CN117538880A - Method for judging invasion of trash fish in breeding area - Google Patents
Method for judging invasion of trash fish in breeding area Download PDFInfo
- Publication number
- CN117538880A CN117538880A CN202311555560.9A CN202311555560A CN117538880A CN 117538880 A CN117538880 A CN 117538880A CN 202311555560 A CN202311555560 A CN 202311555560A CN 117538880 A CN117538880 A CN 117538880A
- Authority
- CN
- China
- Prior art keywords
- fish
- slices
- image
- sonar
- slice
- 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.)
- Pending
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 202
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000009545 invasion Effects 0.000 title claims abstract description 24
- 238000009395 breeding Methods 0.000 title description 4
- 230000001488 breeding effect Effects 0.000 title description 4
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000012937 correction Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 13
- 238000009313 farming Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 2
- 239000012634 fragment Substances 0.000 abstract 1
- 238000004590 computer program Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 208000035473 Communicable disease Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000005541 medical transmission Effects 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G01S15/89—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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method for judging invasion of trash fish in a culture area, which comprises the steps of collecting echo information in the culture area by using a sonar detection device, constructing a fish swarm image according to the echo information, carrying out three-dimensional histogram correction and pixel value correction, carrying out gray-scale treatment, slicing the fish swarm image to obtain a plurality of fish slices, judging and repairing the fish slices to obtain new fish slices, and extracting trash fish information from the repaired fish slices by using a target recognition method. According to the invention, the sonar system is realized to efficiently acquire information from the culture area, the acquired sonar image is subjected to noise reduction and enhancement, then the sonar system is segmented, and unclear fragments in the sonar system are judged and repaired, so that the subsequent cultured fish identification model is effectively operated.
Description
Technical Field
The invention relates to the technical field of aquaculture, in particular to a method for judging invasion of trash fish in a culture area.
Background
Trash fish in the culture pond generally comes from fries, sometimes comes from natural water invasion, can cause the influence to the breed fingerling in ecology, and the influence includes: the trash fish competes with the cultivated fish species for resources such as food, living space, oxygen and the like, so that the cultivated fish is limited in growth and the development speed of the cultivated fish is slowed down; infectious disease transmission: trash fish can be potential carriers of pathogens, and if they are mixed with farmed fish, they increase the risk of transmission of infectious diseases in the farmed area, reducing harvest; feeding of the trash fish can lead to waste of feed; the original ecological balance is destroyed, threat is caused to other organisms, and the stability of the aquatic ecological system is affected. And therefore require periodic detection and control.
The common method includes the steps of using an image or video of fish in a culture area to identify a fish group, for example, patent document with publication number CN116452967A discloses that a target detection model is obtained by training a YOLOv7 network by using the collected video, and the swimming speed is calculated after the profile of the fish is extracted according to the target detection model; the patent document with publication number CN114943929a also discloses the use of YOLOv5 network to extract fish characteristics. However, accurate information is difficult to obtain only by means of an image recognition technology, the image acquisition is limited by the clarity of water, and when more fish are in a culture area, obvious overlapping or shielding can occur, so that information is lost during target tracking or background subtraction.
In recent years, an underwater sonar technology is introduced into the field of fish shoal detection, an acoustic lens system combination of the sonar can gather beams, clear image information is obtained in a dark and turbid water body environment, and the formed acoustic image has high accuracy for fish individual analysis and has great advantages compared with a detection method of a pure image. Along with the rapid development of information technology, the sonar data processing method is continuously improved, and a new thought is provided for underwater fish shoal detection in a complex environment.
Disclosure of Invention
The invention aims to provide a method for judging invasion of trash fish in a breeding area, which aims to solve one or more technical problems in the prior art and at least provides a beneficial selection or creation condition.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a method of determining intrusion of a fish in a farming area, the method comprising the steps of:
step 1, acquiring echo information by using a sonar detection device in an acquisition and cultivation area;
step 2, constructing a fish-shoal image according to the echo information, correcting a three-dimensional histogram and correcting pixel values, and performing graying treatment;
step 3, slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices;
and 4, extracting the trash fish information from the repaired fish slices by using a target recognition method.
Further, in step 1, the sub-step of acquiring echo information by using a sonar detection device in the acquisition culture area is as follows:
and configuring a sonar system, detecting the region by using a DIDSON (Dual-frequency Identification Sonar) sonar system, and acquiring echo information.
