandoned, the method has the advantages of controllable production and environment and recycling after the cultivation water is purified, the requirements on realizing circular economy are well met, the purposes of energy conservation and emission reduction are achieved, and the method gradually becomes an emerging, efficient and healthy cultivation mode for cultivating the excellent fish products.
Most of the RAS at home and abroad is reformed based on a culture mode of a common running water form, and the RAS has been well applied to the culture of fish varieties such as cynoglossus semilaevis (Cynoglossus semilaevis), turbot (Scophthalmus maximus), grouper (Epinephelusspp) and the like in China. Foreign countries focus on the cultivation of fish species such as European eel (Anguilla anguilla) and Atlantic salmon (Salmo salar), both of which have characteristics of tending to excellent fish cultivation. The RAS is mostly composed of a culture pond, a particulate matter sedimentation pond, a biological filter pond, a micro-filter, an ultraviolet sterilization and aeration oxygenation water treatment unit, and the like, but tail water treatment devices and technologies can be optimized on the basis, intelligent feeding equipment and the like are additionally arranged, so that the created growth environment is more beneficial to healthy and rapid growth of fishes.
The light environment includes various factors such as illumination intensity, spectral range, photoperiod, physicochemical features of the water body, and the degree of photosensitivity of the relevant species to the illumination system in a natural/unnatural illumination system. The physiological and behavioral characteristics of most fish are the result of their long-term adaptation to changes in the light environment. The production of photoreceptors and clocking mechanisms in fish at early stages of ontogenesis is already highly coordinated with the corresponding light environment. The circadian light cycle and the spectrum of different wavelength ranges are one of the main environmental challenges that fish must deal with in order to survive. Under artificial cultivation conditions, farmers want to be able to formulate an illumination system according to the principle of maximizing the growth and survival benefits of fish, and research on the influence of 'unnatural' illumination conditions (different illumination and dark periods) and illumination characteristics (different spectral components) on fish shows that: photoperiod and spectrum have important effects on growth, survival, deformity, metamorphosis, molting, gonadal development and antioxidant capacity, stress level and the like of aquatic organisms at each stage.
The inventors found that: in the artificial fish culture scene, the control strategy of 'unnatural' illumination is usually fixed and cannot be dynamically adjusted; and only environmental parameters in a cultivation scene are generally considered, but the growth condition and the real-time behavior of the fish are ignored, the illumination requirement of the fish cannot be accurately met, the feeding-training effect of the fish is influenced, and the growth speed and the survival rate of the fish are influenced.
In view of the above, there is a need for an adaptive illumination method for fish reproduction based on AI to improve the accuracy of illumination control in fish reproduction scenes, thereby improving the reproduction benefits of fish.
Disclosure of Invention
In view of the above, the application provides an AI-based adaptive illumination method, an AI-based adaptive illumination device and a storage medium for fish reproduction, so as to solve the technical problem that the illumination in a fish reproduction scene cannot be adjusted in a self-adaptive and dynamic manner in the prior art.
In a first aspect, the present application provides an AI-based adaptive illumination method for fish reproduction, the method comprising:
acquiring identification information and growth condition information of fish;
according to the identification information and the growth condition information, matching a target illumination requirement and a target food-domestication requirement from a database, and generating an illumination strategy according to the target illumination requirement and the target food-domestication requirement;
determining the acquisition requirement of fish-shoal sample information according to the current illumination strategy, and acquiring a fish-shoal sample image sequence in a target area;
Based on the shoal sample image sequence, identifying the current shoal density, the shoal growth condition and the shoal behavior in the target area through a trained neural network model;
comparing the current fish school density, the fish school growth condition and the fish school behavior in the target area with target expected fish school information, and regenerating an illumination strategy by combining the current illumination strategy to perform self-adaptive illumination.
In an optional embodiment, the generating an illumination strategy according to the target illumination requirement and the target feeding-training requirement includes:
based on the daily feeding times of the target food-domestication requirement, uniformly dividing a target single-day illumination time length and a target single-day non-illumination time length to obtain illumination time length and non-illumination time length required by single feeding;
determining the illumination start and end time of each feeding according to each feeding time node of the target feeding demand;
generating a basic illumination strategy according to the illumination time length and the non-illumination time length required by the single feeding and the illumination start and end time of each feeding; wherein the spectrum and the light intensity of the basic illumination strategy are adapted to the target illumination requirement.
In an optional embodiment, the determining the collection requirement of the fish farm sample information according to the current illumination strategy includes:
determining the collection frequency of the shoal illumination samples according to the illumination time required by the single feeding;
and determining the collection frequency of the shoal non-illumination samples according to the non-illumination time length required by the single feeding.
In an alternative embodiment, the acquiring the sequence of fish-school sample images in the target area includes:
Determining a single sample acquisition time length, and continuously acquiring images in a target area in the single sample acquisition time length to obtain a single sample image sequence;
Based on the fish shoal illumination sample acquisition frequency, continuously acquiring the single sample image sequence to obtain an illumination sample image sequence of the fish shoal in the acquisition target area;
And continuously acquiring the single sample image sequence based on the non-illumination sample acquisition frequency of the fish shoal to obtain a non-illumination sample image sequence of the fish shoal in the acquisition target area.
