CN110046619B - Full-automatic fish school detection method and system for unmanned fish finding boat, unmanned fish finding boat and storage medium - Google Patents
Full-automatic fish school detection method and system for unmanned fish finding boat, unmanned fish finding boat and storage medium Download PDFInfo
- Publication number
- CN110046619B CN110046619B CN201910313053.1A CN201910313053A CN110046619B CN 110046619 B CN110046619 B CN 110046619B CN 201910313053 A CN201910313053 A CN 201910313053A CN 110046619 B CN110046619 B CN 110046619B
- Authority
- CN
- China
- Prior art keywords
- fish
- boat
- suspected target
- unmanned
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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 full-automatic fish school detection method and system for an unmanned fish finding boat, the unmanned fish finding boat and a storage medium, wherein the method comprises the steps of collecting a real-time sonar image, and acquiring a scanning circle and a chromaticity bar; acquiring an echo intensity value according to the chromatic value of the pixel points in the scanning circle; acquiring a binary image; merging the suspected target points in the binary image through a region growing algorithm to obtain a suspected target region; calculating the area of each suspected target area; and judging whether the area of the suspected target area is within a preset area. According to the method, the scanning circle and the chromaticity bar are combined, the pixel points of the real-time sonar image in the scanning circle acquire the echo intensity corresponding to the chromaticity value, the image binarization is performed after the echo intensity corresponding to the pixel points is compared with the echo intensity threshold value, the suspected target area corresponding to the fish school is acquired, the judgment efficiency of the fish school is improved, and then the fish school detection information is sent to the fishing boat in real time for fishing, so that the fuel consumption of the fishing boat is saved.
Description
Technical Field
The invention relates to the technical field of fish finding methods, in particular to a full-automatic fish school detection method and system for an unmanned fish finding boat, the unmanned fish finding boat and a storage medium.
Background
China is a large country in marine fishery and has a long coastline, but with deterioration of offshore environment and exhaustion of fishery resources, development of offshore fishing industry is trapped in a predicament, and the ocean fishing industry becomes a new growth point of the marine fishing industry. However, ocean fishing requires a large-tonnage fishing boat, the working distance is long, the fishing boat needs to travel in a large range to search and track fish schools, the working efficiency is low, and the fuel oil loss is large.
The fishing process of the marine fishery mainly depends on a fishing assisting instrument to complete the detection and tracking of underwater fish schools, the fishing boat is a special device for fishing boats and mainly has the functions of finding fish schools and monitoring net conditions, and the fish detecting instrument mainly comprises a fish detector, a net condition (detection) instrument and the like. The main detection means of the fish detector is sound waves because electromagnetic waves are attenuated quickly in water. In the early 50 s, norway began to build sonar specially for fish detection, and the earliest commercial fish detectors were born. In the past 60 years, the fish detector has become an essential fishing aid in marine fishing. After the 90 s in the 20 th century, the digital technology was widely applied to fish finders, the performance and practicability of the fish finders spanned a large step, and digital fishing sonars began to be equipped on ocean-going fishing boats in large quantities.
At present, in the traditional fish finding method, a manned fishing boat is generally used for carrying a fish finder to realize fish finding and fishing, and a mode of combining an unmanned fish finding boat is also provided, the unmanned fish finding boat is carried with the fish finder, and the unmanned fish finding boat is controlled to search fish groups by adopting a mode of data return, manual interpretation and remote control.
Disclosure of Invention
Based on this, it is necessary to provide a full-automatic fish school detection method and system for an unmanned fish finding boat, the unmanned fish finding boat and a storage medium, in order to overcome the defects of the prior art, the method and system for detecting the fish school are characterized in that a scanning circle and a chromaticity bar are combined, pixel points of a real-time sonar image in the scanning circle are used for obtaining echo intensities corresponding to chromaticity values of the pixel points, image binarization is performed after comparison is performed between the echo intensities corresponding to the pixel points and echo intensity threshold values, and therefore suspected target areas corresponding to the fish school are obtained, the judgment efficiency of the fish school is improved, the purpose of automatically searching and tracking the fish school is achieved, and then fish school detection information is sent to a fishing boat in real time for fishing, so that the fuel consumption of the fishing boat is reduced.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
in a first aspect, a full-automatic fish school detection method for an unmanned fish finding boat is provided, which comprises the following steps: .
Acquiring a real-time sonar image, and acquiring a scanning circle and a chromaticity bar in the real-time sonar image;
obtaining an echo intensity value corresponding to a pixel point according to the chromatic value of the pixel point in the scanning circle;
acquiring a binary image corresponding to the real-time sonar image; in a scanning circle of the real-time sonar image, a pixel point corresponding to the echo intensity value which is greater than or equal to the echo intensity threshold value is a suspected target point, the pixel value of the suspected target point is set to be 1, the pixel value of the pixel point corresponding to the echo intensity value which is less than the echo intensity threshold value is set to be 0, and a binary image corresponding to the real-time sonar image in the scanning circle is obtained;
merging suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain a suspected target region P;
calculating the area Sp of each suspected target area;
judging whether the area Sp of the suspected target area is within a preset area or not; if yes, the suspected target area is judged as a fish school.
In a second aspect, a fully automatic shoal detection system for an unmanned fish finder boat is provided, which comprises:
the acquisition module is used for acquiring a real-time sonar image and acquiring a scanning circle and a chromaticity bar in the real-time sonar image;
the intensity obtaining module is used for obtaining the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scanning circle;
the binarization module is used for acquiring a binarization image corresponding to the real-time sonar image;
the suspected region acquisition module is used for merging suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain suspected target regions P and calculating the area Sp of each suspected target region;
and the judging module is used for judging whether the area Sp of the suspected target area is within a preset area.
In a third aspect, an unmanned fish finder boat is provided, comprising a memory and a processor; the storage is stored with a computer program, the processor realizes the full-automatic fish school detection method of the unmanned fish finding boat when executing the computer program, and sends the fish school detection information to the fishing boat in a wireless communication mode.
In a fourth aspect, a storage medium is provided, which stores a computer program comprising program instructions that, when executed, implement the fully automatic fish school detection method of the unmanned fish finding boat described above.
In summary, the unmanned fish finding boat, the fully-automatic fish school detection method and system thereof, and the unmanned fish finding boat and the storage medium acquire the echo intensity corresponding to the chromatic value of the pixel point of the real-time sonar image in the scanning circle by adopting the mode of combining the scanning circle with the chromaticity bar, and perform image binarization after comparing the echo intensity corresponding to the pixel point with the echo intensity threshold value, thereby acquiring the suspected target area corresponding to the fish school, improving the judgment efficiency of the fish school, achieving the purpose of automatically searching and tracking the fish school, and then sending the fish school detection information to the fishing boat for fishing in real time, so as to save the fuel consumption of the fishing boat.
Drawings
Fig. 1 is a schematic flow chart of a full-automatic fish school detection method for an unmanned fish finder boat according to an embodiment of the present invention;
fig. 2 is another schematic flow chart of a fully automatic fish school detection method of an unmanned fish finder boat according to an embodiment;
fig. 3 is a schematic specific flow chart of a fully automatic fish school detection method for an unmanned fish finder boat according to an embodiment of the present invention;
fig. 4 is a block diagram of a first fully-automatic fish school detection system of an unmanned fish finder boat according to an embodiment of the present invention;
fig. 5 is a structural block diagram of a full-automatic fish school detection system of a second unmanned fish finding boat provided by the embodiment of the invention;
fig. 6 is a block diagram of a third fully-automatic fish school detection system of an unmanned fish finder boat according to an embodiment of the present invention;
fig. 7 is a block diagram of an internal structure of an unmanned fish finder boat according to an embodiment of the present invention;
fig. 8 is a display diagram of a real-time sonar image according to an embodiment of the present invention.
Detailed Description
For further understanding of the features and technical means of the present invention, as well as the specific objects and functions attained by the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description.
Fig. 1 is a schematic flow diagram of a full-automatic fish school detection method for an unmanned fish finder boat according to an embodiment of the present invention, and as shown in fig. 1, the full-automatic fish school detection method for the unmanned fish finder boat specifically includes the following steps:
step S110, collecting a real-time sonar image, and acquiring a scanning circle and a chromaticity bar in the real-time sonar image; the real-time sonar image is a sonar image displayed on a monitoring screen after the fish finder detects an underwater target in a preset range, a scanning circle is the maximum coverage range of the sonar image in the real-time sonar image, the scanning circle range can be selected manually, a chromaticity bar is a distribution map corresponding to the chromaticity value of each pixel point of the sonar image in the real-time sonar image, the chromaticity bar is displayed in the real-time sonar image of the fish finder, and the chromaticity bar is specifically arranged at the lower right corner of the real-time sonar image, as shown in fig. 8.
In one embodiment, the image acquisition mode of the real-time sonar image can adopt a video port expansion mode such as a VGA deconcentrator, an input signal of a display screen of the original fish finder equipment is copied to an industrial personal computer, and the industrial personal computer adopts an image acquisition card to perform analog-to-digital conversion, so that the display function of the original fish finder equipment is kept, and image distortion and color difference caused by difference of different display equipment can be avoided.
