Search

KR-20260063609-A - Water movement monitoring apparatus and method

KR20260063609AKR 20260063609 AKR20260063609 AKR 20260063609AKR-20260063609-A

Abstract

A water body detection device and method are disclosed. The water body detection method of the present invention comprises a memory; and a processor that executes instructions stored in the memory, wherein the processor analyzes a ground-mounted image to detect a boundary line between a water body and a non-water body within the ground-mounted image, extracts a water body by analyzing the boundary line, and calculates the area of the extracted water body.

Inventors

  • 최민하
  • 이성우
  • 조신현

Assignees

  • 성균관대학교산학협력단

Dates

Publication Date
20260507
Application Date
20241030

Claims (20)

  1. Memory; and It includes a processor that executes instructions stored in the above memory, and A water body detection device that analyzes ground-captured images to detect a boundary line between a water body and a non-water body within the ground-captured images, analyzes the boundary line to extract the water body, and calculates the area of the extracted water body.
  2. In paragraph 1, The above ground-capturing image is a water body detection device that uses near-infrared (NIR) image data among multispectral image data.
  3. In paragraph 2, A water body detection device in which the processor calculates an NDWI (Normalized Difference Water Index) using the near-infrared image data and detects edges using the NDWI index.
  4. In paragraph 1, A water body detection device in which the processor calculates a gradient in the vertical and horizontal directions for each pixel of the ground-capturing image, extracts the intensity of the pixel using the gradient, and detects edges according to the extracted intensity of the pixel.
  5. In paragraph 1, A water body detection device that, the processor forms a circle with a preset radius centered on a center pixel centered on a pixel on the boundary line, forms a plurality of triangles within the circle formed at a preset angle centered on the center pixel, and then selects one of the triangles as a tracking pixel.
  6. In paragraph 5, The above processor is a water body detection device that removes at least one of the triangles according to the tracking direction for selecting the tracking pixel.
  7. In paragraph 6, The above tracking direction is a water body detection device selected according to the direction from a preset start pixel to a preset end pixel.
  8. In paragraph 5, A water body detection device in which at least one of the radius and the angle is adjustable.
  9. In paragraph 5, A water body detection device in which the processor calculates pixel information of pixels included inside the triangle by angle, compares the pixel information by angle with each other to select a tracking angle based on similarity, and selects one of the pixels placed at the selected tracking angle as a tracking pixel.
  10. In paragraph 5, The above processor is a water body detection device that selects a pixel whose distance from the above-mentioned center pixel is within the above-mentioned radius as the above-mentioned tracking pixel.
  11. In Paragraph 10, A water body detection device that determines whether the distance from the center pixel is within the radius based on whether the area of a reference triangle formed by a pixel whose distance from the center pixel is within the radius, the center pixel, and a preset reference pixel is within the area of the triangle.
  12. A step in which a processor analyzes a ground-captured image and detects the boundary line between a water body and a non-water body within the ground-captured image; The step of the processor analyzing the boundary line to extract the water body; and A water body detection method comprising the step of calculating the area of the water body extracted by the above processor.
  13. In Paragraph 12, The above ground-capturing image is a water body detection method that is near-infrared (NIR) image data among multispectral image data.
  14. In Clause 13, in the step of detecting the boundary line, A water body detection method in which the processor calculates an NDWI (Normalized Difference Water Index) using the near-infrared image data and detects the boundary line using the NDWI index.
  15. In Clause 12, in the step of detecting the boundary line, A water body detection method in which the processor calculates a gradient in the vertical and horizontal directions for each pixel of the ground-captured image, extracts the intensity of the pixel using the gradient, and detects an edge according to the extracted intensity of the pixel.
  16. In Clause 12, in the step of extracting the region of the above-mentioned water body, A water body detection method in which the processor forms a circle with a predetermined radius centered on a central pixel centered on a pixel on the boundary line, forms a plurality of triangles within the circle formed at a predetermined angle centered on the central pixel, and then selects one of the triangles as a tracking pixel.
  17. In Clause 16, in the step of extracting the region of the above water body, A water body detection method in which the processor removes at least one of the triangles according to the tracking direction for selecting the tracking pixel.
  18. In Paragraph 17, The above tracking direction is a water body detection method selected according to the direction from a preset starting pixel to a preset end pixel.
  19. In Paragraph 16, A water body detection method in which at least one of the radius and the angle is adjustable.
  20. In Clause 16, in the step of extracting the region of the above water body, A water body detection method in which the processor calculates pixel information of pixels included inside the triangle by angle, compares the pixel information by angle with each other to select a tracking angle based on similarity, and selects one of the pixels placed at the selected tracking angle as a tracking pixel.

