CN116994293A - Method and system for optimizing fishing efficiency of net based on image recognition - Google Patents
Method and system for optimizing fishing efficiency of net based on image recognition Download PDFInfo
- Publication number
- CN116994293A CN116994293A CN202311240465.XA CN202311240465A CN116994293A CN 116994293 A CN116994293 A CN 116994293A CN 202311240465 A CN202311240465 A CN 202311240465A CN 116994293 A CN116994293 A CN 116994293A
- Authority
- CN
- China
- Prior art keywords
- net
- fishing
- fish
- target
- area
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 241000251468 Actinopterygii Species 0.000 claims abstract description 349
- 238000012544 monitoring process Methods 0.000 claims abstract description 41
- 230000006698 induction Effects 0.000 claims abstract description 31
- 238000005516 engineering process Methods 0.000 claims abstract description 24
- 238000005286 illumination Methods 0.000 claims description 70
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 18
- 230000002319 phototactic effect Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 16
- 239000002699 waste material Substances 0.000 abstract description 6
- 230000000366 juvenile effect Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000012163 sequencing technique Methods 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000029264 phototaxis Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
- A01K79/00—Methods or means of catching fish in bulk not provided for in groups A01K69/00 - A01K77/00, e.g. fish pumps; Detection of fish; Whale fishery
-
- 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
- A01K79/00—Methods or means of catching fish in bulk not provided for in groups A01K69/00 - A01K77/00, e.g. fish pumps; Detection of fish; Whale fishery
- A01K79/02—Methods or means of catching fish in bulk not provided for in groups A01K69/00 - A01K77/00, e.g. fish pumps; Detection of fish; Whale fishery by electrocution
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
-
- 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
- G06V10/443—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 by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
- G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
- G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Biodiversity & Conservation Biology (AREA)
- General Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Mechanical Means For Catching Fish (AREA)
Abstract
The method comprises the steps of acquiring image data of a fishing environment of the net, positions of the net and fish characteristic data in real time, analyzing the image data by combining an image recognition technology and a satellite positioning system, and determining the types, positions and densities of fish shoals; according to the judgment of the fish shoal position and the net position, the net position is adjusted in real time, and the optimal net throwing place is intelligently selected to optimize the fishing efficiency; judging whether the loading capacity of the net is within the loading capacity range by monitoring the fishing data of the net, evaluating whether the number of the target fishes reaches a preset fishing amount in real time, and starting a target fish induction system when the number of the target fishes does not reach the preset fishing amount; through the steps, the method can realize real-time monitoring, adjustment and optimization of the fishing process of the net, improve the fishing efficiency and reduce the resource waste.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method and a system for optimizing fishing efficiency of a net based on image recognition.
Background
Conventional fishing methods typically rely on artificial experience and intuition, which presents a number of limitations and challenges. The traditional fishing method often cannot accurately evaluate the loading capacity of the net, so that the problems of resource waste and excessive fishing are caused. The image recognition technology can realize accurate recognition of information such as the type, the position, the density and the like of the shoal of fish by analyzing the image data of the fishing environment. At present, an optimization method and system for fishing efficiency of a net based on image recognition are not available, and the net fishing data can be monitored in real time and the positions and the mesh sizes of the net can be adjusted by comprehensively utilizing an image recognition technology and a satellite positioning system so as to maximize the fishing efficiency. Therefore, there is a need for an optimization method and system for fishing efficiency of a net based on image recognition, so as to overcome the limitation of the traditional fishing method, improve the fishing efficiency, and realize the development of sustainable fishery.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides a net fishing efficiency optimization method and system based on image recognition.
The first aspect of the invention provides a method for optimizing fishing efficiency of a net based on image recognition, which comprises the following steps:
Acquiring image data of a fishing environment of the net in real time, and acquiring the position of the net and the characteristic data of fish;
based on an image recognition technology and a geographic information system, analyzing image data of the fishing environment of the net, and determining the type, position and density of the fish shoals;
judging whether the position of the fish school coincides with the position of the net according to the position of the fish school and the position of the net, and adjusting the position of the net in real time;
according to the type, position and density of the fish shoals, the optimal net throwing place is intelligently selected;
acquiring net fishing data in real time, acquiring the number of target fishes according to the net fishing data, judging whether the number of the target fishes reaches a preset fishing amount, and starting a target fish induction system if the number of the target fishes does not reach the preset fishing amount;
and monitoring the fishing data of the net in real time, and judging whether the loading capacity of the net is within the loading capacity range.
In this scheme, acquire image data, the netting gear position of netting gear fishing environment in real time, specifically do:
acquiring image data of a fishing environment of the net according to underwater shooting equipment of the net, wherein the image data comprises a fish swarm image;
and acquiring the position of the net through GPS positioning of the net.
In this scheme, based on image recognition technique and geographic information system, carry out the analysis to the image data of netting gear fishing environment, confirm kind, position and the density of shoal of fish, specifically do:
Constructing an image recognition model based on a convolutional neural network, importing image data of a fishing environment of the net into the image recognition model, and extracting image features;
comparing the extracted image features with the fish feature data to obtain fish information in the image;
obtaining the fish type and density according to the fish information;
labeling the image data based on a geographic information system to obtain an image data acquisition position;
and analyzing according to the image data acquisition position to determine the position of the fish school.
In this scheme, according to the position of shoal of fish and netting gear position, judge whether the position of shoal of fish coincides with netting gear position, the position of real-time adjustment netting gear specifically does:
obtaining a horizontal edge position of the fish school and a horizontal edge position of the net according to the fish school position and the net position;
constructing a netting gear position adjusting system, marking and connecting the horizontal edge positions of the shoal of fish and the horizontal edge positions of the netting gear to form a closed area, wherein the closed area comprises a shoal of fish area and a netting gear area;
comparing the fish school area with the netting gear area, and judging the position relationship between the fish school area and the netting gear area;
if the fish area is overlapped, calculating the overlapping percentage of the fish area and the net area, and if the overlapping percentage is smaller than a preset value, utilizing the net to drag the robot to move the net position until the overlapping percentage of the fish area and the net area is larger than the preset value;
If the fish areas do not overlap, the net dragging robot is also used for moving the net positions until the overlapping percentage of the fish areas and the net areas is larger than a preset value.
In this scheme, according to the kind, position and the density of shoal of fish, the best netting gear of intelligent choice puts in place, specifically does:
real-time monitoring and analyzing the target fishing area through an image recognition technology to obtain monitoring results, wherein the monitoring results comprise water depth, fish school distribution condition and fish school behaviors;
acquiring historical target fishing area data, wherein the historical target fishing area data comprises historical fishing quantity and historical fishing depth;
carrying out correlation analysis on the monitoring result, the historical target fishing area data, the type, the position and the density of the fish shoal, and predicting the fishing amount of different positions of the target fishing area to obtain a prediction result;
according to the prediction result, the fishing efficiency and the fishing gain of different throwing places of the net are evaluated, and an evaluation result is obtained;
and obtaining the optimal net throwing place according to the evaluation result.
In this scheme, acquire the netting gear in real time and catch data, acquire target fish quantity according to netting gear and catch data, judge whether target fish quantity reaches the volume of predetermineeing and catch, if not reach the volume of predetermineeing and catch, start target fish induction system specifically does:
Identifying fish types in the net through the net monitoring device, and respectively counting the fish types to obtain net fishing data, wherein the fishing data comprise fish capturing amount and fish types;
analyzing the fishing data to obtain the number of target fishes;
comparing the number of the target fishes with a preset fishing amount, and judging whether the number of the target fishes reaches the preset fishing amount or not;
if the preset fishing amount is not reached, acquiring phototactic illumination color and photosensitive comfort of the target fish;
and adjusting the illumination color and illumination intensity of the target fish induction system in real time according to the illumination color and the photosensitive comfort level.
In this scheme, real-time supervision netting gear catches data, judges whether netting gear loading capacity is in the loading capacity within range, specifically does:
monitoring fishing data of the net in real time through underwater camera equipment and sensor equipment, wherein the fishing data comprise fishing quantity, fish types and sizes of the net;
monitoring tension change of the net in the fishing process in real time through a tension sensor;
judging whether the tension change is in a preset tension range according to the preset tension range, and obtaining a judging result;
and judging whether the loading capacity of the net is within the loading capacity range according to the judging result and the catching amount.
The second aspect of the present invention also provides an image recognition-based net fishing efficiency optimization system, which comprises: the device comprises a storage and a processor, wherein the storage comprises an image recognition-based net fishing efficiency optimization method program, and when the image recognition-based net fishing efficiency optimization method program is executed by the processor, the following steps are realized:
acquiring image data of a fishing environment of the net in real time, and acquiring the position of the net and the characteristic data of fish;
based on an image recognition technology and a geographic information system, analyzing image data of the fishing environment of the net, and determining the type, position and density of the fish shoals;
judging whether the position of the fish school coincides with the position of the net according to the position of the fish school and the position of the net, and adjusting the position of the net in real time;
according to the type, position and density of the fish shoals, the optimal net throwing place is intelligently selected;
acquiring net fishing data in real time, acquiring the number of target fishes according to the net fishing data, judging whether the number of the target fishes reaches a preset fishing amount, and starting a target fish induction system if the number of the target fishes does not reach the preset fishing amount;
and monitoring the fishing data of the net in real time, and judging whether the loading capacity of the net is within the loading capacity range.
In this scheme, according to the position of shoal of fish and netting gear position, judge whether the position of shoal of fish coincides with netting gear position, the position of real-time adjustment netting gear specifically does:
obtaining a horizontal edge position of the fish school and a horizontal edge position of the net according to the fish school position and the net position;
constructing a netting gear position adjusting system, marking and connecting the horizontal edge positions of the shoal of fish and the horizontal edge positions of the netting gear to form a closed area, wherein the closed area comprises a shoal of fish area and a netting gear area;
comparing the fish school area with the netting gear area, and judging the position relationship between the fish school area and the netting gear area;
if the fish area is overlapped, calculating the overlapping percentage of the fish area and the net area, and if the overlapping percentage is smaller than a preset value, utilizing the net to drag the robot to move the net position until the overlapping percentage of the fish area and the net area is larger than the preset value;
if the fish areas do not overlap, the net dragging robot is also used for moving the net positions until the overlapping percentage of the fish areas and the net areas is larger than a preset value.
In this scheme, according to the netting gear data of fishing, acquire target fish quantity, judge whether target fish quantity reaches the volume of predetermineeing and catch, if not reach the volume of predetermineeing and catch, start target fish induction system, specifically:
Analyzing the fishing data to obtain the number of target fishes;
comparing the number of the target fishes with a preset fishing amount, and judging whether the number of the target fishes reaches the preset fishing amount or not;
if the preset fishing amount is not reached, acquiring phototactic illumination color and photosensitive comfort of the target fish;
and adjusting the illumination color and illumination intensity of the target fish induction system in real time according to the illumination color and the photosensitive comfort level.
The invention discloses an image recognition-based net fishing efficiency optimization method, which is characterized in that image data of a net fishing environment, net position and fish characteristic data are obtained in real time, and the image data are analyzed by combining an image recognition technology and a satellite positioning system to determine the type, position and density of a fish swarm; according to the judgment of the fish shoal position and the net position, the net position is adjusted in real time, and the optimal net throwing place is intelligently selected to optimize the fishing efficiency; judging whether the loading capacity of the net is within the loading capacity range by monitoring the fishing data of the net, evaluating whether the number of the target fishes reaches a preset fishing amount in real time, and starting a target fish induction system when the number of the target fishes does not reach the preset fishing amount; through the steps, the method can realize real-time monitoring, adjustment and optimization of the fishing process of the net, improve the fishing efficiency and reduce the resource waste.
Drawings
FIG. 1 shows a flow chart of a method for optimizing fishing efficiency of a net based on image recognition of the present application;
FIG. 2 is a flow chart illustrating the intelligent selection of an optimal netting gear delivery location according to the present application;
FIG. 3 shows a flow chart of the start-up target fish induction system of the present application;
fig. 4 shows a block diagram of an image recognition based net fishing efficiency optimization system of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of an optimization method of fishing efficiency of a net based on image recognition.
As shown in fig. 1, the first aspect of the present application provides a method for optimizing fishing efficiency of a net based on image recognition, including:
S102, acquiring image data of a fishing environment of the net, positions of the net and characteristic data of fish in real time;
s104, analyzing image data of the fishing environment of the net based on an image recognition technology and a geographic information system, and determining the type, position and density of the fish shoals;
s106, judging whether the position of the fish school is overlapped with the position of the net according to the position of the fish school and the position of the net, and adjusting the position of the net in real time;
s108, intelligently selecting an optimal net delivery place according to the type, the position and the density of the fish school;
s110, acquiring net fishing data in real time, acquiring the number of target fishes according to the net fishing data, judging whether the number of the target fishes reaches a preset fishing amount, and starting a target fish induction system if the number of the target fishes does not reach the preset fishing amount;
s112, monitoring the fishing data of the net in real time, and judging whether the loading capacity of the net is within the loading capacity range.
According to the embodiment of the invention, the real-time acquisition of the image data of the fishing environment of the net and the position of the net comprises the following specific steps:
acquiring image data of a fishing environment of the net according to underwater shooting equipment of the net, wherein the image data comprises a fish swarm image;
and acquiring the position of the net through GPS positioning of the net.
It should be noted that the netting gear is provided with a shooting device and a positioning device; the image data of the fishing environment of the netting gear is acquired by using the underwater shooting equipment of the netting gear. The image data comprise fish shoal images, and the fish activity in the surrounding water can be captured through underwater shooting equipment. By using these image data, information about the shoal distribution, the number, the behavior, and the like can be acquired; by using the GPS positioning technology, the accurate coordinates of the netting gear in water can be obtained in real time.
According to the embodiment of the invention, based on the image recognition technology and the geographic information system, the image data of the fishing environment of the net is analyzed to determine the type, the position and the density of the fish shoals, specifically:
constructing an image recognition model based on a convolutional neural network, importing image data of a fishing environment of the net into the image recognition model, and extracting image features;
comparing the extracted image features with the fish feature data to obtain fish information in the image;
obtaining the fish type and density according to the fish information;
labeling the image data based on a geographic information system to obtain an image data acquisition position;
and analyzing according to the image data acquisition position to determine the position of the fish school.
The method is characterized in that the image recognition model is built based on the convolutional neural network, and image data of the fishing environment of the net can be analyzed and features can be extracted through training; the fish information includes the kind and the number of fish; the image data is marked based on a geographic information system, so that the position information of each image data can be obtained; the position information is combined with fish information, further analysis is carried out, and the specific position of the fish shoal in the water area can be determined according to the position obtained by the image data.
According to the embodiment of the invention, according to the position of the fish school and the position of the net, whether the position of the fish school is coincident with the position of the net is judged, and the position of the net is adjusted in real time, specifically:
obtaining a horizontal edge position of the fish school and a horizontal edge position of the net according to the fish school position and the net position;
constructing a netting gear position adjusting system, marking and connecting the horizontal edge positions of the shoal of fish and the horizontal edge positions of the netting gear to form a closed area, wherein the closed area comprises a shoal of fish area and a netting gear area;
comparing the fish school area with the netting gear area, and judging the position relationship between the fish school area and the netting gear area;
If the fish area is overlapped, calculating the overlapping percentage of the fish area and the net area, and if the overlapping percentage is smaller than a preset value, utilizing the net to drag the robot to move the net position until the overlapping percentage of the fish area and the net area is larger than the preset value;
if the fish areas do not overlap, the net dragging robot is also used for moving the net positions until the overlapping percentage of the fish areas and the net areas is larger than a preset value.
It should be noted that, under the condition that the net is put in, according to the embodiment of the invention, the position change of the fish shoal can be judged to change the position of the net, thereby avoiding the situation that the net is recycled and put in again and avoiding the low fishing efficiency of the net caused by the position change of the fish shoal; the net dragging robots are distributed on the edge of the net and can drag the net to move, so that the maximum position of the net coincides with the position of the fish shoal, and the fish capturing quantity is improved.
Fig. 2 shows a flow chart of the invention for intelligently selecting the best net drop location.
According to the embodiment of the invention, the optimal net throwing place is intelligently selected according to the type, the position and the density of the fish shoals, and specifically comprises the following steps:
s202, monitoring and analyzing a target fishing area in real time through an image recognition technology to obtain a monitoring result, wherein the monitoring result comprises water depth, fish school distribution condition and fish school behavior;
S204, acquiring historical target fishing area data, wherein the historical target fishing area data comprises historical fishing amount and historical fishing depth;
s206, carrying out correlation analysis on the monitoring result, the historical target fishing area data, the types, the positions and the densities of the shoal, and predicting the fishing amount of different positions of the target fishing area to obtain a prediction result;
s208, according to the prediction result, evaluating the fishing efficiency and the fishing gain of different throwing places of the net to obtain an evaluation result;
and S210, obtaining the optimal net delivery place according to the evaluation result.
It should be noted that the embodiment of the invention provides a method for intelligently selecting an optimal net throwing place based on the type, the position and the density of a fish shoal, the method can accurately predict the fishing amount of different positions of a target fishing area by utilizing an image recognition technology, historical data and correlation analysis, and evaluate the fishing efficiency and the fishing gain of the net at different throwing places, so that the optimal net throwing place is determined, the capturing efficiency can be improved to the greatest extent in the fishing process, resources are effectively utilized, and ineffective throwing and resource waste are reduced; the historical target fishing area data is obtained through a historical fishing database; the history fishing database is used for recording the capturing amount of the fishing boat and the types of the fishing fishes. FIG. 3 shows a flow chart of the start-up target fish induction system of the present invention.
According to the embodiment of the invention, the real-time acquisition of the fishing data of the net is performed, the number of target fishes is acquired according to the fishing data of the net, whether the number of target fishes reaches a preset fishing amount is judged, and if the number of target fishes does not reach the preset fishing amount, a target fish induction system is started, specifically:
s302, identifying fish types in the net through a net monitoring device, and respectively counting the fish types to obtain net fishing data, wherein the fishing data comprise fish capturing amount and fish types;
s304, analyzing the fishing data to obtain the number of the target fish;
s306, comparing the number of the target fishes with a preset fishing amount, and judging whether the number of the target fishes reaches the preset fishing amount;
s308, if the preset fishing amount is not reached, acquiring phototactic illumination color and photosensitive comfort level of the target fish;
and S310, adjusting the illumination color and the illumination intensity of the target fish induction system in real time according to the illumination color and the photosensitive comfort level.
It should be noted that, according to the embodiment of the present invention, a method for determining the number of target fishes and a target fish induction system based on net fishing data is provided, the method acquires net fishing data in real time, and determines whether the number of target fishes reaches a preset fishing amount by analysis, if the number of target fishes does not reach the preset fishing amount, the system starts the target fish induction system, and adjusts illumination conditions according to illumination color and light sensing comfort level so as to increase attraction and fishing efficiency of the target fishes; the preset fishing amount refers to the lowest fishing gain set for the target fish.
According to the embodiment of the invention, the real-time monitoring of the fishing data of the net tool judges whether the loading capacity of the net tool is within the loading capacity range, specifically:
monitoring fishing data of the net in real time through underwater camera equipment and sensor equipment, wherein the fishing data comprise fishing quantity, fish types and sizes of the net;
monitoring tension change of the net in the fishing process in real time through a tension sensor;
judging whether the tension change is in a preset tension range according to the preset tension range, and obtaining a judging result;
and judging whether the loading capacity of the net is within the loading capacity range according to the judging result and the catching amount.
It should be noted that, the embodiment of the invention provides a method for judging whether the loading capacity of the net is within the loading capacity range by monitoring the fishing data and tension change of the net in real time and combining preset parameters, and the method can help fishermen or related personnel to know the state of the net in time, so that the net is prevented from being damaged due to excessive fishing, and economic loss is avoided; the preset tension range is calculated by the safe carrying weight of the net, which is obtained by the factory specification of the net.
According to an embodiment of the present invention, further comprising:
acquiring phototactic information of various target fishes, wherein the phototactic information comprises illumination color, illumination intensity and illumination frequency;
Based on a computer vision technology, fusing phototactic information of various target fishes to obtain optimal fused illumination information, wherein the optimal fused illumination information comprises optimal illumination color and frequency;
the method comprises the steps of obtaining driving sound wave information of non-target fish, wherein the driving sound wave information comprises sound frequency and sound size;
transmitting the dispelling sound wave information and the optimal fusion illumination to a target fish induction system to adjust the illumination color, frequency and sound frequency;
dividing the illumination intensity into 10 grades, and obtaining fishing information of the net under each illumination intensity grade, wherein the fishing information comprises fish types and fishing gains;
acquiring the capturing proportion of adult fish to juvenile fish under each illumination intensity according to the fishing information;
analyzing according to the capturing proportion of adult fish and juvenile fish under each illumination intensity to obtain the optimal capturing proportion;
calculating according to the fish types and the fish gains to obtain the fish gains of the target fish types;
analyzing according to the optimal capturing proportion and the fishing gain of the target fish, and obtaining the optimal illumination intensity level of the net fishing;
the optimal illumination intensity and illumination color are constructed as an optimal induction fishing scheme.
The fish is trapped under the optimal illumination intensity, so that the optimal capturing proportion of the juvenile fish to the adult fish is obtained, the excessive fishing of the juvenile fish is avoided, and the sustainable development of fishery resources is realized; according to the embodiment of the invention, the ratio of the captured adult fish to the young fish can be obtained according to the optimal illumination intensity to be the optimal ratio, and the larger the optimal ratio is, the higher the adult fish ratio is; the illumination intensity is divided into 10 grades, and the illumination intensity is gradually increased.
According to an embodiment of the present invention, further comprising:
based on a geographic information system, acquiring a target fishing area, and dividing the target fishing area into N grids in a grid mode;
sending the optimal induced fishing protocol into a fishing vessel within a grid;
acquiring fishing information of a plurality of fishing boats in N grids according to the optimal induced fishing scheme within preset time, wherein the fishing information comprises total capturing amount and target fish capturing amount;
according to the fishing information, sequencing the total capturing quantity of the plurality of fishing boats in different grids from high to low to obtain a sequencing result;
Acquiring the position information of the first 5 grids according to the sequencing result, and formulating an optimal route for the fishing boat to travel among the 5 grids according to the position information;
and analyzing according to the optimal route to obtain the optimal throwing route of the net.
It should be noted that, each of the N grids performs fishing operation according to the illumination color and the optimal illumination intensity in the grid by at least one fishing boat in the near month; the optimal route is the shortest distance route traveled by the fishing boat among the first 5 grids, and the 5 grids are all on the optimal route; the net is put in according to the optimal route of the fishing boat, so that the fishing efficiency and the fishing gain of the net can be increased to the greatest extent; the preset time is 1 month; in different grids, the water temperature and the water flow speed are different, and the phototaxis of the fishes are also influenced to a certain extent, so that the total capturing amount and the target fish capturing amount obtained in different capturing areas of the fishing vessel when the optimal induced capturing scheme is applied are also different.
According to an embodiment of the present invention, further comprising:
acquiring image information of different underwater netting gear fishing conditions;
preprocessing according to the image information to identify different pieces of network tool information;
Analyzing the fishing amount of the net according to different net information;
according to the fishing amount, the fishing efficiency of different nets is analyzed, and according to the fishing efficiency, a net recommendation report is generated.
It should be noted that, the embodiment of the invention provides an image-based method for deducing the fishing amount and the fishing efficiency of different nets by acquiring the image information of different nets under water and performing preprocessing, analysis and evaluation, and the method can provide guidance and advice about the adjustment and optimization of the nets for fishermen or related personnel so as to improve the fishing efficiency and economic benefit; the netting gear information comprises the position, the shape and the capturing object of the netting gear under water; the adjusting the netting gear proposal report includes increasing or decreasing the use of netting gears, adjusting the netting gear layout.
Fig. 4 shows a block diagram of an image recognition based net fishing efficiency optimization system of the present invention.
The second aspect of the present invention also provides an image recognition-based net fishing efficiency optimizing system 4, which comprises: the device comprises a memory 41 and a processor 42, wherein the memory comprises a mesh fishing efficiency optimizing method program based on image recognition, and when the mesh fishing efficiency optimizing method program based on the image recognition is executed by the processor, the following steps are realized:
Acquiring image data of a fishing environment of the net in real time, and acquiring the position of the net and the characteristic data of fish;
based on an image recognition technology and a geographic information system, analyzing image data of the fishing environment of the net, and determining the type, position and density of the fish shoals;
judging whether the position of the fish school coincides with the position of the net according to the position of the fish school and the position of the net, and adjusting the position of the net in real time;
according to the type, position and density of the fish shoals, the optimal net throwing place is intelligently selected;
acquiring net fishing data in real time, acquiring the number of target fishes according to the net fishing data, judging whether the number of the target fishes reaches a preset fishing amount, and starting a target fish induction system if the number of the target fishes does not reach the preset fishing amount;
and monitoring the fishing data of the net in real time, and judging whether the loading capacity of the net is within the loading capacity range.
According to the embodiment of the invention, the real-time acquisition of the image data of the fishing environment of the net and the position of the net comprises the following specific steps:
acquiring image data of a fishing environment of the net according to underwater shooting equipment of the net, wherein the image data comprises a fish swarm image;
and acquiring the position of the net through GPS positioning of the net.
It should be noted that the netting gear is provided with a shooting device and a positioning device; the image data of the fishing environment of the netting gear is acquired by using the underwater shooting equipment of the netting gear. The image data comprise fish shoal images, and the fish activity in the surrounding water can be captured through underwater shooting equipment. By using these image data, information about the shoal distribution, the number, the behavior, and the like can be acquired; by using the GPS positioning technology, the accurate coordinates of the netting gear in water can be obtained in real time.
According to the embodiment of the invention, based on the image recognition technology and the geographic information system, the image data of the fishing environment of the net is analyzed to determine the type, the position and the density of the fish shoals, specifically:
constructing an image recognition model based on a convolutional neural network, importing image data of a fishing environment of the net into the image recognition model, and extracting image features;
comparing the extracted image features with the fish feature data to obtain fish information in the image;
obtaining the fish type and density according to the fish information;
labeling the image data based on a geographic information system to obtain an image data acquisition position;
and analyzing according to the image data acquisition position to determine the position of the fish school.
The method is characterized in that the image recognition model is built based on the convolutional neural network, and image data of the fishing environment of the net can be analyzed and features can be extracted through training; the fish information includes the kind and the number of fish; the image data is marked based on a geographic information system, so that the position information of each image data can be obtained; the position information is combined with fish information, further analysis is carried out, and the specific position of the fish shoal in the water area can be determined according to the position obtained by the image data.
According to the embodiment of the invention, according to the position of the fish school and the position of the net, whether the position of the fish school is coincident with the position of the net is judged, and the position of the net is adjusted in real time, specifically:
obtaining a horizontal edge position of the fish school and a horizontal edge position of the net according to the fish school position and the net position;
constructing a netting gear position adjusting system, marking and connecting the horizontal edge positions of the shoal of fish and the horizontal edge positions of the netting gear to form a closed area, wherein the closed area comprises a shoal of fish area and a netting gear area;
comparing the fish school area with the netting gear area, and judging the position relationship between the fish school area and the netting gear area;
if the fish area is overlapped, calculating the overlapping percentage of the fish area and the net area, and if the overlapping percentage is smaller than a preset value, utilizing the net to drag the robot to move the net position until the overlapping percentage of the fish area and the net area is larger than the preset value;
if the fish areas do not overlap, the net dragging robot is also used for moving the net positions until the overlapping percentage of the fish areas and the net areas is larger than a preset value.
It should be noted that, under the condition that the net is put in, according to the embodiment of the invention, the position change of the fish shoal can be judged to change the position of the net, thereby avoiding the situation that the net is recycled and put in again and avoiding the low fishing efficiency of the net caused by the position change of the fish shoal; the net dragging robots are distributed on the edge of the net and can drag the net to move, so that the maximum position of the net coincides with the position of the fish shoal, and the fish capturing quantity is improved.
According to the embodiment of the invention, the optimal net throwing place is intelligently selected according to the type, the position and the density of the fish shoals, and specifically comprises the following steps:
real-time monitoring and analyzing the target fishing area through an image recognition technology to obtain monitoring results, wherein the monitoring results comprise water depth, fish school distribution condition and fish school behaviors;
acquiring historical target fishing area data, wherein the historical target fishing area data comprises historical fishing quantity and historical fishing depth;
carrying out correlation analysis on the monitoring result, the historical target fishing area data, the type, the position and the density of the fish shoal, and predicting the fishing amount of different positions of the target fishing area to obtain a prediction result;
according to the prediction result, the fishing efficiency and the fishing gain of different throwing places of the net are evaluated, and an evaluation result is obtained;
and obtaining the optimal net throwing place according to the evaluation result.
It should be noted that the embodiment of the invention provides a method for intelligently selecting an optimal net throwing place based on the type, the position and the density of a fish shoal, the method can accurately predict the fishing amount of different positions of a target fishing area by utilizing an image recognition technology, historical data and correlation analysis, and evaluate the fishing efficiency and the fishing gain of the net at different throwing places, so that the optimal net throwing place is determined, the capturing efficiency can be improved to the greatest extent in the fishing process, resources are effectively utilized, and ineffective throwing and resource waste are reduced; the historical target fishing area data is obtained through a historical fishing database; the history fishing database is used for recording the capturing amount of the fishing boat and the types of the fishing fishes. According to the embodiment of the invention, the real-time acquisition of the fishing data of the net is performed, the number of target fishes is acquired according to the fishing data of the net, whether the number of target fishes reaches a preset fishing amount is judged, and if the number of target fishes does not reach the preset fishing amount, a target fish induction system is started, specifically:
Identifying fish types in the net through the net monitoring device, and respectively counting the fish types to obtain net fishing data, wherein the fishing data comprise fish capturing amount and fish types;
analyzing the fishing data to obtain the number of target fishes;
comparing the number of the target fishes with a preset fishing amount, and judging whether the number of the target fishes reaches the preset fishing amount or not;
if the preset fishing amount is not reached, acquiring phototactic illumination color and photosensitive comfort of the target fish;
and adjusting the illumination color and illumination intensity of the target fish induction system in real time according to the illumination color and the photosensitive comfort level.
It should be noted that, according to the embodiment of the present invention, a method for determining the number of target fishes and a target fish induction system based on net fishing data is provided, the method acquires net fishing data in real time, and determines whether the number of target fishes reaches a preset fishing amount by analysis, if the number of target fishes does not reach the preset fishing amount, the system starts the target fish induction system, and adjusts illumination conditions according to illumination color and light sensing comfort level so as to increase attraction and fishing efficiency of the target fishes; the preset fishing amount refers to the lowest fishing gain set for the target fish.
According to the embodiment of the invention, the real-time monitoring of the fishing data of the net tool judges whether the loading capacity of the net tool is within the loading capacity range, specifically:
monitoring fishing data of the net in real time through underwater camera equipment and sensor equipment, wherein the fishing data comprise fishing quantity, fish types and sizes of the net;
monitoring tension change of the net in the fishing process in real time through a tension sensor;
judging whether the tension change is in a preset tension range according to the preset tension range, and obtaining a judging result;
and judging whether the loading capacity of the net is within the loading capacity range according to the judging result and the catching amount.
It should be noted that, the embodiment of the invention provides a method for judging whether the loading capacity of the net is within the loading capacity range by monitoring the fishing data and tension change of the net in real time and combining preset parameters, and the method can help fishermen or related personnel to know the state of the net in time, so that the net is prevented from being damaged due to excessive fishing, and economic loss is avoided; the preset tension range is calculated by the safe carrying weight of the net, which is obtained by the factory specification of the net.
According to an embodiment of the present invention, further comprising:
acquiring phototactic information of various target fishes, wherein the phototactic information comprises illumination color, illumination intensity and illumination frequency;
Based on a computer vision technology, fusing phototactic information of various target fishes to obtain optimal fused illumination information, wherein the optimal fused illumination information comprises optimal illumination color and frequency;
the method comprises the steps of obtaining driving sound wave information of non-target fish, wherein the driving sound wave information comprises sound frequency and sound size;
transmitting the dispelling sound wave information and the optimal fusion illumination to a target fish induction system to adjust the illumination color, frequency and sound frequency;
dividing the illumination intensity into 10 grades, and obtaining fishing information of the net under each illumination intensity grade, wherein the fishing information comprises fish types and fishing gains;
acquiring the capturing proportion of adult fish to juvenile fish under each illumination intensity according to the fishing information;
analyzing according to the capturing proportion of adult fish and juvenile fish under each illumination intensity to obtain the optimal capturing proportion;
calculating according to the fish types and the fish gains to obtain the fish gains of the target fish types;
analyzing according to the optimal capturing proportion and the fishing gain of the target fish, and obtaining the optimal illumination intensity level of the net fishing;
the optimal illumination intensity and illumination color are constructed as an optimal induction fishing scheme.
The fish is trapped under the optimal illumination intensity, so that the optimal capturing proportion of the juvenile fish to the adult fish is obtained, the excessive fishing of the juvenile fish is avoided, and the sustainable development of fishery resources is realized; according to the embodiment of the invention, the ratio of the captured adult fish to the young fish can be obtained according to the optimal illumination intensity to be the optimal ratio, and the larger the optimal ratio is, the higher the adult fish ratio is; the illumination intensity is divided into 10 grades, and the illumination intensity is gradually increased.
According to an embodiment of the present invention, further comprising:
based on a geographic information system, acquiring a target fishing area, and dividing the target fishing area into N grids in a grid mode;
sending the optimal induced fishing protocol into a fishing vessel within a grid;
acquiring fishing information of a plurality of fishing boats in N grids according to the optimal induced fishing scheme within preset time, wherein the fishing information comprises total capturing amount and target fish capturing amount;
according to the fishing information, sequencing the total capturing quantity of the plurality of fishing boats in different grids from high to low to obtain a sequencing result;
Acquiring the position information of the first 5 grids according to the sequencing result, and formulating an optimal route for the fishing boat to travel among the 5 grids according to the position information;
and analyzing according to the optimal route to obtain the optimal throwing route of the net.
It should be noted that, each of the N grids performs fishing operation according to the illumination color and the optimal illumination intensity in the grid by at least one fishing boat in the near month; the optimal route is the shortest distance route traveled by the fishing boat among the first 5 grids, and the 5 grids are all on the optimal route; the net is put in according to the optimal route of the fishing boat, so that the fishing efficiency and the fishing gain of the net can be increased to the greatest extent; the preset time is 1 month; in different grids, the water temperature and the water flow speed are different, and the phototaxis of the fishes are also influenced to a certain extent, so that the total capturing amount and the target fish capturing amount obtained in different capturing areas of the fishing vessel when the optimal induced capturing scheme is applied are also different.
According to an embodiment of the present invention, further comprising:
acquiring image information of different underwater netting gear fishing conditions;
preprocessing according to the image information to identify different pieces of network tool information;
Analyzing the fishing amount of the net according to different net information;
according to the fishing amount, the fishing efficiency of different nets is analyzed, and according to the fishing efficiency, a net recommendation report is generated.
It should be noted that, the embodiment of the invention provides an image-based method for deducing the fishing amount and the fishing efficiency of different nets by acquiring the image information of different nets under water and performing preprocessing, analysis and evaluation, and the method can provide guidance and advice about the adjustment and optimization of the nets for fishermen or related personnel so as to improve the fishing efficiency and economic benefit; the netting gear information comprises the position, the shape and the capturing object of the netting gear under water; the adjusting the netting gear proposal report includes increasing or decreasing the use of netting gears, adjusting the netting gear layout.
The invention discloses an image recognition-based net fishing efficiency optimization method, which is characterized in that image data of a net fishing environment, net position and fish characteristic data are obtained in real time, and the image data are analyzed by combining an image recognition technology and a satellite positioning system to determine the type, position and density of a fish swarm; according to the judgment of the fish shoal position and the net position, the net position is adjusted in real time, and the optimal net throwing place is intelligently selected to optimize the fishing efficiency; judging whether the loading capacity of the net is within the loading capacity range by monitoring the fishing data of the net, evaluating whether the number of the target fishes reaches a preset fishing amount in real time, and starting a target fish induction system when the number of the target fishes does not reach the preset fishing amount; through the steps, the method can realize real-time monitoring, adjustment and optimization of the fishing process of the net, improve the fishing efficiency and reduce the resource waste.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The method for optimizing the fishing efficiency of the net based on the image recognition is characterized by comprising the following steps of:
acquiring image data of a fishing environment of the net in real time, and acquiring the position of the net and the characteristic data of fish;
based on an image recognition technology and a geographic information system, analyzing image data of the fishing environment of the net, and determining the type, position and density of the fish shoals;
judging whether the position of the fish school coincides with the position of the net according to the position of the fish school and the position of the net, and adjusting the position of the net in real time;
according to the type, position and density of the fish shoals, the optimal net throwing place is intelligently selected;
acquiring net fishing data in real time, acquiring the number of target fishes according to the net fishing data, judging whether the number of the target fishes reaches a preset fishing amount, and starting a target fish induction system if the number of the target fishes does not reach the preset fishing amount;
And monitoring the fishing data of the net in real time, and judging whether the loading capacity of the net is within the loading capacity range.
2. The method for optimizing fishing efficiency of a net based on image recognition according to claim 1, wherein the real-time acquisition of image data of a fishing environment of the net and a position of the net specifically comprises:
acquiring image data of a fishing environment of the net according to underwater shooting equipment of the net, wherein the image data comprises a fish swarm image;
and acquiring the position of the net through GPS positioning of the net.
3. The method for optimizing fishing efficiency of a fishing net based on image recognition according to claim 1, wherein the image data of the fishing environment of the fishing net is analyzed based on the image recognition technology and the geographic information system to determine the kind, position and density of the fish shoals, specifically:
constructing an image recognition model based on a convolutional neural network, importing image data of a fishing environment of the net into the image recognition model, and extracting image features;
comparing the extracted image features with the fish feature data to obtain fish information in the image;
obtaining the fish type and density according to the fish information;
labeling the image data based on a geographic information system to obtain an image data acquisition position;
And analyzing according to the image data acquisition position to determine the position of the fish school.
4. The method for optimizing fishing efficiency of a fishing net based on image recognition according to claim 1, wherein the step of judging whether the position of the fishing net coincides with the position of the fishing net according to the position of the fishing net and the position of the fishing net, and the step of adjusting the position of the fishing net in real time is as follows:
obtaining a horizontal edge position of the fish school and a horizontal edge position of the net according to the fish school position and the net position;
constructing a netting gear position adjusting system, marking and connecting the horizontal edge positions of the shoal of fish and the horizontal edge positions of the netting gear to form a closed area, wherein the closed area comprises a shoal of fish area and a netting gear area;
comparing the fish school area with the netting gear area, and judging the position relationship between the fish school area and the netting gear area;
if the fish area is overlapped, calculating the overlapping percentage of the fish area and the net area, and if the overlapping percentage is smaller than a preset value, utilizing the net to drag the robot to move the net position until the overlapping percentage of the fish area and the net area is larger than the preset value;
if the fish areas do not overlap, the net dragging robot is also used for moving the net positions until the overlapping percentage of the fish areas and the net areas is larger than a preset value.
5. The method for optimizing fishing efficiency of a net based on image recognition according to claim 1, wherein the intelligent selection of the optimal net throwing place according to the type, position and density of the fish shoals is specifically as follows:
real-time monitoring and analyzing the target fishing area through an image recognition technology to obtain monitoring results, wherein the monitoring results comprise water depth, fish school distribution condition and fish school behaviors;
acquiring historical target fishing area data, wherein the historical target fishing area data comprises historical fishing quantity and historical fishing depth;
carrying out correlation analysis on the monitoring result, the historical target fishing area data, the type, the position and the density of the fish shoal, and predicting the fishing amount of different positions of the target fishing area to obtain a prediction result;
according to the prediction result, the fishing efficiency and the fishing gain of different throwing places of the net are evaluated, and an evaluation result is obtained;
and obtaining the optimal net throwing place according to the evaluation result.
6. The method for optimizing fishing efficiency of a net based on image recognition according to claim 1, wherein the capturing data of the net is obtained in real time, the number of target fishes is obtained according to the capturing data of the net, whether the number of target fishes reaches a preset fishing amount is judged, and if the number of target fishes does not reach the preset fishing amount, a target fish induction system is started, specifically:
Identifying fish types in the net through the net monitoring device, and respectively counting the fish types to obtain net fishing data, wherein the fishing data comprise fish capturing amount and fish types;
analyzing the fishing data to obtain the number of target fishes;
comparing the number of the target fishes with a preset fishing amount, and judging whether the number of the target fishes reaches the preset fishing amount or not;
if the preset fishing amount is not reached, acquiring phototactic illumination color and photosensitive comfort of the target fish;
and adjusting the illumination color and illumination intensity of the target fish induction system in real time according to the illumination color and the photosensitive comfort level.
7. The method for optimizing fishing efficiency of a net based on image recognition according to claim 1, wherein the real-time monitoring of the fishing data of the net judges whether the loading capacity of the net is within the loading capacity range, specifically:
monitoring fishing data of the net in real time through underwater camera equipment and sensor equipment, wherein the fishing data comprise fishing quantity, fish types and sizes of the net;
monitoring tension change of the net in the fishing process in real time through a tension sensor;
judging whether the tension change is in a preset tension range according to the preset tension range, and obtaining a judging result;
And judging whether the loading capacity of the net is within the loading capacity range according to the judging result and the catching amount.
8. The system for optimizing the fishing efficiency of the net tool based on the image recognition is characterized by comprising a storage and a processor, wherein the storage comprises a net tool fishing efficiency optimizing method program based on the image recognition, and when the net tool fishing efficiency optimizing method program based on the image recognition is executed by the processor, the following steps are realized:
acquiring image data of a fishing environment of the net in real time, and acquiring the position of the net and the characteristic data of fish;
based on an image recognition technology and a geographic information system, analyzing image data of the fishing environment of the net, and determining the type, position and density of the fish shoals;
judging whether the position of the fish school coincides with the position of the net according to the position of the fish school and the position of the net, and adjusting the position of the net in real time;
according to the type, position and density of the fish shoals, the optimal net throwing place is intelligently selected;
acquiring net fishing data in real time, acquiring the number of target fishes according to the net fishing data, judging whether the number of the target fishes reaches a preset fishing amount, and starting a target fish induction system if the number of the target fishes does not reach the preset fishing amount;
And monitoring the fishing data of the net in real time, and judging whether the loading capacity of the net is within the loading capacity range.
9. The system for optimizing fishing efficiency of a fishing net based on image recognition according to claim 8, wherein the determining whether the position of the fishing net coincides with the position of the fishing net according to the position of the fishing net and the position of the fishing net, and the adjusting the position of the fishing net in real time specifically comprises:
obtaining a horizontal edge position of the fish school and a horizontal edge position of the net according to the fish school position and the net position;
constructing a netting gear position adjusting system, marking and connecting the horizontal edge positions of the shoal of fish and the horizontal edge positions of the netting gear to form a closed area, wherein the closed area comprises a shoal of fish area and a netting gear area;
comparing the fish school area with the netting gear area, and judging the position relationship between the fish school area and the netting gear area;
if the fish area is overlapped, calculating the overlapping percentage of the fish area and the net area, and if the overlapping percentage is smaller than a preset value, utilizing the net to drag the robot to move the net position until the overlapping percentage of the fish area and the net area is larger than the preset value;
if the fish areas do not overlap, the net dragging robot is also used for moving the net positions until the overlapping percentage of the fish areas and the net areas is larger than a preset value.
10. The system for optimizing fishing efficiency of a net based on image recognition according to claim 8, wherein the step of obtaining the number of the target fish according to the fishing data of the net, judging whether the number of the target fish reaches a preset fishing amount, and if not, starting the target fish induction system specifically comprises:
analyzing the fishing data to obtain the number of target fishes;
comparing the number of the target fishes with a preset fishing amount, and judging whether the number of the target fishes reaches the preset fishing amount or not;
if the preset fishing amount is not reached, acquiring phototactic illumination color and photosensitive comfort of the target fish;
and adjusting the illumination color and illumination intensity of the target fish induction system in real time according to the illumination color and the photosensitive comfort level.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311240465.XA CN116994293B (en) | 2023-09-25 | 2023-09-25 | Method and system for optimizing fishing efficiency of net based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311240465.XA CN116994293B (en) | 2023-09-25 | 2023-09-25 | Method and system for optimizing fishing efficiency of net based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116994293A true CN116994293A (en) | 2023-11-03 |
CN116994293B CN116994293B (en) | 2024-01-12 |
Family
ID=88521577
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311240465.XA Active CN116994293B (en) | 2023-09-25 | 2023-09-25 | Method and system for optimizing fishing efficiency of net based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116994293B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109186553A (en) * | 2018-08-15 | 2019-01-11 | 上海海洋大学 | Tuna seine detection of fish school tracing system and method based on unmanned air vehicle technique |
WO2019140771A1 (en) * | 2018-01-22 | 2019-07-25 | 无锡职业技术学院 | Fishery system for carrying out long range fishing operations by utilizing internet of things big data |
CN110447607A (en) * | 2019-08-07 | 2019-11-15 | 唐山哈船科技有限公司 | A kind of fish-catching apparatus and fishing method based on image recognition |
CN111955425A (en) * | 2020-08-27 | 2020-11-20 | 上海海洋大学 | Auxiliary decision-making system and method for accurate capture of tuna seine |
CN116724964A (en) * | 2023-05-25 | 2023-09-12 | 上海海洋大学 | Fish detection system and method based on lamplight trapping |
-
2023
- 2023-09-25 CN CN202311240465.XA patent/CN116994293B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019140771A1 (en) * | 2018-01-22 | 2019-07-25 | 无锡职业技术学院 | Fishery system for carrying out long range fishing operations by utilizing internet of things big data |
CN109186553A (en) * | 2018-08-15 | 2019-01-11 | 上海海洋大学 | Tuna seine detection of fish school tracing system and method based on unmanned air vehicle technique |
CN110447607A (en) * | 2019-08-07 | 2019-11-15 | 唐山哈船科技有限公司 | A kind of fish-catching apparatus and fishing method based on image recognition |
CN111955425A (en) * | 2020-08-27 | 2020-11-20 | 上海海洋大学 | Auxiliary decision-making system and method for accurate capture of tuna seine |
CN116724964A (en) * | 2023-05-25 | 2023-09-12 | 上海海洋大学 | Fish detection system and method based on lamplight trapping |
Non-Patent Citations (1)
Title |
---|
沈军宇等: "一种基于YOLO算法的鱼群检测方法", 《中国体视学与图像分析》, no. 02, pages 54 - 60 * |
Also Published As
Publication number | Publication date |
---|---|
CN116994293B (en) | 2024-01-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112465738B (en) | Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images | |
CN114170513B (en) | Insect condition monitoring method, system and storage medium for spodoptera frugiperda | |
CN114494837B (en) | Intelligent density identification method and system for fishery resources | |
CN115100512A (en) | Monitoring, identifying and catching method and system for marine economic species and storage medium | |
KR20200067743A (en) | Fish net surveillance apparatus using Remotely-Operated underwater Vehicle, controlling method of the same | |
CN110728259A (en) | Chicken group weight monitoring system based on depth image | |
CN116935327B (en) | Aquaculture monitoring method, device, equipment and storage medium based on AI vision | |
CN115797844A (en) | Fish body fish disease detection method and system based on neural network | |
CN117741077A (en) | Aquatic plant harvesting-based aquatic ecological environment protection method | |
CN116192917A (en) | Comprehensive observation and forecast platform for ocean pasture | |
CN114493680B (en) | Fishery resource statistical method and system based on stream stab net investigation | |
CN111563439A (en) | Aquatic organism disease detection method, device and equipment | |
CN116994293B (en) | Method and system for optimizing fishing efficiency of net based on image recognition | |
NL2037440A (en) | A method, system, and medium for intelligent recognition of fishing activities based on image processing | |
Shishkin et al. | Analysis of image clusterization methods for oceanographical equipment | |
CN113313042B (en) | Image processing method, ingestion state detection method and storage medium | |
CN112783180B (en) | Multi-view camouflage type underwater organism recognition system and method | |
CN115376023A (en) | Cultivation area detection method based on deformation convolutional network, unmanned aerial vehicle and medium | |
CN113627359A (en) | Fishing boat behavior intelligent monitoring algorithm based on bidirectional long-time and short-time neural network | |
CN116849188B (en) | Lossless continuous suction-catching method and system | |
CN117193304B (en) | Unmanned ship cluster control method and related equipment | |
CN117893949B (en) | Gun-ball integrated solar hunting camera management method based on intelligent recognition | |
CN117057948B (en) | Ocean safety production method, system and medium based on big data | |
CN109034105B (en) | Tuna fishery position prediction method based on unmanned aerial vehicle | |
CN118095585A (en) | Feeding path evaluation method and system based on intelligent perception |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |