Fixed piloting equipment guiding method based on two-dimensional code and depth vision fusion

Abstract

The embodiment of the invention provides a fixed piloting equipment guiding method based on two-dimensional code and depth vision fusion, and the method comprises the steps: preparing a pre-selected development board, and configuring a corresponding development environment; information needing to be carried by the two-dimensional code is determined, the data format of the information needing to be carried is designed, and corresponding information is provided for the ship; designing an identification algorithm of the fixed piloting equipment and an identification algorithm of the two-dimensional code, performing fusion matching on the depth visual identification and the two-dimensional code, and zooming the camera to complete two-dimensional code identification after the fixed piloting equipment is identified; training and obtaining a model of an identification algorithm; information in the two-dimensional code is extracted, and the position of the two-dimensional code is calculated. The application field of QR-Code is further expanded to assist ship positioning, the concept of edge calculation is introduced, an artificial intelligence chip K-210 is used for replacing a traditional PC end CPU to complete the task of image processing at the edge, and the problem of data transmission delay in a traditional mode is solved. And meanwhile, the edge nodes have computing power, and emergency judgment can be carried out.

Description

Technical Field

[0001] This invention relates to the field of ship-assisted positioning and edge computing application technology, and in particular to a fixed pilotage guidance method based on the fusion of QR codes and depth vision. The method involves attaching a QR code containing information such as its own GPS coordinates to the navigation aid (i.e., fixed pilotage equipment), and using the K-210 artificial intelligence chip based on the RISC-V architecture for QR code target detection and content extraction. Background Technology

[0002] QR-Code is a matrix barcode symbol developed by Denso in September 1994. It has advantages such as large capacity, high reliability, ability to represent various information including Chinese characters and images, strong confidentiality and anti-counterfeiting capabilities, and the information it carries can be read. It is widely used in daily life and is often used to store relevant information about items and for login verification.

[0003] In recent years, some researchers have also attempted to apply QR codes to indoor robot navigation and localization, as well as drone landing site marking, achieving relatively good experimental results. Most of these studies utilize QR codes carrying information about their location. Images are captured by cameras on mobile devices and transmitted to a remote PC for QR code image recognition and content extraction. The processed results are then used as the basis for determining the next action.

[0004] Since most of these studies are conducted in indoor environments, direct communication between PCs and mobile devices can be used for data transmission over short distances. Alternatively, image data collected by the device can be uploaded to the cloud for processing, allowing the PC to remotely monitor and issue commands for the next action. Although existing cloud computing power is sufficient, data transmission latency remains an unavoidable issue. The key to solving this problem lies in enabling devices to also possess computing power, allowing them to independently process data and make simple judgments. The K-210 AI chip based on the RISC-V architecture can effectively address this issue. This chip uses a RISC-V processor architecture, featuring a dual-core 64-bit CPU and 1 TOPS of computing power. It supports multimodal recognition of machine vision and machine hearing, and its low power consumption, easy scalability, and strong programmability make it well-suited for use as an edge node.

[0005] Meanwhile, given the requirements for intelligent development in the domestic shipping industry and considering the presence of numerous fixed pilotage devices in ship navigation scenarios, it is entirely feasible to use QR-Code as a means of ship auxiliary positioning, analogous to the application scenario of QR-Code indoor navigation. Summary of the Invention

[0006] Based on the aforementioned background technology research and combined with the concept of edge computing, this invention provides a fixed pilotage guidance method based on the fusion of QR codes and depth vision. Large QR codes are installed on fixed pilotage equipment such as buoys and shore markers, displaying their detailed information and location. A QR code recognition algorithm suitable for this application scenario is designed, and the K-210 development board is used for image processing. Based on the acquired information, the ship's position is calculated backwards, assisting in satellite positioning as a supplement to ship positioning. Simultaneously, corresponding sensors can be used to collect navigation environment information. After processing by the K-210 edge node, the data is uploaded to the cloud. A PC can request this data and perform visualization operations, enabling remote monitoring of environmental information during ship navigation and timely warnings for adverse weather conditions. Corresponding warning commands are sent to the ship via the cloud.