In an optional embodiment, the identifying, based on the sequence of fish-school sample images, the current fish-school density, fish-school growth condition, and fish-school behavior in the target area through training the completed neural network model includes:
determining a current first target image sequence based on the single sample image sequence, identifying the total number of fish shoals in the current first target image sequence through a trained neural network model, and calculating the current fish shoal density in a target area;
Determining a current second target image based on the single sample image sequence, identifying a shoal contour in the current second target image sequence through the trained neural network model, and determining a current shoal growth condition in a target area according to the area of the shoal contour;
And determining a current third target image sequence based on the single sample image sequence, identifying and tracking a fish-shoal moving target in the current third target image sequence through the trained neural network model, and identifying the current fish-shoal behavior in a target area.
In an optional embodiment, the training neural network model identifies and tracks the fish-school moving object in the current third object image sequence, and identifies the current fish-school behavior in the object area, including:
filtering each frame image in the current third target image sequence, and removing the background of each frame image after filtering according to the background image corresponding to the target area;
Performing histogram equalization on each frame of image subjected to background removal processing, and performing threshold segmentation by using an Ojin method to obtain a fish swarm moving target image sequence;
And identifying the current fish school behavior in the target area based on the change of the fish school moving target in the fish school moving target image sequence.
In an optional implementation manner, the comparing with the target expected fish-swarm information according to the current fish-swarm density, the fish-swarm growth condition and the fish-swarm behavior in the target area, and regenerating the illumination strategy to perform adaptive illumination by combining with the current illumination strategy includes:
If the current fish school growing condition in the target area is not in the range of the target expected fish school growing condition, increasing the target illumination time required by next feeding;
If the current fish school density in the target area is not in the target expected fish school density range, re-determining the target illumination time length, the non-illumination time length and the illumination start and end time required by the next feeding according to the illumination time length and the non-illumination time length required by the single feeding;
If the current fish school behavior type in the target area is negative trend behavior, reducing target illumination time required by next feeding, and adjusting spectrum and light intensity of next illumination.
In a second aspect, the present application provides an AI-based adaptive illumination device for fish reproduction, the device comprising:
the information acquisition module is used for acquiring identification information and growth condition information of the fish;
the initial illumination module is used for matching target illumination requirements and target food training requirements from a database according to the identification information and the growth condition information, and generating illumination strategies according to the target illumination requirements and the target food training requirements;
The image acquisition module is used for determining the acquisition requirement of the fish-shoal sample information according to the current illumination strategy and acquiring a fish-shoal sample image sequence in the target area;
The fish school identification module is used for identifying the current fish school density, the current fish school growth condition and the current fish school behavior in the target area through a trained neural network model based on the fish school sample image sequence;
and the self-adaptive adjustment module is used for comparing the current fish swarm density, the fish swarm growth condition and the fish swarm behavior in the target area with target expected fish swarm information, and regenerating an illumination strategy by combining the current illumination strategy so as to carry out self-adaptive illumination.
In a third aspect, the present application provides a computer device comprising: the self-adaptive illumination method for fish reproduction based on the AI of the first aspect is realized by executing the computer instructions.
In a fourth aspect, the present application provides a computer readable storage medium storing computer instructions which, when executed by a processor, implement the adaptive illumination method for fish reproduction based on AI of the first aspect.
The self-adaptive illumination method, device and storage medium for fish reproduction based on AI provided by the application have at least the following beneficial effects:
According to the technical scheme provided by the application, the fish swarm density, the fish swarm growth condition and the fish swarm behavior in the target area under the current illumination strategy can be identified through collecting fish swarm sample information in the target area and through the AI model, so that the illumination disadvantage under the current illumination strategy is found, the illumination strategy can be timely adjusted, and the better illumination strategy can be obtained through adjusting and correcting the illumination strategy one time and the other time. Meanwhile, the self-adaptive illumination mode can carry out self-adaptive illumination adjustment according to different fishes and different propagation stages, so that the applicability of the scheme is improved.
Therefore, the accuracy of illumination control can be improved to a certain extent through the mode, the illumination strategy is adaptively adjusted based on the recognition result through the recognition of the fish swarm density, the fish swarm growth condition and the fish swarm behavior, and the flexibility and the practicability of the illumination control are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application 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. It will be apparent to those of ordinary skill in the art that the drawings in the following description are of some embodiments of the application and that other drawings may be derived from these drawings without undue effort. It should be noted that the drawings in the following description are illustrative and should not be construed as limiting the application in any way, and that:
Fig. 1 is a schematic view showing an adaptive illumination method for AI-based fish reproduction in an embodiment of the present application;
FIG. 2 shows a frame of an image after histogram equalization processing in one embodiment of the application;
FIG. 3 shows a frame of an image after an Ojin thresholding process in one embodiment of the present application;
FIG. 4 shows a schematic diagram of an AI-based adaptive illumination device for fish reproduction in one embodiment of the application;
FIG. 5 shows a schematic diagram of a computer device in one embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other examples, which a person skilled in the art would obtain without making any inventive effort, based on the embodiments of the application fall within the scope of the application.
In the description of the present application, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; the two components can be directly connected or indirectly connected through an intermediate medium, or can be communicated inside the two components, or can be connected wirelessly or in a wired way. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
In addition, the technical features of the different embodiments of the present application described below may be combined with each other as long as they do not collide with each other.