Description

Water movement monitoring apparatus and method The present invention relates to a water body detection device and method. Climate change caused by global warming is increasing the frequency and intensity of extreme weather events such as floods and droughts. This phenomenon further highlights the importance of water detection technology in water resource management and disaster prevention. Securing long-term observational data is essential for accurate flood disaster prediction, and this requires a large volume of accurately labeled data. However, the current labeling process relies heavily on user proficiency, resulting in significant disparities in data accuracy and processing speed. The manual-centric approach of existing labeling methods entails high time costs due to repetitive and tedious tasks, which increases the likelihood of data errors. Particularly in long-term data analysis, such as reservoir change monitoring, securing labeled data of consistent quality is a key element for building a successful model. Differences in data quality based on user proficiency act as a major factor undermining the reliability and accuracy of predictive models, which can consequently have a negative impact on model performance. The background technology of the present invention is disclosed in the ‘Digital Twin-based Virtual Reservoir Monitoring System’ of Korean Published Patent Application No. 10-2024-0039858 (March 27, 2024). FIG. 1 is a block diagram of a water body detection device according to one embodiment of the present invention. FIG. 2 is a flowchart of a water body detection process of a processor according to one embodiment of the present invention. FIG. 3 is a drawing showing a ground-based image according to one embodiment of the present invention. FIG. 4 is a diagram showing an example of a near-infrared image according to one embodiment of the present invention. FIG. 5 is a diagram showing an image in which Canny edge detection is applied to a near-infrared image according to one embodiment of the present invention. FIG. 6 is a diagram showing an image with a Sobel filter applied to an image to which Canny edge detection according to one embodiment of the present invention has been applied. FIG. 7 is a diagram illustrating an example of selecting a tracking direction according to an embodiment of the present invention. FIG. 8 is a diagram illustrating the process of tracking a boundary line based on a triangle according to one embodiment of the present invention. FIG. 9 is a drawing illustrating an example of selecting a tracking pixel according to an embodiment of the present invention. FIG. 10 is a diagram showing the result of tracking boundary lines on an image to which a Sobel filter according to one embodiment of the present invention has been applied. FIG. 11 is a flowchart of a water body detection method according to one embodiment of the present invention. The following describes an embodiment of a water body detection device and method according to an embodiment of the present invention. In this process, the thickness of lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of explanation. Furthermore, the terms described below are defined considering their functions in the present invention, and these may vary depending on the intention or convention of the user or operator. Therefore, the definitions of these terms should be based on the content throughout this specification. The present invention may be implemented in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the invention in the drawings, parts unrelated to the description have been omitted, and similar parts throughout the specification have been given similar reference numerals. Throughout the specification, when a part is described as "including" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. The implementations described herein may be implemented, for example, as methods or processes, devices, software programs, data streams, or signals. Even if discussed only in the context of a single form of implementation (e.g., discussed only as a method), the implementation of the discussed features may also be implemented in other forms (e.g., devices or programs). Devices may be implemented in appropriate hardware, software, and firmware, etc. Methods may be implemented in devices such as processors, which generally refer to processing devices including, for example, computers, microprocessors, integrated circuits, or programmable logic devices. FIG. 1 is a block diagram of a water body detection device according to an embodiment of the present invention, FIG. 2 is a flowchart of a water body detection process of a processor according to an embodiment of the present invention, FIG. 3 is a diagram showing a ground