[0007] This invention provides a fixed navigation device guidance method based on the fusion of QR codes and depth vision, comprising: Step 1: Prepare the pre-selected development board and configure the corresponding development environment; Step 2: Determine the information that the QR code needs to carry, design the data format of the information to be carried, and provide the corresponding information to the ship; Step 3: Design recognition algorithms for fixed navigation equipment and QR codes, and fuse and match depth vision recognition with QR codes so that after the fixed navigation equipment is recognized, the camera zooms to complete the QR code recognition. Step 4: Train and obtain the model for the recognition algorithm; Step 5: Extract the information from the QR code to deduce your own location.

[0008] In some embodiments of the present invention, preparing a pre-selected development board and configuring the corresponding development environment includes: Prepare the K210 development board, use the corresponding toolchain to configure the development environment, and flash the MicroPython-based MaixPy firmware to the development board so that the written development board program can call Python libraries and expand the K210 development board to connect to the corresponding camera.

[0009] In some embodiments of the present invention, determining the information to be carried by the QR code and designing the data format of the information to be carried includes: Design the data format and form for the information carried by the QR code, and transmit the data in binary form; QR codes of appropriate size are installed on buoys and shore markers. The size of the QR code is determined by testing different fixed navigation equipment to find a suitable QR code size for detection. The information carried by the QR code includes at least detailed information about the fixed navigation equipment and its GPS data, with the GPS data rounded to two decimal places.

[0010] In some embodiments of the present invention, when designing the fixed navigation device identification algorithm, YOLOv2 is used, and the camera is controlled to zoom in and out according to the position and size of the fixed navigation device in the image until the QR code can be identified.

[0011] This project uses OpenCV and Zbar to extract and recognize QR codes in images. Specifically, it extracts the QR code region from the image by calling OpenCV functions, and then uses Zbar to recognize the QR code.

[0012] In some embodiments of the present invention, the specific steps for calling OpenCV functions to extract QR codes are as follows: S1. Grayscale Conversion In image processing, the original three-dimensional RGB image is converted into a two-dimensional grayscale image to eliminate color interference. S2. Gaussian smoothing filter We introduce the GasussianBlur() function from OpenCV to blur the original image using a Gaussian filter; S3. Median Filtering Using the OpenCV function medianBlur(), a median filtering method is employed to remove noise while preserving the edge details of the image, thus extracting the region where the QR code is located. S4. Edge Detection The Sobel edge detection algorithm is used to first calculate the gradients in the X and Y directions of the image, and then the gradient results in the two directions are superimposed. S5. Binarization The threshold function in OpenCV is used to binarize the acquired image so that it has only black and white color values, in order to better highlight the outline of the target area. S6. Closing Operation Using the OpenCV function morphologyEx(), the gap between QR codes is widened, isolated interference points are removed, and the image is closed by first dilating and then eroding. S7. Area where the code is obtained Use the findContours() function to find the rectangular boundary of the QR-Code region in the image, then find the contour with the largest area and crop the original image according to this region, save it as the corresponding result for recognition, and record the size of the QR-Code contour region and the position of the region center.

[0013] In some embodiments of the present invention, the steps for QR-Code recognition using Zbar are as follows: i. Initialize and construct a Zbar scanner ImageScanner object, and then use the set_config() method to set its corresponding parameters; ii. Obtain the image information extracted in the previous step and define the scanning range; iii. Call the scan() method of the image scanner to read the QR-Code data from the image.

[0014] In some embodiments of the present invention, after reading the QR-Code data in the image, the method further includes: Based on the camera imaging principle and the lens transmission principle f / D=h / H, D is calculated, and by comparing the center of the QR-Code area with the center of the image, the approximate direction of the QR-Code is estimated. in: f: indicates the focal length of the lens, in mm; D: Distance between the lens and the object, in meters (m); h: The height of the lens's target surface, a parameter of the image sensor, in mm; H: The height of the shooting location, in meters (m).

