CN110046619A - The full-automatic shoal of fish detection method of unmanned fish finding ship and system, unmanned fish finding ship and storage medium - Google Patents
The full-automatic shoal of fish detection method of unmanned fish finding ship and system, unmanned fish finding ship and storage medium Download PDFInfo
- Publication number
- CN110046619A CN110046619A CN201910313053.1A CN201910313053A CN110046619A CN 110046619 A CN110046619 A CN 110046619A CN 201910313053 A CN201910313053 A CN 201910313053A CN 110046619 A CN110046619 A CN 110046619A
- Authority
- CN
- China
- Prior art keywords
- fish
- shoal
- pixel
- value
- unmanned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of full-automatic shoal of fish detection method of unmanned fish finding ship and system, unmanned fish finding ship and storage medium, this method includes acquiring real-time sonar image, obtains that scanning is round and coloration item；Echo strength value is obtained according to the chromatic value of pixel in scanning circle；Obtain binary image；Suspected target point is merged in binary image by algorithm of region growing, obtains suspected target region；Calculate the area in each suspected target region；Judge the area in suspected target region whether in preset area.The present invention combines the mode of coloration item by using scanning circle, real-time sonar image is obtained into the corresponding echo strength of its chromatic value in scanning pixel within the circle point, it is corresponded to after echo strength is compared with echo strength threshold value according to pixel and carries out image binaryzation, to get the corresponding suspected target region of the shoal of fish, improve the judging efficiency of the shoal of fish, then shoal of fish detection information is sent to fishing boat in real time to catch, to save the fuel consumption of fishing boat.
Description
Technical field
The present invention relates to fish finding method and technology fields, more particularly, to a kind of unmanned full-automatic shoal of fish detection method of fish finding ship
And system, unmanned fish finding ship and storage medium.
Background technique
China is sea fishery big country, possesses very long coastline, but as paralic environment deterioration and fishery resources are exhausted,
The development of inshore fishing industry has got into a difficult position, and ocean-going fishing industry becomes Marine Fishing Industry new growth point.But long range fishing needs
Large-tonnage fishing boat, and operation distance is remote, fishing boat needs are travelled on a large scale, search for and track the shoal of fish, and working efficiency is low, fuel oil
Loss is big.
Sea fishery fishing process relies primarily on fishing aid equipment to complete detection and tracking to the underwater shoal of fish, is fishing boat spy
Some equipments, main function are the discovery shoals of fish, and monitoring net feelings, fish finding quasi-instrument mainly includes fish detector, net feelings (detection) instrument etc..
Since electromagnetic wave is decayed quickly in water, the main detection means of fish finding quasi-instrument are sound waves.The beginning of the fifties, Norway start to build
It is specifically used to the sonar of fish finding, be thus born earliest commercial fish detector.To the sixties, fish detector has become marine fishing
In essential fishing aid equipment.After the 1990s, digital technology is widely applied in fish detector, fish detector performance and
Practicability spans major step, and digital fishing starts largely to equip on ocean fishing vessel with sonar.
Fish finding method traditional at present generally carries fish finder using someone's fishing boat and realizes fish finding and fishing, also there is combination
The mode of unmanned fish finding ship carries fish detector on unmanned fish finding ship, in such a way that the artificial interpretation of data back is plus remote control
It controls unmanned fish finding ship to scan for the shoal of fish, above-mentioned first method fuel oil loss is big, and second method human cost is high, work
Make low efficiency.
Summary of the invention
Based on this, it is necessary in view of the deficiencies of the prior art, provide a kind of full-automatic shoal of fish detection method of unmanned fish finding ship
And system, unmanned fish finding ship and storage medium, the mode of coloration item is combined by using scanning circle, and real-time sonar image is being swept
It retouches pixel within the circle point and obtains the corresponding echo strength of its chromatic value, echo strength and echo strength threshold value are corresponded to according to pixel
Image binaryzation is carried out after being compared, to get the corresponding suspected target region of the shoal of fish, improves the judgement effect of the shoal of fish
Rate achievees the purpose that search for and track the shoal of fish automatically, then shoal of fish detection information is sent to fishing boat in real time and caught, with section
The about fuel consumption of fishing boat.
In order to solve the above technical problems, the technical scheme adopted by the invention is that:
In a first aspect, providing a kind of full-automatic shoal of fish detection method of unmanned fish finding ship comprising following steps:.
Real-time sonar image is acquired, scanning circle and coloration item in real-time sonar image are obtained；
The corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle；
Obtain the corresponding binary image of real-time sonar image；In the scanning circle of real-time sonar image, echo strength value
Pixel corresponding more than or equal to echo strength threshold value is suspected target point, the pixel value of suspected target point is set to 1, by echo
The pixel value that intensity value is less than the corresponding pixel of echo strength threshold value is set to 0, and it is right in scanning circle to obtain real-time sonar image
The binary image answered；
The suspected target point that adjacent pixel values are 1 is merged in binary image by algorithm of region growing, is obtained
To suspected target region P；
Calculate the area Sp in each suspected target region；
Judge the area Sp in suspected target region whether in preset area；If so, suspected target regional determination is fish
Group.
Second aspect provides a kind of full-automatic shoal of fish detection system of unmanned fish finding ship comprising:
Acquisition module obtains scanning circle and coloration item in real-time sonar image for acquiring real-time sonar image；
Intensity obtains module, for obtaining the corresponding echo strength of the pixel according to the chromatic value of pixel in scanning circle
Value；
Binarization block, for obtaining the corresponding binary image of real-time sonar image；
Suspicious region obtains module, for being 1 by adjacent pixel values in binary image by algorithm of region growing
Suspected target point merges, and obtains suspected target region P and calculates the area Sp in each suspected target region；
Judgment module, for judging the area Sp in suspected target region whether in preset area.
The third aspect provides a kind of unmanned fish finding ship comprising memory and processor；It is stored on the memory
Computer program, the processor realize the above-mentioned unmanned fish finding ship full-automatic shoal of fish detection side when executing the computer program
Method, and fishing boat is sent for shoal of fish detection information by wireless communication mode.
Fourth aspect provides a kind of storage medium, is stored with computer program, and the computer program includes program
The above-mentioned full-automatic shoal of fish detection method of unmanned fish finding ship is realized in instruction, described program instruction upon being performed.
In conclusion the full-automatic shoal of fish detection method of the unmanned fish finding ship of the present invention and system, unmanned fish finding ship and storage are situated between
Matter combines the mode of coloration item by using scanning circle, and real-time sonar image is obtained its chromatic value in scanning pixel within the circle point
Corresponding echo strength corresponds to after echo strength is compared with echo strength threshold value according to pixel and carries out image binaryzation,
To get the corresponding suspected target region of the shoal of fish, the judging efficiency of the shoal of fish is improved, reaches automatic search and the tracking shoal of fish
Purpose, then shoal of fish detection information is sent to fishing boat in real time and caught, to save the fuel consumption of fishing boat.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of unmanned full-automatic shoal of fish detection method of fish finding ship provided in an embodiment of the present invention；
Fig. 2 is a kind of another flow diagram for unmanned full-automatic shoal of fish detection method of fish finding ship that embodiment provides；
Fig. 3 is the idiographic flow schematic diagram of the full-automatic shoal of fish detection method of unmanned fish finding ship provided in an embodiment of the present invention；
Fig. 4 is the structural block diagram of the first unmanned full-automatic shoal of fish detection system of fish finding ship provided in an embodiment of the present invention；
Fig. 5 is the structural block diagram of the second provided in an embodiment of the present invention unmanned full-automatic shoal of fish detection system of fish finding ship；
Fig. 6 is the structural block diagram of the third unmanned full-automatic shoal of fish detection system of fish finding ship provided in an embodiment of the present invention；
Fig. 7 is a kind of internal structure block diagram of unmanned fish finding ship provided in an embodiment of the present invention；
Fig. 8 is a kind of display diagram of real-time sonar image provided in an embodiment of the present invention.
Specific embodiment
To further understand the features of the present invention, technological means and specific purposes achieved, function, below with reference to
Present invention is further described in detail with specific embodiment for attached drawing.
If Fig. 1 is a kind of process signal of unmanned full-automatic shoal of fish detection method of fish finding ship provided in an embodiment of the present invention
Figure, as shown in Figure 1, the unmanned full-automatic shoal of fish detection method of fish finding ship, specifically comprises the following steps:
Step S110, real-time sonar image is acquired, scanning circle and coloration item in real-time sonar image are obtained；Wherein, in real time
Sonar image is that fish detector detects the sonar image for being output to monitoring screen display in presetting range after submarine target, and scanning circle is
The maximum coverage range of sonar figure in real-time sonar image can scan circle range by the way that manual type is selected, and coloration item is real-time
The corresponding distribution map of each pixel chromatic value of sonar figure in sonar image, the coloration item is in the real-time sonar image of fish detector
Have and show, the coloration item is specifically placed in the lower right corner in real-time sonar image, as shown in Figure 8.
In one embodiment, the Image Acquisition mode of real-time sonar image can take video port extended mode such as VGA
Deconcentrator, the input signal for replicating the display screen of former fish detector equipment arrive industrial personal computer, and industrial personal computer takes image pick-up card progress mould
Number conversion had not only remained the included display function of former fish detector equipment in this way, but also has been avoided that different display equipment difference brings
Pattern distortion and color difference.
Step S120, the corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle, specifically
Ground, the method that the corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle are as follows:
Step S121, the chromatic value c of one first pixel in scanning circle is obtained；
Step S122, position of the chromatic value c of the first pixel on coloration item is obtained；
Step S123, the corresponding echo strength f (c) of the first pixel that chromatic value is c is calculated, whereinxc
For the abscissa value of chromatic value c appearance position on coloration item of the first pixel, xl is the abscissa value of coloration left edge,
Xr is the abscissa value of coloration right hand edge.
Wherein, the coordinate system where coloration item is the rectangular coordinate system monitored where screen, and the origin of coordinate system is shielding
The lower left corner of curtain, the positive direction of the x-axis of coordinate system is towards the right side, and the y-axis direction of coordinate system is upward；The chromatic value c of first pixel is in color
Spend the acquisition methods of the abscissa value xc of appearance position on item are as follows:
Obtain chromatic value c corresponding color component value Rc, Gc, Bc of the first pixel；
The pixel in coloration strip area is from left to right successively searched for, the color that color component value is respectively Rc, Gc, Bc is found
Corresponding second pixel of angle value；
Coordinate system where coloration item gets the abscissa value xc of the second pixel in coloration strip area.
By the above method, scan the corresponding chromatic value of each pixel in circle can be converted into it is corresponding in 0~1 range
Echo strength value, so that the judgement to each pixel echo strength in scanning circle is realized, to facilitate the detection of the subsequent shoal of fish.
