WO2022080407A1 - 魚数算出方法、魚数算出プログラム、及び、魚数算出装置 - Google Patents
魚数算出方法、魚数算出プログラム、及び、魚数算出装置 Download PDFInfo
- Publication number
- WO2022080407A1 WO2022080407A1 PCT/JP2021/037884 JP2021037884W WO2022080407A1 WO 2022080407 A1 WO2022080407 A1 WO 2022080407A1 JP 2021037884 W JP2021037884 W JP 2021037884W WO 2022080407 A1 WO2022080407 A1 WO 2022080407A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- fish
- echo image
- space
- underwater space
- underwater
- Prior art date
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 492
- 238000004364 calculation method Methods 0.000 title claims description 68
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 52
- 238000004088 simulation Methods 0.000 claims description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 39
- 230000033001 locomotion Effects 0.000 claims description 8
- 239000012530 fluid Substances 0.000 claims description 2
- 235000019688 fish Nutrition 0.000 description 451
- 230000006399 behavior Effects 0.000 description 38
- 238000003860 storage Methods 0.000 description 25
- 238000010586 diagram Methods 0.000 description 20
- 238000004891 communication Methods 0.000 description 18
- 210000004712 air sac Anatomy 0.000 description 14
- 238000009826 distribution Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 12
- 238000010276 construction Methods 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 6
- 230000010365 information processing Effects 0.000 description 6
- 230000001141 propulsive effect Effects 0.000 description 5
- 239000013535 sea water Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 241000238557 Decapoda Species 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 244000144992 flock Species 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000029264 phototaxis Effects 0.000 description 3
- 238000002834 transmittance Methods 0.000 description 3
- 241001282110 Pagrus major Species 0.000 description 2
- 241001504592 Trachurus trachurus Species 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 239000013505 freshwater Substances 0.000 description 2
- 230000002940 repellent Effects 0.000 description 2
- 239000005871 repellent Substances 0.000 description 2
- 230000009182 swimming Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 206010001488 Aggression Diseases 0.000 description 1
- 241000972773 Aulopiformes Species 0.000 description 1
- 239000002028 Biomass Substances 0.000 description 1
- 241000238366 Cephalopoda Species 0.000 description 1
- 241000238424 Crustacea Species 0.000 description 1
- 241000237852 Mollusca Species 0.000 description 1
- 241000238413 Octopus Species 0.000 description 1
- 241001600434 Plectroglyphidodon lacrymatus Species 0.000 description 1
- 241000269978 Pleuronectiformes Species 0.000 description 1
- 241000277331 Salmonidae Species 0.000 description 1
- 241000276699 Seriola Species 0.000 description 1
- 230000016571 aggressive behavior Effects 0.000 description 1
- 208000012761 aggressive behavior Diseases 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 235000012489 doughnuts Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005401 electroluminescence Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 208000010824 fish disease Diseases 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002319 phototactic effect Effects 0.000 description 1
- 230000027870 phototropism Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 235000019515 salmon Nutrition 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000028838 turning behavior Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/90—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination
- A01K61/95—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination specially adapted for fish
-
- 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
- G01S15/89—Sonar systems specially adapted for specific applications for mapping or imaging
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/15—Fishing
-
- 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
Definitions
- the present invention relates to a fish number calculation method, a fish number calculation program, and a fish number calculation device.
- the amount of fish is estimated by a fish finder using underwater ultrasonic waves and a fish finder using the principle of the fish finder, and the fish stock is investigated. Although it is possible to determine the distribution of fish schools, the depth of fish schools, and the density of fish schools with a fish finder, it was difficult to count the number of fish.
- An object of the present invention is to easily grasp the number of fish existing in an underwater space such as a cage.
- the disclosed technique employs the following means in order to solve the above problems. That is, the first aspect is The computer Each includes a learning echo image based on the sound wave reflected and received by the fish when the sound wave is transmitted into the underwater space where the fish is present, and the number of fish existing in the underwater space in the echo image.
- an estimator that estimates the number of fish existing in the underwater space
- the echo image generated based on the sound waves transmitted into the underwater space and reflected and received by an unknown number of fish present in the underwater space is used in the underwater.
- To calculate the number of the unknown fish existing in the space It is a method of calculating the number of fish including.
- the aspect of disclosure may be realized by executing the program by the information processing device. That is, the configuration of the disclosure can be specified as a program for causing the information processing apparatus to execute the process executed by each means in the above-described embodiment, or as a computer-readable recording medium on which the program is recorded. Further, the configuration of the disclosure may be specified by a method in which the information processing apparatus executes the processing executed by each of the above-mentioned means. The configuration of the disclosure may be specified as a system including an information processing apparatus that performs processing executed by each of the above-mentioned means.
- the number of fish existing in an underwater space such as a cage can be easily grasped.
- FIG. 1 is a diagram showing a configuration example of the system of the embodiment.
- FIG. 2 is a diagram showing an example of a functional block of a fish number calculation device.
- FIG. 3 is a diagram showing an example of an operation flow of a fish behavior simulation process and a simulated echo image generation process by a fish number calculation device.
- FIG. 4 is a diagram showing an example of a cage used in a numerical simulation by a fish number calculation device.
- FIG. 5 is a diagram showing an example of an operation flow of construction of an estimator for estimating the number of fish by the fish number calculation device.
- FIG. 6 is a diagram showing an example of an operation flow of calculating the number of fish by the fish number calculation device.
- FIG. 7 is a diagram showing an example of a fish finder and a fish.
- FIG. 8 is a diagram showing an example of xz coordinates fixed to a fish and uv coordinates.
- FIG. 9 is a diagram showing an example of xy coordinates fixed to the fish.
- FIG. 10 is a diagram showing an example of reflection and transmission of sound waves in a fish body and an example of reflection and transmission in a swim bladder.
- FIG. 11 is a diagram showing an example of a simulated echo image generated.
- a learning echo image and a learning echo image based on the sound wave reflected and received by the fish when the computer transmits a sound wave into the underwater space where the fish is present respectively.
- an estimator to estimate the number of fish present in the underwater space by machine learning using multiple learning data sets as teacher data, including the number of fish present in the underwater space in the water, and to construct an underwater estimator.
- the echo image generated based on the sound waves transmitted to the space and reflected and received by an unknown number of fish present in the underwater space, using an estimator, said to be present in the underwater space. Includes calculating the number of unknown fish.
- the underwater space includes, for example, the space below the water surface such as rivers, lakes, ponds, and the sea, or the inner space such as a cage that divides the water using a net or the bottom of the water.
- the water includes freshwater, brackish water, and seawater in which the fish to be counted can live.
- Underwater spaces include not only those that utilize the natural environment, but also the spaces inside structures that artificially store water, such as pools and water tanks. In the underwater space, there are multiple fish to be counted.
- the fish may be freshwater fish or saltwater fish, and the types of fish are, for example, fish to be cultivated (yellowtail, red sea bream, red sea bream, amberjack, horse mackerel, horse mackerel, trough, flatfish, salmon and trout, etc.). Not limited.
- fish and shellfish aquatic organisms such as shrimp can also be counted.
- the boundary between the inside and the outside is separated by a net, the surface of the water, the bottom of the water, etc., so that fish cannot move between the inside and the outside of the cage.
- various shapes such as a rectangular parallelepiped, a cube, and a columnar shape can be adopted.
- the underwater space it is conceivable to define the underwater space by a rectangular parallelepiped in length, width, and height.
- the space in the water is a rectangular parallelepiped space having a length X in the horizontal direction, a length Y in the vertical direction, and a length Z in the depth direction.
- the horizontal direction, the vertical direction, and the depth direction may be orthogonal to each other.
- the water surface may be defined as the upper surface of the underwater space.
- the above is an example, and the three-dimensional shape of the space in the water is not limited to a rectangular parallelepiped.
- the echo image is an image generated based on the sound pressure of a sound wave transmitted from the water surface of an underwater space and received as a reflected wave reflected by a fish or the like in a fish finder or the like.
- the fish number calculation method it is possible to construct an estimator that estimates the number of fish existing in the underwater space by using the learning data set including the learning echo image and the number of fish as teacher data.
- the number of fish existing in the underwater space is calculated based on the constructed estimator and the echo image obtained by the fish finder installed in the underwater space such as a cage. be able to.
- the number of fish existing in the underwater space can be calculated more accurately by constructing an estimator using more teacher data.
- the configuration of the embodiment is an example.
- the configuration of the invention is not limited to the specific configuration of the embodiment. In carrying out the invention, a specific configuration according to the embodiment may be appropriately adopted.
- FIG. 1 is a diagram showing a configuration example of the system of the present embodiment.
- the system of the present embodiment includes a fish number calculation device 100 and a fish finder 200.
- the fish number calculation device 100 is communicably connected to the fish finder 200 directly or via a network such as the Internet.
- the fish number calculation device 100 transmits sound waves within a predetermined range (underwater space such as a cage) in which a plurality of fish exist, and acquires an echo image based on the sound waves reflected and received by the plurality of fish.
- Sound waves include ultrasonic waves.
- the fish number calculation device 100 constructs an estimator that estimates the number of fish from the echo image by machine learning using the pair of the echo image and the number of fish existing in the predetermined range as teacher data.
- the fish number calculation device 100 calculates the number of fish existing in the cage or the like from an echo image obtained from a fish finder or the like installed in the vicinity of the actual cage or the like by using the constructed estimator. do.
- the fish number calculation device 100 simulates the behavior of fish existing within a predetermined range and an echo image obtained from a fish finder or the like, and generates a learning echo image for machine learning.
- the fish number calculation device 100 includes a dedicated or general-purpose computer (information processing device) such as a workstation (WS, WorkStation), a PC (Personal Computer), a smartphone, a tablet terminal, or an electronic device equipped with a computer. It is feasible to use.
- the fish number calculation device 100 can be realized by using a computer (server device) that provides a service through a network.
- the fish number calculation device 100 can be realized by a computer that executes parallelization by MPI (Message Passing Interface) in which CPUs or GPUs are parallelized on a large scale.
- MPI Message Passing Interface
- the fishfinder 200 transmits sound waves into the water and receives reflected waves reflected by an object such as a fish in the water. Further, the fishfinder 200 generates an echo image based on the sound pressure (echo sound pressure) of the sound wave received as the reflected wave.
- the horizontal axis is the time timing when the sound wave was transmitted
- the vertical axis is the distance from the fishfinder
- the sound pressure (echo sound pressure) of the sound wave received by the fishfinder is represented by the shade of color. It is an image.
- the fishfinder 200 is installed on the water surface (sea surface) of an underwater space such as a cage.
- the fish number calculation device 100 includes a processor 101, a memory 102, a storage device 103, an input device 104, an output device 105, and a communication control device 106. These are connected to each other by a bus.
- the memory 102 and the storage device 103 are non-temporary computer-readable recording media.
- the hardware configuration of the fish number calculation device 100 is not limited to the example shown in FIG. 1, and components may be omitted, replaced, or added as appropriate.
- the fish number calculation device 100 meets a predetermined purpose by having the processor 101 load the program stored in the recording medium into the work area of the memory 102 and execute the program, and each component or the like is controlled through the execution of the program. It is possible to realize the functions that have been achieved.
- the processor 101 is, for example, a CPU (Central Processing Unit) or the like.
- the processor 101 loads and executes the program stored in the memory 102 to execute the fish behavior simulation process 151, the echo image generation process 152, the estimator construction process 153, and the fish number estimation process 154. Further, the processor 101 acquires data or the like used in each process from another device such as the fish finder 200 via the storage device 103 or the communication control device 106.
- a CPU Central Processing Unit
- the memory 102 is composed of, for example, a RAM (RandomAccessMemory), a RAM, and a ROM (ReadOnlyMemory).
- the memory 102 is also called a main storage device.
- the storage device 103 is, for example, an EPROM (ErasableProgrammableROM), a hard disk drive (HDD, HardDiskDrive), or the like. Further, the storage device 103 can include a removable medium, that is, a portable recording medium.
- the removable media is, for example, a USB (Universal Serial Bus) memory or a disc recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc).
- the storage device 103 is also called a secondary storage device.
- the storage device 103 stores various programs, various data, and various tables used in the fish number calculation device 100 in a readable / writable recording medium.
- the storage device 103 stores an operating system (Operating System: OS), various application programs, various tables, and the like.
- OS Operating System
- the information stored in the storage device 103 may be stored in the memory 102. Further, the information stored in the memory 102 may be stored in the storage device 103.
- a program for executing fish behavior simulation processing, echo image generation processing, estimator construction processing, fish number estimation processing, etc. is installed in the storage device 103. Further, the storage device 103 stores various data related to fish, fish cages, etc. used in the numerical simulation, such as echo images acquired by the fish finder, calculation results calculated by each process, and the like.
- the operating system is software that mediates between software and hardware, manages memory space, manages files, manages processes and tasks, and so on.
- the operating system includes a communication interface.
- the communication interface is a program for exchanging data with other external devices and the like connected via the communication control device 106.
- the external device and the like include, for example, another information processing device, an external storage device, and the like.
- the input device 104 includes a keyboard, a pointing device, a wireless remote controller, a touch panel, and the like. Further, the input device 104 can include a video or image input device such as a camera, or an audio input device such as a microphone.
- the output device 105 includes a display device such as an LCD (Liquid Crystal Display), an EL (Electroluminescence) panel, a CRT (Cathode Ray Tube) display, a PDP (Plasma Display Panel), and an output device such as a printer. Further, the output device 105 can include an audio output device such as a speaker.
- a display device such as an LCD (Liquid Crystal Display), an EL (Electroluminescence) panel, a CRT (Cathode Ray Tube) display, a PDP (Plasma Display Panel), and an output device such as a printer.
- the output device 105 can include an audio output device such as a speaker.
- the communication control device 106 is connected to another device and controls communication between the fish number calculation device 100 and the other device.
- the communication control device 106 is, for example, a LAN (Local Area Network) interface board, a wireless communication circuit for wireless communication, and a communication circuit for wired communication.
- the LAN interface board and the wireless communication circuit are connected to a network such as the Internet.
- the step of writing a program includes not only the processes performed in chronological order in the described order but also the processes executed in parallel or individually even if they are not necessarily processed in chronological order. Some of the steps in writing the program may be omitted.
- the series of processes executed by the processor 101 can be executed by hardware or software.
- Hardware components are hardware circuits, such as FPGAs (Field Programmable Gate Arrays), application-specific integrated circuits (ASICs), gate arrays, logic gate combinations, analog circuits, and the like. ..
- FIG. 2 is a diagram showing an example of a functional block of the fish number calculation device 100.
- the processor 101 of the fish number calculation device 100 executes the fish behavior simulation process 151, the echo image generation process 152, the estimator construction process 153, and the fish number estimation process 154 by executing the program stored in the memory 102. Further, the processor 101 acquires data or the like used in each process from another device such as the fish finder 200 via the storage device 103 or the communication control device 106.
- the fish behavior simulation process 151 is a process for performing a numerical simulation to calculate the position (fish behavior) of each fish existing in an underwater space such as a cage based on an equation showing the behavior of the fish (equation of motion of the fish), the size of the cage, and the like. be.
- the fish behavior simulation process 151 calculates the time change of the position of each fish by the numerical simulation for calculating the position of the fish.
- the echo image generation process 152 is a simulated echo image (simulated) based on the echo sound pressure of the sound wave reflected from the fish existing in the predetermined range when the sound wave is transmitted from the fish finder on the sea surface to the predetermined range. It is a process to generate an echo image).
- the sound wave reflected by each fish is calculated based on the position (fish behavior) of each fish calculated by the fish behavior simulation process 151.
- the sound waves reflected by each fish are added together, and the echo sound pressure is calculated for each distance from the fish finder.
- a simulated echo image is generated based on the calculated echo sound pressure for each distance.
- various simulated echo images are generated by changing the number of fish, the size of the fish, and the like.
- the estimator construction process 153 determines the data of the simulated echo image (learning echo image) generated by the echo image generation process 152 and the number of fish (and the size of the fish) used in generating the simulated echo image. This is a process of constructing an estimator that estimates the number of fish (and the size of fish) from an echo image using a data set (learning data set) including data as teacher data.
- the fish number estimation process 154 uses the estimator constructed by the estimator construction process 153 based on the echo image generated by the actual fishfinder, and the number of fish (and the size of the fish) for the echo image. ) Is the process of calculating.
- FIG. 3 is a diagram showing an example of an operation flow of a fish behavior simulation process and a simulated echo image generation process executed by a computer processor 101 operating as a fish number calculation device 100.
- the fish number calculation device 100 assumes a fish existing in a predetermined range in water (a space in water such as a cage), and performs a numerical simulation (numerical calculation) of the behavior (time change of position) of the fish. Further, the fish number calculation device 100 calculates the sound pressure (echo sound pressure) of the sound wave transmitted by the fish finder to the fish finder and reflected by the fish and received by the fish finder based on the position of each fish. ..
- the fish number calculation device 100 adds the echo sound pressures for each distance from the fishfinder to the fish, and calculates the echo sound pressure for each distance. Further, the fish number calculation device 100 calculates the echo sound pressure for each distance by shifting the time. The fish number calculation device 100 generates a simulated echo image based on the calculated echo sound pressure. Further, the fish number calculation device 100 changes the number of fish existing in a predetermined range and the size of the fish, performs a numerical simulation of the behavior of the fish, and generates simulated echo images having different numbers of fish and the size of the fish.
- the simulated echo image is an image showing the distribution of fish in a predetermined range.
- the cage 300 used in the numerical simulation is installed on the surface of the sea such as the ocean.
- the cage 300 has vertical and horizontal directions on the sea surface, and a net or the like is installed at the boundary between the inside and the outside of the cage to prevent fish from going back and forth between the inside and the outside of the cage 300.
- the cage 300 is, for example, a rectangular parallelepiped having a width of 10 m, a length of 10 m, and a depth of 8 m.
- the top of the cage 300 is above the sea surface (water surface).
- the shape of the cage 300 is not limited to a rectangular parallelepiped, and may be a cylinder or the like.
- the fishfinder that transmits and receives sound waves underwater is installed at a predetermined position on the sea surface in the cage 300. It is assumed that the fish finder is installed at a position 1.5 m in the horizontal direction and 1.5 m in the vertical direction from the center of the cage, for example.
- the fishfinder may be installed in the center of the sea surface in the cage.
- the fish shown in FIG. 4 exists at a position (underwater) where the distance from the fishfinder is r or more and less than r + ⁇ r.
- the fish number calculation device 100 numerically simulates the behavior of each fish in the cage 300 in the fish behavior simulation process.
- the fish number calculation device 100 calculates the sound pressure (echo sound pressure) of the reflected wave reflected by the fish inside the fish cage 300 from the sound wave (transmitted wave) transmitted from the fish finder. It is assumed that the fish cage 300 or the like used in the numerical simulation is the same as the fish cage or the like for which the number of fish is calculated by the fish number calculation device 100.
- the processor 101 of the fish number calculation device 100 acquires the data used in the numerical simulation.
- the processor 101 acquires data such as the size of a predetermined range (fish cage) to be calculated, the number of fish, the size of each fish, the initial position of each fish, the equation of fish behavior, and various parameters stored in the storage device 103. ..
- the processor 101 may acquire these data from other devices via the communication control device 106, the network, and the like.
- the processor 101 numerically simulates the behavior of the fish (time change in position) based on the data acquired in S101.
- the processor 101 calculates the behavior of the fish by the equation showing the behavior of the fish for each fish assumed to exist in the cage to be numerically simulated.
- the processor 101 stores the calculated behavior of each fish (time change of the position of each fish) in the storage unit 107.
- the behavior of the fish is represented, for example, as the position of the fish at each time for each fish. The calculation of fish behavior (fish behavior simulation processing) will be described in detail later.
- the processor 101 calculates the echo sound pressure based on the position of each fish whose position was calculated in S102.
- Processor 101 assumes a fishfinder installed on the surface of the sea in a cage.
- the processor 101 calculates the sound pressure of the sound wave transmitted from the fish finder, reflected by each fish, and received by the fish finder based on the position of each fish whose position is calculated in S102.
- the processor 101 aggregates the sound pressures of sound waves from each fish and calculates the sound pressure (echo sound pressure) for each distance from the fishfinder. Further, the processor 101 depends on the time from the transmission of the sound wave to the reception of the sound wave in the distance from the fish finder.
- the processor 101 In S104, the processor 101 generates a simulated echo image based on the echo sound pressure for each distance from the fishfinder calculated in S103.
- the simulated echo image is an image that simulates the echo image generated by the fishfinder.
- the processor 101 changes the time and calculates the sound pressure for each distance from the fish finder based on the position of the fish at different times.
- the processor 101 generates a simulated echo image based on the sound pressure at each time and every distance.
- the processor 101 stores the generated simulated echo image in the storage unit 107 together with the data of the number of fish and the size of the fish used in generating the simulated echo image.
- the fish number calculation device 100 variously changes the number of fish, the size of the fish (distribution of the size of the fish), and the like, and generates simulated echo images in various cases.
- the size (size) of fish can be classified into a plurality of types, and the number of fish for each class can be obtained (for example, size A or less is X tails, A or more and less than B is Y tails, and B or more is Z tails).
- the size of the fish is, for example, the body length of the fish, the thickness of the fish, and the weight of the fish.
- the size of the fish is an example of the shape of the fish. In this way, the estimator is learning to be able to estimate the number of fish existing in the underwater space for each class.
- the fish number calculation device 100 defines the equation of motion of the fish for each kind of fish according to the characteristics of the fish, and simulates and simulates the fish behavior. You may generate an echo image or the like.
- the behavioral equations of each organism are defined according to the characteristics of each organism, and the behavior of each organism. Simulation, generation of simulated echo images, etc. may be performed.
- FIG. 5 is a diagram showing an example of an operation flow of construction of an estimator for estimating the number of fish by the fish number calculation device.
- the fish number calculation device 100 uses a learning data set including a simulated echo image generated based on a numerical simulation and a number of fish as teacher data, and uses a deep learning model of machine learning to obtain the number of fish from the echo image. Build an estimator to estimate.
- the number of fish and the size of the fish may be used instead of the number of fish.
- the processor 101 of the fish number calculation device 100 acquires the simulated echo image obtained by the operation flow of FIG. 3 and the number of fish associated with the simulated echo image from the storage device 103.
- the processor 101 uses a deep learning model of machine learning, and uses a learning data set including the simulated echo image acquired in S201 and the number of fish as teacher data, and the number of fish from the simulated echo image (echo image). Build an estimator to estimate. Any model may be used as the deep learning model used here.
- the processor 101 stores an estimator for estimating the number of constructed fish in the storage device 103.
- a method using a learning space such as deep learning by a neural network, multiple regression analysis, Look Up Table, etc. can be used. Methods other than machine learning may be used in the construction of the estimator.
- the simulated echo image as the teacher data, more teacher data can be prepared as compared with using the actual echo image. By using a lot of teacher data, it is possible to build a higher performance estimator.
- the simulated echo image and echo image used here are examples of learning echo images.
- the fish number calculation device 100 constructed an estimator using the simulated echo image generated by the numerical simulation, but instead of the simulated echo image or by adding it to the simulated echo image, the actual An echo image generated by the fishfinder 200 installed on the water surface of the cage may be used. At this time, it is assumed that the number of fish in the cage and the size of the fish are known. By using the actual echo image, a more realistic estimator can be constructed.
- FIG. 6 is a diagram showing an example of an operation flow of calculating the number of fish by the fish number calculation device.
- the fish number calculation device 100 acquires an actual echo image generated by the fishfinder 200 installed in the cage as shown in FIG. 4, and calculates the number of fish by using the constructed estimator.
- the size of the cage used in the numerical simulation when constructing the estimator, the installation position of the fish finder, the type of fish, etc. are shown here as the actual size of the cage for which the number of fish is calculated, and the fish finder. It is assumed that it is the same as the installation position, the type of fish, etc.
- the operation flow of FIG. 6 also uses the number of fish instead of the number of fish.
- the number and size of fish aretribution of fish size).
- the processor 101 of the fish number calculation device 100 acquires the echo image generated by the fish finder 200 installed in the cage via the communication control device 106.
- the processor 101 stores the acquired echo image in the storage device 103.
- the echo image generated by the fishfinder 200 may be stored in the storage device 103 in advance.
- the processor 101 is equipped with a fishfinder 200 that generates an echo image based on the echo image acquired in S301 using the estimator that estimates the number of fish constructed in the operation flow of FIG. Calculate the number of fish contained in the fish cage.
- the processor 101 associates the estimated number of fish with the echo image and stores it in the storage device 103.
- the fish number calculation device 100 can calculate the number of fish existing in the cage in which the fishfinder 200 is installed by using the echo image generated by the fishfinder 200.
- the fish behavior simulation process of S102 in FIG. 3 will be described in detail.
- the behavior (time change of position) of the fish existing in the underwater space (fish cage) is numerically simulated.
- a plurality of fish exist in an underwater space such as a cage installed in the ocean or the like.
- a net or the like is installed at the boundary between the inside and the outside of the cage to prevent fish from going back and forth between the inside and the outside of the cage.
- the size of the cage is 10 m in width, 10 m in length, and 8 m in depth.
- the horizontal direction is the x direction
- the vertical direction is the y direction
- the depth direction (the direction from the seabed to the sea surface) is the z direction.
- the x-direction, y-direction, and z-direction are orthogonal to each other.
- fish form a flock and orbit in a cage in a truncated cone shape with a larger radius toward the bottom.
- each fish is regarded as a self-oscillating particle, and the motion of the fish is described as follows by the second-order differential equation (equation of motion of the fish).
- x is the fish position vector (x, y, z)
- v is the fish velocity vector (vx, vy, vz)
- F is the force vector sum
- ⁇ is noise.
- the force vector F includes attractive force, alignment force, repulsive force, propulsive force, water resistance, light repellent, pressure from a wall (boundary), and the like.
- the upper limit of the field of view and the angle at which the direction can be changed per second is set for each fish.
- ⁇ Suction force, repulsion force> The fish in the flock try to get closer to each other.
- the suction force expresses this as the force acting between two individuals (two fish).
- the suction forces Fiji and tract received by the i-th fish from the j-th fish are inversely proportional to the distance rig between the two individuals.
- the suction force Fiji and tract are expressed as follows.
- xi is the position vector of the i-th fish
- c1 and c2 are constants.
- the suction force Fi and tract received by the i-th fish are expressed as follows.
- Ni and a are the number of fish in the perceptual area of the i-th fish.
- Si and a are spheres having a radius of Ra.
- the repulsive force expresses this as the force acting between two individuals.
- the repulsive force Fiji repulsive received by the i-th fish from the j-th fish is expressed as follows.
- c3 and c4 are constants.
- the average of Fiji and repulsive received from the fish of Ni and r included in the perceptual region Si and r represented by the sphere of radius Rr is the repulsive force Fi and repulsive received by the i-th fish. Become.
- the repulsive force Fi and repulsive are expressed as follows.
- ⁇ Alignment power> Fish in a flock try to reduce energy consumption by riding the flow of water created by the surrounding fish, or head to a place with a common purpose such as food. At this time, the fish tries to match its speed with other fish around it.
- the alignment force expresses this as the force acting between two individuals.
- the alignment force Fiji, orientation received by the i-th fish from the j-th fish can be expressed as follows using the constant J. Assuming that the perceptual region of the i-th fish is Si, o, the alignment force Fi, orientation received by the i-th fish is expressed as follows.
- Ni and o are the number of fish in the perceptual region defined by the sphere of radius Ro.
- the alignment force Fi orientation is expressed as follows.
- the constant J is, for example, 0.95.
- the alignment force is often determined according to the speed of the surrounding fish, but the fish sense the surrounding flow velocity on the lateral line. Therefore, the average velocity ⁇ v> i may be given at the flow velocity in the cage by adjusting the velocity to the in-situ flow velocity rather than the swimming velocity of other fish in the perceptual region.
- the flow velocity in the cage can be estimated from the current meter installed at the corner of the cage. However, it is difficult to measure the flow velocity everywhere in the fish cage.
- the flow velocity distribution is given as in the following Case01-Case03. The flow velocity given here is a value close to the measurement result of the current meter.
- the swimming power of the fish itself is called the propulsive force
- the force received from the water against the movement is called the resistance force.
- the propulsive force and resistance force Fi, spp received by the i-th fish are expressed as follows using the constants k and ⁇ .
- the first term on the right side represents the propulsive force.
- Propulsive force is the force that further accelerates in the direction of travel.
- the second term on the right side represents resistance.
- the resistance force is in the form of receiving a decelerating force opposite to the direction of travel.
- the constant k is 0.05 and the constant ⁇ is 1.0.
- this pseudo wall (the first fish from the wall) has a little more range of motion than the actual wall, it is considered that the force toward the center received by the second fish is weaker than the force received by the first fish. .. Similarly, it is considered that the third and subsequent fish from the wall are also subjected to a force toward the center that gradually weakens. Therefore, it is assumed that the closer to the wall (the farther from the center), the stronger the force toward the center of the cage.
- the force Fwall from the wall is applied like the following Case11-Case14. Further, it is assumed that the force Fwall from the wall does not change in the depth direction. The force Fwall from the wall does not have to be applied.
- the fish receives the resultant force from the entire wall surface of the force toward the center from the wall, which is attenuated in proportion to the distance rw from the wall.
- Fboundary is a force from the wall toward the center, and the absolute value is 0.43.
- the viewing angle is assumed to be, for example, 180 °, 270 °, and 360 °.
- the viewing angle is less than 360 °, the fish outside the field of view are not recognized, and the suction force, the repulsive force, and the alignment force do not work on these fish.
- the angle is given at, for example, 20 °, 30 °, 40 °, 50 °, and 60 °. For example, even if a fish tries to change direction at a steep angle due to the influence of another individual, it actually changes direction only up to the size of the changeable angle.
- noise is given, for example, to follow four normal distributions with a mean of 0 and a standard deviation of 0.0, 0.02, 0.1, 1.0. When the average is 0 and the standard deviation is 0.0, there is no noise.
- a repulsive force is applied by the following method of Case22a-Case22c.
- Case22a Since the actual body length distribution in the cage is a normal distribution, c3 is also given so as to follow the normal distribution.
- the behavior (position) of each fish existing within the predetermined range (border) is determined.
- the number of fish is, for example, 100 to 10,000 fish.
- each fish may be given a different size (body length). Since it is known that the actual body length distribution of fish in the cage is normally distributed, the body length of the fish may be given so that the distribution of the body length of each fish is normally distributed.
- the fishfinder 200 has a transmitter for transmitting sound waves (including ultrasonic waves) and a receiver for receiving sound waves.
- the fishfinder 200 transmits a burst wave or a PCW (Pulsed Continuous Wave) from the transmitter toward the water. Due to the directivity of the transmitter, the sensitivity varies depending on the direction from the transmitter.
- FIG. 7 is a diagram showing an example of a fish finder and a fish.
- the fishfinder 200 is installed on the surface of the water, and fish are moving in the water.
- the sound pressure sound pressure of the wave: the magnitude of the sound wave (transmitted sound) to be transmitted
- D ( ⁇ ) is called a directivity function. D ( ⁇ ) becomes the largest when, for example, ⁇ is 0.
- the sound wave transmitted from the transmitter undergoes attenuation (diffusion attenuation or divergence attenuation) due to the spread of the sound wave and attenuation (absorption attenuation) due to absorption by seawater in the process of propagating the sound wave to the position of the fish.
- the incident sound pressure of the sound wave incident on the fish (sound pressure at a position 1 m away from the fish) is Pi
- the sound pressure of the sound wave reflected by the fish is Pr. ..
- the intensity of reflection in a fish is expressed by the target strength (Ts), which is the ratio of the intensity of the reflected wave to the intensity of the incident wave (the ratio of the square in the sound pressure).
- the reflected wave is affected by the same attenuation and directivity as the incident wave, and is received as an echo sound pressure P by the receiver of the fishfinder.
- the time from when a sound wave is transmitted from a fishfinder to when it is reflected by a fish and received by the fishfinder depends on (almost proportionally) the distance from the fishfinder to the fish.
- the echo sound pressure P when the sound wave transmitted from the transmitter is reflected by the fish existing at the position r in the ⁇ direction when viewed from the transmitter and received by the receiver is calculated as follows. Will be done.
- the echo sound pressure P depends on the target strength Ts and the distance r to the fish.
- ⁇ is an absorption coefficient and is expressed as follows based on Thorp's equation.
- f is the frequency of the sound wave transmitted from the transmitter.
- Ts in the equation of echo sound pressure P is a linear quantity.
- a swim bladder scattering model a model in which Clay's Kirchhoff, sound line approximation, gas, and cylinder model is modified into a short cylinder synthesis model and the sound line theory is incorporated is used. Also, as a fish scattering model, a similar short cylinder synthetic model for fluids is used. The results of these two models are coherently added (scattering amplitude is added by a complex number) to obtain an overall model. The swim bladder and the fish body are approximated by the synthesis of short cylinders, and the scattered waves from each short cylinder are added.
- the xyz coordinate fixed to the fish the u coordinate parallel to the wavefront of the sound wave incident on x at an angle ⁇ , and the v coordinate orthogonal to the u coordinate are introduced.
- FIGS. 8 to 9 are diagrams showing an example of xyz coordinates fixed to the fish and uv coordinates.
- the x-coordinate is taken in the direction of the body axis of the fish, that is, in the direction from the head to the rear of the fish.
- the y coordinate is taken from the left side to the right side of the fish.
- the direction of the y coordinate is the direction from the front surface to the back surface of the paper.
- the z coordinate is taken from the lower side to the upper side of the fish.
- the direction of the z coordinate is the direction from the back surface to the front surface of the paper.
- the fish are divided at equal intervals ( ⁇ x) along the x-coordinate from the head side of the fish, the x-coordinate on the head side of the j-th part of the fish body is x (j), and the j-th part of the fish body.
- the upper z-coordinate on the head side is zU (j)
- the lower z-coordinate is zL (j).
- the body width on the head side of the j-th part of the fish body is defined as w (j).
- the v-coordinates corresponding to zU (j) and zL (j) are vU (j) and vL (j), respectively.
- the fish body and the swim bladder are approximated by a plurality of cylinders (short cylinders) having a height of ⁇ x arranged so that the central axes are parallel to each other in the x direction.
- FIG. 10 is a diagram showing an example of reflection and transmission of sound waves in a fish body and an example of reflection and transmission in a swim bladder.
- Rbs indicates the reflectance between the fish body (b) and the swim bladder (s)
- Rwb indicates the reflectance between the ambient water (w) and the fish body
- Rbw indicates the reflectance between the fish body and the ambient water.
- Twb indicates the transmittance between the ambient water and the fish body
- Tbw indicates the transmittance between the fish body and the ambient water.
- TwbTbw 1-Rwb2 between the reflectance and the transmittance.
- the scattering amplitude Ass of the swim bladder is obtained as follows by adding the transmission and reflection of sound waves in the swim bladder to the short cylinder synthetic model based on the Kirchhoff approximation of the finite long cylinder.
- Ns is the number of divisions of the swim bladder
- kb is the radius of the swim bladder
- cw is the speed of sound of seawater
- cb is the speed of sound of a fish body
- cs is the speed of sound of a swim bladder.
- ⁇ w indicates the density of seawater
- ⁇ b indicates the density of the fish body
- ⁇ s indicates the density of the swim bladder.
- Aj and ⁇ sj are amplitude and phase correction terms when ka is small, respectively.
- the scattering amplitude Asb by the fish body is also obtained as follows by the same method as that of the swim bladder.
- Nb is the number of divisions of the fish body.
- the simulated echo image is based on the sound pressure (echo sound pressure) of the sound wave received as the reflected wave of the sound wave transmitted into the fish cage in the fish finder installed at the predetermined position (sea surface) of the fish cage where multiple fish exist.
- This is a simulated image of the echo image generated by the above.
- the sound wave transmitted from the fishfinder is, for example, a continuous wave of a 100 kHz sound wave modulated with a pulse of 1 ms.
- the frequency of sound waves transmitted from the fishfinder is, for example, 800 times / minute.
- the fishfinder is installed at a predetermined position on the sea surface of the cage when generating the simulated echo image.
- the position of the fish finder is, for example, 1.5 m in the horizontal direction and 1.5 m in the vertical direction from the center of the cage (10 m in width, 10 m in length and 8 m in depth) as shown in FIG.
- the echo sound pressure of each fish is calculated based on the distance between the fishfinder and the fish and the target strength.
- the echo sound pressure at r + ⁇ r is calculated from the distance r from the fishfinder.
- the echo sound pressure from all the fish in the cage can be calculated by moving r from 0 to the distance of the boundary of the cage every ⁇ r.
- the position of each fish at each time is calculated by numerical simulation of the position of the fish.
- the target strength of each fish is also calculated by numerical simulation.
- the echo sound pressure is calculated at predetermined time intervals by simulating that sound waves are transmitted from the fish finder at predetermined time intervals.
- the echo image generated by the fishfinder has the time when the sound wave was transmitted on the horizontal axis and the distance (depth) from the fishfinder on the vertical axis, and the sound pressure (echo sound) of the sound wave received by the fishfinder. It is an image showing pressure) by the shade of color and the like.
- the distance from the fishfinder corresponds to the time from when the sound wave is transmitted to when it is received.
- the simulated echo image is generated as an image in which the echo sound pressure at each time and distance is represented by a shade of color or the like.
- the fishfinder has a stronger directivity in the vertical direction.
- the installation position of the fish finder is preferably a position where more fish are present directly under the fish finder (vertical direction) so that strong echo sound pressure from more fish can be received. This is because when the fishfinder is installed at a position where there are few fish directly underneath, there is little difference in the echo image between the case where the number of fish in the cage is large and the case where the number of fish is small.
- the fishfinder may be installed at a position on the water surface that is calculated by numerical simulation of fish behavior in the cage to have a high probability of having fish directly underneath (the number of fish is large).
- FIG. 11 is a diagram showing an example of a simulated echo image generated.
- the horizontal axis represents time and the vertical axis represents the distance from the fishfinder.
- the time on the horizontal axis corresponds to the time when the fishfinder transmitted the sound wave.
- the shade of color indicates the echo sound pressure at each time and distance. The closer to the bottom of the cage, the higher the echo sound pressure (more fish).
- the intensity of the echo sound pressure changes with the movement of the fish.
- Numerical simulation of fish behavior and generation of simulated echo images may be performed by a device other than the fish number calculation device 100.
- the processor 101 of the fish number calculation device 100 acquires the simulated echo image from the other device that generated the simulated echo image by numerical simulation via the communication control device 106, the network, and the like.
- the fish number calculation device 100 exists in a predetermined range based on the number of fish existing in a predetermined range (underwater space such as a cage), the size of the fish, the size of the predetermined range, the force acting on the fish, the flow velocity of seawater, and the like.
- the behavior of the fish is calculated by numerical simulation.
- the fish number calculation device 100 generates a simulated echo image simulating the echo image generated by the fish finder based on the behavior of the fish in a predetermined range calculated by the numerical simulation.
- the fish number calculation device 100 calculates the behavior of fish by changing the number of fish and the size of the fish, and generates simulated echo images of various numbers of fish and the size of the fish.
- the fish number calculation device 100 constructs an estimator that estimates the number of fish and the size of fish from the echo image by using the set of the simulated echo image and the number of fish and the size of fish as teacher data. According to the fish number calculation device 100, the behavior of fish is calculated by numerical simulation for various numbers of fish, and more simulated echo images are generated, so that only the echo images generated by the actual fish finder are used. It is possible to create more teacher data for the echo image than in the case of doing so. According to the fish number calculation device 100, by constructing an estimator using more teacher data, the number of fish and the size of fish in the cage where an unknown number of fish exist (the number of fish in each class of fish size). Etc.) can be calculated more accurately.
- Computer readable recording medium A program that realizes any of the above functions in a computer or other machine or device (hereinafter referred to as a computer or the like) can be recorded on a recording medium that can be read by a computer or the like. Then, by having a computer or the like read and execute the program of this recording medium, the function can be provided.
- a recording medium that can be read by a computer or the like is a recording medium that can store information such as data and programs by electrical, magnetic, optical, mechanical, or chemical action and can be read from a computer or the like.
- elements constituting a computer such as a CPU and a memory may be provided, and the CPU may execute a program.
- recording media those that can be removed from a computer or the like include, for example, flexible disks, magneto-optical disks, CD-ROMs, CD-R / Ws, DVDs, DATs, 8 mm tapes, memory cards, and the like.
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Environmental Sciences (AREA)
- Zoology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Marine Sciences & Fisheries (AREA)
- Acoustics & Sound (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Business, Economics & Management (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
Description
即ち、第1の態様は、
コンピュータが、
魚が存在する水中の空間に音波を送信した場合に前記魚により反射されて受信される音波に基づく学習用エコー画像と前記エコー画像における前記水中の空間に存在する魚の数とを夫々が含む、複数の学習用データセットを教師データとして利用した機械学習によって、前記水中の空間に存在する魚の数を推定する推定器を構築することと、
前記水中の空間に音波を送信し、前記水中の空間に存在する未知の数の魚により反射されて受信される音波に基づき生成されたエコー画像に関して、前記推定器を使用して、前記水中の空間内に存在する前記未知数の魚の数を算出することと、
を含む魚数算出方法である。
実施形態に係る魚数算出方法は、コンピュータが、夫々が、魚が存在する水中の空間に音波を送信した場合に魚により反射されて受信される音波に基づく学習用エコー画像と学習用エコー画像における水中の空間に存在する魚の数とを含む、複数の学習用データセットを教師データとして利用した機械学習によって、水中の空間に存在する魚の数を推定する推定器を構築することと、水中の空間に音波を送信し、水中の空間に存在する未知の数の魚により反射されて受信される音波に基づき生成されたエコー画像に関して、推定器を使用して、水中の空間内に存在する前記未知数の魚の数を算出することを含む。
図1は、本実施形態のシステムの構成例を示す図である。本実施形態のシステムは、魚数算出装置100と、魚群探知機200とを含む。魚数算出装置100は、魚群探知機200と、直接、または、インターネットなどのネットワーク等を介して、通信可能に接続される。
〈魚行動模擬処理、模擬エコー画像生成処理〉
図3は、魚数算出装置100として動作するコンピュータのプロセッサ101によって実行される魚行動模擬処理、及び模擬エコー画像生成処理の動作フローの例を示す図である。魚数算出装置100は、水中の所定範囲(生簀などの水中の空間)に存在する魚を想定して、魚の行動(位置の時間変化)の数値シミュレーション(数値計算)を行う。さらに、魚数算出装置100は、各魚の位置に基づいて、生簀に魚群探知機から音波を送信し魚で反射されて魚群探知機で受信される音波の音圧(エコー音圧)を算出する。魚数算出装置100は、魚群探知機から魚までの距離毎にエコー音圧を足し合わせて、当該距離毎のエコー音圧を算出する。また、魚数算出装置100は、時刻をずらして、距離毎のエコー音圧を算出する。魚数算出装置100は、算出したエコー音圧に基づいて、模擬エコー画像を生成する。さらに、魚数算出装置100は、所定範囲に存在する魚の数や魚の大きさを変更して、魚の行動の数値シミュレーションを行い、魚の数や魚の大きさの異なる模擬エコー画像を生成する。模擬エコー画像は所定範囲における魚の分布を示す画像である。
図5は、魚数算出装置による魚の数を推定する推定器の構築の動作フローの例を示す図である。魚数算出装置100は、数値シミュレーションに基づいて生成された模擬エコー画像と、魚の数とを含む学習用データセットを教師データとして、機械学習の深層学習モデルを使用して、エコー画像から魚の数を推定する推定器を構築する。ここで、魚の数の代わりに、魚の数及び魚の大きさ(魚の大きさの分布)としてもよい。
図6は、魚数算出装置による魚の数の算出の動作フローの例を示す図である。魚数算出装置100は、図4のような生簀に設置された魚群探知機200で生成された実際のエコー画像を取得して、魚の数の算出を、構築した推定器を使用して行う。推定器を構築した際に数値シミュレーションで使用した生簀の大きさ、魚群探知機の設置位置、魚の種類等は、ここで、魚の数を算出する対象の実際の生簀の大きさ、魚群探知機の設置位置、魚の種類等と同様であるとする。ここで、図3、図5の動作フローで、魚の数の代わりに、魚の数及び魚の大きさ(魚の大きさの分布)とした場合、図6の動作フローでも、魚の数の代わりに、魚の数及び魚の大きさ(魚の大きさの分布)とする。
ここでは、図3のS102の魚行動模擬処理について詳しく説明する。魚行動模擬処理では、水中の空間(生簀)に存在する魚の行動(位置の時間変化)を数値シミュレーションする。ここでは、海洋等に設置される生簀等の水中の空間内に複数の魚が存在するとする。生簀の内側と外側との境界には網等が設置され、魚が生簀の内側と外側とを行き来できないようにされているとする。ここで、図4のように、生簀の大きさは、横10m、縦10m、深さ8mとする。ここでは、横方向をx方向、縦方向をy方向、深さ方向(海底から海面の方向)をz方向とする。x方向、y方向、z方向は、互いに直交する。魚は、例えば、群れをなして、生簀の中を、底へ向かって半径の大きくなる円錐台状に周遊する。
ここで、xは魚の位置ベクトル(x,y,z)、vは魚の速度ベクトル(vx,vy,vz)、Fは力のベクトル和、ηはノイズである。力のベクトルFは、吸引力、整列力、反発力、推進力、水の抵抗、光の忌避、壁(境界)からの圧力などを含む。また、それぞれの魚には視野と1秒間に方向転換可能な角度の上限が設定される。
群れにおける魚は互いに近づこうとする。これを2個体(2つの魚)間に働く力として表したのが吸引力である。i番目の魚がj番目の魚から受ける吸引力Fij,attractは2個体間の距離rijに反比例する。吸引力Fij,attractは、次のように表される。
ここで、xiはi番目の魚の位置ベクトル、c1、c2は、定数である。
ここで、c3、c4は、定数である。
群れにおける魚は、周りの魚の作る水の流れに乗ってエネルギーの消費を抑えようとしたり、餌などの共通の目的のある場所に向かったりする。このとき、魚はまわりの他の魚とその速度を合わせようとする。これを2個体間に働く力として表したものが整列力である。一般には、整列力の式として、実際に周りの魚の速度を認識するという表式が使われる。i番目の魚がj番目の魚から受ける整列力Fij,orientationは、定数Jを用いて次のように表せる。
i番目の魚の知覚領域をSi,oとすると、i番目の魚が受ける整列力Fi,orientationは、次のように表される。
ここで、Ni,oは半径Roの球で定義される知覚領域内にいる魚の数である。
(Case01)深度と生簀内の場所によらず0.6m/sの一様な流速を与える。
(Case02)深度方向には変化しないが角速度がω=0.15で一定となるよう中心に向かって流速を減速させる。
(Case03)魚が高密度で存在する、中心の空いた円錐台の部分にのみ流速を与える流速はCase1と同様に0.6m/sとする。
魚自身が持つ遊泳力を推進力、その運動に対して水から受ける力を抵抗力と呼ぶ。i番目の魚が受ける推進力及び抵抗力Fi,sppは、定数k、βを使って、次のように表される。
右辺の第1項は、推進力を表す。推進力は、進んでいる方向に対してさらに加速させる力である。右辺の第2項は、抵抗力を表す。抵抗力は、進んでいる方向とは逆の減速させる力を受ける形になっている。例えば、定数kは0.05、定数βは1.0である。
複数の魚を旋回させた状態からシミュレーションを行うとより長時間旋回行動を継続できることが知られている。そこで、複数の魚を、生簀の底面から、0.5mから3.5mまでの範囲にドーナツ状に配置し、角速度0.1で旋回させた状態からシミュレーションを開始する。
実際の生簀の魚の観測では、魚は生簀の下方に集中する。また、多くの魚で光源から遠ざかろうとする趨光性(Phototropism)が見られることが知られている。そこで、魚に働く力に下向きの力Fphotoを与えることで趨光性を表現する。基本的には深度(深さ)zが大きくなるほど(海面に近づくほど)、鉛直下向きの力Fphotoが大きくなる。Fphotoは、例えば、次のいずれかのように表される。ここで、生簀の底面でz=0とする。
1番目の式及び2番目の式は、光が深度に対して指数関数的に減衰することを反映している。2番目の式は、1番目の式より上層での値が大きい。3番目の式は、ある程度の深度(明度)になれば趨光性がなくなることを仮定し、底面から2mまでの範囲で0となるように調整されている。魚の位置の計算において、力Fphotoは、与えられなくてもよい。
魚は、趨光性の条件により底面に集まろうとするが、底面に近づきすぎると減速すると考えられる。そこで、底面からの距離に応じて、魚の速度を減速させるようにしてもよい。また、実際に魚の位置が底面を超えた場合は、例えば、底面から対照となる位置に移動させる。
生簀内は高密度なので、最も壁際の魚には近接個体から壁に押しつける力が常に働いているが、最も壁際の魚は壁に衝突しないために踏みとどまっている。この状態は、壁から生簀の中心に向かう力を受けているとも言える。次に壁から2番目の位置にいる魚を考えると、この魚も壁の方に動こうとした場合、この魚と壁の間に位置する壁から1番目の魚がいるために、壁と逆に中心に向かう力によって踏みとどまらざるを得ない。言い換えれば、2番目の魚も擬似的な壁から中心に向かう力を受けていることになる。ただしこの擬似的な壁(壁から1番目の魚)は実際の壁よりは多少可動域があるので、2番目の魚が受ける中心に向かう力は1番目の魚が受ける力より弱いと考えられる。同様に、壁から3番目以降の魚も徐々に弱まる中心向きの力を受けていると考えられる。そこで、壁に近いほど(中心から遠いほど)強く生簀の中心に向かう力が働くとする。ここでは、例えば、次のCase11-Case14のように壁からの力Fwallを与える。また、壁からの力Fwallは深度方向には変化しないとする。壁からの力Fwallは、与えられなくてもよい。
魚は自分の後方を見られないと考えられることから、視野角が、例えば、180°、270°、360°であるとする。視野角が360°未満である場合、視野外の魚は認識でないので、これらの魚に対し吸引力、反発力、整列力は働かないとする。
ノイズは、例えば、平均が0、標準偏差が0.0、0.02、0.1、1.0となる4通りの正規分布に従うように与えられる。平均が0、標準偏差が0.0である場合は、ノイズがない場合である。
一部の魚では、体サイズに影響を受けた種内順位関係が発達し、摂餌場所を巡って同種に攻撃行動を示すことが知られている。養殖場では給餌時に大型個体ほど早く浮上し摂餌する行動が見られることから、明確な種内順位が存在するとは言わないまでも、体サイズが大きいほど有利な場所を占めやすいのではないかと考えられる。そこで、まず、次のCase21-22で、種内順位を考慮する。
(Case22)順位が低い個体は高い個体から強い反発力を受け、高い個体は低い個体から弱い反発力を受ける。
Case21、22において、順位は体長の大きい順に振るものとする。反発力の大きさは、反発力に関する定数c3を調整して表現する。さらに、Case21の場合、体長差が小さければ順位差による反発力の違いは発生しない可能性があると考え、ある程度順位が離れている場合のみ反発力に差が生じるとしてもよい。また、Case22の場合、次のCase22a-Case22cの方法で、反発力を与える。
(Case22a)実際の生簀内の体長分布は正規分布になっていることから、同様にc3も正規分布に従うように与える。
(Case22b)魚を体長別に5つのグループに分け、それぞれのグループにc3=0.1、0.2、0.3、0.4、0.5となる反発力を与える。
(Case22c)自分の順位から500位より上の個体からはc3=0.3、500位より下の個体からはc3=0.05、その他の個体からはc3=0.2となる反発力を受ける。
〈エコー音圧の算出〉
ここでは、図3の動作フローのS103の魚群探知機で受信されるエコー音圧の算出について説明する。魚群探知機200は、音波(超音波を含む)を送信する送波器と、音波を受信する受波器とを有する。魚群探知機200は、送波器からバースト波またはPCW(Pulsed Continuous Wave)を、水中に向けて送波する。送波器の指向性のため、送波器からの方向により感度が異なる。
この式では、エコー音圧Pは、ターゲットストレングスTsと魚までの距離rとに依存する。ここで、αは、吸収係数であり、Thorpの式に基づいて、次のように表される。
ここで、fは、送波器から送信される音波の周波数である。エコー音圧Pの式におけるTsは線形量である。
ここでは、ターゲットレングスTsの算出について説明する。ここでは、魚のTsを算出するために、魚の鰾による散乱(鰾散乱モデル)と、魚の体(魚体)による散乱(魚体散乱モデル)とを考慮する。
ここで、Nsは鰾の分割数、kbは鰾の半径、cwは海水の音速、cbは魚体の音速、csは鰾の音速を示す。また、ρwは海水の密度、ρbは魚体の密度、ρsは鰾の密度を示す。また、Ajとψsjは、それぞれ、kaが小さいときの振幅と位相の補正項である。
ここでは、図3の動作フローのS104の模擬エコー画像の生成について説明する。模擬エコー画像は、複数の魚が存在する生簀の所定位置(海面)に設置した魚群探知機において、生簀内に送信した音波の反射波として受信される音波の音圧(エコー音圧)に基づいて生成されるエコー画像を、模擬した画像である。魚群探知機から送信される音波は、例えば、100kHzの音波の連続波(Continuous Wave)を1msのパルスで変調したものである。魚群探知機から送信される音波の発射頻度は、例えば、800回/分である。
魚の行動の数値シミュレーションや模擬エコー画像の生成は、魚数算出装置100以外の他の装置で行われてもよい。このとき、魚数算出装置100のプロセッサ101は、数値シミュレーションによって模擬エコー画像を生成した当該他の装置から、通信制御装置106、ネットワーク等を介して、模擬エコー画像を取得する。
魚数算出装置100は、所定範囲(生簀などの水中の空間)に存在する魚の数、魚の大きさ、所定範囲の大きさ、魚に働く力、海水の流速等に基づいて、所定範囲に存在する魚の行動(位置の時間変化)を数値シミュレーションにより算出する。また、魚数算出装置100は、数値シミュレーションにより算出した所定範囲の魚の行動に基づいて、魚群探知機が生成するエコー画像を模擬した模擬エコー画像を生成する。魚数算出装置100は、魚の数や魚の大きさを変更して魚の行動を算出し、様々な魚の数や魚の大きさについての模擬エコー画像を生成する。魚数算出装置100は、模擬エコー画像と魚の数及び魚の大きさとの組を教師データとして、エコー画像から魚の数及び魚の大きさを推定する推定器を構築する。魚数算出装置100によれば、様々な魚の数等について魚の行動を数値シミュレーションにより算出し、より多くの模擬エコー画像を生成することで、実際の魚群探知機で生成されたエコー画像のみを使用する場合に比べて、エコー画像をより多くの教師データを作成することができる。魚数算出装置100によれば、より多くの教師データを使用して推定器を構築することで、未知数の魚が存在する生簀における魚の数及び魚の大きさ(魚の大きさのクラス毎の魚の数など)を、より正確に算出することができる。
コンピュータその他の機械、装置(以下、コンピュータ等)に上記いずれかの機能を実現させるプログラムをコンピュータ等が読み取り可能な記録媒体に記録することができる。そして、コンピュータ等に、この記録媒体のプログラムを読み込ませて実行させることにより、その機能を提供させることができる。
101 プロセッサ
102 メモリ
103 記憶装置
104 入力装置
105 出力装置
106 通信制御装置
200 魚群探知機
Claims (6)
- コンピュータが、
魚が存在する水中の空間に音波を送信した場合に前記魚により反射されて受信される音波に基づく学習用エコー画像と前記学習用エコー画像における前記水中の空間に存在する魚の数とを夫々が含む、複数の学習用データセットを教師データとして利用した機械学習によって、前記水中の空間に存在する魚の数を推定する推定器を構築することと、
前記水中の空間に音波を送信し、前記水中の空間に存在する未知数の魚により反射されて受信される音波に基づき生成されたエコー画像に関して、前記推定器を使用して、前記水中の空間内に存在する前記未知数の魚の数を算出することと、
を含む魚数算出方法。 - 前記学習用エコー画像は、前記水中の空間、前記水中の空間内に存在する魚の夫々の位置及び形状、並びに、前記水中の空間内に音波を送信した場合に魚により反射されて受信される音波を模擬した数値シミュレーションの結果を用いて生成された模擬的なエコー画像である、
請求項1に記載の魚数算出方法。 - コンピュータが、
前記数値シミュレーションにおいて、前記水中の空間内に存在する前記魚について、少なくとも、魚の大きさと、魚に働く力と、魚の視野角と、前記水中の空間の大きさと、前記水中の空間内での流体の流速とをパラメータとして使用して、それぞれの魚の運動方程式により、前記水中の空間における前記魚の位置を算出すること
を含む請求項2に記載の魚数算出方法。 - 前記水中の空間に存在する魚は、2以上の魚の大きさのクラスにクラス分けされており、
前記推定器は、前記学習用データセットを用いた機械学習により、前記水中の空間に存在する魚の、前記クラス毎の数を推定可能に学習しており、
コンピュータが、前記推定器を使用して、前記エコー画像に関する、前記水中の空間に存在する魚の、前記クラス毎の魚の数を算出する
請求項1乃至3のいずれか1項に記載の魚数算出方法。 - コンピュータが、
魚が存在する水中の空間に音波を送信した場合に前記魚により反射されて受信される音波に基づく学習用エコー画像と前記学習用エコー画像における前記水中の空間に存在する魚の数とを夫々が含む、複数の学習用データセットを教師データとして利用した機械学習によって、前記水中の空間に存在する魚の数を推定する推定器を構築することと、
前記水中の空間に音波を送信し、前記水中の空間に存在する未知の数の魚により反射されて受信される音波に基づき生成されたエコー画像に関して、前記推定器を使用して、前記水中の空間内に存在する前記未知数の魚の数を算出することと、
を実行するための魚数算出プログラム。 - 魚が存在する水中の空間に音波を送信した場合に前記魚により反射されて受信される音波に基づく学習用エコー画像と前記学習用エコー画像における前記水中の空間に存在する魚の数とを夫々が含む、複数の学習用データセットを教師データとして利用した機械学習によって、前記水中の空間に存在する魚の数を推定する推定器を構築し、
前記水中の空間に音波を送信し、前記水中の空間に存在する未知の数の魚により反射されて受信される音波に基づき生成されたエコー画像に関して、前記推定器を使用して、前記水中の空間内に存在する前記未知数の魚の数を算出するプロセッサ
を備える魚数算出装置。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/031,222 US20230389530A1 (en) | 2020-10-14 | 2021-10-13 | Fish Count Calculation Method, Fish Count Calculation Program, and Fish Count Calculation Device |
JP2022557041A JP7287734B2 (ja) | 2020-10-14 | 2021-10-13 | 魚数算出方法、魚数算出プログラム、及び、魚数算出装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020173549 | 2020-10-14 | ||
JP2020-173549 | 2020-10-14 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022080407A1 true WO2022080407A1 (ja) | 2022-04-21 |
Family
ID=81209154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/037884 WO2022080407A1 (ja) | 2020-10-14 | 2021-10-13 | 魚数算出方法、魚数算出プログラム、及び、魚数算出装置 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20230389530A1 (ja) |
JP (1) | JP7287734B2 (ja) |
WO (1) | WO2022080407A1 (ja) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20240037917A1 (en) * | 2022-07-28 | 2024-02-01 | Softbank Corp. | Information processing method, non-transitory computer-readable storage medium, and information processing device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11296650A (ja) * | 1998-04-08 | 1999-10-29 | Nec Corp | 生魚計数装置 |
JP2009213473A (ja) * | 2008-02-29 | 2009-09-24 | Pukyong National Univ Industry-Univ Cooperation Foundation | 漁撈シミュレーション方法と、漁撈シミュレーションの遂行方法及び漁撈シミュレーター |
WO2014207991A1 (ja) * | 2013-06-28 | 2014-12-31 | 日本電気株式会社 | 教師データ生成装置、方法、プログラム、および群衆状態認識装置、方法、プログラム |
JP2019200175A (ja) * | 2018-05-18 | 2019-11-21 | 古野電気株式会社 | 魚種推定システム、魚種推定方法、及びプログラム |
JP2020085609A (ja) * | 2018-11-22 | 2020-06-04 | 株式会社アイエンター | 魚体サイズ算出装置 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016142708A (ja) | 2015-02-05 | 2016-08-08 | 株式会社豊田中央研究所 | 混相状態分布計測装置 |
JP6714279B2 (ja) | 2017-03-02 | 2020-06-24 | 日本電信電話株式会社 | 通信制御方法、通信システム及び事前学習補助装置 |
JP6849081B2 (ja) | 2017-09-04 | 2021-03-24 | 日本電気株式会社 | 情報処理装置、計数システム、計数方法およびコンピュータプログラム |
AU2019227780A1 (en) | 2018-03-02 | 2020-10-15 | Umitron Pte. Ltd. | Automatic feeding assistance device, automatic feeding assistance method, and recording medium |
JP7106384B2 (ja) | 2018-07-27 | 2022-07-26 | キヤノンメディカルシステムズ株式会社 | 医用画像処理装置及びx線コンピュータ断層撮影装置 |
-
2021
- 2021-10-13 JP JP2022557041A patent/JP7287734B2/ja active Active
- 2021-10-13 WO PCT/JP2021/037884 patent/WO2022080407A1/ja active Application Filing
- 2021-10-13 US US18/031,222 patent/US20230389530A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11296650A (ja) * | 1998-04-08 | 1999-10-29 | Nec Corp | 生魚計数装置 |
JP2009213473A (ja) * | 2008-02-29 | 2009-09-24 | Pukyong National Univ Industry-Univ Cooperation Foundation | 漁撈シミュレーション方法と、漁撈シミュレーションの遂行方法及び漁撈シミュレーター |
WO2014207991A1 (ja) * | 2013-06-28 | 2014-12-31 | 日本電気株式会社 | 教師データ生成装置、方法、プログラム、および群衆状態認識装置、方法、プログラム |
JP2019200175A (ja) * | 2018-05-18 | 2019-11-21 | 古野電気株式会社 | 魚種推定システム、魚種推定方法、及びプログラム |
JP2020085609A (ja) * | 2018-11-22 | 2020-06-04 | 株式会社アイエンター | 魚体サイズ算出装置 |
Non-Patent Citations (1)
Title |
---|
ONITSUKA YUKI: "Development of fish school behavior simulator in running water", RIVER MAINTENANCE FUND SUBSIDY PROJECT, GRADUATE SCHOOL OF ENGINEERING, KYUSHU INSTITUTE OF TECHNOLOGY, 25 March 2013 (2013-03-25), XP055921856, Retrieved from the Internet <URL:http://public-report.kasen.or.jp/241212010.pdf> * |
Also Published As
Publication number | Publication date |
---|---|
US20230389530A1 (en) | 2023-12-07 |
JP7287734B2 (ja) | 2023-06-06 |
JPWO2022080407A1 (ja) | 2022-04-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wahlberg et al. | Source parameters of echolocation clicks from wild bottlenose dolphins (Tursiops aduncus and Tursiops truncatus) | |
Liu et al. | Numerical analysis of the influence of reef arrangements on artificial reef flow fields | |
Miller et al. | First indications that northern bottlenose whales are sensitive to behavioural disturbance from anthropogenic noise | |
Michalec et al. | Zooplankton can actively adjust their motility to turbulent flow | |
KR100923668B1 (ko) | 어로 시뮬레이션 방법과 어로 시뮬레이션 수행방법 및 어로시뮬레이터 | |
WO2022170901A1 (zh) | 一种鱼类偏好栖息地的确定方法及终端设备 | |
Rieucau et al. | School level structural and dynamic adjustments to risk promote information transfer and collective evasion in herring | |
Rieucau et al. | Experimental evidence of threat-sensitive collective avoidance responses in a large wild-caught herring school | |
Mortensen et al. | Agent‐based models to investigate sound impact on marine animals: bridging the gap between effects on individual behaviour and population level consequences | |
Holmin et al. | Simulations of multi-beam sonar echos from schooling individual fish in a quiet environment | |
Mann et al. | Active and passive acoustics to locate and study fish | |
WO2022080407A1 (ja) | 魚数算出方法、魚数算出プログラム、及び、魚数算出装置 | |
Jaffe | To sea and to see: That is the answer | |
Cutter Jr et al. | Accounting for scattering directivity and fish behaviour in multibeam-echosounder surveys | |
Kristmundsson et al. | Fish monitoring in aquaculture using multibeam echosounders and machine learning. | |
Wei et al. | Possible limitations of dolphin echolocation: a simulation study based on a cross-modal matching experiment | |
Hassan et al. | Fish as a source of acoustic signal measurement in an aquaculture tank: Acoustic sensor based time frequency analysis | |
Mirabet et al. | Spatial structures in simulations of animal grouping | |
Sibley et al. | Sound sees more: a comparison of imaging sonars and optical cameras for estimating fish densities at artificial reefs | |
Lin et al. | Measuring fish length and assessing behaviour in a high‐biodiversity reach of the Upper Yangtze River using an acoustic camera and echo sounder | |
Banno et al. | Expanded vision for the spatial distribution of Atlantic salmon in sea cages | |
Handegard et al. | Evaluating the effect of seismic surveys on fish—the efficacy of different exposure metrics to explain disturbance | |
Weber et al. | Near resonance acoustic scattering from organized schools of juvenile Atlantic bluefin tuna (Thunnus thynnus) | |
Schecklman et al. | Comparison of methods used for computing the impact of sound on the marine environment | |
Andrews et al. | High resolution population density imaging of random scatterers with the matched filtered scattered field variance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21880145 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022557041 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18031222 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21880145 Country of ref document: EP Kind code of ref document: A1 |