Detection method for salvage of underwater ship anchor and propeller

Abstract

The invention discloses a detection method for salvage of an underwater ship anchor and a propeller. The method comprises the following steps: acquiring an underwater image of a target area; carrying out image enhancement processing on the obtained underwater image, wherein the image enhancement processing comprises the following steps: carrying out image denoising processing based on time domain frame averaging on the underwater image; and contrast-limited adaptive histogram equalization processing is carried out on the denoised underwater image. Collecting underwater ship anchor and propeller images to construct a training data set, and performing data enhancement processing; performing model training on a preset deep learning neural network by using the enhanced training data set to obtain an underwater anchor and propeller target detection model, calculating confidence loss and classification loss by using Focal Loss in model training, and calculating bounding box regression loss by using CIoU loss; and performing target detection and identification on the underwater image after image enhancement processing by using an underwater anchor and propeller target detection model. The underwater detection requirements of propeller and anchor salvage under different environment working conditions are effectively met.

Description

Technical Field

[0001] The present invention relates to the field of underwater detection, and more particularly to a detection method for salvaging underwater anchors and propellers. Background Art

[0002] The detection and identification of underwater sediments is an important topic in fields such as marine geology, marine engineering, and resource exploration. With the development of deep-sea areas, underwater target detection and identification methods have received widespread attention and application. Traditional underwater sediment detection mainly relies on sonar systems, side-scan sonars, multi-beam echo sounders and other equipment. These technologies have significant advantages in seabed topography mapping and obstacle detection. However, it is still difficult to detect anchors and propellers in seabed sediments. The opacity and turbidity of seawater and changes in lighting conditions seriously affect the imaging quality, making it difficult to obtain clear and stable image data. In addition, the seabed topography is complex and varied, and the sediment types are diverse, ranging from fine sand to gravel to clay. Each type has different physical properties and reflective characteristics, which increases the difficulty of identification.

[0003] On a technical level, existing underwater imaging equipment, such as sonar and optical cameras, has limitations in resolution, coverage, and depth penetration, making it difficult to simultaneously meet the requirements for high-precision and wide-area searches. Regarding data processing, underwater images are often accompanied by noise, shadows, and occlusions, posing challenges to automatic recognition algorithms. Traditional methods have limitations in accurately identifying subtle features and sediment properties in complex seafloor environments. In recent years, with the rapid development of computer vision and machine learning technologies, breakthroughs have been made in underwater target detection and recognition methods. Methods based on image processing and deep learning have gradually become a research hotspot. By acquiring seafloor image data using high-resolution underwater cameras or sonar imaging systems and analyzing and processing these images using convolutional neural network (CNN) deep learning models, automatic target classification and recognition can be achieved.

[0004] Therefore, developing an adaptable and robust anchor and propeller detection and identification system based on deep learning is a key direction to overcome current difficulties and improve the ability to detect seabed sediments. It has important practical significance and usage needs for underwater anchor and propeller detection. Summary of the Invention

[0005] The purpose of the present invention is to provide a detection method for underwater anchor and propeller salvage, to provide an underwater imaging and target detection method for underwater anchor and propeller detection and salvage, to realize seabed anchor and propeller detection, and to meet the requirements of target automatic detection and recognition capabilities.

[0006] To achieve the above object, the technical solutions adopted by the present invention are as follows: In a first aspect of the present invention, a detection method for underwater anchor and propeller salvage is provided, the method comprising: Acquire underwater images of the target area; Performing image enhancement processing on the acquired underwater image, the image enhancement processing comprising: Performing image denoising on underwater images based on time-domain frame averaging; and Perform contrast-limited adaptive histogram equalization on the denoised underwater image; Build an underwater anchor and propeller target detection model, and use this model to perform target detection and recognition on underwater images after image enhancement, including: Collect underwater anchor and propeller images to construct a training dataset, and perform data augmentation on the training dataset; The enhanced training dataset is used to train the preset deep learning neural network model to obtain an underwater anchor and propeller target detection model. The model training uses Focal Loss to calculate the confidence loss and classification loss, and CIoU loss to calculate the bounding box regression loss. The underwater anchor and propeller target detection model is used to detect and identify anchors and propellers in underwater images after image enhancement. Images that failed detection are added to the training dataset as difficult samples, and the deep learning neural network is retrained until the network parameters are fitted; The newly trained underwater anchor and propeller target detection model is used to detect and identify anchors and propellers in underwater images after image enhancement.