[0015] In some embodiments of the present invention, the step of extracting information from the QR code and calculating its own position includes: Based on the calculated results, combined with the GPS coordinates of the fixed navigation equipment in the WGS84 coordinate system obtained from the QR-Code, the corresponding GPS coordinates are converted into plane coordinates in the form of (X, Y) in this coordinate system, in meters. The coordinates (X1, Y1) of the ship's location are estimated and converted into latitude and longitude for display, thus deriving the ship's own GPS coordinates.

[0016] In some embodiments of the present invention, after calculating the ship's own GPS coordinates, the method further includes: A threshold is set for the distance between the vessel and the fixed pilotage equipment. When the distance between the two is less than the threshold, a collision warning program is activated to assist safe driving.

[0017] In some embodiments of the present invention, the specific steps for remotely monitoring the ship's navigation environment are as follows: Expand the K210 development board to connect a sensor module consisting of multiple sensors to collect environmental information during navigation; After processing the data, along with the coordinates of the fixed pilotage equipment and the distance to the ship obtained above, it is packaged into a complete JSON data packet. The TCP protocol is used to realize bidirectional communication between the K-210 development board and the cloud, and the data packet is uploaded to the cloud. After receiving the data, the cloud stores it. The cloud adopts a multi-threaded mode to establish bidirectional communication with the PC for data transmission. After the PC makes a data request, the data is sent to the PC in sequence at a set frequency. After receiving the data, the PC calls the pre-written visualization module to display the data and sends commands to the K-210 development board through the cloud.

[0018] Compared with existing technologies, the advantages of the fixed pilotage guidance method based on QR code and deep vision fusion provided in this invention are as follows: it further expands the application field of QR codes to assist in ship positioning, and introduces the concept of edge computing. It uses the K-210 artificial intelligence chip to replace the traditional PC CPU to complete image processing tasks at the edge, thus solving the data transmission latency problem existing in the traditional mode to a certain extent. At the same time, the addition of the artificial intelligence chip gives edge nodes computing power, enabling them to make some emergency judgments. Finally, a simple and easy-to-implement solution is constructed, which not only completes data processing at the edge nodes but also remotely detects navigation environment information. Attached Figure Description

[0019] Figure 1 A conceptual diagram of edge computing involved in the fixed navigation equipment guidance method based on the fusion of QR code and depth vision provided in the embodiments of the present invention; Figure 2 A schematic diagram of the overall solution for the fixed navigation device guidance method based on the fusion of QR code and depth vision provided in an embodiment of the present invention; Figure 3 A flowchart of a fixed navigation device guidance method based on QR code and depth vision fusion provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the camera imaging principle in the fixed navigation device guidance method based on the fusion of QR code and depth vision provided in an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Various embodiments and features of this application are described herein with reference to the accompanying drawings.

[0022] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0023] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application, which have the features described in the claims and are therefore all within the scope of protection defined herein.

[0024] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0025] Specific embodiments of this application are described below with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to ascertain the true intent based on the user's historical operations, and to avoid unnecessary or redundant details that would obscure this application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in various ways with substantially any suitable detailed structure.

[0026] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.

[0027] This invention provides a fixed navigation device guidance method based on the fusion of QR codes and depth vision, such as... Figures 1 to 4 As shown, the method includes: Step 1: Prepare the pre-selected development board and configure the corresponding development environment; the pre-selected development board can be the K-210 development board; Step 2: Determine the information that the QR code needs to carry, design the data format of the information to be carried, and provide the corresponding information to the ship; The third step is to design recognition algorithms for fixed navigation equipment and QR codes, and to fuse and match depth vision recognition with QR codes so that after the fixed navigation equipment is identified, the camera zooms in to complete the QR code recognition. In this scenario, QR code recognition needs to be completed in two stages. The first stage is to identify the fixed navigation equipment, such as shore markers and buoys. The second stage is to zoom in the camera to complete the QR code recognition.

[0028] Step 4: Train and obtain the model for the recognition algorithm; Step 5: Extract information from the QR code to deduce your own location. To facilitate understanding of the above technical solutions, a detailed explanation is provided below with reference to the accompanying drawings and specific examples. The specific implementation methods can be divided into two aspects. One aspect is ship positioning assistance based on QR-Code, and the general design concept is as follows: Figure 3 As shown; on the other hand, it is for remote monitoring of the ship's navigation environment.

[0029] The specific implementation steps for ship positioning assistance based on QR codes are as follows: 1) Prepare the K210 development board and configure the development environment using the corresponding toolchain. This involves flashing the MicroPython-based MaixPy firmware to the development board, enabling the written development board programs to call most Python libraries, thus facilitating subsequent operations. Also, expand the K-210 by connecting a corresponding camera.

[0030] 2) The data format and form of the information carried by the QR code are designed. This patent uses binary data transmission. Considering different application scenarios, appropriately sized QR codes are installed on buoys and shore markers. The specific size of the QR code needs to be tested for different fixed navigation equipment; codes that are too large or too small are not suitable for QR code detection. Furthermore, the information carried by the QR code should include at least the detailed information of the fixed navigation equipment and its GPS data, with two decimal places for the GPS data.

[0031] 3) Designing a fixed navigation device recognition algorithm is a typical target detection algorithm. Currently, popular target detection algorithms fall into two categories: one is the R-CNN series algorithms (R-CNN, Fast R-CNN, Faster R-CNN) based on Region Proposals, which are two-stage, requiring the use of heuristic methods (selective search) or CNN networks (RPN) to generate Region Proposals, and then performing classification and regression on the Region Proposals. The other category is one-stage algorithms like YOLO and SSD, which use only a single CNN network to directly predict the category and location of different targets. The first type of method has higher accuracy but is slower, while the second type of algorithm is faster but less accurate. Considering the practical application scenario, the fixed navigation device detection algorithm is implemented using YOLOv2. Based on the position and size of the fixed navigation device in the image, the camera zooms in until the QR code can be recognized.

[0032] 4) Taking into account the QR-Code in practical application scenarios, the extraction and recognition of QR-Code in images are completed based on OpenCV and Zbar. That is, the QR-Code region in the image is extracted by calling OpenCV functions, and then the QR-Code is further recognized by Zbar.

[0033] 5) The specific steps for using OpenCV functions to extract QR codes are as follows: i. Grayscale conversion In image processing, converting the original three-dimensional RGB image into a two-dimensional grayscale image eliminates color interference and makes it easier to process. The cvtColor() function provided by OpenCV is a color space conversion function that can convert the original RGB image into a grayscale image.

[0034] ii. Gaussian smoothing filter Gaussian filtering is a linear smoothing filter that is often used to eliminate Gaussian noise with good results. Therefore, the GasussianBlur() function in OpenCV is introduced to blur the original image using a Gaussian filter.

[0035] iii. Median Filtering Median filtering, a non-linear filtering method, removes noise while preserving edge details in the image, making it suitable for extracting the region containing QR codes. The OpenCV function for this is medianBlur().

[0036] iv. Edge detection The purpose of edge detection is to extract the contours of target regions, which can reduce the amount of data processed in the image, remove background image information that is irrelevant to the QR code, and retain only the QR code region information. The Sobel edge detection algorithm is used, which first calculates the gradients in the X and Y directions of the image separately, and then superimposes the gradient results in the two directions.

[0037] v. Binarization To facilitate further processing and avoid interference from excessive colors, the acquired image is binarized, resulting in only black and white values, which better highlights the contours of the target region. This is achieved using the `threshold` function in OpenCV.

[0038] vi. Closing operation To widen the gaps between QR codes and remove isolated interference points, a closing operation is performed on the image, first dilating and then eroding. The function in OpenCV is morphologyEx().

[0039] vii. The area where the code is obtained The `findContours()` function is used to locate the rectangular boundaries of the QR-Code regions in the image. Then, the largest contour area is identified, and the original image is cropped out along this contour area. The result is saved for recognition purposes, and the size and center position of the QR-Code contour region are recorded.

[0040] 6) The steps for QR code recognition using Zbar are as follows: i. Initialize and construct a Zbar scanner ImageScanner object, and then use the set_config() method to set its corresponding parameters. ii. Obtain the image information extracted in the previous step and define the scanning range. iii. Call the scan() method of the image scanner to read the QR-Code data from the image.

