KR-20260063486-A - Method for rescuing drowning person, computing apparatus for performing the same, and drowning person rescue system including the same

KR20260063486AKR 20260063486 AKR20260063486 AKR 20260063486AKR-20260063486-A

Abstract

A method for rescuing a drowning person according to one embodiment of the present invention may include the steps of: acquiring a captured image in which a water surface area is captured; extracting an area where a person is located in the captured image as a tracking area; detecting a first drowning judgment value using upper limb movement information of the person within the tracking area; detecting a second drowning judgment value using movement displacement information of the person within the tracking area; calculating a drowning risk value of the person using the first drowning judgment value and the second drowning judgment value; and transmitting a rescue signal generated based on the drowning risk value to a rescue device.

Inventors

박규민
이현기
이흐산 울라

Assignees

재단법인대구경북과학기술원

Dates

Publication Date: 20260507
Application Date: 20241030

Claims (16)

A step of acquiring a captured image of a sleep area; A step of extracting the area where a person is located in the above-mentioned captured image as a tracking area; A step of detecting a first drowning judgment value using upper limb movement information of the person within the tracking area; A step of detecting a second drowning judgment value using the movement displacement information of the person within the tracking area; A step of calculating the drowning risk value of the person using the first drowning risk judgment value and the second drowning risk judgment value; and A method for rescuing a drowning person, comprising the step of transmitting a rescue signal generated based on the above drowning risk value to the rescue device.
In paragraph 1, The step of detecting the first drowning judgment value is, A method for rescuing a drowning person, wherein a plurality of points forming the upper limbs of the person are input into a pre-trained model to detect the first drowning judgment value.
In paragraph 1, The step of detecting the second drowning judgment value is, A method for rescuing a drowning person, which detects a second drowning judgment value using information on the reciprocating movement of the person in the up and down direction.
In paragraph 3, The step of detecting the second drowning judgment value is, A method for rescuing a drowning person, which detects a second drowning judgment value based on the amplitude of the reciprocating movement of the person in the up and down direction.
In paragraph 1, The step of calculating the drowning risk value of the above person is, A method for rescuing a drowning person, wherein a first weight is assigned to the first drowning judgment value and a second weight is assigned to the second drowning judgment value to calculate the drowning risk value.
In paragraph 5, A method for rescuing a drowning person, wherein the first weight is relatively smaller than the second weight.
In paragraph 1, The above method is, A method for rescuing a drowning person, further comprising the step of detecting a third drowning judgment value using a wave pattern of the water surface within the tracking area.
In paragraph 1, A method for rescuing a drowning person, further comprising the step of inputting change data of images within the tracking area acquired in a time series into a pre-trained drowning person behavior model to detect a third drowning judgment value.
At least one memory; and Includes at least one processor; and The above-mentioned at least one processor is, A computing device that acquires a captured image of a water surface area, extracts an area where a person is located in the captured image as a tracking area, detects a first drowning judgment value using upper limb movement information of the person within the tracking area, detects a second drowning judgment value using movement displacement information of the person within the tracking area, calculates a drowning risk value of the person using the first drowning judgment value and the second drowning judgment value, and transmits a rescue signal generated based on the drowning risk value to the rescue device.
In Paragraph 9, Detecting the above-mentioned first drowning judgment value is, A computing device that detects the first drowning judgment value by inputting a plurality of points forming the upper limbs of the person into a pre-trained model.
In Paragraph 9, Detecting the above second drowning judgment value is, A computing device that detects a second drowning judgment value using information on the reciprocating movement of the above person in the up and down direction.
In Paragraph 11, Detecting the above second drowning judgment value is, A computing device that detects the second drowning judgment value based on the amplitude of the reciprocating movement of the person in the up and down direction.
At least one imaging device for capturing a sleep area; A computing device that acquires a captured image of the water surface area captured from the above-mentioned capturing device and generates a structural signal; and It includes at least one rescue device that receives the rescue signal from the computing device, flies to the water surface area, and provides rescue equipment to the water surface area. A drowning rescue system comprising: a computing device acquiring a captured image of a water surface area, extracting an area where a person is located in the captured image as a tracking area, detecting a first drowning judgment value using upper limb movement information of the person within the tracking area, detecting a second drowning judgment value using movement displacement information of the person within the tracking area, calculating a drowning risk value of the person using the first drowning judgment value and the second drowning judgment value, and transmitting a rescue signal generated based on the drowning risk value to a rescue device.
In Paragraph 13, Detecting the above-mentioned first drowning judgment value is, A drowning rescue system that detects the first drowning judgment value by inputting a plurality of points forming the upper limbs of the person into a pre-trained model.
In Paragraph 13, Detecting the above second drowning judgment value is, A drowning rescue system that detects a second drowning judgment value using information on the reciprocating movement of the person in the up and down direction.
In paragraph 15, Detecting the above second drowning judgment value is, A drowning rescue system that detects the second drowning judgment value based on the amplitude of the reciprocating movement of the person in the up and down direction.