Step S120, obtaining the echo strength value corresponding to the pixel point according to the chromatic value of the pixel point in the scan circle, specifically, the method for obtaining the echo strength value corresponding to the pixel point according to the chromatic value of the pixel point in the scan circle includes:
step S121, obtaining a chromatic value c of a first pixel point in a scanning circle;
step S122, acquiring the position of the chromatic value c of the first pixel point on the chromatic strip;
step S123, calculating an echo intensity f (c) corresponding to the first pixel point with a chromatic value c, wherein,
xc is an abscissa value of a position where the chromaticity value c of the first pixel point appears on the chromaticity bar, xl is an abscissa value of a left edge of the chromaticity bar, and xr is an abscissa value of a right edge of the chromaticity bar.
The system comprises a screen, a chromaticity bar, a monitor screen, a coordinate system, a display screen and a display screen, wherein the coordinate system of the chromaticity bar is a rectangular coordinate system of the monitor screen, the origin of the coordinate system is at the lower left corner of the screen, the positive direction of the x axis of the coordinate system faces to the right, and the direction of the y axis of the coordinate system faces to the upper side; the method for obtaining the abscissa value xc of the position of the chromatic value c of the first pixel point on the chromatic strip comprises the following steps:
acquiring color component values Rc, gc and Bc corresponding to the chromatic value c of the first pixel point;
sequentially searching pixel points in the chroma strip area from left to right, and finding out second pixel points corresponding to chroma values of the color component values of Rc, gc and Bc respectively;
and acquiring an abscissa value xc of the second pixel point in the chromaticity bar area according to the coordinate system of the chromaticity bar.
By the method, the chromatic values corresponding to the pixel points in the scanning circle can be converted into the corresponding echo intensity values in the range of 0-1, so that the echo intensity of the pixel points in the scanning circle can be judged, and the subsequent fish school detection is facilitated.
S130, acquiring a binary image corresponding to the real-time sonar image; in a scanning circle of the real-time sonar image, a pixel point corresponding to the echo intensity value which is greater than or equal to the echo intensity threshold value is a suspected target point, the pixel value of the suspected target point is set to be 1, the pixel value of the pixel point corresponding to the echo intensity value which is less than the echo intensity threshold value is set to be 0, and a binary image corresponding to the real-time sonar image in the scanning circle is obtained.
And step S140, merging the suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain a suspected target region P.
Step S150, calculating an area Sp of each suspected target area, wherein,
r i ＝D/L*K，r i the method is characterized in that the method is a normalized distance from any suspected target point i in a suspected target area P to the circle center o of a scanning circle, D is the pixel length of a line segment io in a real-time sonar image, L is the pixel length of the outer diameter of the scanning circle, K is the radius of a detection scanning range of a fish finder, and the pixel length is the number of pixels in unit length.
Step S160, judging whether the area Sp of the suspected target area is within the preset area,if yes, the suspected target area is judged as a fish school; if the area Sp of the suspected target area is larger than the maximum value S1 of the preset area, the suspected target area is judged as external noise; if the area Sp of the suspected target area is smaller than the minimum value S2 of the preset area, judging the suspected target area as the water bottom; specifically, S1 may take the value 0.1K 2 And S2 can be 10 square meters, the preset area represents the size of a horizontal projection area of the fish school to be fished on the real-time sonar image, and the maximum value and the minimum value of the preset area can be adjusted according to the fish condition of the unmanned fish finding boat in the working sea area.
Fig. 2 is another schematic flow chart of the fully automatic fish school detection method for the unmanned fish finder boat according to the embodiment of the present invention, and as shown in fig. 2, the step S160 of determining whether the area Sp of the suspected target area is within the preset area further includes:
step S170, acquiring an included angle a between a line segment oT and a y-axis direction in a real-time sonar image and an actual length d corresponding to the line segment oT according to a geometric gravity center T of a suspected target area, wherein the actual length d corresponding to the line segment oT is calculated by firstly acquiring the pixel length L of the line segment oT, and combining the pixel length L of the scanning circle outer diameter and the radius K of a fish finder detection scanning range to know that d = L/L K; the geometric barycenter T of the suspected target area has the coordinate of (x) T ，y T )，
N is the number of pixels in the suspected target area, x i An abscissa value, y, corresponding to the ith pixel point in the suspected target area i And the longitudinal coordinate value corresponding to the ith pixel point in the suspected target area.
And step S180, inputting the included angle a serving as a fish school azimuth angle and the actual length d corresponding to the line segment oT serving as a distance from the fish school to a control system of the unmanned fish finding boat, and using the included angle a as a target position of the next movement of the unmanned fish finding boat, so as to control the unmanned fish finding boat to track the fish school.
The boat speed V of the unmanned fish exploring boat is not more than d, the heading alpha of the unmanned fish exploring boat is not more than a, and a first-order linear control is taken as an example: suppose that the ship speed of the unmanned fish-finding boat is V 0 Course of direction alpha 0 And if the distance between the tail of the unmanned fish finding boat and the fish school is 100 meters, the next navigational speed V of the unmanned fish finding boat is determined 1 And heading alpha 1 It should be:
the output time interval of two adjacent frames of real-time sonar images dt, m and n are adjustable smoothing coefficients larger than 0, the smaller the value of the adjustable smoothing coefficients is, the more stable the running track of the unmanned fish finder boat is, but the dynamic tracking performance is low; the larger the value is, the higher the tracking precision of the unmanned fish finder boat is, but the more the running track is vibrated.