While the processes described below include a plurality of operations that occur in a particular order, it should be understood that the processes may include additional or fewer operations, which may be performed in sequence or in parallel.
Example 1
The self-adaptive illumination method for fish reproduction based on AI provided by the application can be suitable for artificial cultivation scenes of fish, and the illumination is dynamically adjusted through self-adaptive control of 'unnatural' illumination so as to accurately meet the illumination requirement of the fish, improve the feeding effect of the fish and improve the growth speed and survival rate of the fish.
Referring to fig. 1, the adaptive illumination method for fish reproduction based on AI according to an embodiment of the present application may include the following steps.
Step S101, identification information and growth condition information of fishes are obtained.
In this embodiment, the identification information of the fish is used to distinguish the fish species, for example, it is possible to determine that the currently applicable fish is a california weever by the identification information of the fish. It should be noted that, to facilitate an understanding of the present scheme, the description herein is primarily directed to the use of the california bass. Growth status information is used to indicate the growth cycle of fish (e.g., micropterus salmoides), such as: first, embryonic stage: refers to a period of time from the start of fertilized eggs to before hatching into fish; 2. and (3) fish larvae: refers to a small fish fry which just hatched from fertilized eggs until the yolk sac is absorbed and disappears; 3. juvenile fish (fish fry): the fish larvae are carefully managed for 3-5 weeks, and the fish larvae (fries) grow to 3 cm long; 4. juvenile fish: the fries grow for more than 2 months, and the goldfish with the body length of more than 3 cm. At this time, the body development of the fish is basically shaped, the character of each fin is obvious, the body color is gradually vivid, and only the gonad is not developed and mature; 5. adult fish: the juvenile fish is cultured, gonad development is completely mature, and secondary sex characteristics appear in the breeding season. More specifically, it is also possible, for example: the artemia feeding period, the artemia and micro-pellet feed mixing feeding period and the micro-pellet feed mixing feeding period. In addition, the growth date of the micropterus salmoides can be directly used for representing the growth condition, and the representation mode is not limited.
Step S102, matching target illumination requirements and target food-training requirements from a database according to the identification information and the growth condition information, and generating an illumination strategy according to the target illumination requirements and the target food-training requirements.
In this embodiment, the database stores the lighting requirements and feeding requirements corresponding to different growth conditions of various fishes. For example, the database is pre-stored with lighting requirements and feeding requirements corresponding to each growth condition of the micropterus salmoides.
In this embodiment, generating an illumination policy according to a target illumination requirement and a target feeding training requirement includes:
based on the daily feeding times of the target feeding demand, equally dividing the target single-day illumination time length and the target single-day non-illumination time length to obtain the illumination time length and the non-illumination time length required by single feeding;
Determining the illumination start and end time of each feeding according to each feeding time node of the target food-domesticating requirement;
Generating a basic illumination strategy according to illumination time and non-illumination time required by single feeding and illumination start and end time of each feeding; wherein the spectrum and the light intensity of the basic illumination strategy are adapted to the target illumination requirement.
In this embodiment, the lighting requirements mainly include a single day lighting time period, a spectrum, and a lighting intensity. For example: the first week of the larval stage of the California weever has a corresponding illumination time of 12 hours, a spectrum of lower energy long wave light (red light) and an illumination intensity of 100 lux (lx).
In this embodiment, the feeding demand mainly includes the daily number of feeding of the bait and the respective feeding time node. For example: the daily feeding times are eight times, feeding is performed at intervals of 3 hours, and the first feeding time is zero.
In this embodiment, the illumination policy is generated according to the illumination demand and the feeding demand, that is, it can be understood that the sunlight illumination duration is equally divided according to the daily feeding times, and the illumination is turned on and off according to the time node of each feeding, so as to realize the control of the illumination. For example, when the above-mentioned illumination requirement and feeding-training requirement are received, illumination is turned on every three hours from the zero point and turned off after the illumination lasts for one half hour in the generated illumination strategy. And the spectrum of illumination is kept to be low-energy long-wave light (red light), and the illumination intensity is 100 lux (lx).
Step S103, according to the current illumination strategy, the acquisition requirement of the fish-school sample information is determined, and a fish-school sample image sequence in the target area is acquired.
In this embodiment, determining, according to a current lighting policy, a collection requirement of fish school sample information includes:
determining the acquisition frequency of the shoal illumination sample according to the illumination time required by single feeding;
and determining the collection frequency of the shoal non-illumination samples according to the non-illumination time length required by single feeding.
In this embodiment, specifically, the acquisition requirements of the fish school sample information should include the acquisition requirements in the case of illumination and the acquisition requirements in the case of non-illumination, so that the respective corresponding acquisition requirements need to be determined for the case of illumination and the case of non-illumination, respectively. For example, to solve the feeding effect of a group of micropterus salmoides, the light is usually sampled more frequently due to the phototaxis of the group of micropterus salmoides, while the light is not. For example, if the single illumination time is 90 minutes, the illumination sample collection times of the weever group in California are correspondingly determined to be 9 times, and 1 time is collected every 10 minutes; and the single non-illumination time length is 90 minutes, and the number of times of non-illumination sample collection of the weever group is correspondingly determined to be 3 times, and 1 time is collected every 30 minutes.
