CN113963145A - Fish growth state identification device and method with vision correction function - Google Patents
Fish growth state identification device and method with vision correction function Download PDFInfo
- Publication number
- CN113963145A CN113963145A CN202111353708.1A CN202111353708A CN113963145A CN 113963145 A CN113963145 A CN 113963145A CN 202111353708 A CN202111353708 A CN 202111353708A CN 113963145 A CN113963145 A CN 113963145A
- Authority
- CN
- China
- Prior art keywords
- module
- growth state
- control module
- fish growth
- electric push
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention provides a fish growth state recognition device with a vision correction function and a fish growth state recognition method, wherein the fish growth state recognition device comprises a control module and a device main body, the device main body comprises a fixing plate, an electric push rod, a purse net and an attitude sensor module, a camera module is installed on the fixing plate, the camera module and the attitude sensor module are in communication connection with the control module, the control module drives the electric push rod through real-time attitude information collected by the attitude sensor module, adjusts the real-time attitude of the device main body through controlling the electric push rod, performs video collection through the camera module, performs image enhancement processing on collected images, and then recognizes the fish growth state. The fish growth state identification device and method with the vision correction function are high in identification precision and simple to operate.
Description
Technical Field
The invention relates to the technical field of fish growth state identification, in particular to a fish growth state identification device with a vision correction function and a method.
Background
With the continuous development and maturity of the internet of things technology, the requirements for intellectualization and automation of the underwater recognition device are higher and higher, and the underwater recognition device has the advantages of relatively low cost, no casualty risk, strong viability, good maneuvering performance, convenient use and the like, so that the underwater recognition device is widely applied in military and civil fields, wherein fish recognition is one of main application markets.
According to statistical analysis, the demand of the identification market of the growth state of fishes in China is large in recent years, and the application prospect is good, but the related application of the identification of the growth state of fishes at the present stage is still in the primary stage. Especially, the existing underwater recognition device generally records video through a camera, only has a camera shooting function, does not have a vision correction function, is difficult to control the real-time posture of the recognition device, and is inaccurate in fish growth state recognition and low in efficiency. And the underwater environment is complex, and the illumination condition is limited, so that the image collected by the camera is blurred. How to improve the identification accuracy, efficiency and maneuverability of the fish growth state identification device is a technical focus and difficulty to be solved by the technical personnel in the field.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a fish growth state identification device and method with a vision correction function, which have high identification precision and simple operation.
In order to solve the problems, the technical scheme of the invention is as follows:
the utility model provides a fish growth state recognition device with vision correction function, the device includes control module and device main part, the device main part includes fixed plate, electric putter, purse seine and attitude sensor module, installs the module of making a video recording on the fixed plate, module of making a video recording and attitude sensor module with control module communication connection, control module passes through the real-time attitude information that attitude sensor module gathered is right electric putter drives, through control electric putter adjusts the real-time gesture of device main part, and rethread camera module carries out video acquisition to carry out fish growth state's discernment after being image enhancement to the image of gathering.
Optionally, the electric push rod comprises four electric push rods parallel to each other, the four electric push rods are connected with the inner side of the bottom purse net, and the electric push rods are in communication connection with the control module through an electric push rod driving module.
Optionally, an LED module is further mounted on the fixing plate, and the LED module is in communication connection with the control module through an LED driving module.
Optionally, the camera module is communicatively connected to an ethernet interface of the control module.
Optionally, a bait box is arranged in the center of the purse net, and a reference point is arranged on the bait box and is a highly reflective material circle for estimating the size of the fish.
Optionally, the device body and the control module are connected in communication through a cable.
Optionally, a lead weight is hung below the device main body, so that the device main body can sink in water and keep stable.
Further, the invention also provides a fish growth state identification method, which comprises the following steps:
after receiving the command of the upper computer, the control module controls the attitude sensor module to acquire the attitude;
judging whether the purse net is horizontal, if so, carrying out video acquisition, otherwise, sending an adjusting signal to the electric push rod driving module by the control module according to the real-time posture, and controlling and adjusting the electric push rod to keep the purse net horizontal;
video acquisition is carried out through a camera module, and image enhancement processing is carried out on the acquired image;
judging whether the processed image is clear or not, and if the image is clear, evaluating the size of the fish in the image according to the reference point;
if the image is not clear, the control module sends a signal to the LED driving module to control and adjust the brightness of the LED device, and the camera module continues to collect the video.
Optionally, the step of controlling the attitude sensor module to perform attitude acquisition after the control module receives the command from the upper computer specifically includes: the attitude sensor measures and calculates the real-time attitude of the purse net, obtains the horizontal deviation angle and sends the horizontal deviation angle to the control module.
Optionally, the step of performing video acquisition through the camera module and performing image enhancement processing on the acquired image specifically includes: and (4) counting the gray level histogram of each channel, calculating and adjusting an upper threshold value and a lower threshold value according to the histogram, setting the pixel to be 0 when the pixel is lower than the lower threshold value, setting the pixel to be 255 when the pixel is higher than the upper threshold value, and converting the rest pixel values into new pixel values through linear transformation to obtain an enhanced image.
Compared with the prior art, the fish growth state recognition device and method with the vision correction function, provided by the invention, have the advantages that the recognition precision is high, the operation is simple, the posture can be adjusted in real time, the image enhancement is carried out, the stability of the device is improved, and the recognition efficiency of the fish growth state is ensured.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic structural diagram of a fish growth status recognition apparatus with a vision correction function according to an embodiment of the present invention;
FIG. 2 is a control diagram of a control module according to an embodiment of the present invention;
fig. 3 is a flowchart of a fish growth status identification method according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
Specifically, fig. 1 is a schematic structural view of a fish growth state recognition device with a vision correction function according to an embodiment of the present invention, and fig. 2 is a schematic control view of a control module according to an embodiment of the present invention, as shown in fig. 1 and fig. 2, the device includes a control module 1, a device body, and a cable 2 connecting the control module 1 and the device body, and a fixing plate 3, a camera module 4, an LED module 6, an electric push rod 7, a purse net 11, a bait box 12, an attitude sensor module 13, and a lead weight 14 are mounted on the device body.
The attitude sensor module 13 is in communication connection with the control module 1, in this embodiment, the control module 1 adopts a Jetson NANO controller, and the attitude sensor module 13 adopts a WTGAHRS1 ten-axis inertial navigation tilt sensor. The center of the purse net 11 is provided with a bait box 12, the bait box 12 is covered with a reference point, and the reference point is a highly reflective material circle with the diameter of 5cm and is used for estimating the size of fishes nearby. The lead weight 14 is dropped below the device main body, so that the device can sink conveniently and keep relatively stable.
The LED module 6 comprises two annular LED devices which are in communication connection with the control module 1 through an LED driving module 5; the camera module 4 comprises a camera which is positioned at the right center of the fixing plate 3; the camera module 4 is in communication connection with the control module 1, performs image acquisition, and performs vision enhancement algorithm processing, and in this embodiment, the camera module 4 is in communication connection with an ethernet interface of the control module 1.
The electric push rods 7 comprise four electric push rods which are parallel to each other, the four electric push rods are connected with the inner side of the purse net 11, and the four electric push rods are in communication connection with the control module 1 through the electric push rod driving module 8. The electric push rod driving module 8 controls the four electric push rods to keep the purse seine 11 horizontal, so that the device main body is kept stable and horizontal underwater.
Fig. 3 is a flowchart of a fish growth status identification method according to an embodiment of the present invention, and as shown in fig. 3, the method includes the following steps:
s1: after receiving the command of the upper computer, the control module controls the attitude sensor module to acquire the attitude;
specifically, the real-time attitude of the purse net is measured and calculated through the attitude sensor, and a horizontal deviation angle is obtained and sent to the control module;
s2: judging whether the purse net is horizontal, if so, carrying out video acquisition, otherwise, sending an adjusting signal to the electric push rod driving module by the control module according to the real-time posture, and controlling and adjusting the electric push rod to keep the purse net horizontal;
s3: video acquisition is carried out through a camera module, and image enhancement processing is carried out on the acquired image;
specifically, when a fish is identified, the electric push rod is driven to adjust the stretching, so that the purse net is more attached to the fish, and the video acquisition is facilitated; in addition, when the acquired image is subjected to image enhancement processing, the gray level histograms of all channels are counted, upper and lower threshold values are calculated and adjusted according to the histograms, the pixel is set to be 0 when the pixel is lower than the lower threshold value, and is set to be 255 when the pixel is higher than the upper threshold value, and the rest pixel values are converted into new pixel values through linear transformation to obtain the enhanced image.
S4: judging whether the processed image is clear or not, and if the image is clear, evaluating the size of the fish in the image according to the reference point;
specifically, if the image is clear, a three-dimensional coordinate system is established by referring to the purse seine, the acquired image is calculated, and the size of the fish in the image is evaluated according to the reference point.
S5: if the image is not clear, the control module sends a signal to the LED driving module to control and adjust the brightness of the LED device, and the camera module continues to collect the video.
Compared with the prior art, the fish growth state recognition device and method with the vision correction function, provided by the invention, have the advantages that the recognition precision is high, the operation is simple, the posture can be adjusted in real time, the image enhancement is carried out, the stability of the device is improved, and the recognition efficiency of the fish growth state is ensured.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. The utility model provides a fish growth state recognition device with vision correction function, a serial communication port, the device includes control module and device main part, the device main part includes fixed plate, electric putter, purse net and attitude sensor module, installs camera module on the fixed plate, camera module and attitude sensor module with control module communication connection, control module passes through the real-time attitude information that attitude sensor module gathered is right electric putter drives, through control electric putter adjusts the real-time gesture of device main part, and rethread camera module carries out video acquisition to do the discernment that carries out fish growth state after the image enhancement is handled to the image of gathering.
2. The fish growth state recognition device with vision correction function of claim 1, wherein the electric push rods comprise four electric push rods parallel to each other, the four electric push rods are connected with the inner side of the bottom purse net, and the electric push rods are in communication connection with the control module through an electric push rod driving module.
3. The fish growth state recognition device with the vision correction function according to claim 1, wherein an LED module is further mounted on the fixing plate, and the LED module is in communication connection with the control module through an LED driving module.
4. The fish growth status recognition device with vision correction function according to claim 1, wherein the camera module is communicatively connected to the ethernet interface of the control module.
5. The fish growth state recognition device with vision correction function of claim 1, wherein a bait box is arranged in the center of the purse net, and a reference point is arranged on the bait box, and the reference point is a highly reflective circle of material for estimating the size of the fish.
6. The fish growth state recognition device with the vision correction function according to claim 1, wherein the device body and the control module are connected in communication by a cable.
7. The fish growth state recognition device with vision correction function according to claim 1, wherein a lead weight is hung under the device body to facilitate sinking of the device body in water and to keep it stable.
8. A fish growth state identification method is characterized by comprising the following steps:
after receiving the command of the upper computer, the control module controls the attitude sensor module to acquire the attitude;
judging whether the purse net is horizontal, if so, carrying out video acquisition, otherwise, sending an adjusting signal to the electric push rod driving module by the control module according to the real-time posture, and controlling and adjusting the electric push rod to keep the purse net horizontal;
video acquisition is carried out through a camera module, and image enhancement processing is carried out on the acquired image;
judging whether the processed image is clear or not, and if the image is clear, evaluating the size of the fish in the image according to the reference point;
if the image is not clear, the control module sends a signal to the LED driving module to control and adjust the brightness of the LED device, and the camera module continues to collect the video.
9. The fish growth state identification method according to claim 8, wherein the step of controlling the attitude sensor module to perform attitude acquisition after the control module receives the command from the upper computer specifically comprises: the attitude sensor measures and calculates the real-time attitude of the purse net, obtains the horizontal deviation angle and sends the horizontal deviation angle to the control module.
10. The fish growth state identification method according to claim 8, wherein the step of performing video acquisition by a camera module and performing image enhancement processing on the acquired image specifically comprises: and (4) counting the gray level histogram of each channel, calculating and adjusting an upper threshold value and a lower threshold value according to the histogram, setting the pixel to be 0 when the pixel is lower than the lower threshold value, setting the pixel to be 255 when the pixel is higher than the upper threshold value, and converting the rest pixel values into new pixel values through linear transformation to obtain an enhanced image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111353708.1A CN113963145A (en) | 2021-11-16 | 2021-11-16 | Fish growth state identification device and method with vision correction function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111353708.1A CN113963145A (en) | 2021-11-16 | 2021-11-16 | Fish growth state identification device and method with vision correction function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113963145A true CN113963145A (en) | 2022-01-21 |
Family
ID=79470655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111353708.1A Pending CN113963145A (en) | 2021-11-16 | 2021-11-16 | Fish growth state identification device and method with vision correction function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113963145A (en) |
-
2021
- 2021-11-16 CN CN202111353708.1A patent/CN113963145A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107094683B (en) | Automatic feeding and water quality monitoring control system for aquaculture | |
CN104482860B (en) | Fish morphological parameters self-operated measuring unit and method | |
WO2022094854A1 (en) | Growth monitoring method for crops, and devices and storage medium | |
CN103529855B (en) | A kind of object recognition and detection device of rotary adjustable binocular vision and the application at agriculture fruit picking mechanical thereof | |
CN107392956B (en) | Crop root phenotype detection method and device | |
CN111460903B (en) | System and method for monitoring growth of field broccoli based on deep learning | |
CN110110797B (en) | Water surface target training set automatic acquisition method based on multi-sensor fusion | |
CN105447853A (en) | Flight device, flight control system and flight control method | |
CN112232978B (en) | Aquatic product length and weight detection method, terminal equipment and storage medium | |
CN109949231B (en) | Method and device for collecting and processing city management information | |
CN111640152A (en) | Fish growth monitoring method and system | |
CN109359577B (en) | System for detecting number of people under complex background based on machine learning | |
CN110796011A (en) | Rice ear recognition method, system, device and medium based on deep learning | |
CN115553132A (en) | Litchi recognition method based on visual algorithm and bionic litchi picking robot | |
CN114596448A (en) | Meat duck health management method and management system thereof | |
CN113484867A (en) | Imaging sonar-based fish school density detection method in closed space | |
CN204202563U (en) | Fish morphological parameters self-operated measuring unit | |
CN105678805A (en) | ARM platform-based aerial-photography target detection system | |
CN113963145A (en) | Fish growth state identification device and method with vision correction function | |
CN113284164A (en) | Shrimp swarm automatic counting method and device, electronic equipment and storage medium | |
CN113706512B (en) | Live pig weight measurement method based on deep learning and depth camera | |
CN113114766B (en) | Potted plant information detection method based on ZED camera | |
CN111678441B (en) | Underwater fish body measuring device and method based on deep learning | |
CN114022831A (en) | Binocular vision-based livestock body condition monitoring method and system | |
CN114782809A (en) | Method for detecting dynamic offset of key part of contact network |
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 |