In one embodiment, before the step S170 of acquiring the angle a between the line segment oT and the y-axis direction and the actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric barycenter T of the suspected target area, the method further includes:
and step S190, calculating a distance area weighting index theta of each fish school, and selecting the corresponding fish school with the largest distance area weighting index theta value for tracking, wherein the distance area weighting index theta = Sp/d.
When a plurality of candidate fish schools exist, the area Sp of the suspected target area is within the preset area, the appropriate fish schools are selected for tracking according to the maximum distance area weighting index theta, manual selection is not needed, and the efficiency of tracking the fish schools by the unmanned fish finding boat is improved.
Fig. 3 is a schematic specific flow chart of a full-automatic fish school detection method for an unmanned fish finding boat according to an embodiment of the present invention, and in order to further clarify the technical solution of the present invention, a preferred embodiment is further described below.
Step S110, collecting a real-time sonar image, and acquiring a scanning circle and a chromaticity bar in the real-time sonar image;
step S120, obtaining the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scanning circle;
s130, acquiring a binary image corresponding to the real-time sonar image; in a scanning circle of the real-time sonar image, a pixel point corresponding to the echo intensity value which is greater than or equal to the echo intensity threshold value is a suspected target point, the pixel value of the suspected target point is set to be 1, the pixel value of the pixel point corresponding to the echo intensity value which is less than the echo intensity threshold value is set to be 0, and a binary image corresponding to the real-time sonar image in the scanning circle is obtained;
step S140, merging the suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain a suspected target region P;
step S150, calculating the area Sp of each suspected target area;
step S160, judging whether the area Sp of the suspected target area is within a preset area; if yes, judging the suspected target area as a fish school;
step S190, calculating a distance area weighting index theta of each fish school, and selecting the corresponding fish school with the largest distance area weighting index theta value for tracking, wherein the distance area weighting index theta = Sp/d;
step S170, acquiring an included angle a between a line segment oT and the y-axis direction and an actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric gravity center T of the suspected target area, wherein the coordinate of the geometric gravity center T of the suspected target area is (x) T ，y T )，
And S180, inputting the included angle a serving as a fish school azimuth angle and the actual length d corresponding to the line segment oT serving as a distance from the fish school to a control system of the unmanned fish finding boat, namely inputting fish school detection information to the control system of the unmanned fish finding boat serving as a target position of the next movement of the unmanned fish finding boat, and controlling the unmanned fish finding boat to track the fish school.
The fully-automatic fish school detection method for the unmanned fish finding boat provided by the embodiment adopts a mode of combining a scanning circle with a chrominance bar, pixel points of a real-time sonar image in the scanning circle acquire echo intensities corresponding to chrominance values of the pixel points, image binarization is performed after comparison is performed according to the echo intensities corresponding to the pixel points and echo intensity threshold values, and therefore suspected target areas corresponding to fish schools are acquired, the judgment efficiency of the fish schools is improved, the purpose of automatically searching and tracking the fish schools is achieved, then fish school detection information is sent to a fishing boat in real time for fishing, and fuel consumption of the fishing boat is saved.
Fig. 4 is a block diagram of a first fully-automatic fish school detection system for an unmanned fish finding boat according to an embodiment of the present invention, and as shown in fig. 4, the fully-automatic fish school detection system for an unmanned fish finding boat corresponds to the fully-automatic fish school detection method for an unmanned fish finding boat, and the present invention further provides a fully-automatic fish school detection system for an unmanned fish finding boat, wherein the fully-automatic fish school detection system for an unmanned fish finding boat comprises a module for executing the fully-automatic fish school detection method for an unmanned fish finding boat, and the system can be configured at a terminal such as a computer device.
Specifically, as shown in fig. 4, the fully automatic fish school detection system of the unmanned fish finder boat includes an acquisition module 110, an intensity acquisition module 120, a binarization module 130, a suspected area acquisition module 140, and a determination module 150.
The acquisition module 110 is used for acquiring a real-time sonar image and acquiring a scanning circle and a chromaticity bar in the real-time sonar image;
the intensity obtaining module 120 is configured to obtain, according to a chromatic value of a pixel point in the scan circle, an echo intensity value corresponding to the pixel point;
a binarization module 130, configured to obtain a binarization image corresponding to the real-time sonar image;
a suspected region obtaining module 140, configured to merge suspected target points whose adjacent pixel values are 1 in the binarized image through a region growing algorithm to obtain suspected target regions P, and calculate an area Sp of each suspected target region;
the determining module 150 is configured to determine whether the area Sp of the suspected target area is within a preset area.