Description

Method for rescuing a drowning person, computing apparatus for performing the same, and drowning person rescue system including the same The present invention relates to a method for rescuing a drowning person, a computing device for performing the same, and a drowning person rescue system including the same. Generally, drowning accidents can occur not only in natural environments such as the sea, rivers, and lakes, but also in swimming pools, harbors, and leisure facilities. In particular, unexpected accidents can easily happen during water activities or leisure pursuits, and drowning victims may face situations where they are unable to surface on their own due to momentary panic, exhaustion, or changes in water temperature. The longer rescue is delayed after a drowning accident, the more rapidly the risk of drowning increases. A drowning victim can rapidly lose consciousness while deprived of oxygen underwater, and brain damage due to oxygen deprivation can occur within minutes. Therefore, it is crucial to rescue the victim promptly within the "golden hour" following the accident. However, in crowded environments such as oceans and swimming pools, it is often difficult to immediately detect a drowning victim. Particularly in crowded water environments, it is challenging to visually locate a drowning victim, and rescue operations are frequently delayed because rescuers fail to recognize the situation immediately after it occurs. Consequently, there is a growing need for the development of technologies capable of rapidly determining the occurrence of a drowning victim, detecting their precise location in real-time, and enabling an immediate response. In response to this need, automated detection and rescue technologies are essential for the rapid and efficient rescue of drowning victims, rather than relying solely on human labor. For example, there is a need to develop technology that combines sensor-based drowning detection technology with automated rescue devices to detect the victim's location in real time and perform rescue operations automatically or semi-automatically. The information described above disclosed in the background technology of this invention is intended only to enhance understanding of the background of the present invention and may therefore include information that does not constitute prior art. The following drawings attached to this specification illustrate preferred embodiments of the present invention and serve to further enhance understanding of the technical concept of the present invention together with the detailed description of the invention provided below; therefore, the present invention should not be interpreted as being limited only to the matters described in such drawings. FIG. 1 is a drawing illustrating a drowning person rescue system according to one embodiment of the present invention. Figure 2 is a block diagram of the computing device shown in Figure 1. FIG. 3 is a flowchart illustrating a method for rescuing a drowning person according to an embodiment of the present invention. Figure 4 is a diagram illustrating a method for performing the step of calculating the drowning risk value shown in Figure 3. FIG. 5 is a diagram for explaining a method for calculating the first drowning judgment value shown in FIG. 4. FIG. 6 is a diagram for explaining a method for calculating the second drowning judgment value shown in FIG. 4. Figure 7 is a graph illustrating, exemplarily, the movement displacement information of a person used to calculate the second drowning judgment value. FIG. 8 is a diagram for explaining a method for calculating the third water level judgment value shown in FIG. 4. The present invention is capable of various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described below in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various forms. Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted. In the following embodiments, terms such as first, second, etc. are used not in a limiting sense, but for the purpose of distinguishing one component from another component. In the following examples, singular expressions include plural expressions unless the context clearly indicates otherwise. In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other