Step S130, the corresponding binary image of real-time sonar image is obtained；In the scanning circle of real-time sonar image, return
It is suspected target point that intensity of wave value, which is more than or equal to the corresponding pixel of echo strength threshold value, and the pixel value of suspected target point is set to
1, the pixel value that echo strength value is less than the corresponding pixel of echo strength threshold value is set to 0, real-time sonar image is obtained and is sweeping
Retouch corresponding binary image in circle.
Step S140, the suspected target that adjacent pixel values are 1 is clicked through in binary image by algorithm of region growing
Row merges, and obtains suspected target region P.
Step S150, the area Sp in each suspected target region is calculated, whereinri=D/L*K, riIt is doubtful
Like the normalized cumulant of the round heart o of suspected target point i range sweep any in the P of target area, D is real-time sonar image middle conductor
The length in pixels of io, L are the length in pixels for scanning circle outer diameter, and K is fish detector detection scanning range radius, and wherein length in pixels is
The quantity of pixel in unit length.
Step S160, the area Sp in suspected target region is judged whether in preset area, if so, suspected target region
It is determined as the shoal of fish；If the area Sp in suspected target region is greater than the maximum value S1 of preset area, suspected target regional determination is
External noise；If the area Sp in suspected target region is less than the minimum value S2 of preset area, suspected target regional determination is water
Bottom；Specifically, S1 can value be 0.1K2, S2 can value be 10 square metres, the preset cartographic represenation of area shoal of fish to be caught is in real-time sonar
The size in floor projection region on image, the maximum value and minimum value of preset area can be according to unmanned fish finding ships in working sea area
The movement pattern of fish is adjusted.
Another process if Fig. 2 is a kind of unmanned full-automatic shoal of fish detection method of fish finding ship provided in an embodiment of the present invention is shown
Be intended to, as shown in Fig. 2, the step S160, judge suspected target region area Sp whether in preset area later also wrap
It includes:
Step S170, real-time sonar image middle conductor oT and y-axis direction are obtained according to the geometric center of gravity T in suspected target region
Angle a and the corresponding physical length d of line segment oT, wherein the calculation method of line segment oT corresponding physical length d is first
The length in pixels l for obtaining line segment oT, in conjunction with the length in pixels L and fish detector detection scanning range radius of scanning circular scan circle outer diameter
K is it is found that d=l/L*K；The coordinate of the geometric center of gravity T in suspected target region is (xT, yT),N
For the pixel quantity in suspected target region, xiFor the corresponding abscissa value of ith pixel point, y in suspected target regioniIt is doubtful
Like the corresponding ordinate value of ith pixel point in target area.
Step S180, using physical length d angle a corresponding as shoal of fish azimuth, line segment oT as with the shoal of fish apart
Distance input to unmanned fish finding ship control system, as the target position of unmanned fish finding ship movement in next step, to control
Unmanned fish finding ship tracks the shoal of fish.
Wherein, unmanned fish finding ship ship's speed V ∝ d, unmanned fish finding ship course α ∝ a, by taking first-order linear controls as an example: assuming that working as
Preceding unmanned fish finding ship ship's speed is V0, course α0, need unmanned fish finding ship to trail 100 meters of distances of the shoal of fish, then unmanned fish finding ship next step
Speed of a ship or plane V1With course α1It should are as follows:
Wherein, the output time interval of the adjacent real-time sonar image of two frames of dt, m, n are the adjustable smoothing factor greater than 0,
Its value is smaller, and unmanned fish finding ship running track is more steady, but performance of dynamic tracking is low；Its value is bigger, unmanned fish finding ship tracking
Precision is higher, but running track more shakes.
In one embodiment, the step S170, real-time sonar figure obtained according to the geometric center of gravity T in suspected target region
Before the middle conductor oT physical length d corresponding with the angle a in y-axis direction and line segment oT further include:
Step S190, calculate each shoal of fish apart from Area-weighted index θ, selected distance Area-weighted index θ value is maximum
The correspondence shoal of fish tracked, wherein apart from Area-weighted index θ=Sp/d.
When the candidate shoal of fish that there are multiple area Sp for meeting suspected target region in preset area, then according to apart from face
Product Weighted Guidelines θ is maximum to select the suitable shoal of fish to be tracked, and without artificially being selected, improves unmanned fish finding ship tracking
The efficiency of the shoal of fish.
Fig. 3 is the idiographic flow schematic diagram of the full-automatic shoal of fish detection method of unmanned fish finding ship provided in an embodiment of the present invention,
In order to be more clear technical solution of the present invention, preferred embodiment is illustrated again below.
Step S110, real-time sonar image is acquired, scanning circle and coloration item in real-time sonar image are obtained；
Step S120, the corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle；
Step S130, the corresponding binary image of real-time sonar image is obtained；In the scanning circle of real-time sonar image, return
It is suspected target point that intensity of wave value, which is more than or equal to the corresponding pixel of echo strength threshold value, and the pixel value of suspected target point is set to
1, the pixel value that echo strength value is less than the corresponding pixel of echo strength threshold value is set to 0, real-time sonar image is obtained and is sweeping
Retouch corresponding binary image in circle；
Step S140, the suspected target that adjacent pixel values are 1 is clicked through in binary image by algorithm of region growing
Row merges, and obtains suspected target region P；
Step S150, the area Sp in each suspected target region is calculated；
Step S160, judge the area Sp in suspected target region whether in preset area；If so, suspected target region
It is determined as the shoal of fish；
Step S190, calculate each shoal of fish apart from Area-weighted index θ, selected distance Area-weighted index θ value is maximum
The correspondence shoal of fish tracked, wherein apart from Area-weighted index θ=Sp/d；
Step S170, real-time sonar image middle conductor oT and y-axis direction are obtained according to the geometric center of gravity T in suspected target region
Angle a and the corresponding physical length d of line segment oT, wherein the coordinate of the geometric center of gravity T in suspected target region is (xT, yT),
Step S180, using physical length d angle a corresponding as shoal of fish azimuth, line segment oT as with the shoal of fish apart
Distance input to the control system of unmanned fish finding ship, i.e., shoal of fish detection information is input to the control system of unmanned fish finding ship,
As the target position that unmanned fish finding ship moves in next step, to control the unmanned fish finding ship tracking shoal of fish.
The full-automatic shoal of fish detection method of unmanned fish finding ship provided in this embodiment using scanning circle combine coloration item by the way of,
Real-time sonar image is obtained into the corresponding echo strength of its chromatic value in scanning pixel within the circle point, echo is corresponded to according to pixel
Intensity carries out image binaryzation after being compared with echo strength threshold value, so that the corresponding suspected target region of the shoal of fish is got,
The judging efficiency for improving the shoal of fish achievees the purpose that search for and track the shoal of fish automatically, then sends shoal of fish detection information in real time
It is caught to fishing boat, to save the fuel consumption of fishing boat.
Fig. 4 is the structural block diagram of the first unmanned full-automatic shoal of fish detection system of fish finding ship provided in an embodiment of the present invention,
As shown in figure 4, corresponding to the above-mentioned unmanned full-automatic shoal of fish detection method of fish finding ship, the present invention also provides a kind of unmanned fish finding ship is complete
Automatic shoal of fish detection system, the unmanned full-automatic shoal of fish detection system of fish finding ship include for executing above-mentioned unmanned fish finding ship entirely certainly
The module of dynamic shoal of fish detection method, the system can be configured in the terminals such as computer equipment, using the unmanned fish finding ship of the present invention
Full-automatic shoal of fish detection system, in such a way that scanning circle combines coloration item, by real-time sonar image in scanning pixel within the circle
Point obtains the corresponding echo strength of its chromatic value, according to pixel correspond to echo strength be compared with echo strength threshold value it is laggard
Row image binaryzation improves the judging efficiency of the shoal of fish, reaches and search automatically to get the corresponding suspected target region of the shoal of fish
Rope and the purpose for tracking the shoal of fish, are then sent to fishing boat for shoal of fish detection information and catch, in real time to save the fuel oil of fishing boat
Consumption.
Specifically, as shown in figure 4, the unmanned full-automatic shoal of fish detection system of fish finding ship includes that acquisition module 110, intensity obtain
Modulus block 120, binarization block 130, suspicious region obtain module 140 and judgment module 150.
Acquisition module 110 obtains scanning circle and coloration item in real-time sonar image for acquiring real-time sonar image；
Intensity obtains module 120, for obtaining the corresponding echo of the pixel according to the chromatic value of pixel in scanning circle
Intensity value；
Binarization block 130, for obtaining the corresponding binary image of real-time sonar image；
Suspicious region obtains module 140, for being 1 by adjacent pixel values in binary image by algorithm of region growing
Suspected target point merge, obtain suspected target region P and calculate the area Sp in each suspected target region；
Judgment module 150, for judging the area Sp in suspected target region whether in preset area.
In one embodiment, the intensity obtains module 120 and is specifically used for:
Step S121, the chromatic value c of one first pixel in scanning circle is obtained；
Step S122, position of the chromatic value c of the first pixel on coloration item is obtained；
Step S123, the corresponding echo strength f (c) of the first pixel that chromatic value is c is calculated, whereinxc
For the abscissa value of chromatic value c appearance position on coloration item of the first pixel, xl is the abscissa value of coloration left edge,
Xr is the abscissa value of coloration right hand edge.
Fig. 5 is the structural block diagram of the second provided in an embodiment of the present invention unmanned full-automatic shoal of fish detection system of fish finding ship.
As shown in figure 5, the full-automatic shoal of fish detection system of unmanned fish finding ship provided in this embodiment is full-automatic in above-mentioned unmanned fish finding ship
Angle length is increased on the basis of shoal of fish detection system obtains module 150 and message output module 160.
Angle length obtains module 150, for being obtained in real-time sonar image according to the geometric center of gravity T in suspected target region
Physical length d line segment oT corresponding with the angle a in y-axis direction and line segment oT.
Message output module 160, for using physical length d angle a corresponding as shoal of fish azimuth, line segment oT as
The control system of unmanned fish finding ship is input to shoal of fish distance.
Fig. 6 is the structural block diagram of the third unmanned full-automatic shoal of fish detection system of fish finding ship provided in an embodiment of the present invention.
As shown in fig. 6, the full-automatic shoal of fish detection system of unmanned fish finding ship provided in this embodiment is full-automatic in above-mentioned unmanned fish finding ship
Shoal of fish selecting module 170 is increased on the basis of shoal of fish detection system, the shoal of fish selecting module is for calculating each shoal of fish
Apart from Area-weighted index θ, the maximum corresponding shoal of fish of selected distance Area-weighted index θ value is tracked.
The full-automatic shoal of fish detection system of unmanned fish finding ship provided in an embodiment of the present invention combines coloration by using scanning circle
Real-time sonar image is obtained the corresponding echo strength of its chromatic value in scanning pixel within the circle point, according to pixel by the mode of item
The corresponding echo strength of point carries out image binaryzation after being compared with echo strength threshold value, so that it is corresponding doubtful to get the shoal of fish
Target area improves the judging efficiency of the shoal of fish, achievees the purpose that search for automatically and tracks the shoal of fish, then by shoal of fish detection information
It is sent to fishing boat in real time to be caught, to save the fuel consumption of fishing boat.