In one embodiment, the intensity obtaining module 120 is specifically configured to:
step S121, obtaining a chromatic value c of a first pixel point in a scanning circle;
step S122, acquiring the position of the chromatic value c of the first pixel point on the chromatic bar;
step S123, calculating an echo intensity f (c) corresponding to the first pixel point with a chromatic value c, wherein,
xc is an abscissa value of a position where the chromaticity value c of the first pixel point appears on the chromaticity bar, xl is an abscissa value of a left edge of the chromaticity bar, and xr is an abscissa value of a right edge of the chromaticity bar.
Fig. 5 is a block diagram of a second fully-automatic fish school detection system of an unmanned fish finder boat according to an embodiment of the present invention. As shown in fig. 5, the fully-automatic fish school detection system of the unmanned fish finder boat provided in this embodiment is added with an included angle length obtaining module 150 and an information output module 160 on the basis of the fully-automatic fish school detection system of the unmanned fish finder boat.
And an included angle length obtaining module 150, configured to obtain, according to the geometric center of gravity T of the suspected target area, an included angle a between the line segment oT and the y-axis direction in the real-time sonar image and an actual length d corresponding to the line segment oT.
And the information output module 160 is configured to input the included angle a as a fish school azimuth angle and the actual length d corresponding to the line segment oT as a distance from the fish school to a control system of the unmanned fish finder boat.
Fig. 6 is a structural block diagram of a full-automatic fish school detection system of a third unmanned fish finder boat provided in the embodiment of the present invention. As shown in fig. 6, the fully-automatic fish school detection system of the unmanned fish finding boat provided in this embodiment is additionally provided with a fish school selection module 170 on the basis of the fully-automatic fish school detection system of the unmanned fish finding boat, where the fish school selection module is configured to calculate a distance area weighting index θ of each fish school, and select a corresponding fish school with the largest distance area weighting index θ value for tracking.
The fully-automatic fish school detection system of the unmanned fish finding boat provided by the embodiment of the invention obtains the echo intensity corresponding to the chromatic value of the pixel point of the real-time sonar image in the scanning circle by combining the scanning circle with the chrominance bar, and carries out image binarization after comparing the echo intensity corresponding to the pixel point with the echo intensity threshold value, thereby obtaining the suspected target area corresponding to the fish school, improving the judgment efficiency of the fish school, achieving the purpose of automatically searching and tracking the fish school, and then sending the fish school detection information to the fishing boat for fishing in real time so as to save the fuel consumption of the fishing boat.
It should be noted that, as can be clearly understood by those skilled in the art, the detailed implementation process of the fully-automatic fish school detection system and each module of the unmanned fish finder boat may refer to the corresponding description in the foregoing method embodiment, and is not described herein again for convenience and conciseness of description.
Fig. 7 is a block diagram of an internal structure of an unmanned fish finder boat according to an embodiment of the present invention, and as shown in fig. 7, the unmanned fish finder boat according to the present invention includes a memory, a processor, and a network interface connected via a system bus, and connected via the system bus; the processor is used for providing calculation and control capacity to support the operation of the whole unmanned fish finding boat, and the processor realizes the full-automatic fish school detection method of the unmanned fish finding boat and sends fish school detection information to the fishing boat in a wireless communication mode when executing the computer program, wherein the fish school detection information is the relative position information of a fish school and the unmanned fish finding boat, and specifically, the relative position information of the fish school and the unmanned fish finding boat comprises an included angle a as an azimuth angle of the fish school relative to the unmanned fish finding boat and an actual length d corresponding to a line segment oT as a distance between the unmanned fish finding boat and the fish school.
The memory may include a non-volatile storage medium storing an operating system and an internal memory, and may further store a computer program, which when executed by the processor, may cause the processor to implement the fully automatic fish school detection method for the unmanned fish finder boat.
The internal memory can also store a computer program, and when the computer program is executed by the processor, the processor can execute the full-automatic fish school detection method of the unmanned fish finding boat. The network interface is for network communication with the parent vessel. It will be understood by those skilled in the art that the configuration shown in figure 7 is a block diagram of only a portion of the configuration associated with the present application and is not intended to limit the application of the present application to other unmanned fish craft, and a particular unmanned fish craft may include more or fewer components than shown, or some components may be combined, or have a different arrangement of components.