[0041] 7) According to the camera imaging principle and the lens transmission principle f / D=h / H, where: f: Indicates the focal length of the lens (fixed focus or zoom, parameter provided by the manufacturer), unit: mm D: Distance between the lens and the object, in meters (m) h: Lens target surface height (fixed and known, generally an "image sensor" parameter, such as 1 / 3" CCD), unit: mm H: The height of the shooting location (generally twice the height of the subject), unit: m. D can be calculated, and by comparing the center of the QR-Code region with the center of the image, the approximate direction of the QR-Code can be estimated.

[0042] 8) Based on the calculated results, and combined with the GPS coordinates of the fixed pilotage equipment in the WGS84 coordinate system obtained from the QR-Code, the corresponding GPS coordinates are converted into (X, Y) plane coordinates in meters. The coordinates (X1, Y1) of the ship's location are estimated and converted into latitude and longitude for display, thereby deriving the ship's own GPS coordinates as a means of ship-aided positioning.

[0043] 9) Set a threshold for the distance to fixed navigation equipment, such as 200m. When the distance between the two is less than 200m, a collision warning program will be activated to assist safe driving.

[0044] The specific steps for remotely monitoring the ship's navigation environment are as follows: 1) Expand the K210 to connect a sensor module consisting of multiple sensors, such as temperature and humidity sensors, wind speed sensors, etc., to collect environmental information during navigation.

[0045] 2) After simple data processing, the data, along with the coordinates of the fixed pilotage equipment and its distance from the ship obtained above, is packaged into a complete JSON data packet. The TCP protocol is then used to enable two-way communication between the K-210 and the cloud, and the data packet is uploaded to the cloud.

[0046] 3) After receiving the data, the cloud stores it. The cloud adopts a multi-threaded mode and establishes bidirectional communication with the PC for data transmission. After the PC makes a data request, the data is sent to the PC in sequence at a certain frequency. After receiving the data, the PC calls the pre-written visualization module to display the data and can send commands to K-210 through the cloud.

[0047] As can be seen from the above technical solutions, the fixed pilotage guidance method based on QR code and depth vision fusion provided in the above embodiments of the present invention further expands the application field of QR-Code to assist in ship positioning, and introduces the concept of edge computing. It uses the K-210 artificial intelligence chip to replace the traditional PC CPU to complete image processing tasks at the edge, thus solving the data transmission latency problem existing in the traditional mode to a certain extent. At the same time, the addition of the artificial intelligence chip gives edge nodes computing power, enabling them to make some emergency judgments. Finally, a simple and easy-to-implement solution is constructed, which not only completes data processing at the edge nodes, but also remotely detects navigation environment information.

[0048] The above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the present invention. The scope of protection of the present invention is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to the present invention within its spirit and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of the present invention.

Claims

1. A method for guiding fixed navigation equipment based on the fusion of QR codes and depth vision, characterized in that, include: Step 1: Prepare the pre-selected development board and configure the corresponding development environment; Step 2: Determine the information that the QR code needs to carry, design the data format of the information to be carried, and provide the corresponding information to the ship; Step 3: Design recognition algorithms for fixed navigation equipment and QR codes, and fuse and match depth vision recognition with QR codes so that after the fixed navigation equipment is recognized, the camera zooms to complete the QR code recognition. Step 4: Train and obtain the model for the recognition algorithm; Step 5: Extract the information from the QR code to deduce your own location.

2. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 1, characterized in that, The preparation of the pre-selected development board and configuration of the corresponding development environment include: Prepare the K210 development board, use the corresponding toolchain to configure the development environment, and flash the MicroPython-based MaixPy firmware to the development board so that the written development board program can call Python libraries and expand the K210 development board to connect to the corresponding camera.

3. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 2, characterized in that, The process of determining the information that the QR code needs to carry and designing the data format for the information includes: Design the data format and form for the information carried by the QR code, and transmit the data in binary form; QR codes of appropriate size are installed on buoys and shore markers. The size of the QR code is determined by testing different fixed navigation equipment to find a suitable QR code size for detection. The information carried by the QR code includes at least detailed information about the fixed navigation equipment and its GPS data, with the GPS data rounded to two decimal places.

4. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 3, characterized in that, When designing the fixed navigation equipment identification algorithm, Yolov2 is used for implementation. Based on the position and size of the fixed navigation equipment in the image, the camera is controlled to zoom and advance until the QR code can be recognized. This project uses OpenCV and Zbar to extract and recognize QR codes in images. Specifically, it extracts the QR code region from the image by calling OpenCV functions, and then uses Zbar to recognize the QR code.

5. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 4, characterized in that, The specific steps for using OpenCV functions to extract QR codes are as follows: S1. Grayscale Conversion In image processing, the original three-dimensional RGB image is converted into a two-dimensional grayscale image to eliminate color interference. S2. Gaussian smoothing filter We introduce the GasussianBlur() function from OpenCV to blur the original image using a Gaussian filter; S3. Median Filtering Using the OpenCV function medianBlur(), a median filtering method is employed to remove noise while preserving the edge details of the image, thus extracting the region where the QR code is located. S4. Edge Detection The Sobel edge detection algorithm is used to first calculate the gradients in the X and Y directions of the image, and then the gradient results in the two directions are superimposed. S5. Binarization The threshold function in OpenCV is used to binarize the acquired image so that it has only black and white color values, in order to better highlight the outline of the target area. S6. Closing Operation Using the OpenCV function morphologyEx(), the gap between QR codes is widened, isolated interference points are removed, and the image is closed by first dilating and then eroding. S7. Area where the code is obtained Use the findContours() function to find the rectangular boundary of the QR-Code region in the image, then find the contour with the largest area and crop the original image according to this region, save it as the corresponding result for recognition, and record the size of the QR-Code contour region and the position of the region center.

6. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 5, characterized in that, The steps for QR code recognition using Zbar are as follows: i. Initialize and construct a Zbar scanner ImageScanner object, and then use the set_config() method to set its corresponding parameters; ii. Obtain the image information extracted in the previous step and define the scanning range; iii. Call the scan() method of the image scanner to read the QR-Code data from the image.

7. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 6, characterized in that, After reading the QR-Code data from the image, the method further includes: Based on the camera imaging principle and the lens transmission principle f / D=h / H, D is calculated, and by comparing the center of the QR-Code area with the center of the image, the approximate direction of the QR-Code is estimated. in: f: indicates the focal length of the lens, in mm; D: Distance between the lens and the object, in meters (m); h: The height of the lens's target surface, a parameter of the image sensor, in mm; H: The height of the shooting location, in meters (m).

8. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 7, characterized in that, The step of extracting information from the QR code and calculating its own location includes: Based on the calculated results, combined with the GPS coordinates of the fixed navigation equipment in the WGS84 coordinate system obtained from the QR-Code, the corresponding GPS coordinates are converted into plane coordinates in the form of (X, Y) in this coordinate system, in meters. The coordinates (X1, Y1) of the ship's location are estimated and converted into latitude and longitude for display, thus deriving the ship's own GPS coordinates.

9. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 8, characterized in that, After calculating the ship's own GPS coordinates, the method further includes: A threshold is set for the distance between the vessel and the fixed pilotage equipment. When the distance between the two is less than the threshold, a collision warning program is activated to assist safe driving.

10. The fixed navigation device guidance method based on QR code and depth vision fusion according to claim 9, characterized in that, The specific steps for remotely monitoring the ship's navigation environment are as follows: Expand the K210 development board to connect a sensor module consisting of multiple sensors to collect environmental information during navigation; After processing the data, along with the coordinates of the fixed pilotage equipment and the distance to the ship obtained above, it is packaged into a complete JSON data packet. The TCP protocol is used to realize bidirectional communication between the K-210 development board and the cloud, and the data packet is uploaded to the cloud. After receiving the data, the cloud stores it. The cloud adopts a multi-threaded mode to establish bidirectional communication with the PC for data transmission. After the PC makes a data request, the data is sent to the PC in sequence at a set frequency. After receiving the data, the PC calls the pre-written visualization module to display the data and sends commands to the K-210 development board through the cloud.

Images