Preferably, the DIDSON sonar is fixed or towed by a towing vessel to expand the detection area.
In step 2, a fish-shoal image is constructed according to echo information, three-dimensional histogram correction and pixel value correction are performed, and the substeps of gray scale processing are as follows:
and carrying out coordinate transformation on data acquired by the sonar to obtain a sonar image, then carrying out sonar image enhancement by using a double-tree complex wavelet and a fuzzy theory, carrying out three-dimensional histogram correction on the fish-school image, and outputting the fish-school image.
The dual-tree complex wavelet and fuzzy theory comprises the following steps:
decomposing the sonar image into m multi-scales through a double-tree complex wavelet, wherein the value of m is dependent on the fineness of the finally decomposed subband image, and m is more than 3;
setting a reasonable threshold value for the wavelet coefficient of the complex high-frequency noise to reduce the processing range, and protecting the wavelet coefficient of the useful information from being changed;
blurring processing is carried out on the complex low-frequency sub-band, a contrast enhancement operator is applied to image enhancement processing, and then blurring inverse transformation is carried out on the processed image;
and reconstructing the denoised high-frequency sub-band with useful information and the blurred enhanced low-frequency sub-band information, and finally optimizing the reconstructed image.
Further, in step 3, slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices, wherein the sub-steps are as follows:
dividing the shoal image by using a set edge recognition algorithm to obtain a plurality of fish slices, wherein the fish slices are independent areas;
equally dividing the edges of the fish slices to be detected and the reference fish slices to obtain edge points;
respectively obtaining the distance between the geometric center point and each edge point of the fish slice to be measured as a distance set LA to be measured;
the distance between the geometric center point of the reference fish slice and each edge point is used as a reference distance set L0;
respectively calculating the difference values of corresponding elements in the distance set LA to be detected and the reference distance set L0 according to the sequence;
calculating the difference delta A between the area of the fish slice to be detected and the area of the reference fish slice;
calculating individual difference values:
,
wherein DIF is the individual difference value of the fish slices, a and b are preset contour weight and area weight parameters respectively, n is the number of edge aliquots, namely the number of edge points, LA i L0 is the i-th element in the distance set to be measured i For the i element in the reference distance set, mean (LA) is the arithmetic mean of all values in the distance set to be measured, mean (L0) is the arithmetic mean of all values in the reference distance set;
if the difference value of the elements corresponding to the distance set LA to be measured and the reference distance set L0 exceeds the first distance difference value and LA exists i And L0 i The difference of (2) is larger than 2×mean (L0) ×dif, and the fish slice is repaired;
the repairing method comprises the following steps:
overlapping geometric center points of the fish slices to be detected and the reference fish slices, adjusting the direction of one slice to enable the sum of distance differences of all edge points of the profiles of the 2 slices to be minimum, and obtaining an edge point set with the distance from the geometric center point to be detected being greater than a second threshold value in the profile of the fish slices to be detected, wherein the point set forms an arc line;
the calculation method of the second threshold is an arithmetic average value of the minimum value of the elements in the distance set LA to be measured and the minimum value of the elements in the reference distance set L0;
the arc line and the profile of the fish slice to be detected are respectively marked as a first intersection point and a second intersection point, the first intersection point and the second intersection point form a straight line segment, the straight line segment and the arc form a closed first space, and if the area of the first space is larger than A (0) x min (LA) i ,L0 i ) Edge correction is performed:
the distance between the fish slice to be measured and the first intersection point and the distance between the fish slice to be measured and the second intersection point are extreme values of an arithmetic series, the number of edge points in the arc line are the number of terms of the arithmetic series, the geometric center point of the fish slice to be measured is taken as an endpoint, elements in the arithmetic series are equal-division angles in the direction from the first intersection point to the second intersection point in radius to form line segments, one end of each obtained line segment is taken as an endpoint, the other end of each obtained line segment is taken as a new edge of the fish slice to be measured, and the number of the line segments is the number of terms of the arithmetic series; obtaining a new fish slice;
a (0) is the area of the reference fish slice, mim (LA) i ,L0 i ) For i, obtaining the LA in the value range i And L0 i When the difference between (a) and (b) is smallest, LA i And L0 i I.e. [1, n ]]；
All fish slices are judged in sequence and repaired when needed.
This step can exclude that 2 or more fish individuals receive coincident indistinguishable signals upon sonar detection. And when the outline is too far away from the reference fish slice, performing segmentation and discarding, and performing edge reconstruction on the segmented main body for the subsequent recognition model.
Because the fishes in the culture area begin to be cultured in the same period, the variety and the growth condition of the cultured fishes are unified, and the shapes and the sizes of the miscellaneous fishes are different, the simple contour recognition can be used for simplifying the recognition process and reducing the recognition resource cost.
Further, in step 4, the substeps of extracting the trash fish information from the repaired fish slices by applying the target recognition method are as follows:
inputting a fish slice image into a preset cultured fish identification model for target detection so as to obtain an identification result of the fish slice image; and obtaining the trash fish information according to the identification result.
Further, the step of obtaining a preset farmed fish identification model comprises the following steps:
and acquiring a sonar sample image of the cultured fish in the current growth period, and inputting the sonar sample image into a fast RCNN network for iterative training until the model converges to obtain a cultured fish identification model.
Further, the fast RCNN adds a full convolutional network layer, namely RPN (Region Proposal Network, RPN), after the last layer of convolutional neural network convolutional feature map based on CNN.
Preferably, all undefined variables in the present invention, if not explicitly defined, may be thresholds set manually.
A system for determining intrusion of a trash fish in a farming area, the system comprising:
sonar detection system: the sonar image acquisition device is used for acquiring sonar images of fish in a culture area;
a data processing system: the method comprises the steps of performing three-dimensional histogram correction and pixel value correction on a sonar image, and performing graying treatment to obtain a fish-shoal image;
slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices;
extracting trash fish information from the repaired fish slices by using a target recognition method;
and a result output module: and the method is used for outputting the extracted trash fish information.
In a third aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor carries out the steps of the method of determining intrusion of a fish in a farming area provided in the first aspect of the present invention.
In a fourth aspect, the present invention provides an electronic device comprising: a memory having a computer program stored thereon; and the processor is used for executing the computer program in the memory to realize the steps of the method for judging the invasion of the trash fish in the cultivation area.
Compared with the prior art, the invention has the following beneficial technical effects:
the sonar system is used for efficiently acquiring information from the culture area, and after the acquired sonar image is subjected to noise reduction and enhancement, the sonar system is segmented, and unclear fish slices in the sonar image are judged and repaired, so that a subsequent cultured fish identification model effectively operates.
Drawings
FIG. 1 is a flow chart of a method for determining invasion of trash fish in a cultivation area according to the present invention;
FIG. 2 is a schematic block diagram of a system for determining invasion of trash fish in a cultivation area according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail with reference to the accompanying drawings and examples. The specific embodiments described herein are to be considered in an illustrative sense only and are not intended to limit the invention.
It is also to be understood that the following examples are given solely for the purpose of illustration and are not to be construed as limitations upon the scope of the invention, since numerous insubstantial modifications and variations will now occur to those skilled in the art in light of the foregoing disclosure. The specific process parameters and the like described below are also merely examples of suitable ranges, i.e., one skilled in the art can make a suitable selection from the description herein and are not intended to be limited to the specific values described below.
The following exemplarily illustrates a method for determining invasion of trash fish in a cultivation area.
Referring to fig. 1, which is a flowchart illustrating a method for determining invasion of a trash fish in a cultivation area, a method for determining invasion of trash fish in a cultivation area according to an embodiment of the present invention will be described with reference to fig. 1, and the method includes the following steps:
step 1, acquiring echo information by using a sonar detection device in an acquisition and cultivation area;
step 2, constructing a fish-shoal image according to the echo information, correcting a three-dimensional histogram and correcting pixel values, and performing graying treatment;
step 3, slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices;
and 4, extracting the trash fish information from the repaired fish slices by using a target recognition method.
Further, in step 1, the sub-step of acquiring echo information by using a sonar detection device in the acquisition culture area is as follows:
and configuring a sonar system, detecting the region by using a DIDSON (Dual-frequency Identification Sonar) sonar system, and acquiring echo information.
Preferably, the DIDSON sonar is fixed or towed by a towing vessel to expand the detection area.
In step 2, a fish-shoal image is constructed according to echo information, three-dimensional histogram correction and pixel value correction are performed, and the substeps of gray scale processing are as follows:
and carrying out coordinate transformation on data acquired by the sonar to obtain a sonar image, then carrying out sonar image enhancement by using a double-tree complex wavelet and a fuzzy theory, carrying out three-dimensional histogram correction on the fish-school image, and outputting the fish-school image.
The dual-tree complex wavelet and fuzzy theory comprises the following steps:
decomposing the sonar image into m multi-scales through a double-tree complex wavelet, wherein the value of m is dependent on the fineness of the finally decomposed subband image, and m is more than 3;
setting a reasonable threshold value for the wavelet coefficient of the complex high-frequency noise to reduce the processing range, and protecting the wavelet coefficient of the useful information from being changed;
blurring processing is carried out on the complex low-frequency sub-band, a contrast enhancement operator is applied to image enhancement processing, and then blurring inverse transformation is carried out on the processed image;
and reconstructing the denoised high-frequency sub-band with useful information and the blurred enhanced low-frequency sub-band information, and finally optimizing the reconstructed image.
Further, in step 3, slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices, wherein the sub-steps are as follows:
dividing the shoal image by using a set edge recognition algorithm to obtain a plurality of fish slices, wherein the fish slices are independent areas;
equally dividing the edges of the fish slices to be detected and the reference fish slices to obtain edge points;
respectively obtaining the distance between the geometric center point and each edge point of the fish slice to be measured as a distance set LA to be measured;
the distance between the geometric center point of the reference fish slice and each edge point is used as a reference distance set L0;
respectively calculating the difference values of corresponding elements in the distance set LA to be detected and the reference distance set L0 according to the sequence;
calculating the difference delta A between the area of the fish slice to be detected and the area of the reference fish slice;
calculating individual difference values:
,
wherein DIF is the individual difference value of the fish slices, a and b are preset contour weight and area weight parameters respectively, n is the number of edge aliquots, namely the number of edge points, LA i L0 is the i-th element in the distance set to be measured i For the i element in the reference distance set, mean (LA) is the arithmetic mean of all values in the distance set to be measured, mean (L0) is the arithmetic mean of all values in the reference distance set;
if the difference value of the elements corresponding to the distance set LA to be measured and the reference distance set L0 exceeds the first distance difference value and LA exists i And L0 i The difference of (2) is larger than 2×mean (L0) ×dif, and the fish slice is repaired;
the repairing method comprises the following steps:
overlapping geometric center points of the fish slices to be detected and the reference fish slices, adjusting the direction of one slice to enable the sum of distance differences of all edge points of the profiles of the 2 slices to be minimum, and obtaining an edge point set with the distance from the geometric center point to be detected being greater than a second threshold value in the profile of the fish slices to be detected, wherein the point set forms an arc line;
the calculation method of the second threshold is an arithmetic average value of the minimum value of the elements in the distance set LA to be measured and the minimum value of the elements in the reference distance set L0;
the arc line and the profile of the fish slice to be detected are respectively marked as a first intersection point and a second intersection point, the first intersection point and the second intersection point form a straight line segment, the straight line segment and the arc form a closed first space, and if the area of the first space is larger than A (0) x min (LA) i ,L0 i ) Edge correction is performed:
the distance between the fish slice to be measured and the first intersection point and the distance between the fish slice to be measured and the second intersection point are extreme values of an arithmetic series, the number of edge points in the arc line are the number of terms of the arithmetic series, the geometric center point of the fish slice to be measured is taken as an endpoint, elements in the arithmetic series are equal-division angles in the direction from the first intersection point to the second intersection point in radius to form line segments, one end of each obtained line segment is taken as an endpoint, the other end of each obtained line segment is taken as a new edge of the fish slice to be measured, and the number of the line segments is the number of terms of the arithmetic series; obtaining a new fish slice;
a (0) is the area of the reference fish slice, mim (LA) i ,L0 i ) For i, obtaining the LA in the value range i And L0 i When the difference between (a) and (b) is smallest, LA i And L0 i I.e. [1, n ]]；
All fish slices are judged in sequence and repaired when needed.
This step can exclude that 2 or more fish individuals receive coincident indistinguishable signals upon sonar detection. And when the outline is too far away from the reference fish slice, performing segmentation and discarding, and performing edge reconstruction on the segmented main body for the subsequent recognition model.
Because the fishes in the culture area begin to be cultured in the same period, the variety and the growth condition of the cultured fishes are unified, and the shapes and the sizes of the miscellaneous fishes are different, the simple contour recognition can be used for simplifying the recognition process and reducing the recognition resource cost.
Further, in step 4, the substeps of extracting the trash fish information from the repaired fish slices by applying the target recognition method are as follows:
inputting a fish slice image into a preset cultured fish identification model for target detection so as to obtain an identification result of the fish slice image; and obtaining the trash fish information according to the identification result.
Further, the step of obtaining a preset farmed fish identification model comprises the following steps:
and acquiring a sonar sample image of the cultured fish in the current growth period, and inputting the sonar sample image into a fast RCNN network for iterative training until the model converges to obtain a cultured fish identification model.
Further, the fast RCNN adds a full convolutional network layer, namely RPN (Region Proposal Network, RPN), after the last layer of convolutional neural network convolutional feature map based on CNN.
Preferably, all undefined variables in the present invention, if not explicitly defined, may be thresholds set manually.
FIG. 2 is a schematic block diagram showing a system for determining invasion of trash fish in a cultivation area according to an embodiment of the invention.
A system for determining intrusion of a trash fish in a farming area, the system comprising:
sonar detection system: the sonar image acquisition device is used for acquiring sonar images of fish in a culture area;
a data processing system: the method comprises the steps of performing three-dimensional histogram correction and pixel value correction on a sonar image, and performing graying treatment to obtain a fish-shoal image;
slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices;
extracting trash fish information from the repaired fish slices by using a target recognition method;
and a result output module: and the method is used for outputting the extracted trash fish information.
In a third aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor carries out the steps of the method of determining intrusion of a fish in a farming area provided in the first aspect of the present invention.
In a fourth aspect, the present invention provides an electronic device comprising: a memory having a computer program stored thereon; and the processor is used for executing the computer program in the memory to realize the steps of the method for judging the invasion of the trash fish in the cultivation area.
The system for judging the invasion of the trash fish in the cultivation area can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server. The system for judging the invasion of the trash fish in the breeding area can be operated by a processor and a memory. It will be appreciated by those skilled in the art that the example is merely an example of a system for determining intrusion of a trash fish in a farming area, and is not intended to be limiting, and that more or fewer components than the example may be included, or certain components may be combined, or different components may be combined, for example, the trash fish intrusion system in a farming area may further include an input and output device, a network access device, a bus, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general processor can be a microprocessor or any conventional processor, and the processor is a control center for judging the running system of the trash fish invasion system in the cultivation area, and various interfaces and lines are used for connecting various parts of the whole trash fish invasion system in the cultivation area.
The memory may be used to store the computer program and/or module, and the processor may implement the various functions of the system for determining intrusion of trash fish in a farming area by running or executing the computer program and/or module stored in the memory and invoking 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 (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (e.g., audio data, phonebook, etc.) created according to the use of the handset. In addition, the memory may include random access memory (RAM, random Access Memory), and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid state storage device.
Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the invention. Furthermore, the foregoing description of the invention has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the invention that may not be presently contemplated, may represent an equivalent modification of the invention.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many variations, modifications, substitutions, and alterations are possible in these embodiments without departing from the principles and spirit of the invention.
Claims (6)
1. A method for determining invasion of a trash fish in a farming area, the method comprising the steps of:
step 1, acquiring echo information by using a sonar detection device in an acquisition and cultivation area;
step 2, constructing a fish-shoal image according to the echo information, correcting a three-dimensional histogram and correcting pixel values, and performing graying treatment;
step 3, slicing the fish swarm image to obtain a plurality of fish slices, and judging and repairing the fish slices to obtain new fish slices;
and 4, extracting the trash fish information from the repaired fish slices by using a target recognition method.
2. The method for determining invasion of trash fish in a cultivation area according to claim 1, wherein in step 1, the sub-steps of acquiring echo information in the cultivation area by using a sonar detection device are as follows:
and configuring a sonar system, detecting the region by using a DIDSON (Dual-frequency Identification Sonar) sonar system, and acquiring echo information.
3. The method for determining invasion of trash fish in a cultivation area according to claim 1, wherein in step 2, a shoal image is constructed according to echo information, three-dimensional histogram correction and pixel value correction are performed, and the substeps of gray scale processing are performed:
and carrying out coordinate transformation on data acquired by the sonar to obtain a sonar image, then carrying out sonar image enhancement by using a double-tree complex wavelet and a fuzzy theory, carrying out three-dimensional histogram correction on the fish-school image, and outputting the fish-school image.
4. A method for determining invasion of trash fish in a cultivation area according to claim 3, wherein in step 3, a plurality of fish slices are obtained after slicing the shoal image, and the sub-steps of determining and repairing the fish slices to obtain new fish slices are as follows:
dividing the shoal image by using a set edge recognition algorithm to obtain a plurality of fish slices, wherein the fish slices are independent areas;
equally dividing the edges of the fish slices to be detected and the reference fish slices to obtain edge points;
respectively obtaining the distance between the geometric center point and each edge point of the fish slice to be measured as a distance set LA to be measured;
the distance between the geometric center point of the reference fish slice and each edge point is used as a reference distance set L0;
respectively calculating the difference values of corresponding elements in the distance set LA to be detected and the reference distance set L0 according to the sequence;
calculating the difference delta A between the area of the fish slice to be detected and the area of the reference fish slice;
calculating individual difference values:
,
wherein DIF is the individual difference value of the fish slices, a and b are preset contour weight and area weight parameters respectively, n is the number of edge aliquots, namely the number of edge points, LA i L0 is the i-th element in the distance set to be measured i For the i element in the reference distance set, mean (LA) is the arithmetic mean of all values in the distance set to be measured, mean (L0) is the arithmetic mean of all values in the reference distance set;
if the difference value of the elements corresponding to the distance set LA to be measured and the reference distance set L0 exceeds the first distance difference value and LA exists i And L0 i The difference of (2) is larger than 2×mean (L0) ×dif, and the fish slice is repaired;
the repairing method comprises the following steps:
overlapping geometric center points of the fish slices to be detected and the reference fish slices, adjusting the direction of one slice to enable the sum of distance differences of all edge points of the profiles of the 2 slices to be minimum, and obtaining an edge point set with the distance from the geometric center point to be detected being greater than a second threshold value in the profile of the fish slices to be detected, wherein the point set forms an arc line;
the calculation method of the second threshold is an arithmetic average value of the minimum value of the elements in the distance set LA to be measured and the minimum value of the elements in the reference distance set L0;
the arc line and the profile of the fish slice to be detected are respectively marked as a first intersection point and a second intersection point, the first intersection point and the second intersection point form a straight line segment, the straight line segment and the arc form a closed first space, and if the area of the first space is larger than A (0) x min (LA) i ,L0 i ) Edge correction is performed:
the distance between the fish slice to be measured and the first intersection point and the distance between the fish slice to be measured and the second intersection point are extreme values of an arithmetic series, the number of edge points in the arc line are the number of terms of the arithmetic series, the geometric center point of the fish slice to be measured is taken as an endpoint, elements in the arithmetic series are equal-division angles in the direction from the first intersection point to the second intersection point in radius to form line segments, one end of each obtained line segment is taken as an endpoint, the other end of each obtained line segment is taken as a new edge of the fish slice to be measured, and the number of the line segments is the number of terms of the arithmetic series; obtaining a new fish slice;
a (0) is the area of the reference fish slice, mim (LA) i ,L0 i ) For i, obtaining the LA in the value range i And L0 i When the difference between (a) and (b) is smallest, LA i And L0 i I.e. [1, n ]]；
All fish slices are judged in sequence and repaired when needed.
5. The method for determining invasion of trash fish in a cultivation area according to claim 1, wherein in step 4, the sub-step of extracting trash fish information from the repaired fish slices by applying the target recognition method is as follows:
inputting a fish slice image into a preset cultured fish identification model for target detection so as to obtain an identification result of the fish slice image; and obtaining the trash fish information according to the identification result.
6. The method for determining invasion of trash fish in a cultivation area according to claim 5, wherein in step 4, the step of obtaining a preset cultivation fish identification model is:
and acquiring a sonar sample image of the cultured fish in the current growth period, and inputting the sonar sample image into a fast RCNN network for iterative training until the model converges to obtain a cultured fish identification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311555560.9A CN117538880A (en) | 2023-11-21 | 2023-11-21 | Method for judging invasion of trash fish in breeding area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311555560.9A CN117538880A (en) | 2023-11-21 | 2023-11-21 | Method for judging invasion of trash fish in breeding area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117538880A true CN117538880A (en) | 2024-02-09 |
Family
ID=89791381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311555560.9A Pending CN117538880A (en) | 2023-11-21 | 2023-11-21 | Method for judging invasion of trash fish in breeding area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117538880A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2383584A1 (en) * | 2010-04-19 | 2011-11-02 | Furuno Electric Company, Limited | Method and device for detecting ultrasound wave, and method and device for detecting school of fish |
| CN202175176U (en) * | 2011-03-31 | 2012-03-28 | 常州工学院 | System for measuring ship tonnage by applying side scan sonar |
| CN113484867A (en) * | 2021-06-25 | 2021-10-08 | 山东航天电子技术研究所 | Imaging sonar-based fish school density detection method in closed space |
| CN114612397A (en) * | 2022-03-02 | 2022-06-10 | 广东省农业科学院农业经济与信息研究所 | Fry sorting method and system, electronic device and storage medium |
-
2023
- 2023-11-21 CN CN202311555560.9A patent/CN117538880A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2383584A1 (en) * | 2010-04-19 | 2011-11-02 | Furuno Electric Company, Limited | Method and device for detecting ultrasound wave, and method and device for detecting school of fish |
| CN202175176U (en) * | 2011-03-31 | 2012-03-28 | 常州工学院 | System for measuring ship tonnage by applying side scan sonar |
| CN113484867A (en) * | 2021-06-25 | 2021-10-08 | 山东航天电子技术研究所 | Imaging sonar-based fish school density detection method in closed space |
| CN114612397A (en) * | 2022-03-02 | 2022-06-10 | 广东省农业科学院农业经济与信息研究所 | Fry sorting method and system, electronic device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 傅小康: "基于图像声纳的浅海鱼群分类识别算法研究", 中国优秀硕士学位论文数据库, 15 July 2006 (2006-07-15), pages 1 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113466232B (en) | Brittle fish meat rapid detection method and system based on computer image | |
| Charutha et al. | An efficient brain tumor detection by integrating modified texture based region growing and cellular automata edge detection | |
| CN113450328B (en) | Medical image key point detection method and system based on improved neural network | |
| CN110956632B (en) | Method and device for automatically detecting pectoralis major region in molybdenum target image | |
| Le et al. | An automated fish counting algorithm in aquaculture based on image processing | |
| Valliammal et al. | Hybrid image segmentation algorithm for leaf recognition and characterization | |
| CN116067964B (en) | Method and system for promoting fish muscle embrittlement by utilizing condensed tannin | |
| CN110992377A (en) | Image segmentation method, device, computer-readable storage medium and equipment | |
| CN113349111A (en) | Dynamic feeding method, system and storage medium for aquaculture | |
| CN116994140A (en) | Cultivated land extraction method, device, equipment and medium based on remote sensing image | |
| CN114092450A (en) | Real-time image segmentation method, system and device based on gastroscopy video | |
| Awalludin et al. | Combination of canny edge detection and blob processing techniques for shrimp larvae counting | |
| Hou et al. | Semantic segmentation of vertebrate microfossils from computed tomography data using a deep learning approach | |
| CN115731282A (en) | Underwater fish weight estimation method and system based on deep learning and electronic equipment | |
| CN114494174A (en) | Chip welding line defect detection method and device | |
| CN117538880A (en) | Method for judging invasion of trash fish in breeding area | |
| CN108447066B (en) | Biliary tract image segmentation method, terminal and storage medium | |
| CN110008881A (en) | The recognition methods of the milk cow behavior of multiple mobile object and device | |
| CN114648463A (en) | Method, device, equipment and medium for adjusting dynamic range of gray level image | |
| Xiao et al. | Automatic image segmentation algorithm based on PCNN and fuzzy mutual information | |
| CN113327221A (en) | Image synthesis method and device fusing ROI (region of interest), electronic equipment and medium | |
| Nirmaladevi et al. | A Review of Image Processing Methods and Segmentations for Brain Tumour Analysis | |
| Raju et al. | New image processing pipelines for membrane detection | |
| CN112464948A (en) | Natural scene target contour extraction method and system based on bionics | |
| Çam et al. | The performance evaluation of the cat and particle swarm optimization techniques in the image enhancement |
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 |