In this paper, a water rescue mission system was developed for water safety management areas by utilizing unmanned mobility( drone systems) and AI-based visual recognition technology to enable automatic detection and localization of drowning persons, allowing timely response within the golden time. First, we detected suspected human subjects in daytime and nighttime videos, then estimated human skeleton-based poses to extract human features and patterns using LSTM models. After detecting the drowning person, we proposed an algorithm to obtain accurate GPS location information of the drowning person for rescue activities. In our experimental results, the accuracy of the Drown detection rate is 80.1% as F1-Score, and the average error of position estimation is about 0.29 meters.

1. 서 론
2. 익수자 탐지모델 및 위치추정 기법
    2.1 드론 주/야간 영상에서의 익수자 탐지모델
    2.2 드론 영상 기반의 익수자 위치추정 기법
3. 실험 및 평가
    3.1 RGB 및 열화상 카메라 영상에서의 익수자탐지 모델의 검증
    3.2 영상기반 익수자 GPS 위치추정 검증
4. 결 론
Acknowledgement
References

• Heon Gyu Lee(AI & Drone Research Center, Gaion Co., Ltd.) | 이헌규 (㈜가이온 AI & 드론 연구소) Corresponding author
• Dongsung Kim(School of IT Convergence, Soongsil University) | 김동성 (숭실대학교 인공지능, IT융합학과)
• Hanhyeok Jho(School of IT Convergence, Soongsil University) | 조한혁 (숭실대학교 인공지능, IT융합학과)