In this embodiment, acquiring a fish-school sample image sequence in a target area includes:
determining a single sample acquisition time length, and continuously acquiring images in a target area in the single sample acquisition time length to obtain a single sample image sequence;
based on the collection frequency of the fish shoal illumination samples, continuously obtaining a single sample image sequence to obtain an illumination sample image sequence of the fish shoals in the target area;
based on the collection frequency of the non-illumination samples of the fish shoal, continuously obtaining a single sample image sequence to obtain the non-illumination sample image sequence of the fish shoal in the target area.
In this embodiment, the single sample collection period may be, for example, 1 minute or 30 seconds. An image within a target area of 1 frame is acquired per second. I.e. a single sample image sequence of 60 consecutive images or 30 consecutive images. In practical applications, the target area may be a central area in the culture pond, for example, a square area of 1 x 1 m.
Step S104, based on the image sequence of the fish school sample, the current fish school density, the fish school growth condition and the fish school behavior in the target area are identified through the trained neural network model.
In this embodiment, based on the image sequence of the fish school sample, the current fish school density, the fish school growth condition and the fish school behavior in the target area are identified by training the completed neural network model, including:
Based on the single sample image sequence, determining a current first target image sequence, identifying the total number of fish shoal in the current first target image sequence through the trained neural network model, and calculating the current fish shoal density in the target area.
Specifically, from a single sample image sequence acquired, a plurality of images is selected to determine a first target image sequence. For example, three images or five images are selected. And identifying the number of the California weever in each image in the first target image sequence through a trained neural network model, and carrying out the same processing on other images so as to obtain the total number of all the California weever in the first target image sequence. And obtaining the average quantity of the California weever in each image by means of averaging, and further calculating to obtain the current density of the California weever group in the target area.
In practical application, the density of the shoal in the target area is relatively high in illumination, and the density of the micropterus salmoides in each area in the culture pond is relatively even in non-illumination. In practical application, when the density of the weever shoals is high, the weever shoals can be irradiated into larger fish shoals to death when stress reaction occurs, so that the density of the weever shoals needs to be monitored in a targeted manner to reduce the fish shoals to death and improve the survival rate of the fish shoals.
In this embodiment, based on the image sequence of the fish school sample, the current fish school density, the fish school growth condition and the fish school behavior in the target area are identified by training the completed neural network model, and the method further includes:
And determining a current second target image based on the single sample image sequence, identifying the profile of the fish shoal in the current second target image sequence through the trained neural network model, and determining the current growth condition of the fish shoal in the target area according to the area of the profile of the fish shoal.
Specifically, from the collected single sample image sequence, the outline image of the weever group containing clearer weever is selected to be determined as the second target image. And aiming at the second target image, performing contour recognition on the weever group in the second target image through training the completed neural network model. The current growth condition of the micropterus salmoides shoals can be known by calculating the area of the outline of the micropterus salmoides. That is, the size of the outline area of the California weever and the corresponding growth condition of the California weever are calculated by using the size of the outline area of the California weever, and the size of the outline area of the California weever can directly reflect the growth condition of the California weever.
In this embodiment, based on the image sequence of the fish school sample, the current fish school density, the fish school growth condition and the fish school behavior in the target area are identified by training the completed neural network model, and the method further includes:
And determining a current third target image sequence based on the single sample image sequence, identifying and tracking a fish-shoal moving target in the current third target image sequence through a trained neural network model, and identifying the current fish-shoal behavior in the target area.
In this embodiment, as shown in fig. 2 and 3, each frame image in the current third target image sequence is subjected to filtering processing, and each frame image after the filtering processing is subjected to background removal processing according to the background image corresponding to the target area; performing histogram equalization processing (see fig. 2) on each frame of image subjected to background removal processing, and performing threshold segmentation by using an Ojin method to obtain a sequence of motion target images (see fig. 3) of the sea bass shoal; based on the change of the motion target of the California weever group in the motion target image sequence, the current behavior of the California weever group in the target area is identified.
In this embodiment, specifically, the types of shoal behaviors include a reaction behavior of the california bass, a swimming behavior of the california bass, a foraging behavior of the california bass, a learning behavior of the california bass, a gathering behavior of the california bass, and the like, wherein the reaction behavior further includes a positive trend behavior and a negative trend behavior, the positive trend behavior shows a close and gather behavior to the stimulus source, and the negative trend behavior shows a deviating and dispersing behavior to the stimulus source. In practical applications, the negative trend behavior or stress behavior of the california weever is easy to cause obvious differences among individuals of the california weever group, and the small california weever is more easy to cause casualties, so that the behavior of the california weever group needs to be monitored, the negative trend behavior of the california weever group is reduced, the individuation difference of the california weever group is reduced, and the growth speed and the survival rate of the california weever are improved.
Step S105, comparing the current fish school density, the fish school growth condition and the fish school behavior in the target area with target expected fish school information, and regenerating an illumination strategy by combining with the current illumination strategy to perform self-adaptive illumination.
