딥러닝 기반 소형선박 승선자 조난 인지 시스템
Deep Learning based Distress Awareness System for Small Boat
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
According to statistics conducted by the Korea Coast Guard, the number of accidents on small boats under 5 tons is increasing every year. This is because only a small number of people are on board. The previously developed maritime distress and safety systems are not well distributed because passengers must be equipped with additional remote equipment. The purpose of this study is to develop a distress awareness system that recognizes man over-board situations in real time. This study aims to present the part of the passenger tracking system among the small ship’s distress awareness situational system that can generate passenger’s location information in real time using deep learning based object detection and tracking technologies. The system consisted of the following steps. 1) the passenger location information is generated in the form of Bounding box using its detection model (YOLOv3). 2) Based on the Bounding box data, Deep SORT predicts the Bounding box’s position in the next frame of the image with Kalman filter. 3) When the actual Bounding Box is created within the range predicted by Kalman-filter, Deep SORT repeats the process of recognizing it as the same object. 4) If the Bounding box deviates the ship’s area or an error occurs in the number of tracking occupant, the system is decided the distress situation and issues an alert. This study is expected to complement the problems of existing technologies and ensure the safety of individuals aboard small boats.
Abstract
According to statistics conducted by the Korea Coast Guard, the number of accidents on small boats under 5 tons is increasing every year. This is because only a small number of people are on board. The previously developed maritime distress and safety systems are not well distributed because passengers must be equipped with additional remote equipment. The purpose of this study is to develop a distress awareness system that recognizes man over-board situations in real time. This study aims to present the part of the passenger tracking system among the small ship’s distress awareness situational system that can generate passenger’s location information in real time using deep learning based object detection and tracking technologies. The system consisted of the following steps. 1) the passenger location information is generated in the form of Bounding box using its detection model (YOLOv3). 2) Based on the Bounding box data, Deep SORT predicts the Bounding box’s position in the next frame of the image with Kalman filter. 3) When the actual Bounding Box is created within the range predicted by Kalman-filter, Deep SORT repeats the process of recognizing it as the same object. 4) If the Bounding box deviates the ship’s area or an error occurs in the number of tracking occupant, the system is decided the distress situation and issues an alert. This study is expected to complement the problems of existing technologies and ensure the safety of individuals aboard small boats.
참고문헌 (15)
- J. S. Yoo, "Marine Distress", Rescue System for Marine Vessel Accident Response, 2017, 463~465
- Korea Coast Guard, "2020 Statistical Yearbook of Marine Accident" (2020)
- B. H. Jeong, "The Operational Concept and Technology Development of GMDSS, a Global Distress Safety System for Ships", Journal of Semiconductor Technology and Science, 24(10), pp.1250~1254 (1997)
- J. J. Kim, "The Device for Generation the Distress Signal and Monitoring System for a Survivor based on WSN", Proceeding of KIIT Conference, pp.215~217 (2010)
- 정선재, "Beacon을 활용한 선박 탑승자 위치확인 시스템의 구현", 한국정보통신학회논문지, 20(1), pp.153~160 (2016), 한국정보통신학회[DOI]
- J. S. Yoo, "Rescue System for Marine Vessel Accident Response", Proceedings of KIIT Conference, pp.463~465 (2017)
- K. Yun, "Small Target Detection for Search and Rescue Operations Using Distributed Deep Learning and Synthetic Data Generation", Pattern Recognition and Tracking XXX, 10995, pp.38~43 (2019)
- M. E. N. Gomes, "Multi-human fall Detection and Localization in Videos", Computer Vision and Image Understanding, 220, pp.103442~ (2022)
- J, Redmon, "YOLOv3: An Incremental Improvement", arXiv preprint, arXiv:1804.02767, ~ (2018)
- N. Wojke, "Simple Online and Realtime Tracking with a Deep Association Metric", IEEE International Conference on Image Processing(ICIP), pp, pp.3645~3649 (2017)
- L. Zheng, "Mars: A Video Benchmark for Large-scale Person Re-identification", European Conference on Computer Vision, pp.868~884 (2016)
- S. Ren, "Faster R-CNN:Toward Real-time Object Detection with Region Proposal Networks", Advances in Neural Information Processing System, (28,) (2015)
- K. Zhou, "Omni-scale Feature Learning for Person Re-identification", Proceedings of the IEEE, 2019, 3702~3712
- D. Bolya, "YOLACT:Real-time Instance Segmentation", Proceedings of the IEEE, 2019, 9157~9166
- A. Milan, "MOT16: A Benchmark for Multi-Object Tracking", arXiv preprint, arXiv:1603.00831, ~ (2016)