In one embodiment, the fully automatic fish school detection method of the unmanned fish finder boat provided by the present application can be implemented as a computer program, and the computer program can be run on the unmanned fish finder boat as shown in fig. 7. The memory of the unmanned fish finder boat may store various program modules constituting the fully-automatic fish school detection system of the unmanned fish finder boat, such as the acquisition module 110, the intensity acquisition module 120, the binarization module 130, the suspected region acquisition module 140, and the determination module 150 shown in fig. 4. The program modules constitute computer programs that cause the processor to execute the steps of the fully automatic fish school detection system of the unmanned fish finding boat in the various embodiments of the present application described in the present specification. For example, the unmanned fish finder boat shown in fig. 7 can acquire a real-time sonar image through the acquisition module 110 in the fully-automatic fish school detection system of the unmanned fish finder boat shown in fig. 4, so as to acquire a scanning circle and a chromaticity bar in the real-time sonar image; the intensity obtaining module 120 obtains the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scanning circle; the binarization module 130 acquires a binarization image corresponding to the real-time sonar image; the suspected region obtaining module 140 merges suspected target points with adjacent pixel values of 1 in the binarized image through a region growing algorithm to obtain suspected target regions P and calculates the area Sp of each suspected target region; the determining module 150 determines whether the area Sp of the suspected target area is within a preset area.
In an embodiment, it is presented an unmanned fish finding boat comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of: step S110, acquiring a real-time sonar image, and acquiring a scanning circle and a chromaticity bar in the real-time sonar image; step S120, obtaining the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scanning circle; s130, acquiring a binary image corresponding to the real-time sonar image; in a scanning circle of the real-time sonar image, pixel points corresponding to the echo intensity values which are greater than or equal to the echo intensity threshold value are suspected target points, the pixel values of the suspected target points are set to be 1, the pixel values of the pixel points corresponding to the echo intensity values which are less than the echo intensity threshold value are set to be 0, and a corresponding binary image of the real-time sonar image in the scanning circle is obtained; step S140, merging the suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain a suspected target region P; step S150, calculating the area Sp of each suspected target area; step S160, judging whether the area Sp of the suspected target area is within a preset area; if yes, the suspected target area is judged as a fish school.
In an embodiment, when the processor implements the step S120 of obtaining the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scan circle, the following steps are specifically implemented: step S121, obtaining a chromatic value c of a first pixel point in a scanning circle; step S122, acquiring the position of the chromatic value c of the first pixel point on the chromatic bar; step S123, calculating an echo intensity f (c) corresponding to the first pixel point with a chroma value c, wherein,
xc is an abscissa value of a position of a chromatic value c of the first pixel point on the chromatic strip, xl is an abscissa value of a left edge of the chromatic strip, and xr is an abscissa value of a right edge of the chromatic strip.
In one embodiment, after the processor performs the step S160 and determines whether the area Sp of the suspected target area is within a preset area, the processor specifically performs the following steps: step S170, acquiring an included angle a between a line segment oT and the y-axis direction and an actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric gravity center T of a suspected target area, wherein the suspected target area is severalThe coordinate of which center of gravity T is (x) T ，y T )，
And S180, inputting the included angle a serving as a fish school azimuth angle and the actual length d corresponding to the line segment oT serving as a distance from the fish school to a control system of the unmanned fish finder boat, and using the included angle a as a target position of the unmanned fish finder boat for next movement, so that the unmanned fish finder boat is controlled to track the fish school.
In one embodiment, before the step S170 of acquiring the angle a between the line segment oT and the y-axis direction and the actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric center of gravity T of the suspected target area, the processor specifically executes the following steps: and step S190, calculating a distance area weighting index theta of each fish school, and selecting the corresponding fish school with the largest distance area weighting index theta value for tracking, wherein the distance area weighting index theta = Sp/d.
It should be understood that in the embodiments of the present Application, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions. The program instructions, when executed by the processor, cause the processor to perform the steps of: step S110, acquiring a real-time sonar image, and acquiring a scanning circle and a chromaticity bar in the real-time sonar image; step S120, obtaining the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scanning circle; s130, acquiring a binary image corresponding to the real-time sonar image; in a scanning circle of the real-time sonar image, a pixel point corresponding to the echo intensity value which is greater than or equal to the echo intensity threshold value is a suspected target point, the pixel value of the suspected target point is set to be 1, the pixel value of the pixel point corresponding to the echo intensity value which is less than the echo intensity threshold value is set to be 0, and a binary image corresponding to the real-time sonar image in the scanning circle is obtained; step S140, merging suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain a suspected target region P; step S150, calculating the area Sp of each suspected target area; step S160, judging whether the area Sp of the suspected target area is within a preset area; if yes, the suspected target area is judged as a fish school.
In one embodiment, the processor executes the program instructions to realize the fully automatic fish school detection method of the unmanned fish finder boat, and further realizes the following steps: acquiring an included angle a between a line segment oT and the y-axis direction and an actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric center of gravity T of the suspected target area, wherein the coordinate of the geometric center of gravity T of the suspected target area is (x) T ，y T )，
And step S180, inputting the included angle a serving as a fish school azimuth angle and the actual length d corresponding to the line segment oT serving as a distance from the fish school to a control system of the unmanned fish finding boat, and using the included angle a as a target position of the next movement of the unmanned fish finding boat, so as to control the unmanned fish finding boat to track the fish school.
In one embodiment, the processor executes the program instructions to realize the fully automatic fish school detection method of the unmanned fish finder boat, and further realizes the following steps: and step S190, calculating a distance area weighting index theta of each fish school, and selecting the corresponding fish school with the largest distance area weighting index theta value for tracking, wherein the distance area weighting index theta = Sp/d.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
In summary, the unmanned fish finding boat, the system and the storage medium of the invention adopt a mode of combining the scanning circle with the chromaticity bar to obtain the echo intensity corresponding to the chromaticity value of the pixel point of the real-time sonar image in the scanning circle, and perform image binarization after comparing the echo intensity corresponding to the pixel point with the echo intensity threshold value, thereby obtaining the suspected target area corresponding to the fish school, improving the judgment efficiency of the fish school, achieving the purpose of automatically searching and tracking the fish school, and then sending the fish school detection information to the fishing boat for fishing in real time, so as to save the fuel consumption of the fishing boat.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing an unmanned fish boat (which may be a personal computer, a terminal, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is specific and detailed, but not to be construed as limiting the scope of the present invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present invention should be subject to the appended claims.
Claims (10)
1. A full-automatic fish school detection method for an unmanned fish finding boat is characterized by comprising the following steps:
acquiring a real-time sonar image, and acquiring a scanning circle and a chromaticity bar in the real-time sonar image;
obtaining an echo intensity value corresponding to a pixel point according to the chromatic value of the pixel point in the scanning circle;
acquiring a binary image corresponding to the real-time sonar image; in a scanning circle of the real-time sonar image, pixel points corresponding to the echo intensity values which are greater than or equal to the echo intensity threshold value are suspected target points, the pixel values of the suspected target points are set to be 1, the pixel values of the pixel points corresponding to the echo intensity values which are less than the echo intensity threshold value are set to be 0, and a corresponding binary image of the real-time sonar image in the scanning circle is obtained;
merging suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain a suspected target region P;
calculating the area Sp of each suspected target area;
judging whether the area Sp of the suspected target area is within a preset area; if yes, the suspected target area is judged as a fish school.
2. The fully-automatic fish school detection method for the unmanned fish finder boat as claimed in claim 1, wherein the method for obtaining the echo intensity value corresponding to a pixel point according to the chromatic value of the pixel point in the scanning circle comprises:
obtaining a chromatic value c of a first pixel point in a scanning circle;
acquiring the position of a chromatic value c of the first pixel point on a chromatic bar;
calculating the echo intensity f (c) corresponding to the first pixel point with a chrominance value c, wherein,
xc is an abscissa value of a position of a chromatic value c of the first pixel point on the chromatic strip, xl is an abscissa value of a left edge of the chromatic strip, and xr is an abscissa value of a right edge of the chromatic strip.
3. The fully-automatic fish school detection method for the unmanned fish finding boat as claimed in claim 2, wherein the method for obtaining the abscissa value of the position of the chromatic value c of the first pixel point on the chromatic strip is as follows:
acquiring color component values Rc, gc and Bc corresponding to the chromatic value c of the first pixel point;
sequentially searching pixel points in the chroma strip area from left to right, and finding out second pixel points corresponding to chroma values of the color component values of Rc, gc and Bc respectively;
and acquiring an abscissa value xc of the second pixel point in the chromaticity bar area according to the coordinate system of the chromaticity bar.
4. The fully automatic fish school detection method for unmanned fish finding boat as claimed in claim 1, wherein said determining whether the area Sp of the suspected target area is within the preset area further comprises:
acquiring an included angle a between a line segment oT and the y-axis direction and an actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric center of gravity T of the suspected target area, wherein the coordinate of the geometric center of gravity T of the suspected target area is (x) T ，y T )，
N is the number of pixels in the suspected target area, x i An abscissa value, y, corresponding to the ith pixel point in the suspected target area i A longitudinal coordinate value corresponding to the ith pixel point in the suspected target area;
and inputting the included angle a serving as a fish school azimuth angle and the actual length d corresponding to the line segment oT serving as the distance from the fish school to a control system of the unmanned fish finding boat.
5. The fully-automatic fish school detection method for the unmanned fish finding boat according to claim 1, wherein before the obtaining of the included angle a between the line segment oT and the y-axis direction and the actual length d corresponding to the line segment oT in the real-time sonar image according to the geometric center of gravity T of the suspected target area, the method further comprises:
and calculating a distance area weighting index theta of each fish school, and selecting the corresponding fish school with the largest distance area weighting index theta value for tracking, wherein the distance area weighting index theta = Sp/d.
6. The utility model provides a full-automatic shoal detecting system of unmanned fish finding boat which characterized in that includes:
the acquisition module is used for acquiring a real-time sonar image and acquiring a scanning circle and a chromaticity bar in the real-time sonar image;
the intensity obtaining module is used for obtaining the echo intensity value corresponding to the pixel point according to the chromatic value of the pixel point in the scanning circle;
the binarization module is used for acquiring a binarization image corresponding to the real-time sonar image;
the suspected region acquisition module is used for merging suspected target points with adjacent pixel values of 1 in the binary image through a region growing algorithm to obtain suspected target regions P and calculating the area Sp of each suspected target region;
and the judging module is used for judging whether the area Sp of the suspected target area is within a preset area.
7. The fully-automatic fish school detection system of the unmanned fish finding boat according to claim 6, characterized by further comprising an included angle length acquisition module, for acquiring an included angle a between a line segment oT and a y-axis direction in a real-time sonar image and an actual length d corresponding to the line segment oT according to a geometric center of gravity T of a suspected target area; and the information output module is used for inputting the included angle a as a fish school azimuth angle and the actual length d corresponding to the line segment oT as a distance from the fish school to the control system of the unmanned fish finding boat.
8. The fully-automatic fish school detection system of the unmanned fish finding boat of claim 7, further comprising a fish school selection module for calculating a distance area weighting index θ of each fish school, and selecting the corresponding fish school with the largest distance area weighting index θ value for tracking.
9. An unmanned fish finding boat which is characterized in that: the unmanned fish finding boat comprises a memory and a processor, wherein the memory is stored with a computer program, and the processor realizes the full-automatic fish school detection method of the unmanned fish finding boat according to any one of claims 1-5 when executing the computer program and sends the fish school detection information to a fishing boat in a wireless communication mode.
10. A storage medium, characterized by: the storage medium stores a computer program comprising program instructions that, when executed, implement the fully automatic shoal detection method of an unmanned fish finder boat as claimed in any one of claims 1-5.
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 CN110046619A (en) | 2019-07-23 |
| CN110046619B true 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) |
Families Citing this family (6)
| 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 |
| 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 |
| CN114076949B (en) * | 2022-01-07 | 2022-05-20 | 视丰达科技（深圳）有限公司 | Fish finder data identification processing method and device |
| CN114581421A (en) * | 2022-03-10 | 2022-06-03 | 北京市生态环境保护科学研究院 | River fish community real-time monitoring method and system |
| 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 |
| 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 |
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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110046619A (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046619B (en) | Full-automatic fish school detection method and system for unmanned fish finding boat, unmanned fish finding boat and storage medium | |
| EP3505951A1 (en) | A target object detecting device, a method of detecting a target object and a computer readable medium | |
| CN111476120B (en) | Unmanned aerial vehicle intelligent ship water gauge identification method and device | |
| CN107219529A (en) | The acquisition methods and system of a kind of high-precision seafloor topography figure | |
| US11473914B2 (en) | Navigation device and method of creating route | |
| CN110619328A (en) | Intelligent ship water gauge reading identification method based on image processing and deep learning | |
| US20210396525A1 (en) | Ship target object detection system, method of detecting ship target object and reliability estimating device | |
| CN115019187B (en) | Detection method, device, equipment and medium for SAR image ship target | |
| US20170261608A1 (en) | Tracking processor and method of tracking processing | |
| CN112526490A (en) | Underwater small target sonar detection system and method based on computer vision | |
| CN117036993A (en) | Ship water gauge remote measurement method based on unmanned aerial vehicle | |
| CN112882037B (en) | Side-scan sonar sea bottom line detection method and device | |
| CN110069987B (en) | Single-stage ship detection algorithm and device based on improved VGG network | |
| CN116596163B (en) | Image detection-based white croaker resource distribution prediction system and method | |
| Shih et al. | An adaptive bottom tracking algorithm for side-scan sonar seabed mapping | |
| US11221409B2 (en) | Underwater detection apparatus and underwater detection method | |
| CN113837924A (en) | Water bank line detection method based on unmanned ship sensing system | |
| US11119208B2 (en) | Echo image generating device | |
| CN116990824A (en) | Graphic geographic information coding and fusion method of cluster side scanning system | |
| CN106991682B (en) | Automatic port cargo ship extraction method and device | |
| CN115113630B (en) | Bridge passing method and device for unmanned ship, computer equipment and storage medium | |
| CN116597447A (en) | Unmanned aerial vehicle image recognition-based ship berthing draft detection and early warning method | |
| CN115082811A (en) | Method for identifying and measuring distance of marine navigation ship according to image data | |
| CN115248436A (en) | Imaging sonar-based fish resource assessment method | |
| CN114879180A (en) | Seamless situation perception method for real-time fusion of unmanned ship-borne multi-element multi-scale radar |
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 |