In this embodiment, according to the current fish school density, fish school growth condition and fish school behavior in the target area, comparing with the target expected fish school information, and regenerating the illumination strategy by combining with the current illumination strategy to perform adaptive illumination, including:
If the current fish school growing condition in the target area is not in the range of the target expected fish school growing condition, increasing the target illumination time required by the next feeding;
If the current fish school density in the target area is not in the target expected fish school density range, re-determining the target illumination time length, the non-illumination time length and the illumination start and end time required by the next feeding according to the illumination time length and the non-illumination time length required by the single feeding;
If the current fish school behavior type in the target area is negative trend behavior, the target illumination time required by next feeding is reduced, and the spectrum and the light intensity of next illumination are adjusted.
In this embodiment, the fish school density, the fish school growth condition and the fish school behavior in the target area under the current illumination strategy can be identified by collecting fish school sample information in the target area and through an AI model, so that the illumination disadvantage under the current illumination strategy can be found, the illumination strategy can be timely adjusted, and the better illumination strategy can be obtained by adjusting and correcting the illumination strategy one time. Meanwhile, the self-adaptive illumination mode can carry out self-adaptive illumination adjustment according to different fishes and different propagation stages, so that the applicability of the scheme is improved.
In the embodiment, the self-adaptive illumination mode improves the accuracy of illumination control to a certain extent, and the illumination strategy is adaptively adjusted based on the identification result by identifying the fish swarm density, the fish swarm growth condition and the fish swarm behavior, so that the flexibility and the practicability of the illumination control are improved.
Example 2
The present embodiment provides an AI-based adaptive illumination device for fish reproduction, and the adaptive illumination method for fish reproduction applied to the AI-based adaptive illumination device provided in embodiment 1 is described. Referring to fig. 4, the adaptive illumination device for fish reproduction based on AI according to an embodiment of the present application may include the following modules.
The information acquisition module is used for acquiring identification information and growth condition information of the fish;
the initial illumination module is used for matching target illumination requirements and target food training requirements from the database according to the identification information and the growth condition information, and generating illumination strategies according to the target illumination requirements and the target food training requirements;
The image acquisition module is used for determining the acquisition requirement of the fish-shoal sample information according to the current illumination strategy and acquiring a fish-shoal sample image sequence in the target area;
the fish school identification module is used for identifying the current fish school density, the current fish school growth condition and the current fish school behavior in the target area through a trained neural network model based on the fish school sample image sequence;
The self-adaptive adjustment module is used for comparing the current fish swarm density, the fish swarm growth condition and the fish swarm behavior in the target area with target expected fish swarm information, and regenerating an illumination strategy by combining with the current illumination strategy so as to carry out self-adaptive illumination.
The adaptive illumination device for fish reproduction based on AI provided by the embodiment of the application can be applied to the adaptive illumination method for fish reproduction based on AI provided by the embodiment 1, and the relevant details refer to the embodiment of the method, so that the implementation principle and the technical effect are similar, and are not repeated here.
It should be noted that: the adaptive illumination device for fish reproduction based on AI provided in the embodiment of the present application is only exemplified by the above-mentioned division of each functional module/functional unit when performing the adaptive illumination for fish reproduction based on AI, and in practical application, the above-mentioned function allocation may be performed by different functional modules/functional units as needed, i.e., the internal structure of the adaptive illumination device for fish reproduction based on AI is divided into different functional modules/functional units, so as to complete all or part of the functions described above. In addition, the embodiment of the adaptive illumination method for fish reproduction based on AI provided in the above method embodiment 1 and the embodiment of the adaptive illumination device for fish reproduction based on AI provided in the present embodiment 2 belong to the same concept, and the specific implementation process of the adaptive illumination device for fish reproduction based on AI provided in the present embodiment 2 is detailed in the above method embodiment 1, and will not be described here again.
Example 3
Referring to fig. 5, an embodiment of the present application further provides a computer device, which may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The computer device may include, but is not limited to, a processor and a memory. Wherein the processor and the memory may be connected by a bus or other means.
The processor may be a central processing unit (Central Processing Unit, CPU). The Processor may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application Specific Integrated Circuits (ASICs), field-Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, graphics processors (Graphics Processing Unit, GPUs), embedded neural network processors (Neural-network Processing Unit, NPUs), or other specialized deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components, etc., or a combination of the above.
The memory is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the methods in the above embodiments of the present application. The processor executes various functional applications of the processor and data processing, i.e., implements the methods of the method embodiments described above, by running non-transitory software programs, instructions, and modules stored in memory.
The memory may include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area may store data created by the processor, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some implementations, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
An embodiment of the present application also provides a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the method of the above-described method embodiment.
It will be appreciated by those skilled in the art that implementing all or part of the above-described methods according to the present application may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the program may include the steps of the above-described embodiments of the methods when executed. Wherein the storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a hard disk (HARD DISK DRIVE, abbreviated as HDD), a Solid state disk (Solid-state-STATE DRIVE, SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
The technical features of the above embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
Although embodiments of the present application have been described in connection with the accompanying drawings, it is not to be construed as limiting the scope of the claims. It should be noted that other variations or modifications in the above description can be made by those of ordinary skill in the art without departing from the spirit of the application. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (8)
1. An AI-based adaptive illumination method for fish reproduction, the method comprising:
acquiring identification information and growth condition information of fish;
according to the identification information and the growth condition information, matching a target illumination requirement and a target food-domestication requirement from a database, and generating an illumination strategy according to the target illumination requirement and the target food-domestication requirement;
determining the acquisition requirement of fish-shoal sample information according to the current illumination strategy, and acquiring a fish-shoal sample image sequence in a target area;
Based on the shoal sample image sequence, identifying the current shoal density, the shoal growth condition and the shoal behavior in the target area through a trained neural network model;
Comparing the current fish school density, the fish school growth condition and the fish school behavior in the target area with target expected fish school information, and regenerating an illumination strategy by combining the current illumination strategy to perform self-adaptive illumination;
Generating an illumination strategy according to the target illumination requirement and the target food training requirement comprises the following steps: based on the daily feeding times of the target food-domestication requirement, uniformly dividing a target single-day illumination time length and a target single-day non-illumination time length to obtain illumination time length and non-illumination time length required by single feeding; determining the illumination start and end time of each feeding according to each feeding time node of the target feeding demand; generating a basic illumination strategy according to the illumination time length and the non-illumination time length required by the single feeding and the illumination start and end time of each feeding; wherein the spectrum and the light intensity of the basic illumination strategy are adapted to the target illumination requirement;
Comparing the current fish swarm density, the fish swarm growth condition and the fish swarm behavior in the target area with target expected fish swarm information, and regenerating an illumination strategy by combining the current illumination strategy to perform self-adaptive illumination, wherein the method comprises the following steps: if the current fish school growing condition in the target area is not in the range of the target expected fish school growing condition, increasing the target illumination time required by next feeding; if the current fish school density in the target area is not in the target expected fish school density range, re-determining the target illumination time length, the non-illumination time length and the illumination start and end time required by the next feeding according to the illumination time length and the non-illumination time length required by the single feeding; if the current fish school behavior type in the target area is negative trend behavior, reducing target illumination time required by next feeding, and adjusting spectrum and light intensity of next illumination.
2. The AI-based adaptive illumination method for fish reproduction of claim 1, wherein determining the acquisition requirement of fish-shoal sample information according to the current illumination strategy comprises:
determining the collection frequency of the shoal illumination samples according to the illumination time required by the single feeding;
and determining the collection frequency of the shoal non-illumination samples according to the non-illumination time length required by the single feeding.
3. The AI-based adaptive illumination method for fish reproduction of claim 2, wherein the acquiring a sequence of fish-shoal sample images within a target area comprises:
Determining a single sample acquisition time length, and continuously acquiring images in a target area in the single sample acquisition time length to obtain a single sample image sequence;
Based on the fish shoal illumination sample acquisition frequency, continuously acquiring the single sample image sequence to obtain an illumination sample image sequence of the fish shoal in the acquisition target area;
And continuously acquiring the single sample image sequence based on the non-illumination sample acquisition frequency of the fish shoal to obtain a non-illumination sample image sequence of the fish shoal in the acquisition target area.
4. The AI-based adaptive illumination method for fish reproduction of claim 3, wherein the identifying the current fish population density, fish population growth conditions, and fish population behavior in the target area by training a completed neural network model based on the fish population sample image sequence comprises:
determining a current first target image sequence based on the single sample image sequence, identifying the total number of fish shoals in the current first target image sequence through a trained neural network model, and calculating the current fish shoal density in a target area;
Determining a current second target image sequence based on the single sample image sequence, identifying a shoal contour in the current second target image sequence through the trained neural network model, and determining the current shoal growth condition in a target area according to the area of the shoal contour;
And determining a current third target image sequence based on the single sample image sequence, identifying and tracking a fish-shoal moving target in the current third target image sequence through the trained neural network model, and identifying the current fish-shoal behavior in a target area.
5. The AI-based adaptive illumination method for fish reproduction of claim 4, wherein the training-completed neural network model identifies and tracks fish-swarm moving objects in the current third target image sequence and identifies current fish-swarm behaviors in a target area, comprising:
filtering each frame image in the current third target image sequence, and removing the background of each frame image after filtering according to the background image corresponding to the target area;
Performing histogram equalization on each frame of image subjected to background removal processing, and performing threshold segmentation by using an Ojin method to obtain a fish swarm moving target image sequence;
And identifying the current fish school behavior in the target area based on the change of the fish school moving target in the fish school moving target image sequence.
6. An AI-based adaptive lighting device for fish reproduction, the device comprising:
the information acquisition module is used for acquiring identification information and growth condition information of the fish;
the initial illumination module is used for matching target illumination requirements and target food training requirements from a database according to the identification information and the growth condition information, and generating illumination strategies according to the target illumination requirements and the target food training requirements;
The image acquisition module is used for determining the acquisition requirement of the fish-shoal sample information according to the current illumination strategy and acquiring a fish-shoal sample image sequence in the target area;
The fish school identification module is used for identifying the current fish school density, the current fish school growth condition and the current fish school behavior in the target area through a trained neural network model based on the fish school sample image sequence;
The self-adaptive adjustment module is used for comparing the current fish swarm density, the fish swarm growth condition and the fish swarm behavior in the target area with target expected fish swarm information, and regenerating an illumination strategy by combining the current illumination strategy so as to perform self-adaptive illumination;
Generating an illumination strategy according to the target illumination requirement and the target food training requirement comprises the following steps: based on the daily feeding times of the target food-domestication requirement, uniformly dividing a target single-day illumination time length and a target single-day non-illumination time length to obtain illumination time length and non-illumination time length required by single feeding; determining the illumination start and end time of each feeding according to each feeding time node of the target feeding demand; generating a basic illumination strategy according to the illumination time length and the non-illumination time length required by the single feeding and the illumination start and end time of each feeding; wherein the spectrum and the light intensity of the basic illumination strategy are adapted to the target illumination requirement;
Comparing the current fish swarm density, the fish swarm growth condition and the fish swarm behavior in the target area with target expected fish swarm information, and regenerating an illumination strategy by combining the current illumination strategy to perform self-adaptive illumination, wherein the method comprises the following steps: if the current fish school growing condition in the target area is not in the range of the target expected fish school growing condition, increasing the target illumination time required by next feeding; if the current fish school density in the target area is not in the target expected fish school density range, re-determining the target illumination time length, the non-illumination time length and the illumination start and end time required by the next feeding according to the illumination time length and the non-illumination time length required by the single feeding; if the current fish school behavior type in the target area is negative trend behavior, reducing target illumination time required by next feeding, and adjusting spectrum and light intensity of next illumination.
7. A computer device, comprising: the system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor realizes the AI-based adaptive illumination method for fish reproduction according to any one of claims 1-5 by executing the computer instructions.
8. A computer readable storage medium storing computer instructions which when executed by a processor implement the AI-based adaptive illumination method for fish reproduction of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310937596.7A CN116863322B (en) | 2023-07-28 | 2023-07-28 | Self-adaptive illumination method, device and storage medium for fish breeding based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310937596.7A CN116863322B (en) | 2023-07-28 | 2023-07-28 | Self-adaptive illumination method, device and storage medium for fish breeding based on AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116863322A CN116863322A (en) | 2023-10-10 |
| CN116863322B true CN116863322B (en) | 2024-04-30 |
Family
ID=88232140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310937596.7A Active CN116863322B (en) | 2023-07-28 | 2023-07-28 | Self-adaptive illumination method, device and storage medium for fish breeding based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116863322B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117575368B (en) * | 2024-01-15 | 2024-05-03 | 中国水产科学研究院南海水产研究所 | Aquatic germplasm resource management method and system based on Internet of things technology |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019153721A1 (en) * | 2018-02-12 | 2019-08-15 | 深圳创维－Rgb电子有限公司 | Denoising method and apparatus for video sequence, server, and storage medium |
| CN112634202A (en) * | 2020-12-04 | 2021-04-09 | 浙江省农业科学院 | Method, device and system for detecting behavior of polyculture fish shoal based on YOLOv3-Lite |
| CN112800994A (en) * | 2021-02-03 | 2021-05-14 | 中国农业大学 | Fish swarm feeding behavior identification method and device, electronic equipment and storage medium |
| CN112931310A (en) * | 2021-02-05 | 2021-06-11 | 大连海洋大学 | Temperature and light regulation and control method for promoting maturity of parent fish of takifugu rubripes |
| CN113516563A (en) * | 2021-07-21 | 2021-10-19 | 中国农业大学 | Fish culture environment adjusting method and system based on sensing data and storage medium |
| CN114004433A (en) * | 2020-07-28 | 2022-02-01 | 中国农业大学 | Method and device for regulating and controlling growth environment of cultured fishes |
| CN114158495A (en) * | 2021-11-30 | 2022-03-11 | 大连海洋大学 | Illumination regulation and control method for promoting growth of juvenile fish of sebastes schlegeli hilgendorf |
| CN114364107A (en) * | 2021-12-14 | 2022-04-15 | 深圳市奥新科技有限公司 | Aquaculture illumination control method, device, equipment and storage medium |
| CN114419320A (en) * | 2022-01-19 | 2022-04-29 | 中山大学 | Fish shoal detection method, system and device based on image recognition |
| CN114463675A (en) * | 2022-01-11 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Underwater fish group activity intensity identification method and device |
| CN115049692A (en) * | 2022-08-15 | 2022-09-13 | 山东万牧农业科技有限公司郯城分公司 | Intelligent regulation method and system for marine aquaculture illumination simulating natural ecology |
| CN115984682A (en) * | 2023-01-13 | 2023-04-18 | 集美大学 | Fish quantity estimation method based on Unet and BP neural network |
| CN116206194A (en) * | 2023-02-22 | 2023-06-02 | 五邑大学 | Method, device, system and storage medium for shoal feeding |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201710372D0 (en) * | 2017-06-28 | 2017-08-09 | Observe Tech Ltd | System and method of feeding aquatic animals |
| CN111165414B (en) * | 2020-01-15 | 2020-11-17 | 浙江大学 | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology |
-
2023
- 2023-07-28 CN CN202310937596.7A patent/CN116863322B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019153721A1 (en) * | 2018-02-12 | 2019-08-15 | 深圳创维－Rgb电子有限公司 | Denoising method and apparatus for video sequence, server, and storage medium |
| CN114004433A (en) * | 2020-07-28 | 2022-02-01 | 中国农业大学 | Method and device for regulating and controlling growth environment of cultured fishes |
| CN112634202A (en) * | 2020-12-04 | 2021-04-09 | 浙江省农业科学院 | Method, device and system for detecting behavior of polyculture fish shoal based on YOLOv3-Lite |
| CN112800994A (en) * | 2021-02-03 | 2021-05-14 | 中国农业大学 | Fish swarm feeding behavior identification method and device, electronic equipment and storage medium |
| CN112931310A (en) * | 2021-02-05 | 2021-06-11 | 大连海洋大学 | Temperature and light regulation and control method for promoting maturity of parent fish of takifugu rubripes |
| CN113516563A (en) * | 2021-07-21 | 2021-10-19 | 中国农业大学 | Fish culture environment adjusting method and system based on sensing data and storage medium |
| CN114158495A (en) * | 2021-11-30 | 2022-03-11 | 大连海洋大学 | Illumination regulation and control method for promoting growth of juvenile fish of sebastes schlegeli hilgendorf |
| CN114364107A (en) * | 2021-12-14 | 2022-04-15 | 深圳市奥新科技有限公司 | Aquaculture illumination control method, device, equipment and storage medium |
| CN114463675A (en) * | 2022-01-11 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Underwater fish group activity intensity identification method and device |
| CN114419320A (en) * | 2022-01-19 | 2022-04-29 | 中山大学 | Fish shoal detection method, system and device based on image recognition |
| CN115049692A (en) * | 2022-08-15 | 2022-09-13 | 山东万牧农业科技有限公司郯城分公司 | Intelligent regulation method and system for marine aquaculture illumination simulating natural ecology |
| CN115984682A (en) * | 2023-01-13 | 2023-04-18 | 集美大学 | Fish quantity estimation method based on Unet and BP neural network |
| CN116206194A (en) * | 2023-02-22 | 2023-06-02 | 五邑大学 | Method, device, system and storage medium for shoal feeding |
Non-Patent Citations (2)
| Title |
|---|
| 基于计算机视觉的鱼类行为学规律与精准投喂的研究;郑书康;《中国优秀硕士学位论文全文数据库农业科技辑》;第8-51页 * |
| 循环水系统中光照强度和周期对日本鳗鲡和罗非鱼生长及生理指标的影响;王奎;《中国优秀硕士学位论文全文数据库农业科技辑》(第5期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116863322A (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bardach et al. | Aquaculture: the farming and husbandry of freshwater and marine organisms | |
| CN101755699B (en) | Method for incubating brachymystax lenok seeds | |
| CN116863322B (en) | Self-adaptive illumination method, device and storage medium for fish breeding based on AI | |
| Rybkina et al. | Habitat preference of three-spined stickleback juveniles in experimental conditions and in wild eelgrass | |
| CN100370896C (en) | Artificial breeding method for semi-smooth tongue sole | |
| CN102283153B (en) | Batch production fry rearing technique for exopalaemon modestus | |
| Ravi et al. | The effect of different pH and photoperiod regimens on the survival rate and developmental period of the larvae of Portunus pelagicus (Decapoda, Brachyura, Portunidae). | |
| CN113080110A (en) | Method for promoting gonad maturation of parent fish of spotted-head fish | |
| Hongtuo et al. | Culture of the oriental river prawn (Macrobrachium nipponense) | |
| JP2022032380A (en) | Hatching breeding device of fertilized egg of inshore fish | |
| US11310999B2 (en) | Aquaculture process for the production of salmon eggs | |
| Hien et al. | Current status of freshwater prawn culture in the Mekong River Delta of Vietnam | |
| CN111109165A (en) | Method for breeding fish in rice field | |
| CN103814853A (en) | Natural selection breeding method for imported penaeus parent shrimps | |
| CN108283163A (en) | Continuous cultural method in a kind of big artemia room of obligate ovoviviparity breeding | |
| KR101474407B1 (en) | Method for mass seedling production by maturation induction of phodeus notatus in korean bitterlings(acheilognathinae) through induced maturing | |
| CN102273419B (en) | Method for cultivating Spanish mackerel | |
| Marichamy | Mudcrab culture and hatchery | |
| CN103947582B (en) | A kind of method improving male hippocampus gestation child care efficiency | |
| Barden et al. | Candidate Species for Marine Ornamental Aquaculture: French Grunt, Haemulon flavolineatum1 | |
| Mwanja et al. | Capture-based aquaculture of the Nile perch | |
| Okunsebor et al. | Effect of water volume on growth, survival rate and condition factor of Clarias gariepinus hatchlings cultured in different enclosures. | |
| Nabhitabhata | Amphioctopus aegina | |
| Moyle et al. | Effect of stocking density on the growth, survival, and behavior of postpuerulus western rock lobster, Panulirus cygnus (George)(Decapoda: Palinuridae) | |
| Hara | Present status of fish culture development project in the Black Sea under JICA program |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 214000 High-tech Agricultural Demonstration Park in Anzhen Street, Xishan District, Wuxi City, Jiangsu Province Applicant after: Jiangsu Zhongshui Dongze Agricultural Development Co.,Ltd. Address before: 2201, Wuxi Chamber of Commerce Building, No. 1 Financial 8th Street, Wuxi Economic Development Zone, Wuxi City, Jiangsu Province, 214000 Applicant before: Jiangsu Zhongshui Dongze Agricultural Development Co.,Ltd. Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |