ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper A Study of AI-based Harbor Surveillance System
Cited 1 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Dongkoo Shon, Jeongsik Kim, Tae Hyun Yoon, Woo-Sung Jung, Dae Seung Yoo
Issue Date
2023-02
Citation
International Conference on Advanced Communications Technology (ICACT) 2023, pp.272-276
Publisher
IEEE
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.23919/ICACT56868.2023.10079320
Abstract
When ships of various types and sizes enter and depart from ports, the risk of collision between ships is high. In particular, collisions between large ships can lead to major accidents. In order to avoid crashes, it is important to quickly identify hazardous situations in advance using harbor surveillance system. But, the harbor surveillance system has limitations in that it continuously requires manpower and the criteria for judgment are different for each person. To solve this problem, we propose an AI based harbor surveillance system including image-based object recognition and abnormal situation recognition. Its superiority was proven through simulation. In the object recognition, YOLOv5, which had the best performance with an mAP of 0.953, was used. The abnormal situation was determined through the distance between the recognized objects, and the comparison of the determination results for 21.5 seconds (66 samples) showed 100%.
KSP Keywords
Abnormal situation, Best performance, Image-based, Major accidents, Object recognition, Situation recognition, Surveillance system, risk of collision