A method for identifying and analyzing the growth process of barnacles based on image measurement

Abstract

The present application relates to the technical field of image recognition analysis, in particular to a method for recognizing and analyzing the growth process of barnacles based on image measurement; the method is realized based on an observation device and an image processing module, and comprises the following steps: setting the observation device to the sea area where barnacles grow, collecting image data of the growth of barnacles through the observation device, and performing image processing on the collected image data of the growth of barnacles through the image processing module; first, the image data of the growth of barnacles is subjected to image enhancement, and after the input RGB image is converted into a gray-scale image, an enhancement operation is performed. The present application optimizes the limitations of the existing method for monitoring the attachment process of barnacles, and simultaneously performs automatic recognition of barnacles and dynamic detection of the attachment process of barnacles, so that the attachment process of barnacles can be monitored and analyzed while the barnacles are recognized and counted, and the growth and attachment process of barnacles can be more intuitively obtained, the method for monitoring the attachment of barnacles is improved, and a long-term tracking observation and adhesion analysis research mechanism is established.

Description

Technical Field

[0001] This invention relates to the field of image recognition and analysis technology, specifically to a method for identifying and analyzing the growth process of barnacles based on image measurement. Background Technology

[0002] Barnacle attachment poses a serious threat to offshore engineering facilities and underwater sensors, causing problems such as distorted measurement data and reduced service life, thus reducing the effectiveness of port infrastructure health monitoring and resulting in huge economic losses.

[0003] Generally, to effectively control the impact of barnacle attachment on port monitoring equipment, it is necessary to analyze the attachment process and its characteristics in depth. Currently, static shallow-sea barnacle tests and dynamic hull coating tests are mainly used to monitor attachment. However, the above-mentioned observation equipment has some drawbacks. In the static shallow-sea barnacle test, the barnacle is placed in seawater and needs to be removed for observation at regular intervals, which can easily affect barnacle adhesion and is not conducive to understanding the actual attachment situation. It is also impossible to achieve real-time monitoring and continuous tracking of barnacle attachment.

[0004] Dynamic hull coating tests involve applying coatings to representative parts of a certain type of vessel and then sailing with it to evaluate the results. These tests are time-consuming, labor-intensive, and difficult. Furthermore, the coating is affected by various factors such as different sea areas, current speeds, salinity, and pH during the voyage, making it impossible to conduct single-factor variable analysis for a specific port.

[0005] Based on this, the present invention provides a method for identifying and analyzing the growth process of barnacles based on image measurement, in order to solve the above-mentioned technical problems. Summary of the Invention

[0006] The purpose of this invention is to provide a method for identifying and analyzing the growth process of barnacles based on image measurement, thereby solving the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: This invention proposes a method for identifying and analyzing the growth process of barnacles based on image measurement. The method is implemented based on an observation device and an image processing module, and includes the following steps: S1. Set up an observation device in the barnacle growing area, collect image data of barnacle growth through the observation device, and process the collected barnacle growth image data through the image processing module; S2. First, perform image enhancement on the barnacle growth image data. After converting the input RGB image to a grayscale image, perform the enhancement operation. S3. Perform adaptive median filtering and morphological opening operations sequentially on the enhanced grayscale image from step S2; S4. Perform edge detection and circle localization on the image processed in step S3; S5. After processing in step S3, the final step is to perform target segmentation and quantization of the barnacle growth image data.

[0008] Preferably, the observation device consists of an external frame and an underwater camera. The external frame is provided with several sets of support frames, each of which is equipped with a camera forearm bracket. The bottom of each camera forearm bracket is connected to one end of a camera upper arm bracket, and the other end of the camera upper arm bracket is installed on the external frame. The angle of the support frame is adjusted by an electric telescopic rod. Each camera forearm bracket is also equipped with a camera base, and each underwater camera is installed on the camera base. The top of the external frame above water is also provided with a solar panel, a battery, and a solar controller. The underwater camera is electrically connected to the solar panel and the battery to provide power to the underwater camera. Sensor frames are also provided on both sides of the external frame.

[0009] Preferably, the implementation steps of step S2 are as follows: S2.1. Histogram equalization: Expands the grayscale distribution range to improve overall contrast; S2.2. Piecewise grayscale transformation: Let the input grayscale value be x. When x is [50, 160], the output y is [0, 255] through nonlinear function mapping to enhance the grayscale difference in the barnacle edge region.

[0010] Preferably, the implementation steps of step S3 are as follows: S3.1. Adaptive Median Filtering: A median filter with an adaptive window size is used to filter the grayscale enhanced image, effectively removing noise and isolated noise points while preserving barnacle edge details. S3.2. Morphological opening operation: Use 33 cross-shaped structural elements to perform erosion and then expansion operations to eliminate interference objects smaller than the structural elements and smooth the edge contour of barnacles.

[0011] Preferably, the implementation steps of step S4 are as follows: S4.1. Canny edge detection: The Sobel operator is used to calculate the gradient magnitude and direction of the image in the x and y directions; then non-maximum suppression is performed to retain local maximum points along the gradient direction to refine the edges; S4.2. Hough Circle Detection: Apply Hough transform to perform circle detection on the edge image, limit the radius search range R [Rmin, Rmax] to improve detection accuracy, count the number of barnacles detected and mark the detected barnacles with red circles on the original image.

[0012] Preferably, the implementation steps of step S5 are as follows: S5.1. Otsu Adaptive Segmentation: The Otsu algorithm is used to automatically obtain the image segmentation threshold, binarize the image into the target barnacle and the background region, and separate the independent connected regions of the barnacle; S5.2. Area Calculation: Count the number of pixels N in the connected region, and combine the calibration relationship. 1 pixel corresponds to the actual area S0mm. Calculate the actual area of ​​the barnacle, as shown in equation (1): S=NS0(1).

[0013] Compared with the prior art, the beneficial effects of the present invention are: This invention optimizes the limitations of existing methods for monitoring the barnacle attachment process by simultaneously performing automatic barnacle identification and dynamic detection of the attachment process. This method can monitor and analyze the attachment process of barnacles while identifying and counting them, providing a more intuitive understanding of the growth and attachment process of barnacles, improving the barnacle attachment monitoring method, and establishing a long-term tracking observation and adhesion analysis research mechanism. Attached Figure Description

[0014] Figure 1 This is a front view of the observation device of the present invention; Figure 2 This is a side view of the observation device of the present invention; Figure 3 This is a top view of the observation device of the present invention.

[0015] Legend: 1. External frame; 2. Underwater camera; 3. Camera base; 4. Camera boom bracket; 5. Camera forearm bracket; 6. Support frame; 7. Sensor frame. Detailed Implementation

[0016] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 , Figure 2 and Figure 3 This invention proposes a method for identifying and analyzing the growth process of barnacles based on image measurement. The method is implemented based on an observation device and an image processing module. It should be noted that the observation device consists of an external frame 1 and an underwater camera 2. The external frame 1 is equipped with several sets of support frames 6, and each support frame 6 is equipped with a camera forearm bracket 5. The bottom of each camera forearm bracket 5 is connected to one end of a camera upper arm bracket 4, and the other end of the camera upper arm bracket 4 is installed on the external frame 1. The angle of the support frame 6 is adjusted by an electric telescopic rod. Each camera forearm bracket 5 is also equipped with a camera base 3, and each underwater camera 2 is installed on the camera base 3. The top of the external frame 1 above water is also equipped with a solar panel, a battery, and a solar controller. The underwater camera 2 is electrically connected to the solar panel and the battery to provide power to the underwater camera 2. Sensor frames 7 are also provided on both sides of the external frame 1.

[0018] Specifically: The observation device consists of an outer frame 1 and an underwater camera 2. Several sets of support frames 6 are set on the outer frame 1. Each support frame 6 is equipped with a camera forearm bracket 5. The bottom of the camera forearm bracket 5 is connected to one end of the camera upper arm bracket 4. The other end of the camera upper arm bracket 4 is installed on the outer frame 1. The angle of the support frame 6 is adjusted by an electric telescopic rod. Each camera forearm bracket 5 is also equipped with a camera base 3. Each underwater camera 2 is installed on the camera base 3. The top of the outer frame 1 above water is also equipped with a solar panel, a battery and a solar controller. The underwater camera 2 is electrically connected to the solar panel and the battery to provide power support for the underwater camera 2. It is made of 304 stainless steel, with a rectangular cross section, a side length of 30mm and a thickness of 2mm. The total length is 3180mm. The interior is divided into 9 equal-sized spaces by a 420mm long steel pipe. Each space is 420-320mm in size. Includes two camera boom brackets and support frames. Designed to support the camera, its structure consists of two rows of 970mm long support booms and a support frame at a 45-degree angle to the booms. Each boom bracket has a buckle welded every 100mm, for a total of 9 buckles. The two boom brackets are symmetrically distributed. The connection between the support booms, the frame, and the support frame is a snap-fit ​​connection that is easy to disassemble. The support frame is divided into left and right parts. The system includes four camera forearm supports, each consisting of two 486mm long steel tubes. These supports surround the main arm of the camera mount and can be adjusted to change the distance between the camera and the frame. They are secured using convenient clips. Additionally, three clips are installed on the forearm supports for stabilizing the camera base. There are two camera bases, made of 2mm thick aluminum plate, equipped with a fixed cylindrical bracket with a diameter of 5mm. The base is firmly fixed to the camera with four 4-1 / 4UNC-20 screws. It includes a sensor frame, designed as a cylindrical shell with a height of 200mm and a diameter of 100mm, with a mesh distribution with 20mm intervals, which can both accommodate the sensor and allow seawater to pass through; The buckle measures 60mm in length, 30mm in width, and 2mm in thickness. A circular hole with a diameter of 9mm is cut in the middle of the rectangle, and the distance from the center of the hole to the center of the wide side of the rectangle is 45mm. After the buckle is made, the surface of the frame is coated with anti-fouling paint. The solar panel is a rectangular plate with a length of 0.6m, a width of 0.465m, and a thickness of 0.01m. It is mainly composed of two cylindrical steel bars with a diameter of 0.003m and a height of 0.1153m and a spherical support point with a diameter of 0.007m. The two solar panels are horizontal and facing upwards, which can absorb more solar energy and convert it into electrical energy. The battery is 0.2m long, 0.13m wide, and 0.1m high. It is mainly responsible for storing the electrical energy converted by the solar panel and providing power to the underwater camera, multi-parameter water quality meter, and 4G network video recorder so that they can monitor in real time. The underwater camera used is the HIKVISION DS-2XC6046-LR model, with a diameter of 0.114m and a width of 0.05m. It supports day / night mode and automatic timer switching. Saturation, brightness, contrast, sharpness, AGC, and white balance can be adjusted remotely via a client or browser. It is equipped with built-in eMMC storage with a capacity of 64GB. It was fixed to the buoy at underwater positions of 0.3m and 1m, facing the two mounting plates respectively, and then secured to the sensor frame. The 4G network video recorder uses Hikvision's independently developed new-generation DS-7600N-S1 / GLT series, measuring 0.092m wide, 0.095m deep, and 0.046m high. It employs multiple advanced IT technologies, such as audio / video encoding / decoding technology, embedded system technology, storage technology, 4G network technology, and intelligent technology, enabling wireless transmission of information collected by cameras and sensors to the client for remote monitoring. In practical applications, the image-based method for identifying and analyzing the growth process of barnacles specifically includes the following steps: S1. Set up an observation device in the barnacle growing area, collect image data of barnacle growth through the observation device, and process the collected barnacle growth image data through the image processing module; S2. First, perform image enhancement on the barnacle growth image data. After converting the input RGB image to a grayscale image, perform the enhancement operation. S3. Perform adaptive median filtering and morphological opening operations sequentially on the enhanced grayscale image from step S2; S4. Perform edge detection and circle localization on the image processed in step S3; S5. After processing in step S3, the final step is to perform target segmentation and quantization of the barnacle growth image data.

[0019] Furthermore, it should be noted that the implementation steps of step S2 are as follows: S2.1. Histogram equalization: Expands the grayscale distribution range to improve overall contrast; S2.2. Piecewise grayscale transformation: Let the input grayscale value be x. When x is [50, 160], the output y is [0, 255] through nonlinear function mapping to enhance the grayscale difference in the barnacle edge region.

[0020] Furthermore, it should be noted that the implementation steps of step S3 are as follows: S3.1. Adaptive Median Filtering: A median filter with an adaptive window size is used to filter the grayscale enhanced image, effectively removing noise and isolated noise points while preserving barnacle edge details. S3.2. Morphological opening operation: Use 33 cross-shaped structural elements to perform erosion and then expansion operations to eliminate interference objects smaller than the structural elements and smooth the edge contour of barnacles.

[0021] Furthermore, it should be noted that the implementation steps of step S4 are as follows: S4.1. Canny edge detection: The Sobel operator is used to calculate the gradient magnitude and direction of the image in the x and y directions; then non-maximum suppression is performed to retain local maximum points along the gradient direction to refine the edges; S4.2. Hough Circle Detection: Apply Hough transform to perform circle detection on the edge image, limit the radius search range R [Rmin, Rmax] to improve detection accuracy, count the number of barnacles detected and mark the detected barnacles with red circles on the original image.

[0022] Furthermore, it should be noted that the implementation steps of step S5 are as follows: S5.1. Otsu Adaptive Segmentation: The Otsu algorithm is used to automatically obtain the image segmentation threshold, binarize the image into the target barnacle and the background region, and separate the independent connected regions of the barnacle; S5.2. Area Calculation: Count the number of pixels N in the connected region, and combine the calibration relationship. 1 pixel corresponds to the actual area S0mm. Calculate the actual area of ​​the barnacle, as shown in equation (1): S=NS0(1) By using the above steps, the method of automatically identifying and dynamically detecting barnacles during their attachment process can simultaneously identify and count barnacles while also monitoring and analyzing the attachment process, providing a more intuitive understanding of the growth and attachment process of barnacles.

[0023] In the description of this specification, references to the terms "an embodiment," "example," and "specific example" refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0024] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and effects.

Claims

1. A method for identifying and analyzing the growth process of barnacles based on image measurement, the method being implemented based on an observation device and an image processing module, characterized in that, Includes the following steps: S1. Set up an observation device in the barnacle growing area, collect image data of barnacle growth through the observation device, and process the collected barnacle growth image data through the image processing module; S2. First, perform image enhancement on the barnacle growth image data. After converting the input RGB image to a grayscale image, perform the enhancement operation. S3. Perform adaptive median filtering and morphological opening operations sequentially on the enhanced grayscale image from step S2; S4. Perform edge detection and circle localization on the image processed in step S3; S5. After processing in step S3, the final step is to perform target segmentation and quantization of the barnacle growth image data.

2. The method for identifying and analyzing barnacle growth process based on image measurement according to claim 1, characterized in that, The observation device consists of an external frame (1) and an underwater camera (2). The external frame (1) is provided with several sets of support frames (6). Each support frame (6) is equipped with a camera forearm bracket (5). The bottom of each camera forearm bracket (5) is connected to one end of a camera upper arm bracket (4). The other end of the camera upper arm bracket (4) is installed on the external frame (1). The angle of the support frame (6) is adjusted by an electric telescopic rod. Each camera forearm bracket (5) is also equipped with a camera base (3). Each underwater camera (2) is installed on the camera base (3). The top of the external frame (1) above the water is also equipped with a solar panel, a battery and a solar controller. The underwater camera (2) is electrically connected to the solar panel and the battery to provide power support for the underwater camera (2). Sensor frames (7) are also provided on both sides of the external frame (1).

3. The method for identifying and analyzing barnacle growth process based on image measurement according to claim 1, characterized in that, The implementation steps of step S2 are as follows: S2.

1. Histogram equalization: Expands the grayscale distribution range to improve overall contrast; S2.

2. Piecewise grayscale transformation: Let the input grayscale value be x. When x is [50, 160], the output y is [0, 255] through nonlinear function mapping to enhance the grayscale difference in the barnacle edge region.

4. The method for identifying and analyzing barnacle growth process based on image measurement according to claim 1, characterized in that, The implementation steps of step S3 are as follows: S3.

1. Adaptive Median Filtering: A median filter with an adaptive window size is used to filter the grayscale enhanced image, effectively removing noise and isolated noise points while preserving barnacle edge details. S3.

2. Morphological opening operation: Use 33 cross-shaped structural elements to perform erosion and then expansion operations to eliminate interference objects smaller than the structural elements and smooth the edge contour of barnacles.

5. The method for identifying and analyzing barnacle growth process based on image measurement according to claim 1, characterized in that, The implementation steps of step S4 are as follows: S4.

1. Canny edge detection: The Sobel operator is used to calculate the gradient magnitude and direction of the image in the x and y directions; then non-maximum suppression is performed to retain local maximum points along the gradient direction to refine the edges; S4.

2. Hough Circle Detection: Apply Hough transform to perform circle detection on the edge image, limit the radius search range R [Rmin, Rmax] to improve detection accuracy, count the number of barnacles detected and mark the detected barnacles with red circles on the original image.

6. The method for identifying and analyzing barnacle growth process based on image measurement according to claim 1, characterized in that, The implementation steps of step S5 are as follows: S5.

1. Otsu Adaptive Segmentation: The Otsu algorithm is used to automatically obtain the image segmentation threshold, binarize the image into the target barnacle and the background region, and separate the independent connected regions of the barnacle; S5.

2. Area Calculation: Count the number of pixels N in the connected region, and combine the calibration relationship. 1 pixel corresponds to the actual area S0mm. Calculate the actual area of ​​the barnacle, as shown in equation (1): S=NS0(1).

Images