KR-20260064969-A - DRONE SYSTEM FOR EARLY RESPONSE TO HEAT-RELATED DISEASES

KR20260064969AKR 20260064969 AKR20260064969 AKR 20260064969AKR-20260064969-A

Abstract

The present invention discloses a drone system for early response to the occurrence of heat-related illnesses. More specifically, the present invention relates to a drone system for early response to heat-related illnesses that can perform early response and emergency rescue procedures for heat-related illnesses that may occur in agricultural fields during the hot season using an autonomous flying drone. According to an embodiment of the present invention, by using an autonomous drone to photograph outdoor farmland, etc. during the hot season and using an artificial intelligence model capable of estimating the current condition of a worker based on their posture, it is possible to determine in real time whether heat is generated in workers located outdoors, attempt to approach and spray water, or notify the control center of their current location, thereby enabling rapid emergency measures for heatstroke patients.

Inventors

정필수
김영헌
김동영
이강욱
전준수
박상하

Assignees

경상국립대학교산학협력단

Dates

Publication Date: 20260508
Application Date: 20241030

Claims (6)

A drone equipped with a gimbal camera and a communication module, which performs autonomous driving according to a set mission execution scenario while simultaneously photographing the ground and generating image information of the photographed ground; and It includes a control server connected to the communication module and network to upload the mission execution scenario to the drone, and to receive the video information and instruct the drone to operate according to one or more structural sequences included in the mission execution scenario. Among the above-mentioned drone and control server, at least one is, For one or more objects appearing in the above video information, a trained artificial intelligence model is used to identify a person in an abnormal state and determine whether a heat-related illness has occurred. The above artificial intelligence model is, A drone system for early response to heatstroke patients, which is trained by a first dataset based on various types of reenactment situations performed in a virtual environment created in correspondence with the actual environment of a drone in flight.
In Article 1, The above artificial intelligence model is, A drone system for early response to heatstroke patients, implemented using the YOLO model, a CNN-based deep learning algorithm.
In Article 2, The above YOLO model is, An object identification model that extracts features of the above image information to identify the type and location of appearing objects; and A posture prediction model that is trained on a second dataset in which multiple key points are defined, and determines an abnormal state of a person by estimating the person's current posture according to the multiple key points when the predicted object type is a person. A drone system for early response to heatstroke patients, including
In Paragraph 3, The above posture prediction model is, A drone system for early response to heatstroke patients, which estimates a person's current posture by extracting 17 key points of a person's joints or body parts according to a person's posture from an object identified from the above image information through a multi-layer perceptron.
In Article 1, The above mission execution scenario is, A first process of instructing the drone to take off to a predetermined height or higher based on relative altitude when flight preparation is complete; A second process of directing the flight of the drone along a flight path determined by a shortest path algorithm for a monitoring target area immediately after takeoff; A third process for performing object detection by receiving image information of the ground along the flight path from the start to the end of the mission; In the above third process, if the artificial intelligence model estimates that the object appearing in the image information is a person and is in a lying position, a fourth process of bringing the drone closer to the object according to an alignment algorithm that minimizes the distance between the object and the drone in horizontal and vertical directions; and A fifth process in which, when the drone approaches an object beyond a certain distance, it performs an early response by spraying water or generating a downdraft, and then resumes the mission according to the aforementioned flight path. A drone system for early response to heatstroke patients, including
In Article 1, The above control server is, A communication unit that receives the above-mentioned video information and GPS information in real time from multiple drones performing missions in each region; A display unit that displays images of the site in each region, including the analysis results of the received image information, separated by each drone; and A notification unit that transmits a rescue request to linked relevant agencies based on a report input by an administrator confirming the presence of a heatstroke patient in the video. A drone system for early response to heatstroke patients, including

Description

Drone System for Early Response to Heat-Related Diseases The present invention relates to a drone system for early response to the occurrence of heat-related illnesses, and in particular, to a drone system for early response to heat-related illnesses that can perform early response and emergency rescue procedures for heat-related illnesses that may occur in agricultural fields during the hot season using an autonomous flying drone. Due to global warming and the frequent occurrence of abnormal weather patterns, extreme heat never before experienced is occurring, and consequently, the incidence of heat-related illnesses during outdoor activities is on the rise. Heat-related illnesses refer to a condition in which body temperature rises due to insufficient intake of fluids and salts and poor heat dissipation from the body when workers are exposed to heat for a long time while working outdoors in fields or engaging in outdoor activities such as hiking during the day in summer. Particularly serious heat-related illnesses include heat exhaustion, heatstroke, and heat cramps. Therefore, when heat-related illnesses occur, it is crucial to detect the patient early and take prompt measures to lower their body temperature, and various solutions are being proposed for this purpose. For example, Korean Registered Patent No. 10-2009637, a prior art document, discloses a configuration of a drone for performing relief activities during disasters and emergencies, comprising a body, a drive unit capable of generating thrust to enable flight and changing direction, a wireless communication unit communicating with a user's terminal, and one or more cameras installed on the body, wherein an infrared detection sensor is connected to a control unit to enable the drone to fly while avoiding obstacles, thereby performing relief activities during disasters and emergencies. However, technologies using drones for disaster or relief according to these prior art documents and known technologies have limitations in that it is difficult to accurately identify whether people located outdoors are in a normal state or are exposed to the risk of heat-related illnesses, which may lead to unnecessary responses due to misjudgment or failure to take appropriate measures for heat-related illness patients who need help. FIG. 1 is a schematic diagram showing the overall structure of a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 2 is a diagram showing the structure of a drone included in a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 3 is a diagram illustrating a method for determining an optimal movement path for performing a mission of a drone system for early response to a heatstroke patient according to an embodiment of the present invention. FIG. 4 is a diagram illustrating training data of an artificial intelligence model used in a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 5 is a diagram illustrating the object detection technology of a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 6 is a diagram illustrating a center alignment algorithm applied to a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 7 is a diagram illustrating a part of source code for implementing a center alignment algorithm applied to a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 8 is a diagram showing the structure of a control server of a drone system for early response to heatstroke patients according to an embodiment of the present invention. FIG. 9 is a flowchart illustrating a drone control method for a drone system for early response to a heatstroke patient according to an embodiment of the present invention. The present invention as described above will be explained in detail through the attached drawings and embodiments. It should be noted that the technical terms used in this invention are used merely to describe specific embodiments and are not intended to limit the invention. Furthermore, unless specifically defined otherwise in this invention, the technical terms used in this invention should be interpreted in the sense generally understood by those skilled in the art to which this invention pertains, and should not be interpreted in an overly broad or overly narrow sense. Additionally, if a technical term used in this invention is an incorrect technical term that fails to accurately express the concept of the invention, it should be replaced with a technical term that can be correctly understood by those skilled in the art. Moreover, general terms used in this invention should be interpreted according to their prior definitions or the context, and should not be