[0007] In the above solution, an underwater image of the target area is acquired by an underwater optical imaging camera.

[0008] In the above scheme, the denoised underwater image is subjected to contrast-limited adaptive histogram equalization processing, including: Segment the denoised underwater image into multiple local regions; Perform histogram statistics on pixels in each local area; Determine the histogram limit threshold of each local area, perform a clipping operation on the histogram of each local area, and evenly distribute the clipped part below the entire histogram; Based on the clipped histogram, each pixel value in each local area is mapped to a new pixel value; According to the position of each local area, bilinear interpolation is performed after transformation through the four-neighbor subgraph transformation function, and the pixel values ​​of each mapped local area are reconstructed to obtain an image processed by limited contrast adaptive histogram equalization.

[0009] In the above scheme, determining the histogram limit threshold of each local area includes: Get the number of pixels and histogram groups in each local area; The number of pixels in each local area is divided by the number of histogram groups to obtain the histogram limit threshold of each local area.

[0010] In the above solution, the data enhancement processing includes at least one of the following: Image flipping, random affine transformation, Mixup image mixing enhancement or Mosaic image mixing enhancement.

[0011] In the above scheme, image flipping includes left-right flipping, and random affine transformation includes translation, scaling, and rotation.

[0012] In the above solution, the preset deep learning neural network includes the YOLOV-5 model.

[0013] In the above scheme, model training uses Focal Loss to calculate confidence loss and classification loss, and uses CIoU loss to calculate bounding box regression loss, including: The model loss function is Focal Loss and CIoU loss, where Focal Loss is:

[0014] Where, is Focal Loss; when the predicted category is the same as the true value category, The value is the predicted probability , modulation factor Value ;on the contrary Value , modulation factor Value ; is the weight factor; The CIoU loss formula is:

[0015] Where, is the CIoU loss; is the intersection-over-union ratio between the predicted box and the true value box, d is the diagonal length of the minimum circumscribed rectangle formed by the prediction box and the true value box, c is the Euclidean distance between the center points of the two target boxes, v Parameters for measuring the consistency of the aspect ratios of the two target boxes are:

[0016] Where, 、 is the width and height of the true value box, 、 is the width and height of the prediction box.

[0017] According to a second aspect of the present invention, an electronic device is provided, comprising: a processor and a memory, the memory storing programs or instructions that can be run on the processor, and the program or instructions, when executed by the processor, implementing the steps of the detection method for underwater anchor and propeller salvage described in any one of the first aspects.

[0018] According to a third aspect of the present invention, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the detection method for underwater anchor and propeller salvage described in any one of the first aspects are implemented.

[0019] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art: This invention combines traditional image processing algorithms to effectively solve the problem of difficulty in identifying low-illuminance and low-contrast images in the neural network target detection and recognition process. It combines deep learning algorithms to effectively solve the problem that traditional algorithms are difficult to stably extract image features. It also achieves stable detection and recognition of propellers and anchors under different illumination levels through a large amount of parameter fitting, effectively meeting the underwater detection needs of propeller and anchor salvage under different environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic flow chart of a detection method for underwater anchor and propeller salvage provided in an embodiment of the present application; Figure 2 A schematic diagram of an image denoising process based on time-domain frame averaging provided in an embodiment of the present application; Figure 3 A flowchart of a CLAHE algorithm provided in an embodiment of the present application; Figure 4 This is an image enhancement result diagram provided by an embodiment of the present application; wherein, Figure 4 (a) in the figure is the original image. Figure 4 (b) in the figure is the enhanced image; Figure 5 A schematic diagram of the construction, detection and recognition process of a target detection model provided in an embodiment of the present application; Figure 6 A YOLOV5 network structure diagram provided in an embodiment of the present application; Figure 7 A training image preprocessing diagram provided in an embodiment of the present application; Figure 8This is a diagram of underwater anchor and propeller detection results provided by an embodiment of the present application; Figure 9 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of the present invention.

[0022] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0023] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0024] Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this application belongs. The terms "a," "an," "an," "the," and similar expressions used herein do not denote quantitative limitations and may refer to either the singular or the plural. The terms "comprise," "include," "have," and any variations thereof, used herein, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules (units) is not limited to the listed steps or units but may also include steps or units not listed, or may include other steps or units inherent to the process, method, product, or apparatus. The terms "connected," "connected," "coupled," and similar expressions used herein are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. As used herein, "plurality" means two or more. "And / or" describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" may mean: A exists alone; A and B exist simultaneously; or B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0025] This application provides an underwater imaging and target detection method for underwater anchor and propeller detection and salvage, realizes seabed anchor and propeller detection, and meets the requirements of target automatic detection and recognition capabilities.

[0026] like Figure 1 As shown in the figure, for underwater target detection, an image enhancement algorithm is first used, including an image denoising method based on time domain frame averaging and a contrast-limited adaptive histogram equalization enhancement method (CLAHE) to enhance the target area image, which increases the clarity and contrast of the image to a certain extent and improves the problems of uneven brightness, color distortion and severe noise in the image caused by the attenuation of light in the underwater environment. The processing process is as follows: Figure 2 and Figure 3 As shown, the processing effect is as follows Figure 4 Then, underwater propeller and anchor data are collected as model training data, and model training is performed based on the YOLOV-5 model, as shown in Figure 5As shown in the figure, underwater sample detection accuracy is low. To improve training results, achieve better detection performance and generalization capabilities, and alleviate the sample imbalance problem in the dataset, Focal Loss is used to calculate confidence loss and classification loss. This allows training to focus on learning difficult-to-classify samples, thereby improving detection performance for underwater target samples. Finally, based on this model, underwater propellers and anchors are automatically captured and recognized. Based on the results, retraining is performed on difficult samples until the network parameters are well-fitted. This method improves the recognition efficiency and accuracy of underwater targets to a certain extent. The recognition results are finally pushed to the display and control module for display and annotation.

[0027] like Figure 1 and Figure 5 As shown, the detection method for underwater anchor and propeller salvage of an embodiment of the present application comprises the following specific steps: (1) Obtain underwater images of the target area using an underwater optical imaging camera.

[0028] (2) Image denoising based on time domain frame averaging, an algorithm that effectively utilizes time dimension information, greatly reduces the impact of echo noise on target detection and stabilizes ultrasound imaging. The specific process is as follows: Figure 2 shown.

[0029] (3) The CLAHE image enhancement algorithm is used to perform contrast-limited adaptive histogram equalization on the descattered image. While maintaining the image details, it processes the noise and improves the local contrast of the image. The processing process is as follows: Figure 3 As shown, the effect is as follows Figure 4 As shown, Figure 4 (a) in the figure is the original image. Figure 4 (b) in the figure is the image after two image enhancements.

[0030] The specific implementation process is as follows: ① The image is divided into local regions of uniform size (in this embodiment, the entire image is divided into 8×8 local regions). The purpose of the division is to process the pixels in each small region separately to achieve local contrast enhancement.

[0031] ② Perform histogram statistics on the pixels in each small area. Calculate the frequency of each gray level to obtain a histogram. This histogram shows the distribution of pixel values ​​in the area.

[0032] ③ Set the histogram limit threshold based on the histogram's characteristics. The threshold is typically determined based on the percentage of pixels within the region. In this project, the threshold is set as the number of pixels in each block divided by the number of histogram groups in each block. The histogram is cropped based on the limit threshold and the cropped portion is evenly distributed below the histogram of the entire image. This improves image contrast and makes details clearer.

[0033] ④ Map each pixel value in the original image to a new pixel value based on the cropped histogram. This makes the pixel values ​​in each small area more evenly distributed, thereby improving the contrast.

[0034] ⑤ According to the position of the image block, the four-neighbor sub-graph transformation function is used to transform the image block and then the bilinear interpolation pixel value is reconstructed.

[0035] (4) By collecting underwater target images, a target data set is formed. After completing the target detection model training, the target detection model is used to perform target detection and recognition on underwater images.

[0036] ① Data collection and enhancement, during the training process, in order to further improve the training effect, such as Figure 7 As shown in the figure, based on the original dataset, a variety of data enhancement methods are used to enhance data diversity, including left-right flipping and random affine transformation (translation, scaling, rotation), etc. At the same time, multiple image mixing enhancement methods such as Mixup and Mosaic are used to increase the complexity of the dataset.

[0037] ②Model training, based on the YOLOV5 network, its network structure is as follows Figure 6 As shown, the model loss function is FocalLoss and CIoU loss, where Focal Loss is described as:

[0038] In the formula, when the predicted category is the same as the true value category, The value is the predicted probability , modulation factor Value ;on the contrary Value , Value ; is the weight factor. For the bounding box loss, the CIoU loss function is retained. This loss function simultaneously considers multiple correlation factors between the predicted box and the true value box: overlapping area, center point distance, and target box aspect ratio. It can well reflect the difference between the predicted box and the true value box and improve the bounding box regression ability of the model. The CIoU loss formula is:

[0039] Where, is the intersection-over-union ratio between the predicted box (Bpre) and the true value box (Bgt), d is the diagonal length of the minimum circumscribed rectangle formed by Bpre and Bgt, c is the Euclidean distance between the center points of the two target boxes, vParameters for measuring the consistency of the aspect ratios of the two target boxes are:

[0040] Where: 、 is the width and height of the true target box, 、 is the width and height of the prediction box.

[0041] (5) The images that failed to be detected are added to the dataset as difficult samples, the network is trained, and the network model is updated. The final recognition effect of anchor and propeller is as follows: Figure 8 shown.

[0042] In addition, combined Figure 1 and Figure 5 The detection methods for underwater anchor and propeller salvage described in the embodiments of the present application can be implemented by a computer device. Figure 9 Schematic diagram of the hardware structure of the computer device of the embodiment of the present application. Figure 9 As shown, the device may include a processor 201 and a memory 202 storing computer program instructions.

[0043] Specifically, the processor 201 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0044] Memory 202 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 202 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 202 may include removable or non-removable (or fixed) media. Where appropriate, memory 202 may be internal or external to the data processing device. In certain embodiments, memory 202 is non-volatile memory. In certain embodiments, memory 202 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data out dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0045] The memory 202 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 201 .

[0046] The processor 201 reads and executes computer program instructions stored in the memory 202 to implement any one of the detection methods for underwater anchor and propeller salvage in the above embodiments.

[0047] In some embodiments, the computer device may further include a communication interface 203 and a bus 200. Figure 9 As shown, the processor 201 , the memory 202 , and the communication interface 203 are connected via a bus 200 and communicate with each other.

[0048] The communication interface 203 is used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present application. The communication interface 203 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0049] Bus 200 includes hardware, software, or both, and couples components of a computer device to each other. Bus 200 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example, and not limitation, bus 200 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Bus 200 may include one or more buses, where appropriate. Although embodiments herein describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

[0050] The computer device can execute the detection method for underwater anchor and propeller salvage in the embodiment of the present application, thereby realizing the combination Figure 1 A detection method for underwater anchor and propeller salvage is described.

[0051] In addition, in conjunction with the detection method for underwater anchor and propeller salvage in the above-mentioned embodiments, embodiments of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when executed by a processor, the computer program instructions implement any of the detection methods for underwater anchor and propeller salvage in the above-mentioned embodiments.

[0052] In summary, the present application provides a detection method, equipment and medium for underwater anchor and propeller salvage. Combined with traditional image processing algorithms, it effectively solves the problem of difficulty in recognizing low-illuminance and low-contrast images in the neural network target detection and recognition process. Combined with deep learning algorithms, it effectively solves the problem that traditional algorithms are difficult to stably extract image features, and through a large amount of parameter fitting, it realizes stable detection and recognition of propellers and anchors under different illumination, effectively meeting the underwater detection needs of propeller and anchor salvage under different environmental conditions.

[0053] It should be noted that the various technical features of the above-described embodiments can be combined in any manner. To simplify the description, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there are no contradictions in the combination of these technical features, they should be considered to be within the scope of this specification. In addition, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, and two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0054] Those skilled in the art will readily understand that the above-described embodiments merely represent several implementation methods of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the invention. It should be noted that a person of ordinary skill in the art may make several variations and improvements without departing from the concept of the present application, and these variations and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the appended claims.

Claims

1. A detection method for underwater anchor and propeller salvage, characterized in that: The method includes: Acquire underwater images of the target area; Performing image enhancement processing on the acquired underwater image, the image enhancement processing comprising: Performing image denoising on underwater images based on time-domain frame averaging; and Perform contrast-limited adaptive histogram equalization on the denoised underwater image; Build an underwater anchor and propeller target detection model, and use this model to perform target detection and recognition on underwater images after image enhancement, including: Collect underwater anchor and propeller images to construct a training dataset, and perform data augmentation on the training dataset; The enhanced training dataset is used to train the preset deep learning neural network model to obtain an underwater anchor and propeller target detection model. The model training uses Focal Loss to calculate the confidence loss and classification loss, and CIoU loss to calculate the bounding box regression loss. The underwater anchor and propeller target detection model is used to detect and identify anchors and propellers in underwater images after image enhancement. Images that failed detection are added to the training dataset as difficult samples, and the deep learning neural network is retrained until the network parameters are fitted; The newly trained underwater anchor and propeller target detection model is used to detect and identify anchors and propellers in underwater images after image enhancement.

2. The detection method for underwater anchor and propeller salvage according to claim 1, characterized in that: The underwater image of the target area is acquired by an underwater optical imaging camera.

3. The detection method for underwater anchor and propeller salvage according to claim 1, characterized in that: The denoised underwater image is subjected to contrast-limited adaptive histogram equalization processing, including: Segment the denoised underwater image into multiple local regions; Perform histogram statistics on pixels in each local area; Determine the histogram limit threshold of each local area, perform a clipping operation on the histogram of each local area, and evenly distribute the clipped part below the entire histogram; Based on the clipped histogram, each pixel value in each local area is mapped to a new pixel value; According to the position of each local area, bilinear interpolation is performed after transformation through the four-neighbor subgraph transformation function, and the pixel values ​​of each mapped local area are reconstructed to obtain an image processed by limited contrast adaptive histogram equalization.

4. The detection method for underwater anchor and propeller salvage according to claim 3, characterized in that: Determine the histogram limit threshold for each local area, including: Get the number of pixels and histogram groups in each local area; The number of pixels in each local area is divided by the number of histogram groups to obtain the histogram limit threshold of each local area.

5. The detection method for underwater anchor and propeller salvage according to claim 1, characterized in that: Data augmentation processing includes at least one of the following: Image flipping, random affine transformation, Mixup image mixing enhancement or Mosaic image mixing enhancement.

6. The detection method for underwater anchor and propeller salvage according to claim 5, characterized in that: Image flipping includes left-right flipping, and random affine transformation includes translation, scaling, and rotation.

7. The detection method for underwater anchor and propeller salvage according to claim 1, characterized in that: The preset deep learning neural networks include the YOLOV-5 model.

8. The detection method for underwater anchor and propeller salvage according to claim 1, characterized in that: Model training uses Focal Loss to calculate confidence loss and classification loss, and CIoU loss to calculate bounding box regression loss, including: The model loss function is Focal Loss and CIoU loss, where Focal Loss is: Where, is Focal Loss; when the predicted category is the same as the true value category, The value is the predicted probability , modulation factor Value ;on the contrary Value , modulation factor Value ; is the weight factor; The CIoU loss formula is: Where, is the CIoU loss; is the intersection-over-union ratio between the predicted box and the true value box, d is the diagonal length of the minimum enclosing rectangle of the prediction box and the true value box, c is the Euclidean distance between the center points of the two target boxes, v Parameters for measuring the consistency of the aspect ratios of the two target boxes are: Where, 、 is the width and height of the true value box, 、 is the width and height of the prediction box.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the detection method for underwater anchor and propeller salvage described in any one of claims 1 to 8 are implemented.

10. A readable storage medium, characterized in that: Programs or instructions are stored thereon, and when the programs or instructions are executed by the processor, the steps of the detection method for underwater anchor and propeller salvage described in any one of claims 1 to 8 are implemented.

Images