CN114637014B - Underwater robot-based unmanned fishing ground fish school behavior recognition system and method - Google Patents
Underwater robot-based unmanned fishing ground fish school behavior recognition system and method Download PDFInfo
- Publication number
- CN114637014B CN114637014B CN202210531440.4A CN202210531440A CN114637014B CN 114637014 B CN114637014 B CN 114637014B CN 202210531440 A CN202210531440 A CN 202210531440A CN 114637014 B CN114637014 B CN 114637014B
- Authority
- CN
- China
- Prior art keywords
- fish
- real
- underwater robot
- time
- frequency
- 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
Images
Classifications
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/96—Sonar systems specially adapted for specific applications for locating fish
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63C—LAUNCHING, HAULING-OUT, OR DRY-DOCKING OF VESSELS; LIFE-SAVING IN WATER; EQUIPMENT FOR DWELLING OR WORKING UNDER WATER; MEANS FOR SALVAGING OR SEARCHING FOR UNDERWATER OBJECTS
- B63C11/00—Equipment for dwelling or working underwater; Means for searching for underwater objects
- B63C11/52—Tools specially adapted for working underwater, not otherwise provided for
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/539—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- 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
Abstract
The invention relates to the technical field of intelligent aquaculture data analysis, and discloses an unmanned fishing ground fish school behavior recognition system and method based on an underwater robot. Under the complex fishing ground aquaculture environment, after measuring the shoal of throwing something and feeding, accurately discern the fish activity in the pond, according to the change of its activity state of scientific analysis pond or the healthy state of shoal, improved the accuracy and the reliability of unusual discernment greatly, greatly reduced breed user or operator because of the economic loss risk that unusual discernment mistake led to of fish formed beneficial effect to the efficiency rate of resource and energy.
Description
Technical Field
The invention belongs to the technical field of data acquisition, relates to the technical field of intelligent aquaculture data analysis, and particularly relates to an unmanned fishing ground fish school behavior identification system and method based on an underwater robot.
Background
In the fish culture industry, cultured fish schools are easily affected by external factors, including uncertain factors such as bacteria, viruses or other species, which can cause the fish schools to be abnormal, the growth of the fish is inhibited in a slight condition, the growth and development speed of the fish is reduced, and the fish ponds are flooded in a severe condition. However, if the health state of the fish or the state of the pond is judged only by human vision or experience, the slight difference cannot be distinguished, so that irreparable economic loss is caused when the abnormal time is discovered too late; therefore, a scientific and effective method for identifying the health of fish schools or the state of ponds to avoid the risks of various abnormalities of the fishes is urgently needed, and the current methods in the prior art detect the activity of the fishes by methods such as diagnosis vibration, computer vision and the like, and have the defects of low detection precision, slow response and low accuracy and reliability caused by various interference factors.
Disclosure of Invention
The invention aims to provide an unmanned fishing ground fish school behavior identification system and method based on an underwater robot, which are used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
In order to achieve the above object, according to an aspect of the present invention, there is provided an unmanned fishing ground fish shoal behavior recognition method based on underwater robots, the method comprising the steps of:
s100, the underwater robot transmits sound waves to the fish school and acquires echo signals of the sound waves;
s200, filtering the echo signal to obtain a first signal;
s300, calculating an active coefficient by using a first signal calculation scheme;
s400, calculating an abnormal rate through the activity coefficient;
s500, identifying whether the behavior state of the fish shoal is normal or not according to the abnormal rate and outputting;
the method for calculating the active coefficient by using the first signal calculation scheme comprises the following steps: at t 0 Feed is fed to a fishery at any time (when feed is fed to a fishpond, feed is uniformly fed to the fishpond, fish shoal in the fishpond is actively increased due to the fact that fish shoal strives for feed in the feeding process, and the obtained signals are increased, so that the accuracy of real-time frequency can be improved), and PMqf (t and t) 0 ) Represents t 0 The real-time frequency of the first signal obtained at the moment; setting a sequence as a frequency real-time sequence LsPM, and adding PMqf (t) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence LsPM;
setting a measured sub-threshold value tGate, wherein tGate is an integer and is set to be [10,30 ];
starting to measure once every time TF to obtain a first signal, wherein the measurement is to transmit sound waves to a fish school and obtain the first signal according to echo signals of the sound waves;
from t 0 Acquiring each real-time frequency PMqf of the first signal T times from the moment (T2), and transmitting the PMqf (T) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence, and then sequentially adding PMqf (T2) meeting a first condition into the frequency real-time sequence LsPM one by one, wherein T2 is from T 0 T-th measurement time from time, T2= T 0 +t×TF；
The first condition is: PMqf (T2) ≧ 0.5 × (max { LsPM } -PMqf (T) 0 ) And t ≦ tGate; wherein max { LsPM } represents the maximum value in LsPM; t is the preset number of measurements to obtain the first signal, and is taken as [30,100 ]]Secondly; PMqf (T2) is from T 0 Measuring the real-time frequency of the acquired first signal from the moment t;
and acquiring a real-time sequence LsPM, and taking an element corresponding to the time when the values of the elements in the LsPM sequentially increase and then decrease for the first time as an active coefficient ACIDX.
Further, in step S100, the method of acquiring the echo signal of the acoustic wave is: putting an underwater robot in a fishing ground, wherein the underwater robot can move in water; the underwater robot is installed with the detecting head, the detecting head contains: transducer or sonar fish finder, receiving and transmitting control unit; the energy converter or the sonar fish finder is used for transmitting an acoustic pulse signal to a fish school in a fishing ground and receiving an echo signal to the receiving and transmitting control unit; the energy converter or the sonar fish finder can at least transmit an acoustic pulse signal to a water body in a fishing ground, the energy converter is provided with a conical open angle, the open angle range is 5-10 degrees, the transceiving control unit is used for generating the acoustic pulse signal according to acoustic parameters and exciting the energy converter or the sonar fish finder to radiate the acoustic pulse signal to the water body in the fishing ground, meanwhile, echo signals of fish schools in the water body in the fishing ground are received, noise in the echo signals is eliminated, the underwater robot is any one of the underwater robots with patent publication numbers CN212149252U, CN216118500U, CN212500964U or CN208979083U, the sonar frequency of the sonar fish finder is 200KHz to 500KHz, the probe detection angle is 45 degrees, the detection range is 0.6-100 meters, the accuracy is 0.1-0.3 meters, and the underwater robot can be provided with one or more than one.
Further, in step S200, the method for obtaining the first signal by filtering the echo signal is: passing a set time threshold TF (TF = [5,10 ]]Minute) of the echo signals, recording the signal size of the obtained echo signals as real-time frequency Mqf or recording the Doppler frequency of the echo signals as real-time frequency Mqf, and controlling the underwater robot to move [2, 24 ]]The real-time frequencies Mqf of all echo signals within an hour form a real-time frequency sequence LMqf, which is [ Mqf ] a1 ](ii) a Wherein a1 is the sequence number of real-time frequency in time sequence, a 1E [1, Pcs]Pcs represents [2, 24 ]]Total number of real-time frequencies Mqf obtained in an hour, Mqf a1 Is the a1 th real-time frequency in LMqf; calculating by using a real-time frequency sequence LMqf to obtain a valley-peak frequency ratio epsilon, wherein epsilon is max { LMqf }/min { LMqf };
wherein max { LMqf } represents the maximum value in the sequence LMqf, and min { LMqf } represents the minimum value in the sequence LMqf;
calculating the sensitivity SstIdx of the real-time frequency of the echo signal by using the sequence LMqf,
wherein a2 is an accumulation variable, EMqf represents the arithmetic mean value of each numerical value in the sequence LMqf, and epsilon represents the ratio of valley to peak frequencies;
calculating the arithmetic mean value PSI of the wave sensitivity SstIdx of the real-time frequency of all echo signals; the echo signal with the sensitivity SstIdx larger than PSI is screened out as the first signal.
Preferably, in step S300, the method for calculating the active coefficient by using the first signal calculation scheme may be further replaced by: at t 0 Constantly feed the fishery (when feed is fed to the fishpond, feed is uniformly fed to the fishpond, fish shoal activity in the fishpond is increased due to the fact that fish shoal feeding during feeding is performed, obtained signals are increased, accuracy of real-time frequency can be improved), PMqf (t 0 ) Represents t 0 The real-time frequency of the first signal obtained at the moment; setting a sequence as a frequency real-time sequence LsPM, and adding PMqf (t) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence LsPM; t is t 0 The moment is the moment when the feed feeding is started;
setting a variable maxPM as a peak measurement value, and initializing the value of the peak measurement value maxPM to PMqf (t) 0 ) (ii) a Setting a variable t as a time counter, and setting the initial value of t to be 1; setting a variable tGate as a measured threshold value with an initial value of [10,30]](ii) a Skipping to step S301;
s301, starting to measure every other time TF to obtain a first signal, wherein the measurement is to transmit sound waves to a fish school and obtain the first signal according to echo signals of the sound waves;
s302, acquiring a real-time frequency PMqf (T2) of the first signal, wherein T2 is from T 0 Time T2= T, the time at which the T-th measurement is started 0 + T × TF if PMqf (T2) ≥ 0.5 × (maxPM-PMqf (T) 0 ) And T is less than or equal to tGate, adding PMqf (T2) into a frequency real-time sequence LsPM, and jumping to the step S303; if PMqf (T2) < 0.5 × (maxPM-PMqf (T) 0 ) And t < tGate), the underwater robot resumes measurement every TF; calculating an active coefficient ACIDX: ACIDX = (maxPM-PMqf (T2))/(tTop-T);
wherein tTop represents a value of T when maxPM is obtained, a value of tGate is set as the value of T when a first frequency value PMqf (T2) in the LsPM exceeds 3 × maxPM for the first time, or the value of tGate is set as a sequence number of a first element with a first decreasing value after values of elements in the LsPM are sequentially increased, and the step S304 is skipped;
s303, if PMqf (T2) > maxPM, updating the value of the maxPM to be the value of the PMqf (T2), adding 1 to the value of a time counter T, and jumping to the step S302; if PMqf (T2) is less than or equal to maxPM, adding 1 to the value of the time counter T, and jumping to the step S302;
and S304, ending.
The beneficial effects of calculating the active coefficient are as follows: the calculated active coefficient can reflect the change trend in the fed fishing ground more sensitively under the condition that the wave frequency of the reflected sound wave is relatively small, the state of the fish activity is quantified by utilizing the characteristics of the change trend, and the active coefficient can accurately record the state of the fish in the fishing ground or the state of the pond, so that the identifiability of the fish is greatly improved, and the fuzziness and uncertainty of human eye observation or experience judgment are overcome.
Further, in step S400, the method of calculating the abnormal rate by the activity coefficient is: after feeding the feed into the fish pond, each underwater robot in the fish pond starts to try to obtain an activity coefficient; when all underwater robots obtain active coefficients, combining all underwater robots in the fish pond to construct a field state list ZLst, wherein the ZLst is [ ACIDX [ ] a3 ]，a3∈[1，K]Wherein a3 represents the serial number, ACIDX, of each underwater robot in the fish pond a3 Representing the activity coefficient obtained by the a3 th underwater robot, K representing the number of the underwater robots in the fish pond, K belonging to [1, 20 ]](ii) a Obtaining a field state list ZLst in rcrd days to form a field state matrix AMtx, wherein [ ZLst ═ AMtx ═ a4 ]，a4∈[1，rcrd]Wherein rcrd is the observation period in natural days and has a value of [30, 60 ]]An internal value, a4 represents the serial number of the date; ZLst a4 Representing a scene list of a4-1 day before the current day; when the value of a4 is 1, ZLst a4 Representing the scene list of the current day; srcrd is used as a short-term value, and the Srcrd is [0.25 Xrcrd ═]In the formula (2)]The symbol is an integer function; the meaning of each is one or more, and the short-term field average floating index SMFI of the current day is calculated:
wherein a5 is an accumulation variable; γ is 2/(1+ Srcrd);
represented by ZLst a5 The arithmetic mean of the individual elements in (b), ZLst a5 Represents the a5 th element in the field state matrix AMtx, i.e. the a5 th field state list; using Lrcrd as long-term value, Lrcrd ═ 0.5 Xrcrd](ii) a Calculating the long-term field average floating index LMFI of the current day,
wherein a6 is an accumulation variable; γ ═ 2/(1+ Lrcrd);
represented by ZLst a6 The arithmetic mean of the individual elements in (1); ZLst a6 Represents the a6 th element in the field state matrix AMtx, i.e. the a6 th field state list; calculating a floating interval DBSL of the current day through the long-term field average floating index LMFI and the short-term field average floating index SMFI, wherein the DBSL is SMFI-LMFI; DBSL takes a value of 0 without the value of LMFI; trend index TRD was calculated by DBSL:
wherein γ is 2/(1+ Srcrd); TRD 'represents a trend index TRD obtained after the feed is fed to a fishery on the last natural day, and the values of TRD and TRD' are 0 when the LMFI value is not available; and (5) calculating to obtain the fish shoal abnormal rate FGWI ═ DBSL-TRD.
Preferably, in step S400, the method for calculating the abnormal rate by the activity coefficient is: calculating to obtain a fish shoal abnormal rate FGWI:
FGWI ═ min { LsPM }/ACIDX, min { LsPM } represents the minimum of LsPM.
The beneficial effects are as follows: by combining with continuous time sequence for analysis, the calculated abnormal fish school rate enables the activity of the fish school or the operation state of the pond to have time dimension, the current state of the fish school can be objectively compared, the characteristics of the activity or the health state of the fish school along with the change of time are refined, and the credibility of fish school abnormal judgment is improved.
Further, in step S500, a method of identifying whether the behavior state of the fish school is normal or not according to the abnormality rate and outputting the same includes: acquiring all fish swarm abnormal rates FGWI of the historical records, judging whether the fish swarm abnormal rates FGWI of the current day are abnormal points or not by taking FGWI as a coefficient of a normally distributed unary outlier detection method, if the fish swarm abnormal rates FGWI of the current day are abnormal points, indicating that abnormal behaviors exist in the fish, and sending an abnormal alarm to a client of a manager.
Preferably, when the fish school abnormal rate FGWI is greater than a preset threshold value, or when the fish school abnormal rate FGWI is greater than the fish school abnormal rate FGWI obtained after feeding the fishery on all the natural days of the last week, it indicates that the fish has abnormal behavior, and sends an abnormal alarm to the client of the manager.
The invention also provides an unmanned fishing ground fish school behavior recognition system based on the underwater robot, which comprises: the unmanned fishery fish shoal behavior recognition system based on the underwater robot can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud data center and the like, and the operable system can comprise, but is not limited to, a processor, a memory and a computer program, wherein the computer program is executed by the processor and run in the following units of the system:
the sound wave detection unit is used for transmitting sound waves to the fish school by the underwater robot and acquiring echo signals of the sound waves;
the filtering processing unit is used for filtering the echo signal to obtain a first signal;
an activity metric unit for calculating an activity coefficient using a first signal calculation scheme;
an abnormality estimation unit for calculating an abnormality rate from the activity coefficient;
and the judging and processing unit is used for identifying whether the behavior state of the fish shoal is normal or not according to the abnormal rate and outputting the behavior state.
The invention has the beneficial effects that: the invention provides an unmanned fishing ground fish school behavior recognition system and method based on an underwater robot, which are used for precisely recognizing the activity of fishes in a pond after measuring fed fish schools in a complex fishing ground culture environment, scientifically analyzing the state of the pond or the health state of the fish schools according to the change of the activity, greatly improving the accuracy and reliability of abnormal recognition, greatly reducing the economic loss risk of culture users or operators caused by the excessive abnormal recognition of the fishes and forming a positive influence on the efficiency of resources and energy.
Drawings
The above and other features of the present invention will become more apparent by describing in detail embodiments thereof with reference to the attached drawings in which like reference numerals designate the same or similar elements, it being apparent that the drawings in the following description are merely exemplary of the present invention and other drawings can be obtained by those skilled in the art without inventive effort, wherein:
FIG. 1 is a flow chart of an unmanned fishing ground fish school behavior identification method based on an underwater robot;
fig. 2 is a structural diagram of an unmanned fishing ground fish school behavior recognition system based on an underwater robot.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Referring to fig. 1, a flow chart of an underwater robot-based method for identifying fish swarm behavior in an unmanned fishery is shown, and an underwater robot-based method for identifying fish swarm behavior in an unmanned fishery according to an embodiment of the invention is described with reference to fig. 1, and the method comprises the following steps:
s100, the underwater robot transmits sound waves to the fish school and acquires echo signals of the sound waves;
s200, filtering the echo signal to obtain a first signal;
s300, calculating an active coefficient by using a first signal calculation scheme;
s400, calculating an abnormal rate through the activity coefficient;
and S500, identifying whether the behavior state of the fish shoal is normal or not according to the abnormal rate and outputting.
Further, in step S100, the method of acquiring the echo signal of the acoustic wave is: putting an underwater robot in a fishing ground, wherein the underwater robot can move in water; the underwater robot is provided with a probe head, and the probe head comprises: transducer or sonar fish finder, receiving and transmitting control unit; the energy converter or the sonar fish finder is used for transmitting an acoustic pulse signal to a fish school in a fishing ground and receiving an echo signal to the receiving and transmitting control unit; the energy converter or the sonar fish finder can at least transmit an acoustic pulse signal to a water body in a fishing ground, the energy converter is provided with a conical open angle, the open angle range is 5-10 degrees, the transceiving control unit is used for generating the acoustic pulse signal according to acoustic parameters and exciting the energy converter or the sonar fish finder to radiate the acoustic pulse signal to the water body in the fishing ground, meanwhile, echo signals of fish schools in the water body in the fishing ground are received, noise in the echo signals is eliminated, the underwater robot is any one of the underwater robots with patent publication numbers CN212149252U, CN216118500U, CN212500964U or CN208979083U, the sonar frequency of the sonar fish finder is 200KHz to 500KHz, the probe detection angle is 45 degrees, the detection range is 0.6-100 meters, the accuracy is 0.1-0.3 meters, and the underwater robot can be provided with one or more than one.
Further, in step S200, the method for obtaining the first signal by filtering the echo signal is: passing a set time threshold TF (TF = [5,10 ]]Minutes) is acquired, the signal size of the acquired echo signal is recorded as real-time frequency Mqf or the Doppler frequency of the echo signal is recorded as real-time frequency Mqf, and the underwater robot is used for [2, 24 ]]The real-time frequencies Mqf of all echo signals within an hour form a real-time frequency sequence LMqf, which is [ Mqf ] a1 ](ii) a Wherein a1 is the sequence number of real-time frequency in time sequence, a1 belongs to [1, Pcs ∈ ]]Pcs represents [2, 24 ]]Total number of real-time frequencies Mqf obtained in an hour, Mqf a1 Is the a1 th real-time frequency in LMqf; calculating by using a real-time frequency sequence LMqf to obtain a valley-peak frequency ratio epsilon, wherein epsilon is max { LMqf }/min { LMqf };
wherein max { LMqf } represents the maximum value in the sequence LMqf, and min { LMqf } represents the minimum value in the sequence LMqf;
calculating the sensitivity SstIdx of the real-time frequency of the echo signal by using the sequence LMqf,
wherein a2 is an accumulation variable, EMqf represents the arithmetic mean value of each numerical value in the sequence LMqf, and epsilon represents the ratio of valley to peak frequencies;
calculating the arithmetic mean value PSI of the wave sensitivity SstIdx of the real-time frequency of all echo signals; an echo signal with a sensitivity SstIdx greater than PSI is screened as the first signal.
Further, in step S300, the method for calculating the active coefficient by using the first signal calculation scheme is: at t 0 Feeding feed to the fishery (when feeding feed to the fishpond, uniformly feeding feed to the fishpond), PMqf (t) 0 ) Represents t 0 The real-time frequency of the first signal obtained at the moment; setting a sequence as a frequency real-time sequence LsPM, and adding PMqf (t) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence LsPM; t is t 0 May be the current time;
setting a variable maxPM as a peak measurement value, initializing the peak measurement value maxPMValue PMqf (t) 0 ) (ii) a Setting a variable t as a time counter, and setting the initial value of t as 1; setting a variable tGate as a measured threshold value with an initial value of [10,30]](ii) a Skipping to step S301;
s301, starting to measure every other time TF to obtain a first signal, wherein the measurement is to transmit sound waves to a fish school and obtain the first signal according to echo signals of the sound waves;
s302, acquiring a real-time frequency PMqf (T2) of the first signal, if the PMqf (T2) is not less than 0.5 x (maxPM-PMqf (T2) ≥ 0.5 × ( 0 ) And T is less than or equal to tGate, adding PMqf (T2) into the frequency real-time sequence LsPM, and jumping to the step S303; if PMqf (T2) < 0.5 × (maxPM-PMqf (T) 0 ) And t < tGate), the underwater robot resumes measurement every TF; calculating an active coefficient ACIDX:
，
wherein tTop represents a value of T when maxPM is obtained, a value of tGate is set as the value of T when a first frequency value PMqf (T2) in the LsPM exceeds 3 × maxPM for the first time, or the value of tGate is set as a sequence number of a first element with a first decreasing value after values of elements in the LsPM are sequentially increased, and the step S304 is skipped;
s303, if PMqf (T2) > maxPM, updating the value of the maxPM to be the value of the PMqf (T2), adding 1 to the value of a time counter T, and jumping to the step S302; if PMqf (T2) is less than or equal to maxPM, adding 1 to the value of the time counter T, and jumping to the step S302;
and S304, ending.
Preferably, in step S300, the method for calculating the active coefficient using the first signal calculation scheme is: at t 0 Feeding feed to the fishery (when feeding feed to the fishpond, uniformly feeding feed to the fishpond), PMqf (t) 0 ) Represents t 0 The real-time frequency of the first signal obtained at the moment; setting a sequence as a frequency real-time sequence LsPM, and adding PMqf (t) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence LsPM;
setting a measuring threshold value tGate to be [10,30 ];
starting to measure once every time TF to obtain a first signal, wherein the measurement is to transmit sound waves to a fish school and obtain the first signal according to echo signals of the sound waves;
from t 0 Acquiring each real-time frequency PMqf of the first signal T times from the moment (T2), and transmitting the PMqf (T) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence, and then sequentially adding PMqf (T2) meeting a first condition into the frequency real-time sequence LsPM one by one, wherein T2 is from T 0 Time T2= T, the time at which the T-th measurement is started 0 +t×TF；
The first condition is: PMqf (T2) ≥ 0.5 × (max { LsPM } -PMqf (T) 0 ) And t ≦ tGate; wherein max { LsPM } represents the maximum value in LsPM; t is the preset number of measurements to obtain the first signal, and is taken as [30,100 ]]Secondly; PMqf (T2) is from T 0 Measuring the real-time frequency of the acquired first signal from the moment t;
and acquiring a real-time sequence LsPM, and taking an element corresponding to the moment when the values of the elements in the LsPM sequentially increase and then decrease for the first time as an activity coefficient ACIDX.
The beneficial effects are as follows: by identifying the change in the fed fishing ground and quantifying the state of the activity of the fishes by using the changed characteristics of the activity coefficient ACIDX, the state of the fishes in the fishing ground or the state of the pond can be accurately recorded, the identifiability of the fishes is greatly improved, and the ambiguity and uncertainty of human eye observation or experience judgment are overcome.
Further, in step S400, the method of calculating the abnormal rate by the activity coefficient is: after feeding the feed into the fish pond, each underwater robot in the fish pond starts to try to obtain an activity coefficient; when all underwater robots obtain active coefficients, combining all underwater robots in the fish pond to construct a field state list ZLst, wherein the ZLst is [ ACIDX [ ] a3 ]，a3∈[1，K]Wherein a3 represents the serial number, ACIDX, of each underwater robot in the fish pond a3 Representing the activity coefficient obtained by the a3 th underwater robot, and K representing the number of the underwater robots in the fish pond; obtaining a field state list ZLst in rcrd days to form a field state matrix AMtx [ ZLst ] a4 ]，a4∈[1，rcrd]Wherein rcrd is the observation period, the unit is the natural day, and the value of rcrd is [30, 6 ]0]An inner value, a4 represents the serial number of the date; when the value of a4 is 1, ZLst a4 Representing the scene list of the current day; srcrd is used as a short-term value, and the Srcrd is [0.25 Xrcrd ═]In the formula (2)]The symbol is an integer function; calculating the short-term field average floating index SMFI of the current day:
wherein a5 is an accumulation variable; γ is 2/(1+ Srcrd);
represented by ZLst a5 The arithmetic mean of the individual elements in (b), ZLst a5 Represents the a5 th element in the field state matrix AMtx, i.e. the a5 th field state list; using Lrcrd as long-term value, Lrcrd ═ 0.5 Xrcrd](ii) a Calculating the long-term field average floating index LMFI of the current day,
wherein a6 is an accumulation variable; γ ═ 2/(1+ Lrcrd);
represented by ZLst a6 The arithmetic mean of the individual elements in (1); ZLst a6 Represents the a6 th element in the field state matrix AMtx, i.e. the a6 th field state list; calculating a floating interval DBSL of the current day through the long-term field average floating index LMFI and the short-term field average floating index SMFI, wherein the DBSL is SMFI-LMFI; DBSL takes a value of 0 without the value of LMFI; trend index TRD was calculated by DBSL:
wherein γ is 2/(1+ Srcrd); TRD 'represents a trend index TRD obtained after the feed is fed to a fishery on the last natural day, and the values of TRD and TRD' are 0 when the LMFI value is not available; and (5) calculating to obtain the fish shoal abnormal rate FGWI ═ DBSL-TRD.
Preferably, in step S400, the method for calculating the abnormal rate by the activity coefficient is: calculating to obtain a fish shoal abnormal rate FGWI:
FGWI ═ min { LsPM }/ACIDX, min { LsPM } represents the minimum of LsPM.
The beneficial effects are as follows: by combining with continuous time sequence for analysis, the fish shoal activity or the pond running state has a time dimension, the current fish shoal state can be objectively compared, the characteristics of the change of the fish shoal activity or the health state along with the time can be extracted, and the credibility of fish shoal abnormality judgment is improved.
Further, in step S500, a method of identifying whether the behavior state of the fish school is normal or not according to the abnormality rate and outputting the same includes: acquiring all fish school abnormal rates FGWI of historical records, judging whether the fish school abnormal rate FGWI of the current day is an abnormal point or not by taking the FGWI as a coefficient of a normally distributed unary outlier detection method, if the fish school abnormal rate FGWI of the current day is the abnormal point, indicating that the fishes have abnormal behaviors, and sending an abnormal alarm to a client of a manager.
Preferably, when the fish school abnormal rate FGWI is greater than a preset threshold value, or when the fish school abnormal rate FGWI is greater than the fish school abnormal rate FGWI obtained after feeding the fishery on all the natural days of the last week, it indicates that the fish has abnormal behavior, and sends an abnormal alarm to the client of the manager.
An embodiment of the present invention provides an unmanned fishing ground fish school behavior recognition system based on an underwater robot, and as shown in fig. 2, is a structural diagram of the unmanned fishing ground fish school behavior recognition system based on the underwater robot, and the unmanned fishing ground fish school behavior recognition system based on the underwater robot of the embodiment includes: the system comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps in the embodiment of the unmanned fishing ground fish school behavior identification system based on the underwater robot.
The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in the units of the following system:
the sound wave detection unit is used for transmitting sound waves to the fish school by the underwater robot and acquiring echo signals of the sound waves;
the filtering processing unit is used for filtering the echo signal to obtain a first signal;
an activity metric unit for calculating an activity coefficient using a first signal calculation scheme;
an abnormality estimation unit for calculating an abnormality rate from the activity coefficient;
and the judging and processing unit is used for identifying whether the behavior state of the fish shoal is normal or not according to the abnormal rate and outputting the behavior state.
The unmanned fishing ground fish school behavior recognition system based on the underwater robot can operate in computing devices such as desktop computers, notebook computers, palm computers and cloud servers. The unmanned fishing ground fish school behavior identification system based on the underwater robot can be operated by a system comprising, but not limited to, a processor and a memory. Those skilled in the art will appreciate that the example is only an example of an unmanned fishing ground fish swarm behavior recognition system based on underwater robots, and does not constitute a limitation of an unmanned fishing ground fish swarm behavior recognition system based on underwater robots, and may include more or less components than a certain proportion, or some components in combination, or different components, for example, the unmanned fishing ground fish swarm behavior recognition system based on underwater robots may further include input and output devices, network access devices, buses, and the like.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the operation system of the unmanned fishing ground fish swarm behavior recognition system based on the underwater robot, and various interfaces and lines are used for connecting all parts of the operation system of the whole unmanned fishing ground fish swarm behavior recognition system based on the underwater robot.
The memory can be used for storing the computer programs and/or modules, and the processor realizes various functions of the unmanned fishery fish school behavior identification system based on the underwater robot by running or executing the computer programs and/or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Although the present invention has been described in considerable detail and with reference to certain illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiment, so as to effectively encompass the intended scope of the invention. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (8)
1. An unmanned fishing ground fish school behavior identification method based on an underwater robot is characterized by comprising the following steps:
s100, the underwater robot transmits sound waves to the fish school and acquires echo signals of the sound waves;
s200, filtering the echo signal to obtain a first signal;
s300, calculating an active coefficient by using a first signal calculation scheme;
s400, calculating an abnormal rate through the activity coefficient;
s500, identifying whether the behavior state of the fish shoal is normal or not according to the abnormal rate and outputting;
the method for calculating the active coefficient by using the first signal calculation scheme comprises the following steps: at t 0 Feeding the feed to the fishery at any moment, and feeding the feed by PMqf (t) 0 ) Represents t 0 The real-time frequency of the first signal obtained at the moment; setting a sequence as a frequency real-time sequence LsPM, and adding PMqf (t) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence LsPM; setting a measured threshold tGate;
starting to measure once every time TF to obtain a first signal, wherein the measurement is to transmit sound waves to a fish school and obtain the first signal according to echo signals of the sound waves;
from t 0 Acquiring each real-time frequency PMqf of the first signal T times from the moment (T2), and transmitting the PMqf (T) 0 ) Adding the frequency real-time sequence LsPM into a frequency real-time sequence, and then sequentially adding PMqf (T2) meeting a first condition into the frequency real-time sequence LsPM one by one, wherein T2 is from T 0 The tth measurement time from the start of the time;
the first condition is: PMqf (T2) ≧ 0.5 × (max { LsPM } -PMqf (T) 0 ) And t ≦ tGate; wherein max { LsPM } represents the maximum value in LsPM; t is a preset measurement frequency for obtaining the first signal; PMqf (T2) is from T 0 Measuring the real-time frequency of the acquired first signal from the moment t;
and acquiring a real-time sequence LsPM, and taking an element corresponding to the time when the values of the elements in the LsPM sequentially increase and then decrease for the first time as an active coefficient ACIDX.
2. The underwater robot-based unmanned fishing ground fish school behavior recognition method according to claim 1, wherein in step S100, the method of acquiring the echo signal of the sound wave is: putting an underwater robot in a fishing ground, wherein the underwater robot can move in water; the underwater robot is installed with the detecting head, the detecting head contains: transducer or sonar fish finder, receiving and transmitting control unit; the energy converter or the sonar fish finder is used for transmitting an acoustic pulse signal to a fish school in a fishing ground and receiving an echo signal to the receiving and transmitting control unit; the energy converter or the sonar fish finder can at least transmit an acoustic pulse signal to a water body in a fishing ground, the transceiving control unit is used for generating the acoustic pulse signal according to acoustic parameters, exciting the energy converter or the sonar fish finder by adopting the acoustic pulse signal to radiate the acoustic pulse signal to the water body in the fishing ground, and meanwhile, receiving echo signals of fish swarms in the water body in the fishing ground.
3. The underwater robot-based unmanned fishing ground fish school behavior recognition method according to claim 1, wherein in step S200, the method for filtering the echo signal to obtain the first signal comprises: acquiring echo signals once every time TF, recording the frequency of the acquired echo signals as real-time frequency Mqf or recording the Doppler frequency of the echo signals as real-time frequency Mqf, and enabling the underwater robot to work at the speed of [2, 24 ]]The real-time frequencies Mqf of all echo signals within an hour form a real-time frequency sequence LMqf, which is [ Mqf ] a1 ](ii) a Wherein a1 is the sequence number of real-time frequency in time sequence, a 1E [1, Pcs]Pcs represents [2, 24 ]]Total number of real-time frequencies Mqf obtained in an hour, Mqf a1 Is the a1 th real-time frequency in LMqf; calculating by using a real-time frequency sequence LMqf to obtain a valley-peak frequency ratio epsilon, wherein epsilon is max { LMqf }/min { LMqf };
wherein max { LMqf } represents the maximum value in the sequence LMqf, and min { LMqf } represents the minimum value in the sequence LMqf;
calculating the sensitivity SstIdx of the real-time frequency of the echo signal by using the sequence LMqf,
wherein a2 is an accumulation variable, EMqf represents the arithmetic mean value of each numerical value in the sequence LMqf, and epsilon represents the ratio of valley to peak frequencies;
calculating the arithmetic mean value PSI of the wave sensitivity SstIdx of the real-time frequency of all echo signals; an echo signal with a sensitivity SstIdx greater than PSI is screened as the first signal.
4. The underwater robot-based unmanned fishing ground fish school behavior recognition method according to claim 1, wherein in step S400, the method for calculating the abnormal rate by the activity coefficient is as follows: after feeding the feed into the fish pond, each underwater robot in the fish pond starts to try to obtain an activity coefficient; when all underwater robots obtain active coefficients, combining all underwater robots in the fish pond to construct a field state list ZLst, wherein the ZLst is [ ACIDX [ ] a3 ]，a3∈[1，K]Wherein a3 represents the serial number, ACIDX, of each underwater robot in the fish pond a3 Representing the activity coefficient obtained by the a3 th underwater robot, and K representing the number of the underwater robots in the fish pond; obtaining a field state list ZLst in rcrd days to form a field state matrix AMtx [ ZLst ] a4 ]，a4∈[1，rcrd]Where rcrd is the observation period and a4 represents the serial number of the date; ZLst a4 Representing a scene list of a4-1 day before the current day; srcrd is used as a short-term value, and the Srcrd is [0.25 Xrcrd ═]In the formula (2)]The symbol is an integer function;
calculating the short-term field average floating index SMFI of the current day:
wherein a5 is an accumulation variable; γ is 2/(1+ Srcrd);
represented by ZLst a5 The arithmetic mean of the individual elements in (b), ZLst a5 Represents the a5 th element in the field state matrix AMtx, i.e. the a5 th field state list; using Lrcrd as long-term value, Lrcrd ═ 0.5 Xrcrd](ii) a Calculating the long-term field average floating index LMFI of the current day,
wherein a6 is an accumulation variable; γ ═ 2/(1+ Lrcrd);
represented by ZLst a6 The arithmetic mean of the individual elements in (1); ZLst a6 Represents the a6 th element in the field state matrix AMtx, i.e. the a6 th field state list; calculating a floating interval DBSL of the current day through the long-term field average floating index LMFI and the short-term field average floating index SMFI, wherein the DBSL is SMFI-LMFI; DBSL takes a value of 0 without the value of LMFI; trend index TRD was calculated by DBSL:
TRD' represents the trend index TRD obtained after the feed is fed to the fishery on the last natural day; and (5) calculating to obtain the fish shoal abnormal rate FGWI ═ DBSL-TRD.
5. The method for identifying the behavior of the fish school in the unmanned fishing ground based on the underwater robot as claimed in claim 1, wherein the method for identifying whether the behavior state of the fish school is normal or not and outputting the behavior state of the fish school according to the abnormality rate in step S500 is: acquiring all fish swarm abnormal rates FGWI of the historical records, judging whether the fish swarm abnormal rates FGWI of the current day are abnormal points or not by taking FGWI as a coefficient of a normally distributed unary outlier detection method, if the fish swarm abnormal rates FGWI of the current day are abnormal points, indicating that abnormal behaviors exist in the fish, and sending an abnormal alarm to a client of a manager.
6. The underwater robot-based unmanned fishing ground fish school behavior recognition method according to claim 2, wherein the transducer has a conical opening angle in a range of 5-10 °.
7. The underwater robot-based unmanned fishing ground fish school behavior recognition method according to claim 2, wherein the sonar fish finder has a sonar frequency of 200KHz to 500KHz and a probe detection angle of 45 degrees, a detection range of 0.6-100 m and an accuracy of 0.1-0.3 m.
8. The utility model provides an unmanned fishing ground fish school behavior recognition system based on underwater robot which characterized in that, an unmanned fishing ground fish school behavior recognition system based on underwater robot includes: the system comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the method for identifying the fish school behavior of the unmanned fishing ground based on the underwater robot according to any one of claims 1 to 6, and the system for identifying the fish school behavior of the unmanned fishing ground based on the underwater robot runs in computing equipment of a desktop computer, a notebook computer, a palm computer and a cloud data center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210531440.4A CN114637014B (en) | 2022-05-17 | 2022-05-17 | Underwater robot-based unmanned fishing ground fish school behavior recognition system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210531440.4A CN114637014B (en) | 2022-05-17 | 2022-05-17 | Underwater robot-based unmanned fishing ground fish school behavior recognition system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114637014A CN114637014A (en) | 2022-06-17 |
| CN114637014B true CN114637014B (en) | 2022-08-09 |
Family
ID=81952895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210531440.4A Active CN114637014B (en) | 2022-05-17 | 2022-05-17 | Underwater robot-based unmanned fishing ground fish school behavior recognition system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114637014B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116193681B (en) * | 2023-04-24 | 2023-06-27 | 聊城市敏锐信息科技有限公司 | Lighting adjusting circuit device of electric lighting source and fish tank lighting system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103616693B (en) * | 2013-11-22 | 2015-09-02 | 江苏科技大学 | Visit fishing sonar and sonar echo signal processing method |
| CN105589073A (en) * | 2014-10-24 | 2016-05-18 | 中国科学院声学研究所 | Walsh-conversion-based fish active acoustic identification method |
| CN105785968A (en) * | 2014-12-25 | 2016-07-20 | 中国科学院声学研究所 | Marine ranch acoustic monitoring system and monitoring method |
| JP6492278B2 (en) * | 2015-03-19 | 2019-04-03 | 本多電子株式会社 | Fish finder |
| CN111783745A (en) * | 2020-08-06 | 2020-10-16 | 珠海南方利洋水产科技有限公司 | Fish health judgment method and device applied to pond culture and computer-readable storage medium |
| CN113327263B (en) * | 2021-05-18 | 2024-03-01 | 浙江工业大学 | Image vision-based fish school activity monitoring method |
| CN113537106B (en) * | 2021-07-23 | 2023-06-02 | 仲恺农业工程学院 | Fish ingestion behavior identification method based on YOLOv5 |
| CN113805162B (en) * | 2021-11-18 | 2022-04-26 | 杭州雅格纳科技有限公司 | Fish growth detection method and device based on ultrasonic phased array |
| CN113822233B (en) * | 2021-11-22 | 2022-03-22 | 青岛杰瑞工控技术有限公司 | Method and system for tracking abnormal fishes cultured in deep sea |
| CN114463843A (en) * | 2022-01-11 | 2022-05-10 | 浙江工业大学 | Multi-feature fusion fish abnormal behavior detection method based on deep learning |
| CN114463675B (en) * | 2022-01-11 | 2023-04-28 | 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 |
| CN114488166A (en) * | 2022-01-22 | 2022-05-13 | 重庆文高科技有限公司 | FPGA fish finding sonar method and system for underwater robot |
-
2022
- 2022-05-17 CN CN202210531440.4A patent/CN114637014B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114637014A (en) | 2022-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10856520B1 (en) | Methods for generating consensus feeding appetite forecasts | |
| US20220000079A1 (en) | Acoustics augmentation for monocular depth estimation | |
| DeRuiter et al. | A multivariate mixed hidden Markov model for blue whale behaviour and responses to sound exposure | |
| KR101814288B1 (en) | A Feeding System for Fish Farm using 3Dimension analyzer | |
| US7447116B2 (en) | Dynamic underwater position tracking of small objects | |
| CN114637014B (en) | Underwater robot-based unmanned fishing ground fish school behavior recognition system and method | |
| US11950576B2 (en) | Multi-factorial biomass estimation | |
| JP7001060B2 (en) | Information processing equipment, information processing methods and information processing systems | |
| Fässler et al. | Acoustic data collected on pelagic fishing vessels throughout an annual cycle: operational framework, interpretation of observations, and future perspectives | |
| JPWO2019198701A1 (en) | Analyzers, analytical methods, programs and aquatic organism monitoring systems | |
| CN114998776A (en) | Acoustic and image combined fish target identification and statistics device and method | |
| Hassan et al. | Fish as a source of acoustic signal measurement in an aquaculture tank: acoustic sensor based time frequency analysis. | |
| WO2020195467A1 (en) | Target measurement device and target measurement method | |
| RU2697430C1 (en) | Hydroacoustic system for fish monitoring in cages of industrial aquaculture enterprises | |
| KR102100664B1 (en) | System for measuring cultured fish and method thereof | |
| CN116609786A (en) | Fish counting method and device | |
| WO2023194319A1 (en) | Methods and systems for determining a spatial feed insert distribution for feeding crustaceans | |
| Kristmundsson et al. | Fish monitoring in aquaculture using multibeam echosounders and machine learning. | |
| EP4057805B1 (en) | A method for monitoring fish using a biomass monitoring system | |
| EP4008179A1 (en) | Method and system for determining biomass of aquatic animals | |
| Pedersen | Hydroacoustic measurement of swimming speed of North Sea saithe in the field | |
| Rowell et al. | Advanced acoustic technologies for the monitoring and management of sustainable fisheries: a practice manual | |
| Mason et al. | Integration of technologies for understanding the functional relationship between reef habitat and fish growth and production | |
| WO2022123732A1 (en) | Processing device, information collection device, information processing method, and program | |
| Barua et al. | Comparison of catch and survey data for assessing northern shrimp (Pandalus borealis) from Arnarfjordur (NW-Iceland) using a stock production model |
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 |