It should be noted that it is apparent to those skilled in the art that, above-mentioned unmanned fish finding ship is full-automatic
The specific implementation process of shoal of fish detection system and each module, can be with reference to the corresponding description in preceding method embodiment, in order to retouch
That states is convenienct and succinct, and details are not described herein.
Fig. 7 is a kind of internal structure block diagram of unmanned fish finding ship provided in an embodiment of the present invention, as shown in fig. 7, of the invention
The unmanned fish finding ship provided includes being connect by memory, processor and the network connected by system bus that system bus connects
Mouthful；Computer program is stored on the memory, the processor is for providing calculating and control ability, to support entire nothing
The operation of people's fish finding ship, the processor realize a kind of above-mentioned unmanned fish finding ship full automatic fishing when executing the computer program
Group's detection method, and fishing boat is sent for shoal of fish detection information by wireless communication mode, wherein shoal of fish detection information is the shoal of fish
With the relative position information of unmanned fish finding ship, specifically, the relative position information of the shoal of fish and unmanned fish finding ship includes making angle a
It is the shoal of fish physical length d corresponding relative to the azimuth of unmanned fish finding ship, line segment oT as unmanned fish finding ship and shoal of fish phase
Away from distance.
Memory may include non-volatile memory medium and built-in storage, which is stored with operation
System can also be stored with computer program, when which is executed by processor, processor may make to realize unmanned fish finding
The full-automatic shoal of fish detection method of ship.
Computer program can also be stored in the built-in storage, when which is executed by processor, may make place
It manages device and executes the unmanned full-automatic shoal of fish detection method of fish finding ship.The network interface is used to carry out network communication with lash ship.This field
Technical staff is appreciated that structure shown in Fig. 7, only the block diagram of part-structure relevant to application scheme, not
The restriction for being applied to other unmanned fish finding ships to application scheme is constituted, specific unmanned fish finding ship may include than in figure
Shown more or fewer components perhaps combine certain components or with different component layouts.
In one embodiment, the full-automatic shoal of fish detection method of unmanned fish finding ship provided by the present application can be realized as a kind of meter
The mode of calculation machine program, computer program can be run on unmanned fish finding ship as shown in Figure 7.The memory of unmanned fish finding ship
In can store form the unmanned full-automatic shoal of fish detection system of fish finding ship each program module, for example, acquisition mould shown in Fig. 4
Block 110, intensity obtain module 120, binarization block 130, suspicious region acquisition module 140 and judgment module 150.Each journey
The computer program of sequence module composition makes processor execute the unmanned fish finding of each embodiment of the application described in this explanation
The step of ship full-automatic shoal of fish detection system.For example, unmanned fish finding ship shown in Fig. 7 can pass through unmanned spy as shown in Figure 4
Acquisition module 110 in the full-automatic shoal of fish detection system of fish ship acquires real-time sonar image, obtains scanning in real-time sonar image
Round and coloration item；Intensity obtains module 120, and according to the chromatic value of pixel in scanning circle, to obtain the corresponding echo of the pixel strong
Angle value；Binarization block 130 obtains the corresponding binary image of real-time sonar image；Suspicious region obtains module 140 and passes through area
Domain growth algorithm merges the suspected target point that adjacent pixel values are 1 in binary image, obtains suspected target region P
And calculate the area Sp in each suspected target region；Whether judgment module 150 judges the area Sp in suspected target region preset
In area.
In one embodiment it is proposed that a kind of unmanned fish finding ship, including memory and processor, the memory and place
Device is managed, the memory is stored with computer program, when the computer program is executed by the processor, so that the processing
Device executes following steps: step S110, acquiring real-time sonar image, obtains scanning circle and coloration item in real-time sonar image；Step
Rapid S120, the corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle；Step S130, it obtains real
When the corresponding binary image of sonar image；In the scanning circle of real-time sonar image, it is strong that echo strength value is more than or equal to echo
Spending the corresponding pixel of threshold value is suspected target point, and the pixel value of suspected target point is set to 1, and echo strength value is less than echo
The pixel value of the corresponding pixel of intensity threshold is set to 0, obtains real-time sonar image corresponding binary image in scanning circle；
Step S140, the suspected target point that adjacent pixel values are 1 is merged in binary image by algorithm of region growing, is obtained
To suspected target region P；Step S150, the area Sp in each suspected target region is calculated；Step S160, judge suspected target area
Whether the area Sp in domain is in preset area；If so, suspected target regional determination is the shoal of fish.
In one embodiment, coloration of the processor realizing the step S120, according to the interior pixel of circle is scanned
When value obtains the step of the corresponding echo strength value of the pixel, it is implemented as follows step: step S121, obtaining in scanning circle
The chromatic value c of one first pixel；Step S122, position of the chromatic value c of the first pixel on coloration item is obtained；Step
S123, the corresponding echo strength f (c) of the first pixel that chromatic value is c is calculated, whereinXc is the first pixel
Chromatic value c appearance position on coloration item abscissa value, xl is the abscissa value of coloration left edge, and xr is that coloration item is right
The abscissa value at edge.
In one embodiment, the processor is in the area Sp for executing the step S160, judging suspected target region
After whether in preset area, following steps are specifically executed: step S170, being obtained according to the geometric center of gravity T in suspected target region
The physical length d for taking real-time sonar image middle conductor oT corresponding with the angle a in y-axis direction and line segment oT, wherein suspected target
The coordinate of the geometric center of gravity T in region is (xT, yT),Step S180, using angle a as the shoal of fish
Azimuth, line segment oT corresponding physical length d as the control system for being input to unmanned fish finding ship with shoal of fish distance,
As the target position that unmanned fish finding ship moves in next step, to control the unmanned fish finding ship tracking shoal of fish.
In one embodiment, the processor execute the step S170, according to the geometry weight in suspected target region
Heart T obtain the step of real-time sonar image middle conductor oT physical length d corresponding with the angle a in y-axis direction and line segment oT it
Before, specifically execute following steps: step S190, calculate each shoal of fish apart from Area-weighted index θ, selected distance Area-weighted
The maximum corresponding shoal of fish of index θ value is tracked, wherein apart from Area-weighted index θ=Sp/d.
It should be appreciated that in the embodiment of the present application, processor can be central processing unit (Central Processing
Unit, CPU), which can also be other general processors, digital signal processor (Digital Signal
Processor, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
At programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or the processor
It is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that relevant hardware can be instructed to complete by computer program.The computer program includes program instruction, computer journey
Sequence can be stored in a storage medium, which is computer readable storage medium.The program instruction is by the department of computer science
At least one processor in system executes, to realize the process step of the embodiment of the above method.
Therefore, the present invention also provides a kind of storage mediums.The storage medium can be computer readable storage medium.This is deposited
Storage media is stored with computer program, and wherein computer program includes program instruction.The program instruction makes when being executed by processor
Processor executes following steps: step S110, acquiring real-time sonar image, obtains scanning circle and coloration in real-time sonar image
Item；Step S120, the corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle；Step S130,
Obtain the corresponding binary image of real-time sonar image；In the scanning circle of real-time sonar image, echo strength value is more than or equal to
The corresponding pixel of echo strength threshold value is suspected target point, and the pixel value of suspected target point is set to 1, and echo strength value is small
It is set to 0 in the pixel value of the corresponding pixel of echo strength threshold value, obtains real-time sonar image corresponding two-value in scanning circle
Change image；Step S140, the suspected target point that adjacent pixel values are 1 is carried out in binary image by algorithm of region growing
Merge, obtains suspected target region P；Step S150, the area Sp in each suspected target region is calculated；Step S160, judgement is doubted
Like target area area Sp whether in preset area；If so, suspected target regional determination is the shoal of fish.
In one embodiment, the processor realizes the full-automatic shoal of fish detection of unmanned fish finding ship executing program instructions
Method also realizes following steps: obtaining real-time sonar image middle conductor oT and y-axis side according to the geometric center of gravity T in suspected target region
To the corresponding physical length d of angle a and line segment oT, wherein the coordinate of the geometric center of gravity T in suspected target region is (xT,
yT),Step S180, actual (tube) length angle a is corresponding as shoal of fish azimuth, line segment oT
D is spent as the control system for being input to unmanned fish finding ship with shoal of fish distance, is moved in next step as unmanned fish finding ship
Target position, to control the unmanned fish finding ship tracking shoal of fish.
In one embodiment, the processor realizes the full-automatic shoal of fish detection of unmanned fish finding ship executing program instructions
Method also realizes following steps: step S190, calculate each shoal of fish apart from Area-weighted index θ, selected distance Area-weighted
The maximum corresponding shoal of fish of index θ value is tracked, wherein apart from Area-weighted index θ=Sp/d.
The storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), magnetic disk
Or the various computer readable storage mediums that can store program code such as CD.
In conclusion a kind of full-automatic shoal of fish detection method of unmanned fish finding ship of the present invention and system, unmanned fish finding ship and depositing
Storage media combines the mode of coloration item by using scanning circle, and real-time sonar image is obtained its color in scanning pixel within the circle point
The corresponding echo strength of angle value corresponds to progress image two-value after echo strength is compared with echo strength threshold value according to pixel
Change, to get the corresponding suspected target region of the shoal of fish, improve the judging efficiency of the shoal of fish, reaches automatic search and tracking fish
The purpose of group, is then sent to fishing boat for shoal of fish detection information and catches, in real time to save the fuel consumption of fishing boat.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided by the present invention, it should be understood that disclosed system and method can pass through it
Its mode is realized.For example, system embodiment described above is only schematical.For example, the division of each unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the present invention
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.If the integrated unit is realized in the form of SFU software functional unit
And when sold or used as an independent product, it can store in one storage medium.Based on this understanding, of the invention
Substantially all or part of the part that contributes to existing technology or the technical solution can be in other words for technical solution
The form of software product embodies, which is stored in a storage medium, including some instructions to
So that a unmanned fish finding ship (can be personal computer, terminal or the network equipment etc.) executes each embodiment of the present invention
The all or part of the steps of the method.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitation of the scope of the invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art,
Without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection model of the invention
It encloses.Therefore, protection scope of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of full-automatic shoal of fish detection method of unmanned fish finding ship, which comprises the steps of:
Real-time sonar image is acquired, scanning circle and coloration item in real-time sonar image are obtained；
The corresponding echo strength value of the pixel is obtained according to the chromatic value of pixel in scanning circle；
Obtain the corresponding binary image of real-time sonar image；In the scanning circle of real-time sonar image, echo strength value is greater than
Pixel corresponding equal to echo strength threshold value is suspected target point, the pixel value of suspected target point is set to 1, by echo strength
The pixel value that value is less than the corresponding pixel of echo strength threshold value is set to 0, and it is corresponding in scanning circle to obtain real-time sonar image
Binary image；
The suspected target point that adjacent pixel values are 1 is merged in binary image by algorithm of region growing, is doubted
Like target area P；
Calculate the area Sp in each suspected target region；
Judge the area Sp in suspected target region whether in preset area；If so, suspected target regional determination is the shoal of fish.
2. the full-automatic shoal of fish detection method of unmanned fish finding ship according to claim 1, which is characterized in that described according to scanning
The chromatic value method that obtains the corresponding echo strength value of the pixel of pixel includes: in circle
Obtain the chromatic value c of one first pixel in scanning circle；
Obtain position of the chromatic value c of the first pixel on coloration item；
Calculate the corresponding echo strength f (c) of the first pixel that chromatic value is c, whereinXc is the first pixel
The abscissa value of chromatic value c appearance position on coloration item, xl are the abscissa value of coloration left edge, and xr is on the right of coloration item
The abscissa value of edge.
3. the full-automatic shoal of fish detection method of unmanned fish finding ship according to claim 2, which is characterized in that first pixel
The acquisition methods of chromatic value c abscissa value of appearance position on coloration item of point are as follows:
Obtain chromatic value c corresponding color component value Rc, Gc, Bc of the first pixel；
The pixel in coloration strip area is from left to right successively searched for, the chromatic value that color component value is respectively Rc, Gc, Bc is found
Corresponding second pixel；
Coordinate system where coloration item gets the abscissa value xc of the second pixel in coloration strip area.
4. the full-automatic shoal of fish detection method of unmanned fish finding ship according to claim 1, which is characterized in that the judgement is doubtful
After whether the area Sp of target area is in preset area further include:
The angle a and line segment of real-time sonar image middle conductor oT Yu y-axis direction are obtained according to the geometric center of gravity T in suspected target region
OT corresponding physical length d, wherein the coordinate of the geometric center of gravity T in suspected target region is (xT, yT),N is the pixel quantity in suspected target region, xiFor ith pixel in suspected target region
The corresponding abscissa value of point, yiFor the corresponding ordinate value of ith pixel point in suspected target region；
The angle a physical length d corresponding as shoal of fish azimuth, line segment oT is input to nothing as with shoal of fish distance
The control system of people's fish finding ship.
5. the full-automatic shoal of fish detection method of unmanned fish finding ship according to claim 1, which is characterized in that described according to doubtful
The geometric center of gravity T of target area obtains the real-time sonar image middle conductor oT reality corresponding with the angle a in y-axis direction and line segment oT
Before the length d of border further include:
Calculate each shoal of fish apart from Area-weighted index θ, the maximum corresponding shoal of fish of selected distance Area-weighted index θ value carries out
Tracking, wherein apart from Area-weighted index θ=Sp/d.
6. a kind of full-automatic shoal of fish detection system of unmanned fish finding ship characterized by comprising
Acquisition module obtains scanning circle and coloration item in real-time sonar image for acquiring real-time sonar image；
Intensity obtains module, for obtaining the corresponding echo strength value of the pixel according to the chromatic value of pixel in scanning circle；
Binarization block, for obtaining the corresponding binary image of real-time sonar image；
Suspicious region obtain module, for by algorithm of region growing in binary image by adjacent pixel values be 1 it is doubtful
Target point merges, and obtains suspected target region P and calculates the area Sp in each suspected target region；
Judgment module, for judging the area Sp in suspected target region whether in preset area.
7. a kind of unmanned full-automatic shoal of fish detection system of fish finding ship according to claim 6, which is characterized in that further include folder
Angular length degree obtains module, for obtaining real-time sonar image middle conductor oT and y-axis side according to the geometric center of gravity T in suspected target region
To the corresponding physical length d of angle a and line segment oT；Message output module, for using angle a as shoal of fish azimuth, line
Section oT corresponding physical length d is as the control system for being input to unmanned fish finding ship with shoal of fish distance.
8. a kind of unmanned full-automatic shoal of fish detection system of fish finding ship according to claim 7, which is characterized in that further include fish
Group selecting module, for calculate each shoal of fish apart from Area-weighted index θ, selected distance Area-weighted index θ value is maximum
The corresponding shoal of fish is tracked.
9. a kind of unmanned fish finding ship, it is characterised in that: the unmanned fish finding ship includes memory and processor, on the memory
It is stored with computer program, the processor is realized as described in any one of claim 1-5 when executing the computer program
The full-automatic shoal of fish detection method of unmanned fish finding ship, and fishing boat is sent for shoal of fish detection information by wireless communication mode.
10. a kind of storage medium, it is characterised in that: the storage medium is stored with computer program, the computer program packet
Program instruction is included, described program instruction realizes that unmanned fish finding ship according to any one of claims 1 to 5 is complete upon being performed
Automatic shoal of fish detection method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910313053.1A CN110046619B (en) | 2019-04-18 | 2019-04-18 | Full-automatic fish school detection method and system for unmanned fish finding boat, unmanned fish finding boat and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910313053.1A CN110046619B (en) | 2019-04-18 | 2019-04-18 | Full-automatic fish school detection method and system for unmanned fish finding boat, unmanned fish finding boat and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110046619A true CN110046619A (en) | 2019-07-23 |
| CN110046619B CN110046619B (en) | 2022-11-29 |
Family
ID=67277842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910313053.1A Active CN110046619B (en) | 2019-04-18 | 2019-04-18 | Full-automatic fish school detection method and system for unmanned fish finding boat, unmanned fish finding boat and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046619B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443247A (en) * | 2019-08-22 | 2019-11-12 | 中国科学院国家空间科学中心 | A kind of unmanned aerial vehicle moving small target real-time detecting system and method |
| CN113658124A (en) * | 2021-08-11 | 2021-11-16 | 杭州费尔马科技有限责任公司 | Method for checking underwater culture assets |
| CN114076949A (en) * | 2022-01-07 | 2022-02-22 | 视丰达科技（深圳）有限公司 | Fish finder data identification processing method and device |
| WO2023225898A1 (en) * | 2022-05-25 | 2023-11-30 | 广东逸动科技有限公司 | Fishing method, fishing apparatus, fishing ship, fishing system and readable storage medium |
| CN117572438A (en) * | 2024-01-12 | 2024-02-20 | 中国水产科学研究院南海水产研究所 | Navigation type fish shoal detection method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007327855A (en) * | 2006-06-08 | 2007-12-20 | Japan Radio Co Ltd | Automatic tracking scanning sonar |
| CN105572676A (en) * | 2015-12-16 | 2016-05-11 | 浙江大学 | Seine object fish shoal tracking method based on horizontal fishgraph images |
| CN108520511A (en) * | 2018-03-19 | 2018-09-11 | 中国海洋大学 | A kind of underwater fish target detection and identification method based on fish finder |
-
2019
- 2019-04-18 CN CN201910313053.1A patent/CN110046619B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007327855A (en) * | 2006-06-08 | 2007-12-20 | Japan Radio Co Ltd | Automatic tracking scanning sonar |
| CN105572676A (en) * | 2015-12-16 | 2016-05-11 | 浙江大学 | Seine object fish shoal tracking method based on horizontal fishgraph images |
| CN108520511A (en) * | 2018-03-19 | 2018-09-11 | 中国海洋大学 | A kind of underwater fish target detection and identification method based on fish finder |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443247A (en) * | 2019-08-22 | 2019-11-12 | 中国科学院国家空间科学中心 | A kind of unmanned aerial vehicle moving small target real-time detecting system and method |
| CN113658124A (en) * | 2021-08-11 | 2021-11-16 | 杭州费尔马科技有限责任公司 | Method for checking underwater culture assets |
| CN113658124B (en) * | 2021-08-11 | 2024-04-09 | 杭州费尔马科技有限责任公司 | Method for checking underwater culture assets |
| CN114076949A (en) * | 2022-01-07 | 2022-02-22 | 视丰达科技（深圳）有限公司 | Fish finder data identification processing method and device |
| WO2023225898A1 (en) * | 2022-05-25 | 2023-11-30 | 广东逸动科技有限公司 | Fishing method, fishing apparatus, fishing ship, fishing system and readable storage medium |
| CN117572438A (en) * | 2024-01-12 | 2024-02-20 | 中国水产科学研究院南海水产研究所 | Navigation type fish shoal detection method and system |
| CN117572438B (en) * | 2024-01-12 | 2024-05-03 | 中国水产科学研究院南海水产研究所 | Navigation type fish shoal detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110046619B (en) | 2022-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046619A (en) | The full-automatic shoal of fish detection method of unmanned fish finding ship and system, unmanned fish finding ship and storage medium | |
| CN105572676A (en) | Seine object fish shoal tracking method based on horizontal fishgraph images | |
| CN103139482B (en) | Vision Builder for Automated Inspection is searched and rescued in the perils of the sea | |
| JP2019527404A (en) | Oil spill detection device and method using satellite image | |
| CN107255798A (en) | Signal processing apparatus and radar image display methods | |
| CN112766221B (en) | Ship direction and position multitasking-based SAR image ship target detection method | |
| CN102540176B (en) | Thing mark detection method, thing mark sniffer and radar installations | |
| CN110516606A (en) | High-resolution satellite image any direction Ship Target Detection method | |
| WO2021132437A1 (en) | Administrative server in ship navigation assistance system, ship navigation assistance method, and ship navigation assistance program | |
| CN113657252B (en) | Efficient SAR image ship target detection method based on encoding and decoding device | |
| CN114418953B (en) | Sonar target detection method and system based on time history accumulated image | |
| CN109001725A (en) | A kind of sea unmanned boat sea multi-object tracking method | |
| US20210396525A1 (en) | Ship target object detection system, method of detecting ship target object and reliability estimating device | |
| CN110070565A (en) | A kind of ship trajectory predictions method based on image superposition | |
| CN109270501A (en) | A kind of ocean clutter cancellation method for all solid state VTS radar | |
| JP4236767B2 (en) | Method for detecting movement information of moving object based on satellite SAR image | |
| CN103975249B (en) | Image processing apparatus, radar installations, image processing method | |
| Wang et al. | Sea bottom line tracking in side-scan sonar image through the combination of points density clustering and chains seeking | |
| CN116596163B (en) | Image detection-based white croaker resource distribution prediction system and method | |
| CN112435249B (en) | Dynamic small target detection method based on circumferential scanning infrared search system | |
| CN107871323A (en) | A kind of sea ice motion information acquisition method based on all solid state radar | |
| CN111627030A (en) | Rapid and efficient sea-land accurate segmentation method for visible light remote sensing image | |
| CN109493366A (en) | Based on background modeling method, system and the medium for visiting bird radar image | |
| CN108959355A (en) | A kind of ship classification method, device and electronic equipment | |
| CN115248436A (en) | Imaging sonar-based fish resource assessment method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |