닫기
216.73.216.28
216.73.216.28
close menu
KCI 등재
UAV 기반 외래거북 탐지를 위한 광학문자 인식(OCR)의 가능성 평가
Feasibility of Optical Character Recognition (OCR) for Non-native Turtle Detection
임태양 ( Lim Tai-yang ) , 김지윤 ( Kim Ji-yoon ) , 김휘문 ( Kim Whee-moon ) , 강완모 ( Kang Wan-mo ) , 송원경 ( Song Won-kyong )
UCI I410-ECN-0102-2023-500-000919094

Alien species cause problems in various ecosystems, reduce biodiversity, and destroy ecosystems. Due to these problems, the problem of a management plan is increasing, and it is difficult to accurately identify each individual and calculate the number of individuals, especially when researching alien turtle species such as GPS and PIT based on capture. this study intends to conduct an individual recognition study using a UAV. Recently, UAVs can take various sensor-based photos and easily obtain high-definition image data at low altitudes. Therefore, based on previous studies, this study investigated five variables to be considered in UAV flights and produced a test paper using them. OCR was used to monitor the displayed turtles using the manufactured test paper, and this confirmed the recognition rate. As a result, the use of yellow numbers showed the highest recognition rate. In addition, the minimum threat distance was confirmed to be 3 to 6m, and turtles with a shell size of 6 to 8cm were also identified during the flight. Therefore, we tried to propose an object recognition methodology for turtle display text using OCR, and it is expected to be used as a new turtle monitoring technique.

Ⅰ. 서 론
Ⅱ. 연구방법
Ⅲ. 결과 및 고찰
Ⅳ. 결 론
References
[자료제공 : 네이버학술정보]
×